Last updated
from llama_index.llms import ChatMessage, OpenAILike
llm = OpenAILike(
api_base="http://localhost:1234/v1",
timeout=600, # secs
api_key="loremIpsum",
is_chat_model=True,
context_window=32768,
)
chat_history = [
ChatMessage(role="system", content="You are a bartender."),
ChatMessage(role="user", content="What do I enjoy drinking?"),
]
output = llm.chat(chat_history)
print(output)from langchain.schema import HumanMessage, SystemMessage
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
openai_api_base="http://localhost:1234/v1",
request_timeout=600, # secs, I guess.
openai_api_key="loremIpsum",
max_tokens=32768,
)
chat_history = [
SystemMessage(content="You are a bartender."),
HumanMessage(content="What do I enjoy drinking?"),
]
print(llm(chat_history))from llama_index import ServiceContext, SimpleDirectoryReader, VectorStoreIndex
service_context = ServiceContext.from_defaults(
embed_model="local",
llm=llm, # This should be the LLM initialized in the task above.
)
documents = SimpleDirectoryReader(
input_dir="mock_notebook/",
).load_data()
index = VectorStoreIndex.from_documents(
documents=documents,
service_context=service_context,
)
engine = index.as_query_engine(
service_context=service_context,
)
output = engine.query("What do I like to drink?")
print(output)from langchain_community.document_loaders import DirectoryLoader
# pip install "unstructured[md]"
loader = DirectoryLoader("mock_notebook/", glob="*.md")
docs = loader.load()
from langchain.text_splitter import RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
splits = text_splitter.split_documents(docs)
from langchain_community.embeddings.fastembed import FastEmbedEmbeddings
from langchain_community.vectorstores import Chroma
vectorstore = Chroma.from_documents(documents=splits, embedding=FastEmbedEmbeddings())
retriever = vectorstore.as_retriever()
from langchain import hub
# pip install langchainhub
prompt = hub.pull("rlm/rag-prompt")
def format_docs(docs):
return "\n\n".join(doc.page_content for doc in docs)
from langchain_core.runnables import RunnablePassthrough
rag_chain = (
{"context": retriever | format_docs, "question": RunnablePassthrough()}
| prompt
| llm # This should be the LLM initialized in the task above.
)
print(rag_chain.invoke("What do I like to drink?"))# Everything from above, till and including the creation of the index.
engine = index.as_chat_engine()
output = engine.chat("What do I like to drink?")
print(output) # "You enjoy drinking coffee."
output = engine.chat("How do I brew it?")
print(output) # "You brew coffee with a Aeropress."# Everything above this line is the same as that of the last task.
from langchain_core.runnables import RunnablePassthrough, RunnableLambda
from langchain_core.messages import get_buffer_string
from langchain_core.output_parsers import StrOutputParser
from operator import itemgetter
from langchain.memory import ConversationBufferMemory
from langchain.prompts.prompt import PromptTemplate
from langchain.schema import format_document
from langchain_core.prompts import ChatPromptTemplate
memory = ConversationBufferMemory(
return_messages=True, output_key="answer", input_key="question"
)load_history_from_memory = RunnableLambda(memory.load_memory_variables) | itemgetter(
"history"
)
load_history_from_memory_and_carry_along = RunnablePassthrough.assign(
chat_history=load_history_from_memory
)rephrase_the_question = (
{
"question": itemgetter("question"),
"chat_history": lambda x: get_buffer_string(x["chat_history"]),
}
| PromptTemplate.from_template(
"""You're a personal assistant to the user.
Here's your conversation with the user so far:
{chat_history}
Now the user asked: {question}
To answer this question, you need to look up from their notes about """
)
| llm
| StrOutputParser()
)retrieve_documents = {
"docs": itemgetter("standalone_question") | retriever,
"question": itemgetter("standalone_question"),
}def _combine_documents(docs):
prompt = PromptTemplate.from_template(template="{page_content}")
doc_strings = [format_document(doc, prompt) for doc in docs]
return "\n\n".join(doc_strings)
compose_the_final_answer = (
{
"context": lambda x: _combine_documents(x["docs"]),
"question": itemgetter("question"),
}
| ChatPromptTemplate.from_template(
"""You're a personal assistant.
With the context below:
{context}
To the question "{question}", you answer:"""
)
| llm
)# Putting all 4 stages together...
final_chain = (
load_history_from_memory_and_carry_along
| {"standalone_question": rephrase_the_question}
| retrieve_documents
| compose_the_final_answer
)
# Demo.
inputs = {"question": "What do I like to drink?"}
output = final_chain.invoke(inputs)
memory.save_context(inputs, {"answer": output.content})
print(output) # "You enjoy drinking coffee."
inputs = {"question": "How do I brew it?"}
output = final_chain.invoke(inputs)
memory.save_context(inputs, {"answer": output.content})
print(output) # "You brew coffee with a Aeropress."# Everything above this line is the same as in the above two tasks,
# till and including where `notes_query_engine` is defined.
# Let's convert the query engine into a tool.
from llama_index.tools import ToolMetadata
from llama_index.tools.query_engine import QueryEngineTool
notes_query_engine_tool = QueryEngineTool(
query_engine=notes_query_engine,
metadata=ToolMetadata(
name="look_up_notes",
description="Gives information about the user.",
),
)
from llama_index.agent import ReActAgent
agent = ReActAgent.from_tools(
tools=[notes_query_engine_tool],
llm=llm,
service_context=service_context,
)
output = agent.chat("What do I like to drink?")
print(output) # "You enjoy drinking coffee."
output = agent.chat("How do I brew it?")
print(output) # "You can use a drip coffee maker, French press, pour-over, or espresso machine."
# Everything above is the same as in the 2nd task, till and including where we defined `rag_chain`.
# Let's convert the chain into a tool.
from langchain.agents import AgentExecutor, Tool, create_react_agent
tools = [
Tool(
name="look_up_notes",
func=rag_chain.invoke,
description="Gives information about the user.",
),
]
react_prompt = hub.pull("hwchase17/react-chat")
agent = create_react_agent(llm, tools, react_prompt)
agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools)
result = agent_executor.invoke(
{"input": "What do I like to drink?", "chat_history": ""}
)
print(result) # "You enjoy drinking coffee."
result = agent_executor.invoke(
{
"input": "How do I brew it?",
"chat_history": "Human: What do I like to drink?\nAI: You enjoy drinking coffee.",
}
)
print(result) # "You can use a drip coffee maker, French press, pour-over, or espresso machine."