Building a web explorer app via LangChain

[moabdelmoez]

Hello All,

I was cloning this repository to see how LangChain can browse the internet and provide context-based answers based on search results. While running the application, I encountered an AssertionError. I hope the community can help me fix this issue.

Error Message;

Traceback (most recent call last): File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py”, line 541, in _run_script exec(code, module.dict) File “/Users/mostafa/Downloads/web-LLM-app/web-explorer/web_explorer.py”, line 103, in result = qa_chain({“question”: question},callbacks=[retrieval_streamer_cb, stream_handler]) File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/chains/base.py”, line 243, in call raise e File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/chains/base.py”, line 237, in call self._call(inputs, run_manager=run_manager) File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/chains/qa_with_sources/base.py”, line 141, in _call docs = self._get_docs(inputs, run_manager=_run_manager) File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/chains/qa_with_sources/retrieval.py”, line 51, in _get_docs docs = self.retriever.get_relevant_documents( File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/schema/retriever.py”, line 181, in get_relevant_documents raise e File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/schema/retriever.py”, line 174, in get_relevant_documents result = self._get_relevant_documents( File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/retrievers/web_research.py”, line 205, in _get_relevant_documents self.vectorstore.add_documents(docs) File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/vectorstores/base.py”, line 104, in add_documents return self.add_texts(texts, metadatas, **kwargs) File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/vectorstores/faiss.py”, line 153, in add_texts return self.__add(texts, embeddings, metadatas=metadatas, ids=ids, **kwargs) File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/langchain/vectorstores/faiss.py”, line 120, in __add self.index.add(vector) File “/Users/mostafa/Downloads/web-LLM-app/venv-web/lib/python3.10/site-packages/faiss/class_wrappers.py”, line 228, in replacement_add assert d == self.d AssertionError

[moabdelmoez]

[moabdelmoez]

The problem was that the embeddings model you were using was from OpenAI, but I am now using a hugging face embedding model (Sentence Transformers).
By default, the pretrained models output embeddings with size 768 (base-models) or with size 1024 (large-models).