Мобильная версияI'm encountering an error when using LangChain's FAISS module to build a vector index from a list of documents. Specifically, I'm getting an IndexError: list index out of range on the line where I call FAISS.from_documents(docs, embeddings).
My code:
import os import streamlit as st import pickle import time from langchain_openai import OpenAI from langchain_openai import OpenAIEmbeddings from langchain.chains import RetrievalQAWithSourcesChain from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain_community.document_loaders import UnstructuredURLLoader from langchain_community.embeddings import OpenAIEmbeddings from langchain_community.vectorstores import FAISS from dotenv import load_dotenv from dotenv import load_dotenv load_dotenv() # take environment variables from .env (especially openai api key) st.title("RockyBot: News Research Tool
") st.sidebar.title("News Article URLs") urls = [] for i in range(1): url = st.sidebar.text_input(f"URL {i+1}") urls.append(url) process_url_clicked = st.sidebar.button("Process URLs") file_path = "faiss_store_openai.pkl" llm = OpenAI(temperature=0.9, max_tokens=500) if process_url_clicked: loader = UnstructuredURLLoader(urls=urls) st.text("data loading...") data = loader.load() text_splitter = RecursiveCharacterTextSplitter( separators=['\n\n', '\n', '.', ','], chunk_size=1000 ) st.text('text splitter started...') docs = text_splitter.split_documents(data) embeddinsg = OpenAIEmbeddings() db = FAISS.from_documents(docs, embeddinsg) st.text('Embedding Vector Started Building...') time.sleep(2) query = st.text_input("Question: ") if query: if os.path.exists(file_path): with open(file_path, "rb") as f: vectorstore = pickle.load(f) chain = RetrievalQAWithSourcesChain.from_llm(llm=llm, retriever=vectorstore.as_retriever()) result = chain({"question": query}, return_only_outputs=True) # result will be a dictionary of this format --> {"answer": "", "sources": [] } st.header("Answer") st.write(result["answer"]) # Display sources, if available sources = result.get("sources", "") if sources: st.subheader("Sources:") sources_list = sources.split("\n") # Split the sources by newline for source in sources_list: st.write(source) The error i'm getting:File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 535, in _run_script exec(code, module.__dict__) File "/Users/rahulsharma/Desktop/2_news_research_tool_project/main.py", line 41, in db = FAISS.from_documents(docs, embeddinsg) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/langchain_core/vectorstores.py", line 528, in from_documents return cls.from_texts(texts, embedding, metadatas=metadatas, **kwargs) File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/langchain_community/vectorstores/faiss.py", line 966, in from_texts return cls.__from( File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/site-packages/langchain_community/vectorstores/faiss.py", line 923, in __from index = faiss.IndexFlatL2(len(embeddings[0])) This error occurs on the line db = FAISS.from_documents(docs, embeddings).
Expected Outcome:
I expect the code to build a vector index using FAISS based on the provided documents and embeddings.
Environment details:
langchain: 0.1.3 python-dotenv: 1.0.0 streamlit: 1.31.1 unstructured: 0.12.5 tiktoken: 0.5.2 faiss-cpu: 1.7.4 libmagic: 1.0 python-magic: 0.4.27 python-magic-bin: None OpenAI: 1.13.3
Источник: https://stackoverflow.com/questions/781 ... -documents
