Langserve error in Assessment - Building RAG agents with LLMs

AI & Data Science Deep Learning (Training & Inference) TensorRT
, ,
1

Getting a 422 Unprocessable Entity

In the DLI course: “Building RAG agents with LLMs” I have added the generator and retriever routes, code below. Tried a lot of variations. However I keep getting this error:

HTTPStatusError: Client error ‘422 Unprocessable Entity’ for url ‘http://0.0.0.0:9012/generator/stream’

I have been trying for 5 hours now :( Please help!!

Steps To Reproduce

%%writefile server_app.py
# https://python.langchain.com/docs/langserve#server
from fastapi import FastAPI
from langchain_nvidia_ai_endpoints import ChatNVIDIA, NVIDIAEmbeddings
from langserve import add_routes

# May be useful later
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate, PromptTemplate
from langchain_core.prompt_values import ChatPromptValue
from langchain_core.runnables import RunnableLambda, RunnableBranch, RunnablePassthrough
from langchain_core.runnables.passthrough import RunnableAssign
from langchain_community.document_transformers import LongContextReorder
from functools import partial
from operator import itemgetter

from langchain_community.vectorstores import FAISS

# TODO: Make sure to pick your LLM and do your prompt engineering as necessary for the final assessment
embedder = NVIDIAEmbeddings(model="nvidia/nv-embed-v1", truncate="END")
instruct_llm = ChatNVIDIA(model="meta/llama3-8b-instruct")
llm = instruct_llm | StrOutputParser()

app = FastAPI(
    title="LangChain Server",
    version="1.0",
    description="A simple api server using Langchain’s Runnable interfaces",
)

# !tar xzvf docstore_index.tgz
docstore = FAISS.load_local("docstore_index", embedder, allow_dangerous_deserialization=True)
docs = list(docstore.docstore._dict.values())

#####################################################################
def docs2str(docs, title="Document"):
    """Useful utility for making chunks into context string. Optional, but useful"""
    out_str = ""
    for doc in docs:
        doc_name = getattr(doc, 'metadata', {}).get('Title', title)
        if doc_name: out_str += f"[Quote from {doc_name}] "
        out_str += getattr(doc, 'page_content', str(doc)) + "\n"
    return out_str

chat_prompt = ChatPromptTemplate.from_template(
    "You are a document chatbot. Help the user as they ask questions about documents."
    " User messaged just asked you a question: {input}\n\n"
    " The following information may be useful for your response: "
    " Document Retrieval:\n{context}\n\n"
    " (Answer only from retrieval. Only cite sources that are used. Make your response conversational)"
    "\n\nUser Question: {input}"
)

def output_puller(inputs):
    """"Output generator. Useful if your chain returns a dictionary with key 'output'"""
    if isinstance(inputs, dict):
        inputs = [inputs]
    for token in inputs:
        if token.get('output'):
            yield token.get('output')
#####################################################################

long_reorder = RunnableLambda(LongContextReorder().transform_documents) ## GIVEN
context_getter = itemgetter('input') | docstore.as_retriever() | long_reorder | docs2str ## TODO
retrieval_chain = {'input' : (lambda x: x)} | RunnableAssign({'context' : context_getter})

# Chain 2 Specs: retrieval_chain → generator_chain
# → {"output" : , …} → output_puller
generator_chain = chat_prompt | llm ## TODO
generator_chain = {'output' : generator_chain} | RunnableLambda(output_puller) ## GIVEN
#####################################################################

rag_chain = retrieval_chain | generator_chain

# PRE-ASSESSMENT: Run as-is and see the basic chain in action
add_routes(
    app,
    instruct_llm,
    path="/basic_chat",
)

# ASSESSMENT TODO: Implement these components as appropriate
add_routes(
    app,
    generator_chain,
    path="/generator",
)

add_routes(
    app,
    retrieval_chain,
    path="/retriever",
)

## Might be encountered if this were for a standalone python file...
if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=9012)
3

Nevermind, figured it out myself. Passed the assessment :)

4

Glad to here that @gautammankatti , Would you mind sharing which tweaks worked for you? It could help the community if others run into a similar issue.

Thank You