Error printing the score when grade is "no" for langgraph_agentic_rag

[shresthakamal]

Checked other resources

• [X] I added a very descriptive title to this issue.
• [X] I searched the LangChain documentation with the integrated search.
• [X] I used the GitHub search to find a similar question and didn't find it.
• [X] I am sure that this is a bug in LangChain rather than my code.

Example Code

def grade_documents(state):
    """
    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
    """

    print("---CHECK RELEVANCE---")

    # Data model
    class grade(BaseModel):
        """Binary score for relevance check."""

        binary_score: str = Field(description="Relevance score 'yes' or 'no'")

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

    # Tool
    grade_tool_oai = convert_to_openai_tool(grade)

    # LLM with tool and enforce invocation
    llm_with_tool = model.bind(
        tools=[convert_to_openai_tool(grade_tool_oai)],
        tool_choice={"type": "function", "function": {"name": "grade"}},
    )

    # Parser
    parser_tool = PydanticToolsParser(tools=[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 | parser_tool

    messages = state["messages"]
    last_message = messages[-1]

    question = messages[0].content
    docs = last_message.content

    score = chain.invoke(
        {"question": question, 
         "context": docs}
    )

    grade = score[0].binary_score

    if grade == "yes":
        print("---DECISION: DOCS RELEVANT---")
        return "yes"

    else:
        print("---DECISION: DOCS NOT RELEVANT---")
        print(score.binary_score)
        return "no"

Error Message and Stack Trace (if applicable)

AttributeError: 'list' object has no attribute 'binary_score'

Description

If the grader grades any document as not relevant, and scores "no", printing the score is not correct

System Info

langchain==0.1.10 langchain-community==0.0.25 langchain-core==0.1.28 langchain-openai==0.0.8 langchain-text-splitters==0.0.1 langchainhub==0.1.14

[shresthakamal]

Can be solved using:

    if grade == "yes":
        print("---DECISION: DOCS RELEVANT---")
        return "yes"

    else:
        print("---DECISION: DOCS NOT RELEVANT---")
        print(score[0].binary_score)
        return "no"

[hwchase17]

fixed! thanks!