-
Hello There,
This may not be specifically a bug, but there seems to be some issue.
For a single chat request sent from bot UI, metrics report that 3 or 3x Open AI requests were made. Also the toke…
-
Research and POC
sam17 updated
2 years ago
-
### Project Name
PhotoRAG
### Description
PhotoRAG is a fullstack Next.JS image search application that leverages Azure AI and infrastructure to implement a Retrieval-Augmented Generation (RAG) sys…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
I am trying to create an index that has documents of different ages. I want to be …
-
I noticed that when I set CHAT_SEARCH_KWARG_K too high my embedding model cannot handle too many request, however I don't understand why this happen, as chunks are already embedded and question is sho…
-
### Feature Description
Addition of batch api will be helpful to improve performance - https://qdrant.tech/documentation/concepts/search/#batch-search-api
## With async (llama-index)
Execution ti…
-
### Question Validation
- [X] I have searched both the documentation and discord for an answer.
### Question
```
vector_store = ChromaVectorStore(chroma_collection=chroma_collection)
storage_con…
-
running in venv
I ran
```pip install lightrag-hku```
```pip list```
lightrag is installed
he…
-
## Description
If a document is imported into a collection with an empty field that is used in an embedding and then that same document (by ID) is updated, the embedding is calculated and inserted …
-
### Have you searched existing issues? 🔎
- [X] I have searched and found no existing issues
### Desribe the bug
I am using beropic with llama3.1 for topic modelling. My text is long, so I use doc_…