TECH BLOG

%%capture --no-stderr
! pip install -U langchain_community tiktoken langchain-openai langchain-cohere langchainhub chromadb langchain langgraph  tavily-python

import getpass
import os

def _set_env(var: str):
    if not os.environ.get(var):
        os.environ[var] = getpass.getpass(f"{var}: ")


_set_env("OPENAI_API_KEY")
_set_env("COHERE_API_KEY")
_set_env("TAVILY_API_KEY")

### Build Index

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import Chroma
from langchain_openai import OpenAIEmbeddings

### from langchain_cohere import CohereEmbeddings

# Set embeddings
embd = OpenAIEmbeddings()

# Docs to index
urls = [
    "https://lilianweng.github.io/posts/2023-06-23-agent/",
    "https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/",
    "https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/",
]

# Load
docs = [WebBaseLoader(url).load() for url in urls]
docs_list = [item for sublist in docs for item in sublist]

# Split
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    chunk_size=500, chunk_overlap=0
)
doc_splits = text_splitter.split_documents(docs_list)

# Add to vectorstore
vectorstore = Chroma.from_documents(
    documents=doc_splits,
    collection_name="rag-chroma",
    embedding=embd,
)
retriever = vectorstore.as_retriever()

embd = OpenAIEmbeddings()

urls = [
    "https://lilianweng.github.io/posts/2023-06-23-agent/",
    "https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/",
    "https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/",
]

docs = [WebBaseLoader(url).load() for url in urls]
docs_list = [item for sublist in docs for item in sublist]

text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    chunk_size=500, chunk_overlap=0
)
doc_splits = text_splitter.split_documents(docs_list)

vectorstore = Chroma.from_documents(
    documents=doc_splits,
    collection_name="rag-chroma",
    embedding=embd,
)

retriever = vectorstore.as_retriever()

### Router
from typing import Literal
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field


# Data model
class RouteQuery(BaseModel):
    """Route a user query to the most relevant datasource."""

    datasource: Literal["vectorstore", "web_search"] = Field(
        ...,
        description="Given a user question choose to route it to web search or a vectorstore.",
    )


# LLM with function call
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm_router = llm.with_structured_output(RouteQuery)

# Prompt
system = """You are an expert at routing a user question to a vectorstore or web search.
The vectorstore contains documents related to agents, prompt engineering, and adversarial attacks.
Use the vectorstore for questions on these topics. Otherwise, use web-search."""
route_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system),
        ("human", "{question}"),
    ]
)

question_router = route_prompt | structured_llm_router

print(question_router.invoke({"question": "Who will the Bears draft first in the NFL draft?"}))
print(question_router.invoke({"question": "What are the types of agent memory?"}))

class RouteQuery(BaseModel):
    """Route a user query to the most relevant datasource."""

    datasource: Literal["vectorstore", "web_search"] = Field(
        ...,
        description="Given a user question choose to route it to web search or a vectorstore.",
    )

llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm_router = llm.with_structured_output(RouteQuery)

system = """You are an expert at routing a user question to a vectorstore or web search.
The vectorstore contains documents related to agents, prompt engineering, and adversarial attacks.
Use the vectorstore for questions on these topics. Otherwise, use web-search."""
route_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system),
        ("human", "{question}"),
    ]
)

question_router = route_prompt | structured_llm_router

print(question_router.invoke({"question": "Who will the Bears draft first in the NFL draft?"}))
print(question_router.invoke({"question": "What are the types of agent memory?"}))

### Retrieval Grader

# Data model
class GradeDocuments(BaseModel):
    """Binary score for relevance check on retrieved documents."""

    binary_score: str = Field(
        description="Documents are relevant to the question, 'yes' or 'no'"
    )

# LLM with function call
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm_grader = llm.with_structured_output(GradeDocuments)

# Prompt
system = """You are a grader assessing relevance of a retrieved document to a user question. \n 
    If the document contains keyword(s) or semantic meaning related to the user question, grade it as relevant. \n
    It does not need to be a stringent test. The goal is to filter out erroneous retrievals. \n
    Give a binary score 'yes' or 'no' score to indicate whether the document is relevant to the question."""
grade_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system),
        ("human", "Retrieved document: \n\n {document} \n\n User question: {question}"),
    ]
)

retrieval_grader = grade_prompt | structured_llm_grader
question = "agent memory"
docs = retriever.invoke(question)
doc_txt = docs[1].page_content
print(retrieval_grader.invoke({"question": question, "document": doc_txt}))

### Generate

from langchain import hub
from langchain_core.output_parsers import StrOutputParser

# Prompt
prompt = hub.pull("rlm/rag-prompt")

# LLM
llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)

# Post-processing
def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)

# Chain
rag_chain = prompt | llm | StrOutputParser()

# Run
generation = rag_chain.invoke({"context": docs, "question": question})
print(generation)

### Hallucination Grader

# Data model
class GradeHallucinations(BaseModel):
    """Binary score for hallucination present in generation answer."""

    binary_score: str = Field(
        description="Answer is grounded in the facts, 'yes' or 'no'"
    )

# LLM with function call
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm_grader = llm.with_structured_output(GradeHallucinations)

# Prompt
system = """You are a grader assessing whether an LLM generation is grounded in / supported by a set of retrieved facts. \n 
     Give a binary score 'yes' or 'no'. 'Yes' means that the answer is grounded in / supported by the set of facts."""
hallucination_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system),
        ("human", "Set of facts: \n\n {documents} \n\n LLM generation: {generation}"),
    ]
)

hallucination_grader = hallucination_prompt | structured_llm_grader
hallucination_grader.invoke({"documents": docs, "generation": generation})

### Answer Grader

# Data model
class GradeAnswer(BaseModel):
    """Binary score to assess answer addresses question."""

    binary_score: str = Field(
        description="Answer addresses the question, 'yes' or 'no'"
    )


# LLM with function call
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)
structured_llm_grader = llm.with_structured_output(GradeAnswer)

# Prompt
system = """You are a grader assessing whether an answer addresses / resolves a question \n 
     Give a binary score 'yes' or 'no'. Yes' means that the answer resolves the question."""
answer_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system),
        ("human", "User question: \n\n {question} \n\n LLM generation: {generation}"),
    ]
)

answer_grader = answer_prompt | structured_llm_grader
answer_grader.invoke({"question": question, "generation": generation})

### Question Re-writer

# LLM
llm = ChatOpenAI(model="gpt-3.5-turbo-0125", temperature=0)

# Prompt
system = """You a question re-writer that converts an input question to a better version that is optimized \n 
     for vectorstore retrieval. Look at the input and try to reason about the underlying semantic intent / meaning."""
re_write_prompt = ChatPromptTemplate.from_messages(
    [
        ("system", system),
        (
            "human",
            "Here is the initial question: \n\n {question} \n Formulate an improved question.",
        ),
    ]
)

question_rewriter = re_write_prompt | llm | StrOutputParser()
question_rewriter.invoke({"question": question})

### Search

from langchain_community.tools.tavily_search import TavilySearchResults
web_search_tool = TavilySearchResults(k=3)

from langchain.schema import Document

def retrieve(state):
    """
    Retrieve documents

    Args:
        state (dict): The current graph state

    Returns:
        state (dict): New key added to state, documents, that contains retrieved documents
    """
    print("---RETRIEVE---")
    question = state["question"]

    # Retrieval
    documents = retriever.invoke(question)
    return {"documents": documents, "question": question}

def generate(state):
    """
    Generate answer

    Args:
        state (dict): The current graph state

    Returns:
        state (dict): New key added to state, generation, that contains LLM generation
    """
    print("---GENERATE---")
    question = state["question"]
    documents = state["documents"]

    # RAG generation
    generation = rag_chain.invoke({"context": documents, "question": question})
    return {"documents": documents, "question": question, "generation": generation}

def grade_documents(state):
    """
    Determines whether the retrieved documents are relevant to the question.

    Args:
        state (dict): The current graph state

    Returns:
        state (dict): Updates documents key with only filtered relevant documents
    """

    print("---CHECK DOCUMENT RELEVANCE TO QUESTION---")
    question = state["question"]
    documents = state["documents"]

    # Score each doc
    filtered_docs = []
    for d in documents:
        score = retrieval_grader.invoke(
            {"question": question, "document": d.page_content}
        )
        grade = score.binary_score
        if grade == "yes":
            print("---GRADE: DOCUMENT RELEVANT---")
            filtered_docs.append(d)
        else:
            print("---GRADE: DOCUMENT NOT RELEVANT---")
            continue
    return {"documents": filtered_docs, "question": question}

def transform_query(state):
    """
    Transform the query to produce a better question.

    Args:
        state (dict): The current graph state

    Returns:
        state (dict): Updates question key with a re-phrased question
    """

    print("---TRANSFORM QUERY---")
    question = state["question"]
    documents = state["documents"]

    # Re-write question
    better_question = question_rewriter.invoke({"question": question})
    return {"documents": documents, "question": better_question}

def web_search(state):
    """
    Web search based on the re-phrased question.

    Args:
        state (dict): The current graph state

    Returns:
        state (dict): Updates documents key with appended web results
    """

    print("---WEB SEARCH---")
    question = state["question"]

    # Web search
    docs = web_search_tool.invoke({"query": question})
    web_results = "\n".join([d["content"] for d in docs])
    web_results = Document(page_content=web_results)

    return {"documents": web_results, "question": question}

### Edges ###
def route_question(state):
    """
    Route question to web search or RAG.

    Args:
        state (dict): The current graph state

    Returns:
        str: Next node to call
    """

    print("---ROUTE QUESTION---")
    question = state["question"]
    source = question_router.invoke({"question": question})
    if source.datasource == "web_search":
        print("---ROUTE QUESTION TO WEB SEARCH---")
        return "web_search"
    elif source.datasource == "vectorstore":
        print("---ROUTE QUESTION TO RAG---")
        return "vectorstore"

def decide_to_generate(state):
    """
    Determines whether to generate an answer, or re-generate a question.

    Args:
        state (dict): The current graph state

    Returns:
        str: Binary decision for next node to call
    """

    print("---ASSESS GRADED DOCUMENTS---")
    state["question"]
    filtered_documents = state["documents"]

    if not filtered_documents:
        # All documents have been filtered check_relevance
        # We will re-generate a new query
        print(
            "---DECISION: ALL DOCUMENTS ARE NOT RELEVANT TO QUESTION, TRANSFORM QUERY---"
        )
        return "transform_query"
    else:
        # We have relevant documents, so generate answer
        print("---DECISION: GENERATE---")
        return "generate"

def grade_generation_v_documents_and_question(state):
    """
    Determines whether the generation is grounded in the document and answers question.

    Args:
        state (dict): The current graph state

    Returns:
        str: Decision for next node to call
    """

    print("---CHECK HALLUCINATIONS---")
    question = state["question"]
    documents = state["documents"]
    generation = state["generation"]

    score = hallucination_grader.invoke(
        {"documents": documents, "generation": generation}
    )
    grade = score.binary_score

    # Check hallucination
    if grade == "yes":
        print("---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---")
        # Check question-answering
        print("---GRADE GENERATION vs QUESTION---")
        score = answer_grader.invoke({"question": question, "generation": generation})
        grade = score.binary_score
        if grade == "yes":
            print("---DECISION: GENERATION ADDRESSES QUESTION---")
            return "useful"
        else:
            print("---DECISION: GENERATION DOES NOT ADDRESS QUESTION---")
            return "not useful"
    else:
        pprint("---DECISION: GENERATION IS NOT GROUNDED IN DOCUMENTS, RE-TRY---")
        return "not supported"

from typing import List
from typing_extensions import TypedDict

class GraphState(TypedDict):
    """
    Represents the state of our graph.

    Attributes:
        question: question
        generation: LLM generation
        documents: list of documents
    """

    question: str
    generation: str
    documents: List[str]

from langgraph.graph import END, StateGraph, START

workflow = StateGraph(GraphState)

# Define the nodes
workflow.add_node("web_search", web_search)  # web search
workflow.add_node("retrieve", retrieve)  # retrieve
workflow.add_node("grade_documents", grade_documents)  # grade documents
workflow.add_node("generate", generate)  # generatae
workflow.add_node("transform_query", transform_query)  # transform_query

# Build graph
workflow.add_conditional_edges(
    START,
    route_question,
    {
        "web_search": "web_search",
        "vectorstore": "retrieve",
    },
)
workflow.add_edge("web_search", "generate")
workflow.add_edge("retrieve", "grade_documents")
workflow.add_conditional_edges(
    "grade_documents",
    decide_to_generate,
    {
        "transform_query": "transform_query",
        "generate": "generate",
    },
)
workflow.add_edge("transform_query", "retrieve")
workflow.add_conditional_edges(
    "generate",
    grade_generation_v_documents_and_question,
    {
        "not supported": "generate",
        "useful": END,
        "not useful": "transform_query",
    },
)

# Compile
app = workflow.compile()

workflow = StateGraph(GraphState)

workflow.add_node("web_search", web_search)  # web search
workflow.add_node("retrieve", retrieve)  # retrieve
workflow.add_node("grade_documents", grade_documents)  # grade documents
workflow.add_node("generate", generate)  # generatae
workflow.add_node("transform_query", transform_query)  # transform_query

workflow.add_conditional_edges(
    START,
    route_question,
    {
        "web_search": "web_search",
        "vectorstore": "retrieve",
    },
)

workflow.add_edge("web_search", "generate")

workflow.add_edge("retrieve", "grade_documents")

workflow.add_conditional_edges(
    "grade_documents",
    decide_to_generate,
    {
        "transform_query": "transform_query",
        "generate": "generate",
    },
)

workflow.add_edge("transform_query", "retrieve")

workflow.add_conditional_edges(
    "generate",
    grade_generation_v_documents_and_question,
    {
        "not supported": "generate",
        "useful": END,
        "not useful": "transform_query",
    },
)

from pprint import pprint

# Run
inputs = {
    "question": "ベアーズが2024年のNFLドラフトで最初に指名すると予想される選手は誰ですか？"
}
for output in app.stream(inputs):
    for key, value in output.items():
        # Node
        pprint(f"Node '{key}':")
        # Optional: print full state at each node
        # pprint.pprint(value["keys"], indent=2, width=80, depth=None)
    pprint("\n---\n")

# Final generation
pprint(value["generation"])

---ROUTE QUESTION---
---ROUTE QUESTION TO WEB SEARCH---
---WEB SEARCH---
"Node 'web_search':"
'\n---\n'
---GENERATE---
---CHECK HALLUCINATIONS---
---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---
---GRADE GENERATION vs QUESTION---
---DECISION: GENERATION ADDRESSES QUESTION---
"Node 'generate':"
'\n---\n'
('2024年のNFLドラフトでシカゴ・ベアーズが最初に指名する選手は、
南カリフォルニア大学出身のQBケーレブ・ウィリアムズと予想されています。 '
 'ベアーズは2024年のNFLドラフトで全体1位指名権を獲得し、ウィリアムズを指名する可能性が高いです。')

# Run
inputs = {"question": "エージェントの記憶の種類にはどのようなものがありますか？"}
for output in app.stream(inputs):
    for key, value in output.items():
        # Node
        pprint(f"Node '{key}':")
        # Optional: print full state at each node
        # pprint.pprint(value["keys"], indent=2, width=80, depth=None)
    pprint("\n---\n")

# Final generation
pprint(value["generation"])

---ROUTE QUESTION---
---ROUTE QUESTION TO RAG---
---RETRIEVE---
"Node 'retrieve':"
'\n---\n'
---CHECK DOCUMENT RELEVANCE TO QUESTION---
---GRADE: DOCUMENT RELEVANT---
---GRADE: DOCUMENT RELEVANT---
---GRADE: DOCUMENT NOT RELEVANT---
---GRADE: DOCUMENT RELEVANT---
---ASSESS GRADED DOCUMENTS---
---DECISION: GENERATE---
"Node 'grade_documents':"
'\n---\n'
---GENERATE---
---CHECK HALLUCINATIONS---
---DECISION: GENERATION IS GROUNDED IN DOCUMENTS---
---GRADE GENERATION vs QUESTION---
---DECISION: GENERATION ADDRESSES QUESTION---
"Node 'generate':"
'\n---\n'
'短期記憶、長期記憶の種類があります。それぞれ、視覚、聴覚、触覚などの感覚情報を保持する感覚記憶と、
学習や推論などの複雑な認知タスクを実行するために必要な情報を保持する作業記憶があります。
長期記憶には、事実や出来事の記憶を意味する陳述記憶と、自動的に実行されるスキルやルーチンを含む
暗黙の記憶があります。'