sergerdn

@kavlata Can you confirm whether you tried to run my code with no modifications and whether it did not work as expected?

Please provide me with your full code for reproducing errors, including the code for inserting data into ChromaDB. Additionally, please use backticks (`) when you post your code. ![Screenshot 2023-04-06...

Do not use the same directory for both the Chrome database and documents under any circumstances. I believe they should be in different directories: ```python documents = SimpleDirectoryReader('/content/sample_data/source_docs/',required_exts='.txt').load_langchain_documents() persist_directory="/content/sample_data/chromadb/" ```...

@kavlata Look at my code, I use: ```python # settings for ChromaDB client_settings = chromadb.config.Settings( chroma_db_impl="duckdb+parquet", persist_directory=DB_DIR, anonymized_telemetry=False ) # create instance vectorstore = Chroma( collection_name="langchain_store", embedding_function=embeddings, client_settings=client_settings, persist_directory=DB_DIR, )...

I have tested my code once again and can confirm that it is working correctly. ```python import logging import os import chromadb from dotenv import load_dotenv from langchain.document_loaders import PyPDFLoader...

@kavlata It seems like we have a bug in the code.

@chintan-donda Try creating the directory for the database first.

> @sergerdn When to create directory? At the time of init_chromadb() step or query_chromadb()? > Can u pls share the sample code snippet? Why not create the directory if it...

> @sergerdn I'm already creating the directory if not exist, before you suggested. Still the same issue. Post your code to repeat your problem. Please do not use a Python...

@chintan-donda Tested and it works. Make sure to uncomment `init_chromadb()` during the first run to create the database with documents. During the second run, only execute `query_chromadb`. Please do not...