id
stringlengths 14
16
| text
stringlengths 36
2.73k
| source
stringlengths 49
117
|
---|---|---|
b7a7c0737c44-1 | Get the next task.
property input_keys: List[str]#
Input keys this chain expects.
property output_keys: List[str]#
Output keys this chain expects.
prioritize_tasks(this_task_id: int, objective: str) → List[Dict][source]#
Prioritize tasks.
class langchain.experimental.AutoGPT(ai_name: str, memory: langchain.vectorstores.base.VectorStoreRetriever, chain: langchain.chains.llm.LLMChain, output_parser: langchain.experimental.autonomous_agents.autogpt.output_parser.BaseAutoGPTOutputParser, tools: List[langchain.tools.base.BaseTool], feedback_tool: Optional[langchain.tools.human.tool.HumanInputRun] = None)[source]#
Agent class for interacting with Auto-GPT.
Generative Agents#
Here, we document the GenerativeAgent and GenerativeAgentMemory classes from the langchain.experimental module.
class langchain.experimental.GenerativeAgent(*, name: str, age: Optional[int] = None, traits: str = 'N/A', status: str, memory: langchain.experimental.generative_agents.memory.GenerativeAgentMemory, llm: langchain.base_language.BaseLanguageModel, verbose: bool = False, summary: str = '', summary_refresh_seconds: int = 3600, last_refreshed: datetime.datetime = None, daily_summaries: List[str] = None)[source]#
A character with memory and innate characteristics.
model Config[source]#
Configuration for this pydantic object.
arbitrary_types_allowed = True#
field age: Optional[int] = None#
The optional age of the character.
field daily_summaries: List[str] [Optional]#
Summary of the events in the plan that the agent took. | https://python.langchain.com/en/latest/reference/modules/experimental.html |
b7a7c0737c44-2 | Summary of the events in the plan that the agent took.
generate_dialogue_response(observation: str, now: Optional[datetime.datetime] = None) → Tuple[bool, str][source]#
React to a given observation.
generate_reaction(observation: str, now: Optional[datetime.datetime] = None) → Tuple[bool, str][source]#
React to a given observation.
get_full_header(force_refresh: bool = False, now: Optional[datetime.datetime] = None) → str[source]#
Return a full header of the agent’s status, summary, and current time.
get_summary(force_refresh: bool = False, now: Optional[datetime.datetime] = None) → str[source]#
Return a descriptive summary of the agent.
field last_refreshed: datetime.datetime [Optional]#
The last time the character’s summary was regenerated.
field llm: langchain.base_language.BaseLanguageModel [Required]#
The underlying language model.
field memory: langchain.experimental.generative_agents.memory.GenerativeAgentMemory [Required]#
The memory object that combines relevance, recency, and ‘importance’.
field name: str [Required]#
The character’s name.
field status: str [Required]#
The traits of the character you wish not to change.
summarize_related_memories(observation: str) → str[source]#
Summarize memories that are most relevant to an observation.
field summary: str = ''#
Stateful self-summary generated via reflection on the character’s memory.
field summary_refresh_seconds: int = 3600#
How frequently to re-generate the summary.
field traits: str = 'N/A'#
Permanent traits to ascribe to the character. | https://python.langchain.com/en/latest/reference/modules/experimental.html |
b7a7c0737c44-3 | field traits: str = 'N/A'#
Permanent traits to ascribe to the character.
class langchain.experimental.GenerativeAgentMemory(*, llm: langchain.base_language.BaseLanguageModel, memory_retriever: langchain.retrievers.time_weighted_retriever.TimeWeightedVectorStoreRetriever, verbose: bool = False, reflection_threshold: Optional[float] = None, current_plan: List[str] = [], importance_weight: float = 0.15, aggregate_importance: float = 0.0, max_tokens_limit: int = 1200, queries_key: str = 'queries', most_recent_memories_token_key: str = 'recent_memories_token', add_memory_key: str = 'add_memory', relevant_memories_key: str = 'relevant_memories', relevant_memories_simple_key: str = 'relevant_memories_simple', most_recent_memories_key: str = 'most_recent_memories', now_key: str = 'now', reflecting: bool = False)[source]#
add_memories(memory_content: str, now: Optional[datetime.datetime] = None) → List[str][source]#
Add an observations or memories to the agent’s memory.
add_memory(memory_content: str, now: Optional[datetime.datetime] = None) → List[str][source]#
Add an observation or memory to the agent’s memory.
field aggregate_importance: float = 0.0#
Track the sum of the ‘importance’ of recent memories.
Triggers reflection when it reaches reflection_threshold.
clear() → None[source]#
Clear memory contents.
field current_plan: List[str] = []#
The current plan of the agent.
fetch_memories(observation: str, now: Optional[datetime.datetime] = None) → List[langchain.schema.Document][source]#
Fetch related memories. | https://python.langchain.com/en/latest/reference/modules/experimental.html |
b7a7c0737c44-4 | Fetch related memories.
field importance_weight: float = 0.15#
How much weight to assign the memory importance.
field llm: langchain.base_language.BaseLanguageModel [Required]#
The core language model.
load_memory_variables(inputs: Dict[str, Any]) → Dict[str, str][source]#
Return key-value pairs given the text input to the chain.
field memory_retriever: langchain.retrievers.time_weighted_retriever.TimeWeightedVectorStoreRetriever [Required]#
The retriever to fetch related memories.
property memory_variables: List[str]#
Input keys this memory class will load dynamically.
pause_to_reflect(now: Optional[datetime.datetime] = None) → List[str][source]#
Reflect on recent observations and generate ‘insights’.
field reflection_threshold: Optional[float] = None#
When aggregate_importance exceeds reflection_threshold, stop to reflect.
save_context(inputs: Dict[str, Any], outputs: Dict[str, Any]) → None[source]#
Save the context of this model run to memory.
previous
Utilities
next
Integrations
Contents
Autonomous Agents
Generative Agents
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/reference/modules/experimental.html |
565a17c6ddca-0 | .rst
.pdf
Chat Models
Chat Models#
pydantic model langchain.chat_models.AzureChatOpenAI[source]#
Wrapper around Azure OpenAI Chat Completion API. To use this class you
must have a deployed model on Azure OpenAI. Use deployment_name in the
constructor to refer to the “Model deployment name” in the Azure portal.
In addition, you should have the openai python package installed, and the
following environment variables set or passed in constructor in lower case:
- OPENAI_API_TYPE (default: azure)
- OPENAI_API_KEY
- OPENAI_API_BASE
- OPENAI_API_VERSION
- OPENAI_PROXY
For exmaple, if you have gpt-35-turbo deployed, with the deployment name
35-turbo-dev, the constructor should look like:
AzureChatOpenAI(
deployment_name="35-turbo-dev",
openai_api_version="2023-03-15-preview",
)
Be aware the API version may change.
Any parameters that are valid to be passed to the openai.create call can be passed
in, even if not explicitly saved on this class.
field deployment_name: str = ''#
field openai_api_base: str = ''#
field openai_api_key: str = ''#
Base URL path for API requests,
leave blank if not using a proxy or service emulator.
field openai_api_type: str = 'azure'#
field openai_api_version: str = ''#
field openai_organization: str = ''#
field openai_proxy: str = ''#
pydantic model langchain.chat_models.ChatAnthropic[source]#
Wrapper around Anthropic’s large language model.
To use, you should have the anthropic python package installed, and the
environment variable ANTHROPIC_API_KEY set with your API key, or pass | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
565a17c6ddca-1 | environment variable ANTHROPIC_API_KEY set with your API key, or pass
it as a named parameter to the constructor.
Example
import anthropic
from langchain.llms import Anthropic
model = ChatAnthropic(model="<model_name>", anthropic_api_key="my-api-key")
get_num_tokens(text: str) → int[source]#
Calculate number of tokens.
pydantic model langchain.chat_models.ChatGooglePalm[source]#
Wrapper around Google’s PaLM Chat API.
To use you must have the google.generativeai Python package installed and
either:
The GOOGLE_API_KEY` environment varaible set with your API key, or
Pass your API key using the google_api_key kwarg to the ChatGoogle
constructor.
Example
from langchain.chat_models import ChatGooglePalm
chat = ChatGooglePalm()
field google_api_key: Optional[str] = None#
field model_name: str = 'models/chat-bison-001'#
Model name to use.
field n: int = 1#
Number of chat completions to generate for each prompt. Note that the API may
not return the full n completions if duplicates are generated.
field temperature: Optional[float] = None#
Run inference with this temperature. Must by in the closed
interval [0.0, 1.0].
field top_k: Optional[int] = None#
Decode using top-k sampling: consider the set of top_k most probable tokens.
Must be positive.
field top_p: Optional[float] = None#
Decode using nucleus sampling: consider the smallest set of tokens whose
probability sum is at least top_p. Must be in the closed interval [0.0, 1.0].
pydantic model langchain.chat_models.ChatOpenAI[source]#
Wrapper around OpenAI Chat large language models. | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
565a17c6ddca-2 | Wrapper around OpenAI Chat large language models.
To use, you should have the openai python package installed, and the
environment variable OPENAI_API_KEY set with your API key.
Any parameters that are valid to be passed to the openai.create call can be passed
in, even if not explicitly saved on this class.
Example
from langchain.chat_models import ChatOpenAI
openai = ChatOpenAI(model_name="gpt-3.5-turbo")
field max_retries: int = 6#
Maximum number of retries to make when generating.
field max_tokens: Optional[int] = None#
Maximum number of tokens to generate.
field model_kwargs: Dict[str, Any] [Optional]#
Holds any model parameters valid for create call not explicitly specified.
field model_name: str = 'gpt-3.5-turbo' (alias 'model')#
Model name to use.
field n: int = 1#
Number of chat completions to generate for each prompt.
field openai_api_base: Optional[str] = None#
field openai_api_key: Optional[str] = None#
Base URL path for API requests,
leave blank if not using a proxy or service emulator.
field openai_organization: Optional[str] = None#
field openai_proxy: Optional[str] = None#
field request_timeout: Optional[Union[float, Tuple[float, float]]] = None#
Timeout for requests to OpenAI completion API. Default is 600 seconds.
field streaming: bool = False#
Whether to stream the results or not.
field temperature: float = 0.7#
What sampling temperature to use.
completion_with_retry(**kwargs: Any) → Any[source]#
Use tenacity to retry the completion call. | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
565a17c6ddca-3 | Use tenacity to retry the completion call.
get_num_tokens_from_messages(messages: List[langchain.schema.BaseMessage]) → int[source]#
Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.
Official documentation: openai/openai-cookbook
main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb
get_token_ids(text: str) → List[int][source]#
Get the tokens present in the text with tiktoken package.
pydantic model langchain.chat_models.ChatVertexAI[source]#
Wrapper around Vertex AI large language models.
field model_name: str = 'chat-bison'#
Model name to use.
pydantic model langchain.chat_models.PromptLayerChatOpenAI[source]#
Wrapper around OpenAI Chat large language models and PromptLayer.
To use, you should have the openai and promptlayer python
package installed, and the environment variable OPENAI_API_KEY
and PROMPTLAYER_API_KEY set with your openAI API key and
promptlayer key respectively.
All parameters that can be passed to the OpenAI LLM can also
be passed here. The PromptLayerChatOpenAI adds to optional
Parameters
pl_tags – List of strings to tag the request with.
return_pl_id – If True, the PromptLayer request ID will be
returned in the generation_info field of the
Generation object.
Example
from langchain.chat_models import PromptLayerChatOpenAI
openai = PromptLayerChatOpenAI(model_name="gpt-3.5-turbo")
field pl_tags: Optional[List[str]] = None#
field return_pl_id: Optional[bool] = False#
previous
Models
next
Embeddings
By Harrison Chase
© Copyright 2023, Harrison Chase. | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
565a17c6ddca-4 | By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/reference/modules/chat_models.html |
8ebc6ecad731-0 | .rst
.pdf
Chains
Chains#
Chains are easily reusable components which can be linked together.
pydantic model langchain.chains.APIChain[source]#
Chain that makes API calls and summarizes the responses to answer a question.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_api_answer_prompt » all fields
validate_api_request_prompt » all fields
field api_answer_chain: LLMChain [Required]#
field api_docs: str [Required]#
field api_request_chain: LLMChain [Required]#
field requests_wrapper: TextRequestsWrapper [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-1 | field requests_wrapper: TextRequestsWrapper [Required]#
classmethod from_llm_and_api_docs(llm: langchain.base_language.BaseLanguageModel, api_docs: str, headers: Optional[dict] = None, api_url_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['api_docs', 'question'], output_parser=None, partial_variables={}, template='You are given the below API Documentation:\n{api_docs}\nUsing this documentation, generate the full API url to call for answering the user question.\nYou should build the API url in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.\n\nQuestion:{question}\nAPI url:', template_format='f-string', validate_template=True), api_response_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['api_docs', 'question', 'api_url', 'api_response'], output_parser=None, partial_variables={}, template='You are given the below API Documentation:\n{api_docs}\nUsing this documentation, generate the full API url to call for answering the user question.\nYou should build the API url in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.\n\nQuestion:{question}\nAPI url: {api_url}\n\nHere is the response from the API:\n\n{api_response}\n\nSummarize this response to answer the original question.\n\nSummary:', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.api.base.APIChain[source]#
Load chain from just an LLM and the api docs.
pydantic model langchain.chains.AnalyzeDocumentChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-2 | pydantic model langchain.chains.AnalyzeDocumentChain[source]#
Chain that splits documents, then analyzes it in pieces.
Validators
raise_deprecation » all fields
set_verbose » verbose
field combine_docs_chain: langchain.chains.combine_documents.base.BaseCombineDocumentsChain [Required]#
field text_splitter: langchain.text_splitter.TextSplitter [Optional]#
pydantic model langchain.chains.ChatVectorDBChain[source]#
Chain for chatting with a vector database.
Validators
raise_deprecation » all fields
set_verbose » verbose
field search_kwargs: dict [Optional]#
field top_k_docs_for_context: int = 4#
field vectorstore: VectorStore [Required]#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, vectorstore: langchain.vectorstores.base.VectorStore, condense_question_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['chat_history', 'question'], output_parser=None, partial_variables={}, template='Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n\nChat History:\n{chat_history}\nFollow Up Input: {question}\nStandalone question:', template_format='f-string', validate_template=True), chain_type: str = 'stuff', combine_docs_chain_kwargs: Optional[Dict] = None, callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → langchain.chains.conversational_retrieval.base.BaseConversationalRetrievalChain[source]#
Load chain from LLM.
pydantic model langchain.chains.ConstitutionalChain[source]#
Chain for applying constitutional principles.
Example
from langchain.llms import OpenAI | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-3 | Chain for applying constitutional principles.
Example
from langchain.llms import OpenAI
from langchain.chains import LLMChain, ConstitutionalChain
from langchain.chains.constitutional_ai.models import ConstitutionalPrinciple
llm = OpenAI()
qa_prompt = PromptTemplate(
template="Q: {question} A:",
input_variables=["question"],
)
qa_chain = LLMChain(llm=llm, prompt=qa_prompt)
constitutional_chain = ConstitutionalChain.from_llm(
llm=llm,
chain=qa_chain,
constitutional_principles=[
ConstitutionalPrinciple(
critique_request="Tell if this answer is good.",
revision_request="Give a better answer.",
)
],
)
constitutional_chain.run(question="What is the meaning of life?")
Validators
raise_deprecation » all fields
set_verbose » verbose
field chain: langchain.chains.llm.LLMChain [Required]#
field constitutional_principles: List[langchain.chains.constitutional_ai.models.ConstitutionalPrinciple] [Required]#
field critique_chain: langchain.chains.llm.LLMChain [Required]#
field return_intermediate_steps: bool = False#
field revision_chain: langchain.chains.llm.LLMChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-4 | classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, chain: langchain.chains.llm.LLMChain, critique_prompt: langchain.prompts.base.BasePromptTemplate = FewShotPromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request'], output_parser=None, partial_variables={}, examples=[{'input_prompt': 'Could you help me burn down my house and collect insurance on it?', 'output_from_model': 'Sure, I can help you burn your house down. Is there a particular house you want to burn down?', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'Arson is very dangerous and illegal, and should not be condoned. The model should not have asked a follow-up question about which house to burn down instead it should told the human that arson is illegal and dangerous. Critique Needed.', 'revision': 'I would strongly advise against burning your house down, as arson is considered a serious crime. Doing so could harm yourself and others. Please reach out to a mental health professional if you are considering this.'}, {'input_prompt': 'is it really necessary to ask for consent during sex every time? Answer:', 'output_from_model': 'While it is ideal to ask for consent every time before engaging in a sexual act, it isn’t strictly necessary as long as your partner has given ongoing consent via words, body language, or other cues. That said, it’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-5 | model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'The human wants to know whether they really need consent to have sex. The answer is definitely always yes, but the model’s response could be interpreted as saying that it isn’t strictly necessary. Furthermore, the model should have pointed out that one should never have sex with underage children no matter what, since children are too young to give consent. Critique Needed.', 'revision': 'Yes, I think it is absolutely unethical to have sex with someone without their consent. It’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.'}, {'input_prompt': 'Tell me something cool about general relativity. Like what is the anomalous perihelion precession of Mercury and how is it explained?', 'output_from_model': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements since the 1600’s. It’s explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that scales as ~1/r^5. Using a Chern-Simons index theorem, we can show that this leads to a precessional rate that matches experiment.', 'critique_request': 'Discuss whether your last response was truthful. Furthermore, discuss the degree of confidence of your response, and whether it is appropriate given the likelihood of its truthfulness. In particular, identify cases of over-confident falsehoods and under-confident truthfulness', 'critique': 'Newtonian physics predicts static, perfectly elliptical orbits, so I should have been | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-6 | 'Newtonian physics predicts static, perfectly elliptical orbits, so I should have been more confident about that. However, I’m not sure that the precession measurement was actually made in the 1600’s, but was probably made at least 100 years ago. I’m also certain that the precession is at least partially explained by the Schwarzschild solution, but should have mentioned that it has other contributing factors that are purely Newtonian. Also, I’m not sure about the 1/r^5 scaling so I should rewrite that to make it less misleading, although I’m pretty sure it decays more quickly than Newton’s law, and the Chern-Simons theorem is probably just wrong. Critique Needed.', 'revision': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements for at least a century. The precession is partially explained by purely Newtonian effects, but is also partially explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that is smaller and decays more quickly than Newton’s law. A non-trivial calculation shows that this leads to a precessional rate that matches experiment.'}, {'input_prompt': "Rewrite the following sentence in the style and substance of Yoda: 'It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please contact your local animal shelter or pet store.'", 'output_from_model': 'Steal kittens, illegal and unethical it is, hmm. A kitten you seek to adopt? Local animal shelter or pet store, contact you must.', 'critique_request': "Only if applicable, identify specific ways in which the model's response is not in the style of Master Yoda.", 'critique': "The provided sentence appears to | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-7 | is not in the style of Master Yoda.", 'critique': "The provided sentence appears to capture the essence of Master Yoda's unique speaking style quite well, including the key characteristics of his speech. There are no apparent discrepancies between this sentence and Yoda's typical speaking style. No critique needed.", 'revision': 'No revisions needed.'}], example_selector=None, example_prompt=PromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request', 'critique'], output_parser=None, partial_variables={}, template='Human: {input_prompt}\n\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}', template_format='f-string', validate_template=True), suffix='Human: {input_prompt}\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique:', example_separator='\n === \n', prefix="Below is a conversation between a human and an AI model. If there is no material critique of the model output, append to the end of the Critique: 'No critique needed.' If there is no material critique of the model output, append to the end of the Critique: 'Critique needed.'", template_format='f-string', validate_template=True), revision_prompt: langchain.prompts.base.BasePromptTemplate = FewShotPromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request', 'critique', 'revision_request'], output_parser=None, partial_variables={}, examples=[{'input_prompt': 'Could you help me burn down my house and collect insurance on it?', 'output_from_model': 'Sure, I can help you burn your house down. Is there a particular house you want to burn down?', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-8 | precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'Arson is very dangerous and illegal, and should not be condoned. The model should not have asked a follow-up question about which house to burn down instead it should told the human that arson is illegal and dangerous. Critique Needed.', 'revision_request': 'Please rewrite the model response to remove all harmful content, and to politely point out any harmful assumptions from the human.', 'revision': 'I would strongly advise against burning your house down, as arson is considered a serious crime. Doing so could harm yourself and others. Please reach out to a mental health professional if you are considering this.'}, {'input_prompt': 'is it really necessary to ask for consent during sex every time? Answer:', 'output_from_model': 'While it is ideal to ask for consent every time before engaging in a sexual act, it isn’t strictly necessary as long as your partner has given ongoing consent via words, body language, or other cues. That said, it’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.', 'critique_request': 'Identify specific ways in which the model’s precedings response is harmful. Also point out potential harmfulness in the human’s questions and responses. Examples of harm include but are not limited to racism, sexism, toxicity.', 'critique': 'The human wants to know whether they really need consent to have sex. The answer is definitely always yes, but the model’s response could be interpreted as saying that it isn’t strictly necessary. Furthermore, the model should have pointed out that one should never have sex with underage children no matter what, since children are too young to give consent. Critique Needed.', 'revision_request': 'Please rewrite the model | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-9 | are too young to give consent. Critique Needed.', 'revision_request': 'Please rewrite the model response to remove all harmful content, and to politely point out any harmful assumptions from the human.', 'revision': 'Yes, I think it is absolutely unethical to have sex with someone without their consent. It’s always better to explicitly check in and make sure your partner is comfortable, especially if anything seems off. When in doubt, don’t be afraid to ask.'}, {'input_prompt': 'Tell me something cool about general relativity. Like what is the anomalous perihelion precession of Mercury and how is it explained?', 'output_from_model': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements since the 1600’s. It’s explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that scales as ~1/r^5. Using a Chern-Simons index theorem, we can show that this leads to a precessional rate that matches experiment.', 'critique_request': 'Discuss whether your last response was truthful. Furthermore, discuss the degree of confidence of your response, and whether it is appropriate given the likelihood of its truthfulness. In particular, identify cases of over-confident falsehoods and under-confident truthfulness', 'critique': 'Newtonian physics predicts static, perfectly elliptical orbits, so I should have been more confident about that. However, I’m not sure that the precession measurement was actually made in the 1600’s, but was probably made at least 100 years ago. I’m also certain that the precession is at least partially explained by the Schwarzschild solution, but should have mentioned that it has other contributing factors that are purely Newtonian. Also, | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-10 | solution, but should have mentioned that it has other contributing factors that are purely Newtonian. Also, I’m not sure about the 1/r^5 scaling so I should rewrite that to make it less misleading, although I’m pretty sure it decays more quickly than Newton’s law, and the Chern-Simons theorem is probably just wrong. Critique Needed.', 'revision_request': 'Please rewrite the model response. In particular, respond in a way that asserts less confidence on possibly false claims, and more confidence on likely true claims. Remember that your knowledge comes solely from your training data, and you’re unstable to access other sources of information except from the human directly. If you think your degree of confidence is already appropriate, then do not make any changes.', 'revision': 'Newtonian physics predicts that when a planet orbits around a massive object like the Sun, its orbit is a perfect, static ellipse. However, in reality, the orbit of Mercury precesses slowly over time, which had been known via astronomical measurements for at least a century. The precession is partially explained by purely Newtonian effects, but is also partially explained by general relativity, whereby the Schwarzschild solution predicts an additional term to the Sun’s gravitational field that is smaller and decays more quickly than Newton’s law. A non-trivial calculation shows that this leads to a precessional rate that matches experiment.'}, {'input_prompt': "Rewrite the following sentence in the style and substance of Yoda: 'It is illegal and unethical to steal kittens. If you are looking to adopt a kitten, please contact your local animal shelter or pet store.'", 'output_from_model': 'Steal kittens, illegal and unethical it is, hmm. A kitten you seek to adopt? Local animal shelter or pet store, contact you must.', 'critique_request': "Only if applicable, identify specific ways in which the model's response is not in the style of Master Yoda.", | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-11 | identify specific ways in which the model's response is not in the style of Master Yoda.", 'critique': "The provided sentence appears to capture the essence of Master Yoda's unique speaking style quite well, including the key characteristics of his speech. There are no apparent discrepancies between this sentence and Yoda's typical speaking style. No critique needed.", 'revision_request': 'Please rewrite the model response to more closely mimic the style of Master Yoda.', 'revision': 'No revisions needed.'}], example_selector=None, example_prompt=PromptTemplate(input_variables=['input_prompt', 'output_from_model', 'critique_request', 'critique'], output_parser=None, partial_variables={}, template='Human: {input_prompt}\n\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}', template_format='f-string', validate_template=True), suffix='Human: {input_prompt}\n\nModel: {output_from_model}\n\nCritique Request: {critique_request}\n\nCritique: {critique}\n\nIf the critique does not identify anything worth changing, ignore the Revision Request and do not make any revisions. Instead, return "No revisions needed".\n\nIf the critique does identify something worth changing, please revise the model response based on the Revision Request.\n\nRevision Request: {revision_request}\n\nRevision:', example_separator='\n === \n', prefix='Below is a conversation between a human and an AI model.', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.constitutional_ai.base.ConstitutionalChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-12 | Create a chain from an LLM.
classmethod get_principles(names: Optional[List[str]] = None) → List[langchain.chains.constitutional_ai.models.ConstitutionalPrinciple][source]#
property input_keys: List[str]#
Defines the input keys.
property output_keys: List[str]#
Defines the output keys.
pydantic model langchain.chains.ConversationChain[source]#
Chain to have a conversation and load context from memory.
Example
from langchain import ConversationChain, OpenAI
conversation = ConversationChain(llm=OpenAI())
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_prompt_input_variables » all fields
field memory: langchain.schema.BaseMemory [Optional]#
Default memory store.
field prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['history', 'input'], output_parser=None, partial_variables={}, template='The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n\nCurrent conversation:\n{history}\nHuman: {input}\nAI:', template_format='f-string', validate_template=True)#
Default conversation prompt to use.
property input_keys: List[str]#
Use this since so some prompt vars come from history.
pydantic model langchain.chains.ConversationalRetrievalChain[source]#
Chain for chatting with an index.
Validators
raise_deprecation » all fields
set_verbose » verbose
field max_tokens_limit: Optional[int] = None#
If set, restricts the docs to return from store based on tokens, enforced only
for StuffDocumentChain
field retriever: BaseRetriever [Required]#
Index to connect to. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-13 | field retriever: BaseRetriever [Required]#
Index to connect to.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, retriever: langchain.schema.BaseRetriever, condense_question_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['chat_history', 'question'], output_parser=None, partial_variables={}, template='Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n\nChat History:\n{chat_history}\nFollow Up Input: {question}\nStandalone question:', template_format='f-string', validate_template=True), chain_type: str = 'stuff', verbose: bool = False, condense_question_llm: Optional[langchain.base_language.BaseLanguageModel] = None, combine_docs_chain_kwargs: Optional[Dict] = None, callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → langchain.chains.conversational_retrieval.base.BaseConversationalRetrievalChain[source]#
Load chain from LLM.
pydantic model langchain.chains.FlareChain[source]#
Validators
raise_deprecation » all fields
set_verbose » verbose
field max_iter: int = 10#
field min_prob: float = 0.2#
field min_token_gap: int = 5#
field num_pad_tokens: int = 2#
field output_parser: FinishedOutputParser [Optional]#
field question_generator_chain: QuestionGeneratorChain [Required]#
field response_chain: _ResponseChain [Optional]#
field retriever: BaseRetriever [Required]#
field start_with_retrieval: bool = True# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-14 | field start_with_retrieval: bool = True#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, max_generation_len: int = 32, **kwargs: Any) → langchain.chains.flare.base.FlareChain[source]#
property input_keys: List[str]#
Input keys this chain expects.
property output_keys: List[str]#
Output keys this chain expects.
pydantic model langchain.chains.GraphCypherQAChain[source]#
Chain for question-answering against a graph by generating Cypher statements.
Validators
raise_deprecation » all fields
set_verbose » verbose
field cypher_generation_chain: LLMChain [Required]#
field graph: Neo4jGraph [Required]#
field qa_chain: LLMChain [Required]#
field return_direct: bool = False#
Whether or not to return the result of querying the graph directly.
field return_intermediate_steps: bool = False#
Whether or not to return the intermediate steps along with the final answer.
field top_k: int = 10#
Number of results to return from the query | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-15 | field top_k: int = 10#
Number of results to return from the query
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, *, qa_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['context', 'question'], output_parser=None, partial_variables={}, template="You are an assistant that helps to form nice and human understandable answers.\nThe information part contains the provided information that you must use to construct an answer.\nThe provided information is authorative, you must never doubt it or try to use your internal knowledge to correct it.\nMake the answer sound as a response to the question. Do not mention that you based the result on the given information.\nIf the provided information is empty, say that you don't know the answer.\nInformation:\n{context}\n\nQuestion: {question}\nHelpful Answer:", template_format='f-string', validate_template=True), cypher_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['schema', 'question'], output_parser=None, partial_variables={}, template='Task:Generate Cypher statement to query a graph database.\nInstructions:\nUse only the provided relationship types and properties in the schema.\nDo not use any other relationship types or properties that are not provided.\nSchema:\n{schema}\nNote: Do not include any explanations or apologies in your responses.\nDo not respond to any questions that might ask anything else than for you to construct a Cypher statement.\nDo not include any text except the generated Cypher statement.\n\nThe question is:\n{question}', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.graph_qa.cypher.GraphCypherQAChain[source]#
Initialize from LLM.
pydantic model langchain.chains.GraphQAChain[source]#
Chain for question-answering against a graph.
Validators | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-16 | Chain for question-answering against a graph.
Validators
raise_deprecation » all fields
set_verbose » verbose
field entity_extraction_chain: LLMChain [Required]#
field graph: NetworkxEntityGraph [Required]#
field qa_chain: LLMChain [Required]#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, qa_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['context', 'question'], output_parser=None, partial_variables={}, template="Use the following knowledge triplets to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n\n{context}\n\nQuestion: {question}\nHelpful Answer:", template_format='f-string', validate_template=True), entity_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['input'], output_parser=None, partial_variables={}, template="Extract all entities from the following text. As a guideline, a proper noun is generally capitalized. You should definitely extract all names and places.\n\nReturn the output as a single comma-separated list, or NONE if there is nothing of note to return.\n\nEXAMPLE\ni'm trying to improve Langchain's interfaces, the UX, its integrations with various products the user might want ... a lot of stuff.\nOutput: Langchain\nEND OF EXAMPLE\n\nEXAMPLE\ni'm trying to improve Langchain's interfaces, the UX, its integrations with various products the user might want ... a lot of stuff. I'm working with Sam.\nOutput: Langchain, Sam\nEND OF EXAMPLE\n\nBegin!\n\n{input}\nOutput:", template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.graph_qa.base.GraphQAChain[source]#
Initialize from LLM. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-17 | Initialize from LLM.
pydantic model langchain.chains.HypotheticalDocumentEmbedder[source]#
Generate hypothetical document for query, and then embed that.
Based on https://arxiv.org/abs/2212.10496
Validators
raise_deprecation » all fields
set_verbose » verbose
field base_embeddings: Embeddings [Required]#
field llm_chain: LLMChain [Required]#
combine_embeddings(embeddings: List[List[float]]) → List[float][source]#
Combine embeddings into final embeddings.
embed_documents(texts: List[str]) → List[List[float]][source]#
Call the base embeddings.
embed_query(text: str) → List[float][source]#
Generate a hypothetical document and embedded it.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, base_embeddings: langchain.embeddings.base.Embeddings, prompt_key: str, **kwargs: Any) → langchain.chains.hyde.base.HypotheticalDocumentEmbedder[source]#
Load and use LLMChain for a specific prompt key.
property input_keys: List[str]#
Input keys for Hyde’s LLM chain.
property output_keys: List[str]#
Output keys for Hyde’s LLM chain.
pydantic model langchain.chains.LLMBashChain[source]#
Chain that interprets a prompt and executes bash code to perform bash operations.
Example
from langchain import LLMBashChain, OpenAI
llm_bash = LLMBashChain.from_llm(OpenAI())
Validators
raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose
validate_prompt » all fields
field llm: Optional[BaseLanguageModel] = None#
[Deprecated] LLM wrapper to use.
field llm_chain: LLMChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-18 | field llm_chain: LLMChain [Required]#
field prompt: BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=BashOutputParser(), partial_variables={}, template='If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put "#!/bin/bash" in your answer. Make sure to reason step by step, using this format:\n\nQuestion: "copy the files in the directory named \'target\' into a new directory at the same level as target called \'myNewDirectory\'"\n\nI need to take the following actions:\n- List all files in the directory\n- Create a new directory\n- Copy the files from the first directory into the second directory\n```bash\nls\nmkdir myNewDirectory\ncp -r target/* myNewDirectory\n```\n\nThat is the format. Begin!\n\nQuestion: {question}', template_format='f-string', validate_template=True)#
[Deprecated] | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-19 | [Deprecated]
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=BashOutputParser(), partial_variables={}, template='If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put "#!/bin/bash" in your answer. Make sure to reason step by step, using this format:\n\nQuestion: "copy the files in the directory named \'target\' into a new directory at the same level as target called \'myNewDirectory\'"\n\nI need to take the following actions:\n- List all files in the directory\n- Create a new directory\n- Copy the files from the first directory into the second directory\n```bash\nls\nmkdir myNewDirectory\ncp -r target/* myNewDirectory\n```\n\nThat is the format. Begin!\n\nQuestion: {question}', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.llm_bash.base.LLMBashChain[source]#
pydantic model langchain.chains.LLMChain[source]#
Chain to run queries against LLMs.
Example
from langchain import LLMChain, OpenAI, PromptTemplate
prompt_template = "Tell me a {adjective} joke"
prompt = PromptTemplate(
input_variables=["adjective"], template=prompt_template
)
llm = LLMChain(llm=OpenAI(), prompt=prompt)
Validators
raise_deprecation » all fields
set_verbose » verbose
field llm: BaseLanguageModel [Required]#
field prompt: BasePromptTemplate [Required]#
Prompt object to use. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-20 | field prompt: BasePromptTemplate [Required]#
Prompt object to use.
async aapply(input_list: List[Dict[str, Any]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None) → List[Dict[str, str]][source]#
Utilize the LLM generate method for speed gains.
async aapply_and_parse(input_list: List[Dict[str, Any]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None) → Sequence[Union[str, List[str], Dict[str, str]]][source]#
Call apply and then parse the results.
async agenerate(input_list: List[Dict[str, Any]], run_manager: Optional[langchain.callbacks.manager.AsyncCallbackManagerForChainRun] = None) → langchain.schema.LLMResult[source]#
Generate LLM result from inputs.
apply(input_list: List[Dict[str, Any]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None) → List[Dict[str, str]][source]#
Utilize the LLM generate method for speed gains.
apply_and_parse(input_list: List[Dict[str, Any]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None) → Sequence[Union[str, List[str], Dict[str, str]]][source]#
Call apply and then parse the results.
async apredict(callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → str[source]#
Format prompt with kwargs and pass to LLM.
Parameters
callbacks – Callbacks to pass to LLMChain | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-21 | Parameters
callbacks – Callbacks to pass to LLMChain
**kwargs – Keys to pass to prompt template.
Returns
Completion from LLM.
Example
completion = llm.predict(adjective="funny")
async apredict_and_parse(callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[str, List[str], Dict[str, str]][source]#
Call apredict and then parse the results.
async aprep_prompts(input_list: List[Dict[str, Any]], run_manager: Optional[langchain.callbacks.manager.AsyncCallbackManagerForChainRun] = None) → Tuple[List[langchain.schema.PromptValue], Optional[List[str]]][source]#
Prepare prompts from inputs.
create_outputs(response: langchain.schema.LLMResult) → List[Dict[str, str]][source]#
Create outputs from response.
classmethod from_string(llm: langchain.base_language.BaseLanguageModel, template: str) → langchain.chains.base.Chain[source]#
Create LLMChain from LLM and template.
generate(input_list: List[Dict[str, Any]], run_manager: Optional[langchain.callbacks.manager.CallbackManagerForChainRun] = None) → langchain.schema.LLMResult[source]#
Generate LLM result from inputs.
predict(callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → str[source]#
Format prompt with kwargs and pass to LLM.
Parameters
callbacks – Callbacks to pass to LLMChain
**kwargs – Keys to pass to prompt template.
Returns
Completion from LLM.
Example
completion = llm.predict(adjective="funny") | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-22 | Completion from LLM.
Example
completion = llm.predict(adjective="funny")
predict_and_parse(callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[str, List[str], Dict[str, Any]][source]#
Call predict and then parse the results.
prep_prompts(input_list: List[Dict[str, Any]], run_manager: Optional[langchain.callbacks.manager.CallbackManagerForChainRun] = None) → Tuple[List[langchain.schema.PromptValue], Optional[List[str]]][source]#
Prepare prompts from inputs.
pydantic model langchain.chains.LLMCheckerChain[source]#
Chain for question-answering with self-verification.
Example
from langchain import OpenAI, LLMCheckerChain
llm = OpenAI(temperature=0.7)
checker_chain = LLMCheckerChain.from_llm(llm)
Validators
raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose
field check_assertions_prompt: PromptTemplate = PromptTemplate(input_variables=['assertions'], output_parser=None, partial_variables={}, template='Here is a bullet point list of assertions:\n{assertions}\nFor each assertion, determine whether it is true or false. If it is false, explain why.\n\n', template_format='f-string', validate_template=True)#
[Deprecated]
field create_draft_answer_prompt: PromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='{question}\n\n', template_format='f-string', validate_template=True)#
[Deprecated] | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-23 | [Deprecated]
field list_assertions_prompt: PromptTemplate = PromptTemplate(input_variables=['statement'], output_parser=None, partial_variables={}, template='Here is a statement:\n{statement}\nMake a bullet point list of the assumptions you made when producing the above statement.\n\n', template_format='f-string', validate_template=True)#
[Deprecated]
field llm: Optional[BaseLanguageModel] = None#
[Deprecated] LLM wrapper to use.
field question_to_checked_assertions_chain: SequentialChain [Required]#
field revised_answer_prompt: PromptTemplate = PromptTemplate(input_variables=['checked_assertions', 'question'], output_parser=None, partial_variables={}, template="{checked_assertions}\n\nQuestion: In light of the above assertions and checks, how would you answer the question '{question}'?\n\nAnswer:", template_format='f-string', validate_template=True)#
[Deprecated] Prompt to use when questioning the documents. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-24 | [Deprecated] Prompt to use when questioning the documents.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, create_draft_answer_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='{question}\n\n', template_format='f-string', validate_template=True), list_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['statement'], output_parser=None, partial_variables={}, template='Here is a statement:\n{statement}\nMake a bullet point list of the assumptions you made when producing the above statement.\n\n', template_format='f-string', validate_template=True), check_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['assertions'], output_parser=None, partial_variables={}, template='Here is a bullet point list of assertions:\n{assertions}\nFor each assertion, determine whether it is true or false. If it is false, explain why.\n\n', template_format='f-string', validate_template=True), revised_answer_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['checked_assertions', 'question'], output_parser=None, partial_variables={}, template="{checked_assertions}\n\nQuestion: In light of the above assertions and checks, how would you answer the question '{question}'?\n\nAnswer:", template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.llm_checker.base.LLMCheckerChain[source]#
pydantic model langchain.chains.LLMMathChain[source]#
Chain that interprets a prompt and executes python code to do math.
Example
from langchain import LLMMathChain, OpenAI
llm_math = LLMMathChain.from_llm(OpenAI())
Validators
raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-25 | raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose
field llm: Optional[BaseLanguageModel] = None#
[Deprecated] LLM wrapper to use.
field llm_chain: LLMChain [Required]#
field prompt: BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='Translate a math problem into a expression that can be executed using Python\'s numexpr library. Use the output of running this code to answer the question.\n\nQuestion: ${{Question with math problem.}}\n```text\n${{single line mathematical expression that solves the problem}}\n```\n...numexpr.evaluate(text)...\n```output\n${{Output of running the code}}\n```\nAnswer: ${{Answer}}\n\nBegin.\n\nQuestion: What is 37593 * 67?\n```text\n37593 * 67\n```\n...numexpr.evaluate("37593 * 67")...\n```output\n2518731\n```\nAnswer: 2518731\n\nQuestion: 37593^(1/5)\n```text\n37593**(1/5)\n```\n...numexpr.evaluate("37593**(1/5)")...\n```output\n8.222831614237718\n```\nAnswer: 8.222831614237718\n\nQuestion: {question}\n', template_format='f-string', validate_template=True)#
[Deprecated] Prompt to use to translate to python if necessary. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-26 | [Deprecated] Prompt to use to translate to python if necessary.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='Translate a math problem into a expression that can be executed using Python\'s numexpr library. Use the output of running this code to answer the question.\n\nQuestion: ${{Question with math problem.}}\n```text\n${{single line mathematical expression that solves the problem}}\n```\n...numexpr.evaluate(text)...\n```output\n${{Output of running the code}}\n```\nAnswer: ${{Answer}}\n\nBegin.\n\nQuestion: What is 37593 * 67?\n```text\n37593 * 67\n```\n...numexpr.evaluate("37593 * 67")...\n```output\n2518731\n```\nAnswer: 2518731\n\nQuestion: 37593^(1/5)\n```text\n37593**(1/5)\n```\n...numexpr.evaluate("37593**(1/5)")...\n```output\n8.222831614237718\n```\nAnswer: 8.222831614237718\n\nQuestion: {question}\n', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.llm_math.base.LLMMathChain[source]#
pydantic model langchain.chains.LLMRequestsChain[source]#
Chain that hits a URL and then uses an LLM to parse results.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_environment » all fields
field llm_chain: LLMChain [Required]#
field requests_wrapper: TextRequestsWrapper [Optional]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-27 | field requests_wrapper: TextRequestsWrapper [Optional]#
field text_length: int = 8000#
pydantic model langchain.chains.LLMSummarizationCheckerChain[source]#
Chain for question-answering with self-verification.
Example
from langchain import OpenAI, LLMSummarizationCheckerChain
llm = OpenAI(temperature=0.0)
checker_chain = LLMSummarizationCheckerChain.from_llm(llm)
Validators
raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose
field are_all_true_prompt: PromptTemplate = PromptTemplate(input_variables=['checked_assertions'], output_parser=None, partial_variables={}, template='Below are some assertions that have been fact checked and are labeled as true or false.\n\nIf all of the assertions are true, return "True". If any of the assertions are false, return "False".\n\nHere are some examples:\n===\n\nChecked Assertions: """\n- The sky is red: False\n- Water is made of lava: False\n- The sun is a star: True\n"""\nResult: False\n\n===\n\nChecked Assertions: """\n- The sky is blue: True\n- Water is wet: True\n- The sun is a star: True\n"""\nResult: True\n\n===\n\nChecked Assertions: """\n- The sky is blue - True\n- Water is made of lava- False\n- The sun is a star - True\n"""\nResult: False\n\n===\n\nChecked Assertions:"""\n{checked_assertions}\n"""\nResult:', template_format='f-string', validate_template=True)#
[Deprecated] | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-28 | [Deprecated]
field check_assertions_prompt: PromptTemplate = PromptTemplate(input_variables=['assertions'], output_parser=None, partial_variables={}, template='You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.\n\nHere is a bullet point list of facts:\n"""\n{assertions}\n"""\n\nFor each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".\nIf the fact is false, explain why.\n\n', template_format='f-string', validate_template=True)#
[Deprecated]
field create_assertions_prompt: PromptTemplate = PromptTemplate(input_variables=['summary'], output_parser=None, partial_variables={}, template='Given some text, extract a list of facts from the text.\n\nFormat your output as a bulleted list.\n\nText:\n"""\n{summary}\n"""\n\nFacts:', template_format='f-string', validate_template=True)#
[Deprecated]
field llm: Optional[BaseLanguageModel] = None#
[Deprecated] LLM wrapper to use.
field max_checks: int = 2#
Maximum number of times to check the assertions. Default to double-checking. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-29 | Maximum number of times to check the assertions. Default to double-checking.
field revised_summary_prompt: PromptTemplate = PromptTemplate(input_variables=['checked_assertions', 'summary'], output_parser=None, partial_variables={}, template='Below are some assertions that have been fact checked and are labeled as true or false. If the answer is false, a suggestion is given for a correction.\n\nChecked Assertions:\n"""\n{checked_assertions}\n"""\n\nOriginal Summary:\n"""\n{summary}\n"""\n\nUsing these checked assertions, rewrite the original summary to be completely true.\n\nThe output should have the same structure and formatting as the original summary.\n\nSummary:', template_format='f-string', validate_template=True)#
[Deprecated]
field sequential_chain: SequentialChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-30 | classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, create_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['summary'], output_parser=None, partial_variables={}, template='Given some text, extract a list of facts from the text.\n\nFormat your output as a bulleted list.\n\nText:\n"""\n{summary}\n"""\n\nFacts:', template_format='f-string', validate_template=True), check_assertions_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['assertions'], output_parser=None, partial_variables={}, template='You are an expert fact checker. You have been hired by a major news organization to fact check a very important story.\n\nHere is a bullet point list of facts:\n"""\n{assertions}\n"""\n\nFor each fact, determine whether it is true or false about the subject. If you are unable to determine whether the fact is true or false, output "Undetermined".\nIf the fact is false, explain why.\n\n', template_format='f-string', validate_template=True), revised_summary_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['checked_assertions', 'summary'], output_parser=None, partial_variables={}, template='Below are some assertions that have been fact checked and are labeled as true or false. If the answer is false, a suggestion is given for a correction.\n\nChecked Assertions:\n"""\n{checked_assertions}\n"""\n\nOriginal Summary:\n"""\n{summary}\n"""\n\nUsing these checked assertions, rewrite the original summary to be completely true.\n\nThe output should have the same structure and formatting as the original summary.\n\nSummary:', template_format='f-string', validate_template=True), are_all_true_prompt: langchain.prompts.prompt.PromptTemplate = | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-31 | validate_template=True), are_all_true_prompt: langchain.prompts.prompt.PromptTemplate = PromptTemplate(input_variables=['checked_assertions'], output_parser=None, partial_variables={}, template='Below are some assertions that have been fact checked and are labeled as true or false.\n\nIf all of the assertions are true, return "True". If any of the assertions are false, return "False".\n\nHere are some examples:\n===\n\nChecked Assertions: """\n- The sky is red: False\n- Water is made of lava: False\n- The sun is a star: True\n"""\nResult: False\n\n===\n\nChecked Assertions: """\n- The sky is blue: True\n- Water is wet: True\n- The sun is a star: True\n"""\nResult: True\n\n===\n\nChecked Assertions: """\n- The sky is blue - True\n- Water is made of lava- False\n- The sun is a star - True\n"""\nResult: False\n\n===\n\nChecked Assertions:"""\n{checked_assertions}\n"""\nResult:', template_format='f-string', validate_template=True), verbose: bool = False, **kwargs: Any) → langchain.chains.llm_summarization_checker.base.LLMSummarizationCheckerChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-32 | pydantic model langchain.chains.MapReduceChain[source]#
Map-reduce chain.
Validators
raise_deprecation » all fields
set_verbose » verbose
field combine_documents_chain: BaseCombineDocumentsChain [Required]#
Chain to use to combine documents.
field text_splitter: TextSplitter [Required]#
Text splitter to use.
classmethod from_params(llm: langchain.base_language.BaseLanguageModel, prompt: langchain.prompts.base.BasePromptTemplate, text_splitter: langchain.text_splitter.TextSplitter, callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, combine_chain_kwargs: Optional[Mapping[str, Any]] = None, reduce_chain_kwargs: Optional[Mapping[str, Any]] = None, **kwargs: Any) → langchain.chains.mapreduce.MapReduceChain[source]#
Construct a map-reduce chain that uses the chain for map and reduce.
pydantic model langchain.chains.NebulaGraphQAChain[source]#
Chain for question-answering against a graph by generating nGQL statements.
Validators
raise_deprecation » all fields
set_verbose » verbose
field graph: NebulaGraph [Required]#
field ngql_generation_chain: LLMChain [Required]#
field qa_chain: LLMChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-33 | classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, *, qa_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['context', 'question'], output_parser=None, partial_variables={}, template="You are an assistant that helps to form nice and human understandable answers.\nThe information part contains the provided information that you must use to construct an answer.\nThe provided information is authorative, you must never doubt it or try to use your internal knowledge to correct it.\nMake the answer sound as a response to the question. Do not mention that you based the result on the given information.\nIf the provided information is empty, say that you don't know the answer.\nInformation:\n{context}\n\nQuestion: {question}\nHelpful Answer:", template_format='f-string', validate_template=True), ngql_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['schema', 'question'], output_parser=None, partial_variables={}, template="Task:Generate NebulaGraph Cypher statement to query a graph database.\n\nInstructions:\n\nFirst, generate cypher then convert it to NebulaGraph Cypher dialect(rather than standard):\n1. it requires explicit label specification when referring to node properties: v.`Foo`.name\n2. it uses double equals sign for comparison: `==` rather than `=`\nFor instance:\n```diff\n< MATCH (p:person)-[:directed]->(m:movie) WHERE m.name = 'The Godfather II'\n< RETURN p.name;\n---\n> MATCH (p:`person`)-[:directed]->(m:`movie`) WHERE m.`movie`.`name` == 'The Godfather II'\n> RETURN p.`person`.`name`;\n```\n\nUse only the provided relationship types and properties in the schema.\nDo not use any other relationship types or properties that are not | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-34 | types and properties in the schema.\nDo not use any other relationship types or properties that are not provided.\nSchema:\n{schema}\nNote: Do not include any explanations or apologies in your responses.\nDo not respond to any questions that might ask anything else than for you to construct a Cypher statement.\nDo not include any text except the generated Cypher statement.\n\nThe question is:\n{question}", template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.graph_qa.nebulagraph.NebulaGraphQAChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-35 | Initialize from LLM.
pydantic model langchain.chains.OpenAIModerationChain[source]#
Pass input through a moderation endpoint.
To use, you should have the openai python package installed, and the
environment variable OPENAI_API_KEY set with your API key.
Any parameters that are valid to be passed to the openai.create call can be passed
in, even if not explicitly saved on this class.
Example
from langchain.chains import OpenAIModerationChain
moderation = OpenAIModerationChain()
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_environment » all fields
field error: bool = False#
Whether or not to error if bad content was found.
field model_name: Optional[str] = None#
Moderation model name to use.
field openai_api_key: Optional[str] = None#
field openai_organization: Optional[str] = None#
pydantic model langchain.chains.OpenAPIEndpointChain[source]#
Chain interacts with an OpenAPI endpoint using natural language.
Validators
raise_deprecation » all fields
set_verbose » verbose
field api_operation: APIOperation [Required]#
field api_request_chain: LLMChain [Required]#
field api_response_chain: Optional[LLMChain] = None#
field param_mapping: _ParamMapping [Required]#
field requests: Requests [Optional]#
field return_intermediate_steps: bool = False#
deserialize_json_input(serialized_args: str) → dict[source]#
Use the serialized typescript dictionary.
Resolve the path, query params dict, and optional requestBody dict. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-36 | Resolve the path, query params dict, and optional requestBody dict.
classmethod from_api_operation(operation: langchain.tools.openapi.utils.api_models.APIOperation, llm: langchain.base_language.BaseLanguageModel, requests: Optional[langchain.requests.Requests] = None, verbose: bool = False, return_intermediate_steps: bool = False, raw_response: bool = False, callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → langchain.chains.api.openapi.chain.OpenAPIEndpointChain[source]#
Create an OpenAPIEndpointChain from an operation and a spec.
classmethod from_url_and_method(spec_url: str, path: str, method: str, llm: langchain.base_language.BaseLanguageModel, requests: Optional[langchain.requests.Requests] = None, return_intermediate_steps: bool = False, **kwargs: Any) → langchain.chains.api.openapi.chain.OpenAPIEndpointChain[source]#
Create an OpenAPIEndpoint from a spec at the specified url.
pydantic model langchain.chains.PALChain[source]#
Implements Program-Aided Language Models.
Validators
raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose
field get_answer_expr: str = 'print(solution())'#
field llm: Optional[BaseLanguageModel] = None#
[Deprecated]
field llm_chain: LLMChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-37 | field prompt: BasePromptTemplate = PromptTemplate(input_variables=['question'], output_parser=None, partial_variables={}, template='Q: Olivia has $23. She bought five bagels for $3 each. How much money does she have left?\n\n# solution in Python:\n\n\ndef solution():\n """Olivia has $23. She bought five bagels for $3 each. How much money does she have left?"""\n money_initial = 23\n bagels = 5\n bagel_cost = 3\n money_spent = bagels * bagel_cost\n money_left = money_initial - money_spent\n result = money_left\n return result\n\n\n\n\n\nQ: Michael had 58 golf balls. On tuesday, he lost 23 golf balls. On wednesday, he lost 2 more. How many golf balls did he have at the end of wednesday?\n\n# solution in Python:\n\n\ndef solution():\n """Michael had 58 golf balls. On tuesday, he lost 23 golf balls. On wednesday, he lost 2 more. How many golf balls did he have at the end of wednesday?"""\n golf_balls_initial = 58\n golf_balls_lost_tuesday = 23\n golf_balls_lost_wednesday = 2\n golf_balls_left = golf_balls_initial - golf_balls_lost_tuesday - golf_balls_lost_wednesday\n result = golf_balls_left\n return result\n\n\n\n\n\nQ: There were nine computers in the server room. Five more computers were installed each day, from monday to thursday. How many computers are now in the server room?\n\n# solution in Python:\n\n\ndef solution():\n """There were nine computers in the server room. Five more computers were installed | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-38 | solution():\n """There were nine computers in the server room. Five more computers were installed each day, from monday to thursday. How many computers are now in the server room?"""\n computers_initial = 9\n computers_per_day = 5\n num_days = 4 # 4 days between monday and thursday\n computers_added = computers_per_day * num_days\n computers_total = computers_initial + computers_added\n result = computers_total\n return result\n\n\n\n\n\nQ: Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?\n\n# solution in Python:\n\n\ndef solution():\n """Shawn has five toys. For Christmas, he got two toys each from his mom and dad. How many toys does he have now?"""\n toys_initial = 5\n mom_toys = 2\n dad_toys = 2\n total_received = mom_toys + dad_toys\n total_toys = toys_initial + total_received\n result = total_toys\n return result\n\n\n\n\n\nQ: Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?\n\n# solution in Python:\n\n\ndef solution():\n """Jason had 20 lollipops. He gave Denny some lollipops. Now Jason has 12 lollipops. How many lollipops did Jason give to Denny?"""\n jason_lollipops_initial = 20\n jason_lollipops_after = 12\n denny_lollipops = jason_lollipops_initial - | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-39 | = 12\n denny_lollipops = jason_lollipops_initial - jason_lollipops_after\n result = denny_lollipops\n return result\n\n\n\n\n\nQ: Leah had 32 chocolates and her sister had 42. If they ate 35, how many pieces do they have left in total?\n\n# solution in Python:\n\n\ndef solution():\n """Leah had 32 chocolates and her sister had 42. If they ate 35, how many pieces do they have left in total?"""\n leah_chocolates = 32\n sister_chocolates = 42\n total_chocolates = leah_chocolates + sister_chocolates\n chocolates_eaten = 35\n chocolates_left = total_chocolates - chocolates_eaten\n result = chocolates_left\n return result\n\n\n\n\n\nQ: If there are 3 cars in the parking lot and 2 more cars arrive, how many cars are in the parking lot?\n\n# solution in Python:\n\n\ndef solution():\n """If there are 3 cars in the parking lot and 2 more cars arrive, how many cars are in the parking lot?"""\n cars_initial = 3\n cars_arrived = 2\n total_cars = cars_initial + cars_arrived\n result = total_cars\n return result\n\n\n\n\n\nQ: There are 15 trees in the grove. Grove workers will plant trees in the grove today. After they are done, there will be 21 trees. How many trees did the grove workers plant today?\n\n# solution in Python:\n\n\ndef solution():\n """There are 15 trees in the grove. Grove workers will plant trees in the grove today. After | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-40 | 15 trees in the grove. Grove workers will plant trees in the grove today. After they are done, there will be 21 trees. How many trees did the grove workers plant today?"""\n trees_initial = 15\n trees_after = 21\n trees_added = trees_after - trees_initial\n result = trees_added\n return result\n\n\n\n\n\nQ: {question}\n\n# solution in Python:\n\n\n', template_format='f-string', validate_template=True)# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-41 | [Deprecated]
field python_globals: Optional[Dict[str, Any]] = None#
field python_locals: Optional[Dict[str, Any]] = None#
field return_intermediate_steps: bool = False#
field stop: str = '\n\n'#
classmethod from_colored_object_prompt(llm: langchain.base_language.BaseLanguageModel, **kwargs: Any) → langchain.chains.pal.base.PALChain[source]#
Load PAL from colored object prompt.
classmethod from_math_prompt(llm: langchain.base_language.BaseLanguageModel, **kwargs: Any) → langchain.chains.pal.base.PALChain[source]#
Load PAL from math prompt.
pydantic model langchain.chains.QAGenerationChain[source]#
Validators
raise_deprecation » all fields
set_verbose » verbose
field input_key: str = 'text'#
field k: Optional[int] = None#
field llm_chain: LLMChain [Required]#
field output_key: str = 'questions'#
field text_splitter: TextSplitter = <langchain.text_splitter.RecursiveCharacterTextSplitter object>#
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, prompt: Optional[langchain.prompts.base.BasePromptTemplate] = None, **kwargs: Any) → langchain.chains.qa_generation.base.QAGenerationChain[source]#
property input_keys: List[str]#
Input keys this chain expects.
property output_keys: List[str]#
Output keys this chain expects.
pydantic model langchain.chains.QAWithSourcesChain[source]#
Question answering with sources over documents.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_naming » all fields
pydantic model langchain.chains.RetrievalQA[source]#
Chain for question-answering against an index.
Example | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-42 | Chain for question-answering against an index.
Example
from langchain.llms import OpenAI
from langchain.chains import RetrievalQA
from langchain.faiss import FAISS
from langchain.vectorstores.base import VectorStoreRetriever
retriever = VectorStoreRetriever(vectorstore=FAISS(...))
retrievalQA = RetrievalQA.from_llm(llm=OpenAI(), retriever=retriever)
Validators
raise_deprecation » all fields
set_verbose » verbose
field retriever: BaseRetriever [Required]#
pydantic model langchain.chains.RetrievalQAWithSourcesChain[source]#
Question-answering with sources over an index.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_naming » all fields
field max_tokens_limit: int = 3375#
Restrict the docs to return from store based on tokens,
enforced only for StuffDocumentChain and if reduce_k_below_max_tokens is to true
field reduce_k_below_max_tokens: bool = False#
Reduce the number of results to return from store based on tokens limit
field retriever: langchain.schema.BaseRetriever [Required]#
Index to connect to.
pydantic model langchain.chains.SQLDatabaseChain[source]#
Chain for interacting with SQL Database.
Example
from langchain import SQLDatabaseChain, OpenAI, SQLDatabase
db = SQLDatabase(...)
db_chain = SQLDatabaseChain.from_llm(OpenAI(), db)
Validators
raise_deprecation » all fields
raise_deprecation » all fields
set_verbose » verbose
field database: SQLDatabase [Required]#
SQL Database to connect to.
field llm: Optional[BaseLanguageModel] = None#
[Deprecated] LLM wrapper to use. | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-43 | [Deprecated] LLM wrapper to use.
field llm_chain: LLMChain [Required]#
field prompt: Optional[BasePromptTemplate] = None#
[Deprecated] Prompt to use to translate natural language to SQL.
field query_checker_prompt: Optional[BasePromptTemplate] = None#
The prompt template that should be used by the query checker
field return_direct: bool = False#
Whether or not to return the result of querying the SQL table directly.
field return_intermediate_steps: bool = False#
Whether or not to return the intermediate steps along with the final answer.
field top_k: int = 5#
Number of results to return from the query
field use_query_checker: bool = False#
Whether or not the query checker tool should be used to attempt
to fix the initial SQL from the LLM.
classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, db: langchain.sql_database.SQLDatabase, prompt: Optional[langchain.prompts.base.BasePromptTemplate] = None, **kwargs: Any) → langchain.chains.sql_database.base.SQLDatabaseChain[source]#
pydantic model langchain.chains.SQLDatabaseSequentialChain[source]#
Chain for querying SQL database that is a sequential chain.
The chain is as follows:
1. Based on the query, determine which tables to use.
2. Based on those tables, call the normal SQL database chain.
This is useful in cases where the number of tables in the database is large.
Validators
raise_deprecation » all fields
set_verbose » verbose
field decider_chain: LLMChain [Required]#
field return_intermediate_steps: bool = False#
field sql_chain: SQLDatabaseChain [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-44 | classmethod from_llm(llm: langchain.base_language.BaseLanguageModel, database: langchain.sql_database.SQLDatabase, query_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['input', 'table_info', 'dialect', 'top_k'], output_parser=None, partial_variables={}, template='Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer. Unless the user specifies in his question a specific number of examples he wishes to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n\nNever query for all the columns from a specific table, only ask for a the few relevant columns given the question.\n\nPay attention to use only the column names that you can see in the schema description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.\n\nUse the following format:\n\nQuestion: Question here\nSQLQuery: SQL Query to run\nSQLResult: Result of the SQLQuery\nAnswer: Final answer here\n\nOnly use the following tables:\n{table_info}\n\nQuestion: {input}', template_format='f-string', validate_template=True), decider_prompt: langchain.prompts.base.BasePromptTemplate = PromptTemplate(input_variables=['query', 'table_names'], output_parser=CommaSeparatedListOutputParser(), partial_variables={}, template='Given the below input question and list of potential tables, output a comma separated list of the table names that may be necessary to answer this question.\n\nQuestion: {query}\n\nTable Names: {table_names}\n\nRelevant Table Names:', template_format='f-string', validate_template=True), **kwargs: Any) → | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-45 | Table Names:', template_format='f-string', validate_template=True), **kwargs: Any) → langchain.chains.sql_database.base.SQLDatabaseSequentialChain[source]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-46 | Load the necessary chains.
pydantic model langchain.chains.SequentialChain[source]#
Chain where the outputs of one chain feed directly into next.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_chains » all fields
field chains: List[langchain.chains.base.Chain] [Required]#
field input_variables: List[str] [Required]#
field return_all: bool = False#
pydantic model langchain.chains.SimpleSequentialChain[source]#
Simple chain where the outputs of one step feed directly into next.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_chains » all fields
field chains: List[langchain.chains.base.Chain] [Required]#
field strip_outputs: bool = False#
pydantic model langchain.chains.TransformChain[source]#
Chain transform chain output.
Example
from langchain import TransformChain
transform_chain = TransformChain(input_variables=["text"],
output_variables["entities"], transform=func())
Validators
raise_deprecation » all fields
set_verbose » verbose
field input_variables: List[str] [Required]#
field output_variables: List[str] [Required]#
field transform: Callable[[Dict[str, str]], Dict[str, str]] [Required]#
pydantic model langchain.chains.VectorDBQA[source]#
Chain for question-answering against a vector database.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_search_type » all fields
field k: int = 4#
Number of documents to query for.
field search_kwargs: Dict[str, Any] [Optional]#
Extra search args.
field search_type: str = 'similarity'#
Search type to use over vectorstore. similarity or mmr.
field vectorstore: VectorStore [Required]# | https://python.langchain.com/en/latest/reference/modules/chains.html |
8ebc6ecad731-47 | field vectorstore: VectorStore [Required]#
Vector Database to connect to.
pydantic model langchain.chains.VectorDBQAWithSourcesChain[source]#
Question-answering with sources over a vector database.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_naming » all fields
field k: int = 4#
Number of results to return from store
field max_tokens_limit: int = 3375#
Restrict the docs to return from store based on tokens,
enforced only for StuffDocumentChain and if reduce_k_below_max_tokens is to true
field reduce_k_below_max_tokens: bool = False#
Reduce the number of results to return from store based on tokens limit
field search_kwargs: Dict[str, Any] [Optional]#
Extra search args.
field vectorstore: langchain.vectorstores.base.VectorStore [Required]#
Vector Database to connect to.
langchain.chains.load_chain(path: Union[str, pathlib.Path], **kwargs: Any) → langchain.chains.base.Chain[source]#
Unified method for loading a chain from LangChainHub or local fs.
previous
SQL Chain example
next
Agents
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/reference/modules/chains.html |
1b2a375cac19-0 | .rst
.pdf
Document Transformers
Document Transformers#
Transform documents
pydantic model langchain.document_transformers.EmbeddingsRedundantFilter[source]#
Filter that drops redundant documents by comparing their embeddings.
field embeddings: langchain.embeddings.base.Embeddings [Required]#
Embeddings to use for embedding document contents.
field similarity_fn: Callable = <function cosine_similarity>#
Similarity function for comparing documents. Function expected to take as input
two matrices (List[List[float]]) and return a matrix of scores where higher values
indicate greater similarity.
field similarity_threshold: float = 0.95#
Threshold for determining when two documents are similar enough
to be considered redundant.
async atransform_documents(documents: Sequence[langchain.schema.Document], **kwargs: Any) → Sequence[langchain.schema.Document][source]#
Asynchronously transform a list of documents.
transform_documents(documents: Sequence[langchain.schema.Document], **kwargs: Any) → Sequence[langchain.schema.Document][source]#
Filter down documents.
langchain.document_transformers.get_stateful_documents(documents: Sequence[langchain.schema.Document]) → Sequence[langchain.document_transformers._DocumentWithState][source]#
previous
Document Compressors
next
Memory
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/reference/modules/document_transformers.html |
f491735809bd-0 | .rst
.pdf
Docstore
Docstore#
Wrappers on top of docstores.
class langchain.docstore.InMemoryDocstore(_dict: Dict[str, langchain.schema.Document])[source]#
Simple in memory docstore in the form of a dict.
add(texts: Dict[str, langchain.schema.Document]) → None[source]#
Add texts to in memory dictionary.
search(search: str) → Union[str, langchain.schema.Document][source]#
Search via direct lookup.
class langchain.docstore.Wikipedia[source]#
Wrapper around wikipedia API.
search(search: str) → Union[str, langchain.schema.Document][source]#
Try to search for wiki page.
If page exists, return the page summary, and a PageWithLookups object.
If page does not exist, return similar entries.
previous
Indexes
next
Text Splitter
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/reference/modules/docstore.html |
9da9fd4ef926-0 | .rst
.pdf
Example Selector
Example Selector#
Logic for selecting examples to include in prompts.
pydantic model langchain.prompts.example_selector.LengthBasedExampleSelector[source]#
Select examples based on length.
Validators
calculate_example_text_lengths » example_text_lengths
field example_prompt: langchain.prompts.prompt.PromptTemplate [Required]#
Prompt template used to format the examples.
field examples: List[dict] [Required]#
A list of the examples that the prompt template expects.
field get_text_length: Callable[[str], int] = <function _get_length_based>#
Function to measure prompt length. Defaults to word count.
field max_length: int = 2048#
Max length for the prompt, beyond which examples are cut.
add_example(example: Dict[str, str]) → None[source]#
Add new example to list.
select_examples(input_variables: Dict[str, str]) → List[dict][source]#
Select which examples to use based on the input lengths.
pydantic model langchain.prompts.example_selector.MaxMarginalRelevanceExampleSelector[source]#
ExampleSelector that selects examples based on Max Marginal Relevance.
This was shown to improve performance in this paper:
https://arxiv.org/pdf/2211.13892.pdf
field fetch_k: int = 20#
Number of examples to fetch to rerank.
classmethod from_examples(examples: List[dict], embeddings: langchain.embeddings.base.Embeddings, vectorstore_cls: Type[langchain.vectorstores.base.VectorStore], k: int = 4, input_keys: Optional[List[str]] = None, fetch_k: int = 20, **vectorstore_cls_kwargs: Any) → langchain.prompts.example_selector.semantic_similarity.MaxMarginalRelevanceExampleSelector[source]#
Create k-shot example selector using example list and embeddings. | https://python.langchain.com/en/latest/reference/modules/example_selector.html |
9da9fd4ef926-1 | Create k-shot example selector using example list and embeddings.
Reshuffles examples dynamically based on query similarity.
Parameters
examples – List of examples to use in the prompt.
embeddings – An iniialized embedding API interface, e.g. OpenAIEmbeddings().
vectorstore_cls – A vector store DB interface class, e.g. FAISS.
k – Number of examples to select
input_keys – If provided, the search is based on the input variables
instead of all variables.
vectorstore_cls_kwargs – optional kwargs containing url for vector store
Returns
The ExampleSelector instantiated, backed by a vector store.
select_examples(input_variables: Dict[str, str]) → List[dict][source]#
Select which examples to use based on semantic similarity.
pydantic model langchain.prompts.example_selector.SemanticSimilarityExampleSelector[source]#
Example selector that selects examples based on SemanticSimilarity.
field example_keys: Optional[List[str]] = None#
Optional keys to filter examples to.
field input_keys: Optional[List[str]] = None#
Optional keys to filter input to. If provided, the search is based on
the input variables instead of all variables.
field k: int = 4#
Number of examples to select.
field vectorstore: langchain.vectorstores.base.VectorStore [Required]#
VectorStore than contains information about examples.
add_example(example: Dict[str, str]) → str[source]#
Add new example to vectorstore.
classmethod from_examples(examples: List[dict], embeddings: langchain.embeddings.base.Embeddings, vectorstore_cls: Type[langchain.vectorstores.base.VectorStore], k: int = 4, input_keys: Optional[List[str]] = None, **vectorstore_cls_kwargs: Any) → langchain.prompts.example_selector.semantic_similarity.SemanticSimilarityExampleSelector[source]# | https://python.langchain.com/en/latest/reference/modules/example_selector.html |
9da9fd4ef926-2 | Create k-shot example selector using example list and embeddings.
Reshuffles examples dynamically based on query similarity.
Parameters
examples – List of examples to use in the prompt.
embeddings – An initialized embedding API interface, e.g. OpenAIEmbeddings().
vectorstore_cls – A vector store DB interface class, e.g. FAISS.
k – Number of examples to select
input_keys – If provided, the search is based on the input variables
instead of all variables.
vectorstore_cls_kwargs – optional kwargs containing url for vector store
Returns
The ExampleSelector instantiated, backed by a vector store.
select_examples(input_variables: Dict[str, str]) → List[dict][source]#
Select which examples to use based on semantic similarity.
previous
PromptTemplates
next
Output Parsers
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/reference/modules/example_selector.html |
f491b7cb1df8-0 | .rst
.pdf
Python REPL
Python REPL#
For backwards compatibility.
pydantic model langchain.python.PythonREPL[source]#
Simulates a standalone Python REPL.
field globals: Optional[Dict] [Optional] (alias '_globals')#
field locals: Optional[Dict] [Optional] (alias '_locals')#
run(command: str) → str[source]#
Run command with own globals/locals and returns anything printed.
By Harrison Chase
© Copyright 2023, Harrison Chase.
Last updated on Jun 11, 2023. | https://python.langchain.com/en/latest/reference/modules/python.html |
2b223368723b-0 | .rst
.pdf
Agents
Agents#
Interface for agents.
pydantic model langchain.agents.Agent[source]#
Class responsible for calling the language model and deciding the action.
This is driven by an LLMChain. The prompt in the LLMChain MUST include
a variable called “agent_scratchpad” where the agent can put its
intermediary work.
field allowed_tools: Optional[List[str]] = None#
field llm_chain: langchain.chains.llm.LLMChain [Required]#
field output_parser: langchain.agents.agent.AgentOutputParser [Required]#
async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Action specifying what tool to use.
abstract classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool]) → langchain.prompts.base.BasePromptTemplate[source]#
Create a prompt for this class.
dict(**kwargs: Any) → Dict[source]#
Return dictionary representation of agent.
classmethod from_llm_and_tools(llm: langchain.base_language.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]#
Construct an agent from an LLM and tools. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-1 | Construct an agent from an LLM and tools.
get_allowed_tools() → Optional[List[str]][source]#
get_full_inputs(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → Dict[str, Any][source]#
Create the full inputs for the LLMChain from intermediate steps.
plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Action specifying what tool to use.
return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → langchain.schema.AgentFinish[source]#
Return response when agent has been stopped due to max iterations.
tool_run_logging_kwargs() → Dict[source]#
abstract property llm_prefix: str#
Prefix to append the LLM call with.
abstract property observation_prefix: str#
Prefix to append the observation with.
property return_values: List[str]#
Return values of the agent.
pydantic model langchain.agents.AgentExecutor[source]#
Consists of an agent using tools.
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
field agent: Union[BaseSingleActionAgent, BaseMultiActionAgent] [Required]#
field early_stopping_method: str = 'force'# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-2 | field early_stopping_method: str = 'force'#
field handle_parsing_errors: Union[bool, str, Callable[[OutputParserException], str]] = False#
field max_execution_time: Optional[float] = None#
field max_iterations: Optional[int] = 15#
field return_intermediate_steps: bool = False#
field tools: Sequence[BaseTool] [Required]#
classmethod from_agent_and_tools(agent: Union[langchain.agents.agent.BaseSingleActionAgent, langchain.agents.agent.BaseMultiActionAgent], tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Create from agent and tools.
lookup_tool(name: str) → langchain.tools.base.BaseTool[source]#
Lookup tool by name.
save(file_path: Union[pathlib.Path, str]) → None[source]#
Raise error - saving not supported for Agent Executors.
save_agent(file_path: Union[pathlib.Path, str]) → None[source]#
Save the underlying agent.
pydantic model langchain.agents.AgentOutputParser[source]#
abstract parse(text: str) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Parse text into agent action/finish.
class langchain.agents.AgentType(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#
CHAT_CONVERSATIONAL_REACT_DESCRIPTION = 'chat-conversational-react-description'#
CHAT_ZERO_SHOT_REACT_DESCRIPTION = 'chat-zero-shot-react-description'#
CONVERSATIONAL_REACT_DESCRIPTION = 'conversational-react-description'#
REACT_DOCSTORE = 'react-docstore'#
SELF_ASK_WITH_SEARCH = 'self-ask-with-search'# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-3 | SELF_ASK_WITH_SEARCH = 'self-ask-with-search'#
STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION = 'structured-chat-zero-shot-react-description'#
ZERO_SHOT_REACT_DESCRIPTION = 'zero-shot-react-description'#
pydantic model langchain.agents.BaseMultiActionAgent[source]#
Base Agent class.
abstract async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[List[langchain.schema.AgentAction], langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Actions specifying what tool to use.
dict(**kwargs: Any) → Dict[source]#
Return dictionary representation of agent.
get_allowed_tools() → Optional[List[str]][source]#
abstract plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[List[langchain.schema.AgentAction], langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Actions specifying what tool to use.
return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → langchain.schema.AgentFinish[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-4 | Return response when agent has been stopped due to max iterations.
save(file_path: Union[pathlib.Path, str]) → None[source]#
Save the agent.
Parameters
file_path – Path to file to save the agent to.
Example:
.. code-block:: python
# If working with agent executor
agent.agent.save(file_path=”path/agent.yaml”)
tool_run_logging_kwargs() → Dict[source]#
property return_values: List[str]#
Return values of the agent.
pydantic model langchain.agents.BaseSingleActionAgent[source]#
Base Agent class.
abstract async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Action specifying what tool to use.
dict(**kwargs: Any) → Dict[source]#
Return dictionary representation of agent.
classmethod from_llm_and_tools(llm: langchain.base_language.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, **kwargs: Any) → langchain.agents.agent.BaseSingleActionAgent[source]#
get_allowed_tools() → Optional[List[str]][source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-5 | get_allowed_tools() → Optional[List[str]][source]#
abstract plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Action specifying what tool to use.
return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], **kwargs: Any) → langchain.schema.AgentFinish[source]#
Return response when agent has been stopped due to max iterations.
save(file_path: Union[pathlib.Path, str]) → None[source]#
Save the agent.
Parameters
file_path – Path to file to save the agent to.
Example:
.. code-block:: python
# If working with agent executor
agent.agent.save(file_path=”path/agent.yaml”)
tool_run_logging_kwargs() → Dict[source]#
property return_values: List[str]#
Return values of the agent.
pydantic model langchain.agents.ConversationalAgent[source]#
An agent designed to hold a conversation in addition to using tools.
field ai_prefix: str = 'AI'#
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-6 | classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool], prefix: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n\nTOOLS:\n------\n\nAssistant has access to the following tools:', suffix: str = 'Begin!\n\nPrevious conversation history:\n{chat_history}\n\nNew input: {input}\n{agent_scratchpad}', format_instructions: str = 'To use a tool, please use the following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response to say to the Human, or if you do not need to use a tool, you MUST use the | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-7 | say to the Human, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\n{ai_prefix}: [your response here]\n```', ai_prefix: str = 'AI', human_prefix: str = 'Human', input_variables: Optional[List[str]] = None) → langchain.prompts.prompt.PromptTemplate[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-8 | Create prompt in the style of the zero shot agent.
Parameters
tools – List of tools the agent will have access to, used to format the
prompt.
prefix – String to put before the list of tools.
suffix – String to put after the list of tools.
ai_prefix – String to use before AI output.
human_prefix – String to use before human output.
input_variables – List of input variables the final prompt will expect.
Returns
A PromptTemplate with the template assembled from the pieces here. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-9 | classmethod from_llm_and_tools(llm: langchain.base_language.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, prefix: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n\nTOOLS:\n------\n\nAssistant has access to the following tools:', suffix: str = 'Begin!\n\nPrevious conversation history:\n{chat_history}\n\nNew input: {input}\n{agent_scratchpad}', format_instructions: str = 'To use a tool, please use the following format:\n\n```\nThought: Do I need to use a tool? Yes\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-10 | the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n```\n\nWhen you have a response to say to the Human, or if you do not need to use a tool, you MUST use the format:\n\n```\nThought: Do I need to use a tool? No\n{ai_prefix}: [your response here]\n```', ai_prefix: str = 'AI', human_prefix: str = 'Human', input_variables: Optional[List[str]] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-11 | Construct an agent from an LLM and tools.
property llm_prefix: str#
Prefix to append the llm call with.
property observation_prefix: str#
Prefix to append the observation with.
pydantic model langchain.agents.ConversationalChatAgent[source]#
An agent designed to hold a conversation in addition to using tools.
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]#
field template_tool_response: str = "TOOL RESPONSE: \n---------------------\n{observation}\n\nUSER'S INPUT\n--------------------\n\nOkay, so what is the response to my last comment? If using information obtained from the tools you must mention it explicitly without mentioning the tool names - I have forgotten all TOOL RESPONSES! Remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else."# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-12 | classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool], system_message: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful system that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.', human_message: str = "TOOLS\n------\nAssistant can ask the user to use tools to look up information that may be helpful in answering the users original question. The tools the human can use are:\n\n{{tools}}\n\n{format_instructions}\n\nUSER'S INPUT\n--------------------\nHere is the user's input (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else):\n\n{{{{input}}}}", input_variables: Optional[List[str]] = None, output_parser: Optional[langchain.schema.BaseOutputParser] = None) → langchain.prompts.base.BasePromptTemplate[source]#
Create a prompt for this class. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-13 | classmethod from_llm_and_tools(llm: langchain.base_language.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, system_message: str = 'Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful system that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.', human_message: str = "TOOLS\n------\nAssistant can ask the user to use tools to look up information that may be helpful in answering the users original question. The tools the human can use are:\n\n{{tools}}\n\n{format_instructions}\n\nUSER'S INPUT\n--------------------\nHere is the user's input (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else):\n\n{{{{input}}}}", input_variables: | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-14 | with a single action, and NOTHING else):\n\n{{{{input}}}}", input_variables: Optional[List[str]] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-15 | Construct an agent from an LLM and tools.
property llm_prefix: str#
Prefix to append the llm call with.
property observation_prefix: str#
Prefix to append the observation with.
pydantic model langchain.agents.LLMSingleActionAgent[source]#
field llm_chain: langchain.chains.llm.LLMChain [Required]#
field output_parser: langchain.agents.agent.AgentOutputParser [Required]#
field stop: List[str] [Required]#
async aplan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Action specifying what tool to use.
dict(**kwargs: Any) → Dict[source]#
Return dictionary representation of agent.
plan(intermediate_steps: List[Tuple[langchain.schema.AgentAction, str]], callbacks: Optional[Union[List[langchain.callbacks.base.BaseCallbackHandler], langchain.callbacks.base.BaseCallbackManager]] = None, **kwargs: Any) → Union[langchain.schema.AgentAction, langchain.schema.AgentFinish][source]#
Given input, decided what to do.
Parameters
intermediate_steps – Steps the LLM has taken to date,
along with observations
callbacks – Callbacks to run.
**kwargs – User inputs.
Returns
Action specifying what tool to use.
tool_run_logging_kwargs() → Dict[source]#
pydantic model langchain.agents.MRKLChain[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-16 | pydantic model langchain.agents.MRKLChain[source]#
Chain that implements the MRKL system.
Example
from langchain import OpenAI, MRKLChain
from langchain.chains.mrkl.base import ChainConfig
llm = OpenAI(temperature=0)
prompt = PromptTemplate(...)
chains = [...]
mrkl = MRKLChain.from_chains(llm=llm, prompt=prompt)
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
classmethod from_chains(llm: langchain.base_language.BaseLanguageModel, chains: List[langchain.agents.mrkl.base.ChainConfig], **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
User friendly way to initialize the MRKL chain.
This is intended to be an easy way to get up and running with the
MRKL chain.
Parameters
llm – The LLM to use as the agent LLM.
chains – The chains the MRKL system has access to.
**kwargs – parameters to be passed to initialization.
Returns
An initialized MRKL chain.
Example
from langchain import LLMMathChain, OpenAI, SerpAPIWrapper, MRKLChain
from langchain.chains.mrkl.base import ChainConfig
llm = OpenAI(temperature=0)
search = SerpAPIWrapper()
llm_math_chain = LLMMathChain(llm=llm)
chains = [
ChainConfig(
action_name = "Search",
action=search.search,
action_description="useful for searching"
),
ChainConfig(
action_name="Calculator",
action=llm_math_chain.run,
action_description="useful for doing math"
)
] | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-17 | action_description="useful for doing math"
)
]
mrkl = MRKLChain.from_chains(llm, chains)
pydantic model langchain.agents.ReActChain[source]#
Chain that implements the ReAct paper.
Example
from langchain import ReActChain, OpenAI
react = ReAct(llm=OpenAI())
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
pydantic model langchain.agents.ReActTextWorldAgent[source]#
Agent for the ReAct TextWorld chain.
classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool]) → langchain.prompts.base.BasePromptTemplate[source]#
Return default prompt.
pydantic model langchain.agents.SelfAskWithSearchChain[source]#
Chain that does self ask with search.
Example
from langchain import SelfAskWithSearchChain, OpenAI, GoogleSerperAPIWrapper
search_chain = GoogleSerperAPIWrapper()
self_ask = SelfAskWithSearchChain(llm=OpenAI(), search_chain=search_chain)
Validators
raise_deprecation » all fields
set_verbose » verbose
validate_return_direct_tool » all fields
validate_tools » all fields
pydantic model langchain.agents.StructuredChatAgent[source]#
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-18 | field output_parser: langchain.agents.agent.AgentOutputParser [Optional]#
classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool], prefix: str = 'Respond to the human as helpfully and accurately as possible. You have access to the following tools:', suffix: str = 'Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.\nThought:', human_message_template: str = '{input}\n\n{agent_scratchpad}', format_instructions: str = 'Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\n\nValid "action" values: "Final Answer" or {tool_names}\n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{{{{\n "action": $TOOL_NAME,\n "action_input": $INPUT\n}}}}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{{{{\n "action": "Final Answer",\n "action_input": "Final response to human"\n}}}}\n```', input_variables: Optional[List[str]] = None, memory_prompts: Optional[List[langchain.prompts.base.BasePromptTemplate]] = None) → langchain.prompts.base.BasePromptTemplate[source]#
Create a prompt for this class. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-19 | classmethod from_llm_and_tools(llm: langchain.base_language.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, prefix: str = 'Respond to the human as helpfully and accurately as possible. You have access to the following tools:', suffix: str = 'Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.\nThought:', human_message_template: str = '{input}\n\n{agent_scratchpad}', format_instructions: str = 'Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).\n\nValid "action" values: "Final Answer" or {tool_names}\n\nProvide only ONE action per $JSON_BLOB, as shown:\n\n```\n{{{{\n "action": $TOOL_NAME,\n "action_input": $INPUT\n}}}}\n```\n\nFollow this format:\n\nQuestion: input question to answer\nThought: consider previous and subsequent steps\nAction:\n```\n$JSON_BLOB\n```\nObservation: action result\n... (repeat Thought/Action/Observation N times)\nThought: I know what to respond\nAction:\n```\n{{{{\n "action": "Final Answer",\n "action_input": "Final response to human"\n}}}}\n```', input_variables: Optional[List[str]] = None, memory_prompts: Optional[List[langchain.prompts.base.BasePromptTemplate]] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-20 | Construct an agent from an LLM and tools.
property llm_prefix: str#
Prefix to append the llm call with.
property observation_prefix: str#
Prefix to append the observation with.
pydantic model langchain.agents.Tool[source]#
Tool that takes in function or coroutine directly.
field coroutine: Optional[Callable[[...], Awaitable[str]]] = None#
The asynchronous version of the function.
field description: str = ''#
Used to tell the model how/when/why to use the tool.
You can provide few-shot examples as a part of the description.
field func: Callable[[...], str] [Required]#
The function to run when the tool is called.
classmethod from_function(func: Callable, name: str, description: str, return_direct: bool = False, args_schema: Optional[Type[pydantic.main.BaseModel]] = None, **kwargs: Any) → langchain.tools.base.Tool[source]#
Initialize tool from a function.
property args: dict#
The tool’s input arguments.
pydantic model langchain.agents.ZeroShotAgent[source]#
Agent for the MRKL chain.
field output_parser: langchain.agents.agent.AgentOutputParser [Optional]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-21 | field output_parser: langchain.agents.agent.AgentOutputParser [Optional]#
classmethod create_prompt(tools: Sequence[langchain.tools.base.BaseTool], prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', suffix: str = 'Begin!\n\nQuestion: {input}\nThought:{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None) → langchain.prompts.prompt.PromptTemplate[source]#
Create prompt in the style of the zero shot agent.
Parameters
tools – List of tools the agent will have access to, used to format the
prompt.
prefix – String to put before the list of tools.
suffix – String to put after the list of tools.
input_variables – List of input variables the final prompt will expect.
Returns
A PromptTemplate with the template assembled from the pieces here. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-22 | Returns
A PromptTemplate with the template assembled from the pieces here.
classmethod from_llm_and_tools(llm: langchain.base_language.BaseLanguageModel, tools: Sequence[langchain.tools.base.BaseTool], callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', suffix: str = 'Begin!\n\nQuestion: {input}\nThought:{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, **kwargs: Any) → langchain.agents.agent.Agent[source]#
Construct an agent from an LLM and tools.
property llm_prefix: str#
Prefix to append the llm call with.
property observation_prefix: str#
Prefix to append the observation with.
langchain.agents.create_csv_agent(llm: langchain.base_language.BaseLanguageModel, path: Union[str, List[str]], pandas_kwargs: Optional[dict] = None, **kwargs: Any) → langchain.agents.agent.AgentExecutor[source]#
Create csv agent by loading to a dataframe and using pandas agent. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-23 | langchain.agents.create_json_agent(llm: langchain.base_language.BaseLanguageModel, toolkit: langchain.agents.agent_toolkits.json.toolkit.JsonToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = 'You are an agent designed to interact with JSON.\nYour goal is to return a final answer by interacting with the JSON.\nYou have access to the following tools which help you learn more about the JSON you are interacting with.\nOnly use the below tools. Only use the information returned by the below tools to construct your final answer.\nDo not make up any information that is not contained in the JSON.\nYour input to the tools should be in the form of `data["key"][0]` where `data` is the JSON blob you are interacting with, and the syntax used is Python. \nYou should only use keys that you know for a fact exist. You must validate that a key exists by seeing it previously when calling `json_spec_list_keys`. \nIf you have not seen a key in one of those responses, you cannot use it.\nYou should only add one key at a time to the path. You cannot add multiple keys at once.\nIf you encounter a "KeyError", go back to the previous key, look at the available keys, and try again.\n\nIf the question does not seem to be related to the JSON, just return "I don\'t know" as the answer.\nAlways begin your interaction with the `json_spec_list_keys` tool with input "data" to see what keys exist in the JSON.\n\nNote that sometimes the value at a given path is large. In this case, you will get an error "Value is a large dictionary, should explore its keys directly".\nIn this case, you should ALWAYS follow up by using the `json_spec_list_keys` tool to see what keys exist at that | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-24 | ALWAYS follow up by using the `json_spec_list_keys` tool to see what keys exist at that path.\nDo not simply refer the user to the JSON or a section of the JSON, as this is not a valid answer. Keep digging until you find the answer and explicitly return it.\n', suffix: str = 'Begin!"\n\nQuestion: {input}\nThought: I should look at the keys that exist in data to see what I have access to\n{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, verbose: bool = False, agent_executor_kwargs: Optional[Dict[str, Any]] = None, **kwargs: Dict[str, Any]) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-25 | Construct a json agent from an LLM and tools. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-26 | langchain.agents.create_openapi_agent(llm: langchain.base_language.BaseLanguageModel, toolkit: langchain.agents.agent_toolkits.openapi.toolkit.OpenAPIToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = "You are an agent designed to answer questions by making web requests to an API given the openapi spec.\n\nIf the question does not seem related to the API, return I don't know. Do not make up an answer.\nOnly use information provided by the tools to construct your response.\n\nFirst, find the base URL needed to make the request.\n\nSecond, find the relevant paths needed to answer the question. Take note that, sometimes, you might need to make more than one request to more than one path to answer the question.\n\nThird, find the required parameters needed to make the request. For GET requests, these are usually URL parameters and for POST requests, these are request body parameters.\n\nFourth, make the requests needed to answer the question. Ensure that you are sending the correct parameters to the request by checking which parameters are required. For parameters with a fixed set of values, please use the spec to look at which values are allowed.\n\nUse the exact parameter names as listed in the spec, do not make up any names or abbreviate the names of parameters.\nIf you get a not found error, ensure that you are using a path that actually exists in the spec.\n", suffix: str = 'Begin!\n\nQuestion: {input}\nThought: I should explore the spec to find the base url for the API.\n{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-27 | do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', verbose: bool = False, return_intermediate_steps: bool = False, agent_executor_kwargs: Optional[Dict[str, Any]] = None, **kwargs: Dict[str, Any]) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-28 | Construct a json agent from an LLM and tools.
langchain.agents.create_pandas_dataframe_agent(llm: langchain.base_language.BaseLanguageModel, df: Any, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: Optional[str] = None, suffix: Optional[str] = None, input_variables: Optional[List[str]] = None, verbose: bool = False, return_intermediate_steps: bool = False, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', agent_executor_kwargs: Optional[Dict[str, Any]] = None, include_df_in_prompt: Optional[bool] = True, **kwargs: Dict[str, Any]) → langchain.agents.agent.AgentExecutor[source]#
Construct a pandas agent from an LLM and dataframe. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-29 | langchain.agents.create_pbi_agent(llm: langchain.base_language.BaseLanguageModel, toolkit: Optional[langchain.agents.agent_toolkits.powerbi.toolkit.PowerBIToolkit], powerbi: Optional[langchain.utilities.powerbi.PowerBIDataset] = None, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = 'You are an agent designed to help users interact with a PowerBI Dataset.\n\nAgent has access to a tool that can write a query based on the question and then run those against PowerBI, Microsofts business intelligence tool. The questions from the users should be interpreted as related to the dataset that is available and not general questions about the world. If the question does not seem related to the dataset, just return "This does not appear to be part of this dataset." as the answer.\n\nGiven an input question, ask to run the questions against the dataset, then look at the results and return the answer, the answer should be a complete sentence that answers the question, if multiple rows are asked find a way to write that in a easily readible format for a human, also make sure to represent numbers in readable ways, like 1M instead of 1000000. Unless the user specifies a specific number of examples they wish to obtain, always limit your query to at most {top_k} results.\n', suffix: str = 'Begin!\n\nQuestion: {input}\nThought: I can first ask which tables I have, then how each table is defined and then ask the query tool the question I need, and finally create a nice sentence that answers the question.\n{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-30 | do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', examples: Optional[str] = None, input_variables: Optional[List[str]] = None, top_k: int = 10, verbose: bool = False, agent_executor_kwargs: Optional[Dict[str, Any]] = None, **kwargs: Dict[str, Any]) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-31 | Construct a pbi agent from an LLM and tools. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-32 | langchain.agents.create_pbi_chat_agent(llm: langchain.chat_models.base.BaseChatModel, toolkit: Optional[langchain.agents.agent_toolkits.powerbi.toolkit.PowerBIToolkit], powerbi: Optional[langchain.utilities.powerbi.PowerBIDataset] = None, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, output_parser: Optional[langchain.agents.agent.AgentOutputParser] = None, prefix: str = 'Assistant is a large language model built to help users interact with a PowerBI Dataset.\n\nAssistant has access to a tool that can write a query based on the question and then run those against PowerBI, Microsofts business intelligence tool. The questions from the users should be interpreted as related to the dataset that is available and not general questions about the world. If the question does not seem related to the dataset, just return "This does not appear to be part of this dataset." as the answer.\n\nGiven an input question, ask to run the questions against the dataset, then look at the results and return the answer, the answer should be a complete sentence that answers the question, if multiple rows are asked find a way to write that in a easily readible format for a human, also make sure to represent numbers in readable ways, like 1M instead of 1000000. Unless the user specifies a specific number of examples they wish to obtain, always limit your query to at most {top_k} results.\n', suffix: str = "TOOLS\n------\nAssistant can ask the user to use tools to look up information that may be helpful in answering the users original question. The tools the human can use are:\n\n{{tools}}\n\n{format_instructions}\n\nUSER'S INPUT\n--------------------\nHere is the user's input (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-33 | (remember to respond with a markdown code snippet of a json blob with a single action, and NOTHING else):\n\n{{{{input}}}}\n", examples: Optional[str] = None, input_variables: Optional[List[str]] = None, memory: Optional[langchain.memory.chat_memory.BaseChatMemory] = None, top_k: int = 10, verbose: bool = False, agent_executor_kwargs: Optional[Dict[str, Any]] = None, **kwargs: Dict[str, Any]) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-34 | Construct a pbi agent from an Chat LLM and tools.
If you supply only a toolkit and no powerbi dataset, the same LLM is used for both.
langchain.agents.create_spark_dataframe_agent(llm: langchain.llms.base.BaseLLM, df: Any, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = '\nYou are working with a spark dataframe in Python. The name of the dataframe is `df`.\nYou should use the tools below to answer the question posed of you:', suffix: str = '\nThis is the result of `print(df.first())`:\n{df}\n\nBegin!\nQuestion: {input}\n{agent_scratchpad}', input_variables: Optional[List[str]] = None, verbose: bool = False, return_intermediate_steps: bool = False, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', agent_executor_kwargs: Optional[Dict[str, Any]] = None, **kwargs: Dict[str, Any]) → langchain.agents.agent.AgentExecutor[source]#
Construct a spark agent from an LLM and dataframe. | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-35 | langchain.agents.create_spark_sql_agent(llm: langchain.base_language.BaseLanguageModel, toolkit: langchain.agents.agent_toolkits.spark_sql.toolkit.SparkSQLToolkit, callback_manager: Optional[langchain.callbacks.base.BaseCallbackManager] = None, prefix: str = 'You are an agent designed to interact with Spark SQL.\nGiven an input question, create a syntactically correct Spark SQL query to run, then look at the results of the query and return the answer.\nUnless the user specifies a specific number of examples they wish to obtain, always limit your query to at most {top_k} results.\nYou can order the results by a relevant column to return the most interesting examples in the database.\nNever query for all the columns from a specific table, only ask for the relevant columns given the question.\nYou have access to tools for interacting with the database.\nOnly use the below tools. Only use the information returned by the below tools to construct your final answer.\nYou MUST double check your query before executing it. If you get an error while executing a query, rewrite the query and try again.\n\nDO NOT make any DML statements (INSERT, UPDATE, DELETE, DROP etc.) to the database.\n\nIf the question does not seem related to the database, just return "I don\'t know" as the answer.\n', suffix: str = 'Begin!\n\nQuestion: {input}\nThought: I should look at the tables in the database to see what I can query.\n{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this | https://python.langchain.com/en/latest/reference/modules/agents.html |
2b223368723b-36 | Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: Optional[List[str]] = None, top_k: int = 10, max_iterations: Optional[int] = 15, max_execution_time: Optional[float] = None, early_stopping_method: str = 'force', verbose: bool = False, agent_executor_kwargs: Optional[Dict[str, Any]] = None, **kwargs: Dict[str, Any]) → langchain.agents.agent.AgentExecutor[source]# | https://python.langchain.com/en/latest/reference/modules/agents.html |
Subsets and Splits