完成快速入门。

app.py

@@ -6,12 +6,13 @@ def chatOpenAI(input):
     return llm(input)
 
 with gr.Blocks() as demo:
+    gr.Markdown("# LangChain Test，LLM跑步上车。")
     gr.Markdown(
         '''
-        # LangChain Test
-        LLM跑步上车。
-        LangChain进度：
-            2023/4/15，接入openAI，简单测试。
+        | 日期 |   进度 | 备注 |
+        | :--: | :--- | :--: |
+        |   2023/04/14   |   接入openAI，简单测试。| |
+        | 2023/04/15 | &nbsp;&nbsp;熟悉LangChain API。<br> &nbsp;&nbsp;熟悉Chain的概念。 <br> &nbsp;&nbsp;熟悉agent goole search。<br> &nbsp;&nbsp;熟悉Prompt Template。| |
         ''')
     gr.Interface(fn=chatOpenAI, inputs="text", outputs="text")
 demo.launch()

openai_chat

@@ -0,0 +1,13 @@
+from langchain.chat_models import ChatOpenAI
+from langchain.schema import (
+    AIMessage,
+    HumanMessage,
+    SystemMessage
+)
+
+chat = ChatOpenAI(temperature=0.5)
+print(
+    chat([
+        SystemMessage(content="你是一名优秀的数学老师"),
+        HumanMessage(content="圆的面积怎么计算？"),
+    ]).content)

openai_chat_agent.py

@@ -0,0 +1,19 @@
+from langchain.agents import load_tools
+from langchain.agents import initialize_agent
+from langchain.agents import AgentType
+from langchain.chat_models import ChatOpenAI
+from langchain.llms import OpenAI
+
+# First, let's load the language model we're going to use to control the agent.
+chat = ChatOpenAI(temperature=0)
+
+# Next, let's load some tools to use. Note that the `llm-math` tool uses an LLM, so we need to pass that in.
+llm = OpenAI(temperature=0)
+tools = load_tools(["serpapi", "llm-math"], llm=llm)
+
+
+# Finally, let's initialize an agent with the tools, the language model, and the type of agent we want to use.
+agent = initialize_agent(tools, chat, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True)
+
+# Now let's test it out!
+agent.run("作为一名优秀的投资理财市，您结合2023年100名优秀专业投资师的报告，给出投资建议。")

openai_chat_prompt_template.py

@@ -0,0 +1,25 @@
+from langchain.chat_models import ChatOpenAI
+from langchain import LLMChain
+from langchain.prompts.chat import (
+    ChatPromptTemplate,
+    SystemMessagePromptTemplate,
+    HumanMessagePromptTemplate
+)
+
+chat = ChatOpenAI(temperature=0)
+
+template = "你是一名翻译助手。把{input_language} 翻译为 {output_language}。"
+system_message_prompt = SystemMessagePromptTemplate.from_template(template)
+
+human_template = "{text}"
+human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)
+
+# 这里是使用chat请求，返回BaseMessage。
+chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])
+result = chat(chat_prompt.format_prompt(input_language="中文", output_language="英语", text="我想请假").to_messages())
+print(result.content)
+
+# 这里是使用chain请求，返回str, 带有聊天模型的chain。
+chain = LLMChain(llm=chat, prompt=chat_prompt)
+result = chain.run(input_language="中文", output_language="英语", text="我想请假")
+print(result)

openai_prompt_template.py

@@ -7,5 +7,5 @@ prompt = PromptTemplate(
     input_variables=["product"],
     template="What is a good name for a company that makes {product}?"
 )
-chain = LLMChain(llm=llm,prompt=prompt)
+chain = LLMChain(llm=llm, prompt=prompt)
 print(chain.run("colorful socks"))