trouble with LlamaIndexRetriever!

[neuralninja7]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

I created by 

import nest_asyncio
import asyncio
from llama_parse import LlamaParse
from llama_index.core import SimpleDirectoryReader

# Apply nest_asyncio to allow async calls in Jupyter
nest_asyncio.apply()

# Set up parser
parser = LlamaParse(result_type="markdown")


# Create an async function to call aload_data explicitly
async def load_documents_async():
    file_extractor = {".pdf": parser}
    documents = SimpleDirectoryReader(input_files=['../data/layout-parser-paper.pdf'], file_extractor=file_extractor)
    # Explicitly call async load function if available
    if hasattr(documents, "aload_data"):
        return await documents.aload_data()
    else:
        return documents.load_data()  # Fallback if only a synchronous load is available

# Run the async function using the Jupyter-compatible event loop
documents = asyncio.run(load_documents_async())
print(documents)


# one extra dep
from llama_index.core import VectorStoreIndex


# create an index from the parsed markdown
vectorstore = VectorStoreIndex.from_documents(documents)



# create a query engine for the index
query_engine = vectorstore.as_query_engine()



# query the engine
query = "tell me about dataset PubLayNet"
response = query_engine.query(query)
print(response)






==============================================================
Above code works fine and i get the context back which proves that that my llamaindex query engine is working fine.
==============================================================

Description

however - i mean to use this vectorDB in my existing langchain chatbot

So what I did was:

from langchain_community.retrievers.llama_index import LlamaIndexRetriever
retriever = LlamaIndexRetriever(query_engine=query_engine)

query = "tell me about dataset PubLayNet"
response = retriever.invoke(query)

print(response)

Above code should have worked fine.

however I get following error:

---

AttributeError Traceback (most recent call last)
Cell In[37], line 1
----> 1 response = retriever.invoke("What is the capital of France?")

File c:\Code\Github\LlamaIndex\venv\lib\site-packages\langchain_core\retrievers.py:254, in BaseRetriever.invoke(self, input, config, **kwargs)
252 except Exception as e:
253 run_manager.on_retriever_error(e)
--> 254 raise e
255 else:
256 run_manager.on_retriever_end(
257 result,
258 )

File c:\Code\Github\LlamaIndex\venv\lib\site-packages\langchain_core\retrievers.py:247, in BaseRetriever.invoke(self, input, config, **kwargs)
245 _kwargs = kwargs if self._expects_other_args else {}
246 if self._new_arg_supported:
--> 247 result = self._get_relevant_documents(
248 input, run_manager=run_manager, **_kwargs
249 )
250 else:
251 result = self._get_relevant_documents(input, **_kwargs)

File c:\Code\Github\LlamaIndex\venv\lib\site-packages\langchain_community\retrievers\llama_index.py:33, in LlamaIndexRetriever._get_relevant_documents(self, query, run_manager)
28 raise ImportError(
...
---> 33 response = index.query(query, **self.query_kwargs)
34 response = cast(Response, response)
35 # parse source nodes

AttributeError: 'NoneType' object has no attribute 'query'

System Info

my requirement.txt:

langchain_openai
python-dotenv
ipykernel
llama-index-core
llama-parse
llama-index-readers-file
llama-index-llms-openai
llama-index-embeddings-openai
langchain
langchain_community
llama-index
langgraph