-
From [here](https://github.com/pinecone-io/pinecone-text/blob/main/pinecone_text/sparse/bm25_encoder.py#L267), the indices array in pinecone-text is a 32-bit unsigned integer. However, the sparse vec…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
Hi,
I am trying to implement a low-level Pinecone Retriever, and I want the ability t…
-
### Documentation Issue Description
Multiple places in the `Qdrant Vector Store - Metadata Filter` page, documentation quotes `Pinecone` but the page is refering to `Qdrant`. please find the attached…
-
Currently, we support In-Memory Store, but we need to add VectorDB support.
We are seeking collaborators who are interested in contributing. Please indicate your interest in enabling VectorDB by ta…
-
### Description of the bug:
This error occurs when the Google Generative AI model cannot encode the character '\ud835' in position 897 of the input text. This is because the character '\ud835' i…
-
**Describe the feature you'd like**
there is an open source rerank model bge-rerank similar to the one provided by Cohere, which is a very obvious efficiency improvement for building RAG applications…
-
\src\lib\pinecone.ts
![image](https://github.com/joschan21/quill/assets/106664947/13d03707-7515-40a4-9f2a-c8b6d60cce60)
![image](https://github.com/joschan21/quill/assets/106664947/a88422d9-ba7b…
-
I want to replace Redis database to another one, properly Pinecone. In Readme documentation, It mentioned that OpenGPT supports 50+ databases, but no ideas how to switch from Redis to another one. Cou…
-
-
### Bug Description
When using `this.getInputConnectionData('ai_vectorStore', 0);` in an LangChain Code Node while an In-Memory Vector Store is connected to it, it results in the following error in…