chatgpt-retrieval-plugin
chatgpt-retrieval-plugin copied to clipboard
openai
The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
## Pull Request (PR) Checklist If you'd like to contribute, please follow the checklist below when submitting a PR. This will help us review and merge your changes faster! Thank...
The original code guessed the file type based on the local temporary file name, which did not have an extension. This commit changes the logic to guess the file type...
Add sentence-transformers embedding support. Use the `EMBEDDING_ENGINE` environment variable to control which engine to use. The `sentence-transformers/all-MiniLM-L6-v2` model generates vector with 384 items. Therefore, some datastores may need to create...
I am trying different databases with this plugin. I have used Chroma on other projects and it has worked fine. I have tried different configurations to achieve persistence with Chroma...
I think the prefix for redis keys are being hardcoded with "doc": ` def _redis_key(document_id: str, chunk_id: str) -> str: """ Create the JSON key for document chunks in Redis....
The vector database uses redis/redis-stack-server:latest. As the amount of data increases, the speed of upsert becomes slower and slower. The amount of data is about 80,000 documents. Currently, 20 documents...
I'm trying to use the retrieval plugin using postgres (installed locally). I created the database, installed pgvector. When I check - I can see that the `migration` script, by default...
Corrected AnalyticDB official website link in setup.md.
### Marqo Datastore This PR adds an implementation for [Marqo](https://github.com/marqo-ai/marqo) as the datastore. Marqo is a multimodal vector search engine with included inference for embeddings. This implementation will extract image...
I want to Install an unverified plugin in plugin sore .please tell me how to do it
