import os from typing import List from chainlit.types import AskFileResponse from aimakerspace.text_utils import CharacterTextSplitter, TextFileLoader from aimakerspace.openai_utils.prompts import ( UserRolePrompt, SystemRolePrompt, AssistantRolePrompt, ) from aimakerspace.openai_utils.embedding import EmbeddingModel from aimakerspace.vectordatabase import VectorDatabase from aimakerspace.openai_utils.chatmodel import ChatOpenAI import chainlit as cl from langchain_text_splitters import RecursiveCharacterTextSplitter # from langchain_experimental.text_splitter import SemanticChunker # from langchain_openai.embeddings import OpenAIEmbeddings import importlib system_template = """\ Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer.""" system_role_prompt = SystemRolePrompt(system_template) user_prompt_template = """\ Context: {context} Question: {question} """ user_role_prompt = UserRolePrompt(user_prompt_template) class AgenticRAGPipeline: def __init__(self, graph: StateGraph, vector_db_retriever: VectorDatabase) -> None: self.graph = graph self.vector_db_retriever = vector_db_retriever async def run_pipeline(self, user_query: str): state = self.graph.execute({"text": user_query, "chunk_size": 100}) context_list = state["retriever"] context_prompt = "\n".join(context_list) formatted_system_prompt = system_role_prompt.create_message() formatted_user_prompt = user_role_prompt.create_message(question=user_query, context=context_prompt) async def generate_response(): async for chunk in self.llm.astream([formatted_system_prompt, formatted_user_prompt]): yield chunk return {"response": generate_response(), "context": context_list} text_splitter = RecursiveCharacterTextSplitter() def process_text_file(file: AskFileResponse): import tempfile from langchain_community.document_loaders.pdf import PyPDFLoader with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=file.name) as temp_file: temp_file_path = temp_file.name with open(temp_file_path, "wb") as f: f.write(file.content) if file.type == 'text/plain': text_loader = TextFileLoader(temp_file_path) documents = text_loader.load_documents() elif file.type == 'application/pdf': pdf_loader = PyPDFLoader(temp_file_path) documents = pdf_loader.load() else: raise ValueError("Provide a .txt or .pdf file") texts = [x.page_content for x in text_splitter.transform_documents(documents)] return texts @cl.on_chat_start async def on_chat_start(): files = None # Wait for the user to upload a file while files == None: files = await cl.AskFileMessage( content="Please upload a Text file or a PDF to begin!", accept=["text/plain", "application/pdf"], max_size_mb=12, timeout=180, ).send() file = files[0] msg = cl.Message( content=f"Processing `{file.name}`...", disable_human_feedback=True ) await msg.send() # load the file texts = process_text_file(file) print(f"Processing {len(texts)} text chunks") # Create a dict vector store vector_db = VectorDatabase() vector_db = await vector_db.abuild_from_list(texts) chat_openai = ChatOpenAI() retriever = vector_db """Graph code here""" from langchain.tools.retriever import create_retriever_tool from typing import Annotated, Literal, Sequence, TypedDict from typing import Annotated, Sequence, TypedDict from langchain_core.messages import BaseMessage from langgraph.graph.message import add_messages from langchain import hub from langchain_core.messages import BaseMessage, HumanMessage from langchain_core.output_parsers import StrOutputParser from langchain_core.prompts import PromptTemplate from langchain_openai import ChatOpenAI from pydantic import BaseModel, Field from langgraph.prebuilt import tools_condition from aimakerspace.vectordatabase import VectorDatabase retriever_tool = create_retriever_tool( retriever, "retrieve_blog_posts", "Search and return information about the responsible and ethical use of AI along with the development of policies and practices to protect civil rights and promote democratic values in the building, deployment, and government of automated systems.", ) tools = [retriever_tool] class AgentState(TypedDict): # The add_messages function defines how an update should be processed # Default is to replace. add_messages says "append" messages: Annotated[Sequence[BaseMessage], add_messages] ### Edges def grade_documents(state) -> Literal["generate", "rewrite"]: """ Determines whether the retrieved documents are relevant to the question. Args: state (messages): The current state Returns: str: A decision for whether the documents are relevant or not """ # Data model class grade(BaseModel): """Binary score for relevance check.""" binary_score: str = Field(description="Relevance score 'yes' or 'no'") # LLM model = ChatOpenAI(temperature=0, model="gpt-4o-mini", streaming=True) # LLM with tool and validation llm_with_tool = model.with_structured_output(grade) # Prompt prompt = PromptTemplate( template="""You are a grader assessing relevance of a retrieved document to a user question. \n Here is the retrieved document: \n\n {context} \n\n Here is the user question: {question} \n If the document contains keyword(s) or semantic meaning related to the user question, grade it as relevant. \n Give a binary score 'yes' or 'no' score to indicate whether the document is relevant to the question.""", input_variables=["context", "question"], ) # Chain chain = prompt | llm_with_tool messages = state["messages"] last_message = messages[-1] question = messages[0].content docs = last_message.content scored_result = chain.invoke({"question": question, "context": docs}) score = scored_result.binary_score if score == "yes": print("---DECISION: DOCS RELEVANT---") return "generate" else: print("---DECISION: DOCS NOT RELEVANT---") print(score) return "rewrite" ### Nodes def agent(state): """ Invokes the agent model to generate a response based on the current state. Given the question, it will decide to retrieve using the retriever tool, or simply end. Args: state (messages): The current state Returns: dict: The updated state with the agent response appended to messages """ print("---CALL AGENT---") messages = state["messages"] model = ChatOpenAI(temperature=0, streaming=True, model="gpt-4o-mini") model = model.bind_tools(tools) response = model.invoke(messages) # We return a list, because this will get added to the existing list return {"messages": [response]} def rewrite(state): """ Transform the query to produce a better question. Args: state (messages): The current state Returns: dict: The updated state with re-phrased question """ print("---TRANSFORM QUERY---") messages = state["messages"] question = messages[0].content msg = [ HumanMessage( content=f""" \n Look at the input and try to reason about the underlying semantic intent / meaning. \n Here is the initial question: \n ------- \n {question} \n ------- \n Formulate an improved question: """, ) ] # Grader model = ChatOpenAI(temperature=0, model="gpt-4o-mini", streaming=True) response = model.invoke(msg) return {"messages": [response]} def generate(state): """ Generate answer Args: state (messages): The current state Returns: dict: The updated state with re-phrased question """ print("---GENERATE---") messages = state["messages"] question = messages[0].content last_message = messages[-1] docs = last_message.content # Prompt prompt = hub.pull("rlm/rag-prompt") # LLM llm = ChatOpenAI(model_name="gpt-4o-mini", temperature=0, streaming=True) # Post-processing def format_docs(docs): return "\n\n".join(doc.page_content for doc in docs) # Chain rag_chain = prompt | llm | StrOutputParser() # Run response = rag_chain.invoke({"context": docs, "question": question}) return {"messages": [response]} from langgraph.graph import END, StateGraph, START from langgraph.prebuilt import ToolNode # Define a new graph workflow = StateGraph(AgentState) # Define the nodes we will cycle between workflow.add_node("agent", agent) # agent retrieve = ToolNode([retriever_tool]) workflow.add_node("retrieve", retrieve) # retrieval workflow.add_node("rewrite", rewrite) # Re-writing the question workflow.add_node( "generate", generate ) # Generating a response after we know the documents are relevant # Call agent node to decide to retrieve or not workflow.add_edge(START, "agent") # Decide whether to retrieve workflow.add_conditional_edges( "agent", # Assess agent decision tools_condition, { # Translate the condition outputs to nodes in our graph "tools": "retrieve", END: END, }, ) # Edges taken after the `action` node is called. workflow.add_conditional_edges( "retrieve", # Assess agent decision grade_documents, ) workflow.add_edge("generate", END) workflow.add_edge("rewrite", "agent") # Compile graph = workflow.compile() """END GRAPH CODE""" # Create a chain retrieval_augmented_qa_pipeline = AgenticRAGPipeline(graph=graph, vector_db_retriever=vector_db) # Let the user know that the system is ready msg.content = f"Processing `{file.name}` done. You can now ask questions!" await msg.update() cl.user_session.set("chain", retrieval_augmented_qa_pipeline) @cl.on_message async def main(message): chain = cl.user_session.get("chain") msg = cl.Message(content="") result = await chain.arun_pipeline(message.content) async for stream_resp in result["response"]: await msg.stream_token(stream_resp) await msg.send()