fix: Updating Langchain handler issues

[ajaynayak]

Fixing two issues:

1. Node name extraction (Langchain sometimes passes a null serialized object)
   https://app.shortcut.com/galileo/story/30649/langchain-langgraph-warning-langchain-core-callbacks-manager-error-in-galileocallback-on-chain-start-callback-attributeerror

2. Allowing users to pass a GalileoLogger with a started trace to the Langchain handler

[codecov]

Codecov Report

Attention: Patch coverage is 92.85714% with 3 lines in your changes missing coverage. Please review.

Project coverage is 78.64%. Comparing base (71d6676) to head (aaebcac).
Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
src/galileo/handlers/langchain/handler.py	88.88%	3 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #118      +/-   ##
==========================================
+ Coverage   78.54%   78.64%   +0.09%     
==========================================
  Files          36       36              
  Lines        2629     2664      +35     
==========================================
+ Hits         2065     2095      +30     
- Misses        564      569       +5     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[andriisoldatenko]

@ajaynayak tested and it works!

import os

from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_core.vectorstores import InMemoryVectorStore # Not used in final setup but present in original imports
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain.tools.retriever import create_retriever_tool
from langgraph.graph import END, StateGraph, START
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition
from typing import Annotated, Sequence, TypedDict
from langchain_core.messages import BaseMessage, HumanMessage

from galileo.handlers.langchain import GalileoCallback

os.environ["OPENAI_API_KEY"] = ""
os.environ["GALILEO_API_KEY"] = ""
os.environ["GALILEO_PROJECT"] = "handler-test"
os.environ["GALILEO_LOG_STREAM"] = "handler-test"
os.environ["GALILEO_CONSOLE_URL"] = ""



urls = [
    "https://lilianweng.github.io/posts/2024-11-28-reward-hacking/",
    "https://lilianweng.github.io/posts/2024-07-07-hallucination/",
    "https://lilianweng.github.io/posts/2024-04-12-diffusion-video/",
]

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

docs[0][0].page_content.strip()[:1000]

docs_list = [item for sublist in docs for item in sublist]

text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    chunk_size=100, chunk_overlap=50
)
doc_splits = text_splitter.split_documents(docs_list)


vectorstore = InMemoryVectorStore.from_documents(
    documents=doc_splits, embedding=OpenAIEmbeddings()
)
retriever = vectorstore.as_retriever()

retriever_tool = create_retriever_tool(
    retriever,
    "retrieve_blog_posts",
    "Search and return information about Lilian Weng blog posts.",
)

retriever_tool.invoke({"query": "types of reward hacking"})

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]



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("--- CALLING AGENT ---")
    messages = state["messages"]
    # Using gpt-4-turbo as it's generally better at tool use
    model = ChatOpenAI(temperature=0, streaming=True, model="gpt-4-turbo-preview") # or "gpt-3.5-turbo"
    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]}


retrieve_node = ToolNode([retriever_tool])

# Define the graph
workflow = StateGraph(AgentState)

# Add nodes
workflow.add_node("agent", agent)
workflow.add_node("retrieve", retrieve_node)