-
I am running ChromaDB in a docker container which is reachable under http://localhost:8000 and I created shell app using `npx create-llama@latest` which gave me a nextJs app with `"llamaindex": "0.5.2…
-
I believe Redis can be used as a vectorstore.
https://redis.io/docs/stack/search/indexing_json/
-
During installation, I had problems as I expected the collection in the vectorstore to be created automatically.
I would like to propose inserting the auto-generation of the vectorstore in an after…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
I have this code:
```
import streamlit as st
from llama_index.llms.azure_openai imp…
-
Hi. I'm trying to adapt the code to run with a Pinecone vector database. I can get it to run without any errors, but the chatbot doesn't actually seem to use the context data from the index. I'm using…
-
**Describe the bug**
When running a chatflow using ollamaembeddings and Redis VectorStore i am receiving this error :
SyntaxError: Expected property name or '}' in JSON at position 1
at JSON.…
-
I used the latest module and while embedding the gguf model into chroma, a critical error occurred
`llamaem= LlamaCppEmbeddings(model_path="D:\models\llama-2-7b-chat.Q4_K_M.gguf")
vectorstore = Chro…
-
### Bug Report
Hi,
using a Docker container with Cuda 12 on Ubuntu 22.04, the Nvidia GForce 3060 is working with Langchain (e.g. when using a local model), but the Langchain Gpt4all Functions …
-
In VectorStores, we are using OpenAI. However, if an API key is not available, the tests are skipped. Why don't we consider using Ollama instead? TestContainers has support for it. For more informatio…
-
https://js.langchain.com/docs/integrations/vectorstores/hnswlib/
Supports saving to file, which is needed for persistence between sessions.
Evaluate encryption.
Estimate database size with re…