Langtrace-Langchain Integration

gistfile1.txt

import os
os.environ['OPENAI_API_KEY'] = 'sk-proj-INSERT_KEY'
os.environ['LANGTRACE_API_KEY']='INSERT_KEY'

import bs4
from langtrace_python_sdk import langtrace, with_langtrace_root_span
from langfuse import Langfuse
from langfuse.openai import openai # OpenAI integration
from langchain import hub
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import WebBaseLoader
from langchain_community.vectorstores import Chroma
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

#### INDEXING ####

# @with_langtrace_root_span()
def main(): 
    # Load Documents
    loader = WebBaseLoader(
        web_paths=("https://lilianweng.github.io/posts/2024-02-05-human-data-quality/",),
        bs_kwargs=dict(
            parse_only=bs4.SoupStrainer(
                class_=("post-content", "post-title", "post-header")
            )
        ),
    )
    docs = loader.load()

    # Split
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    splits = text_splitter.split_documents(docs)

    # Embed
    vectorstore = Chroma.from_documents(documents=splits, embedding=OpenAIEmbeddings())

    retriever = vectorstore.as_retriever()

    #### RETRIEVAL and GENERATION ####

    # 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 = (
        {"context": retriever | format_docs, "question": RunnablePassthrough()}
        | prompt
        | llm
        | StrOutputParser()
    )

    # Question
    rag_chain.invoke("what is the opposite of the summary?")
    
main()