handrew/gpt-memory
Using embeddings to create memory.
This project helps developers build applications that can answer questions from a large collection of diverse documents, acting like an intelligent assistant that knows which knowledge base to consult. You provide a set of documents, organize them into named indexes, and then ask questions. The system figures out which knowledge base is most relevant to your question and provides an answer. This is ideal for developers creating smart Q&A systems or chatbots for varied topics.
No commits in the last 6 months.
Use this if you are a developer building an application that needs to answer questions from a vast and varied set of documents, where different document sets cover different topics.
Not ideal if your application deals with a single, monolithic set of documents or if you need to perform complex analytical queries rather than simple Q&A.
Stars
30
Forks
—
Language
Python
License
—
Category
Last pushed
Apr 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/handrew/gpt-memory"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
yuniko-software/bge-m3-onnx
ONNX implementation of the BGE-M3 multilingual embedding model and tokenizer with native C#,...
substratusai/stapi
Sentence Transformers API: An OpenAI compatible embedding API server
EulerSearch/embedding_studio
Embedding Studio is a framework which allows you transform your Vector Database into a...
turian/embeddingcache
Retrieve text embeddings, but cache them locally if we have already computed them.
faisal-fida/Text-Embeddings-API
This project provides a REST API for generating text embeddings using the Sentence Transformers...