mattneary / salience
automatic sentence highlights based on their significance to the document
☆191Updated last year
Alternatives and similar repositories for salience:
Users that are interested in salience are comparing it to the libraries listed below
- GPT-based Conversation Summarizer☆148Updated 2 years ago
- Simple embedding -> text model trained on a small subset of Wikipedia sentences.☆153Updated last year
- A collection of LLM services you can self host via docker or modal labs to support your applications development☆185Updated last year
- ☆114Updated last year
- Hands-free companionship on demand.☆77Updated 2 years ago
- ☆174Updated 2 years ago
- Demo of ConversationEntityMemory in Streamlit.☆52Updated 2 years ago
- Some of the scripts I use for scribepod @ https://scribepod.substack.com/, an automated AI podcast☆171Updated 2 years ago
- ☆106Updated last year
- Fluid Database☆114Updated 7 months ago
- Layered, depth-first reading—start with summaries, tap to explore details, and gain clarity on complex topics.☆271Updated last year
- ☆131Updated 2 years ago
- ☆135Updated last year
- A simple wrapper for OpenAI to log input/outputs.☆104Updated last year
- ☆56Updated 2 years ago
- A backend API to perform search over Wikipedia using LangChain, Cohere and Weaviate☆105Updated last year
- Hosted embedding platform to discover, evaluate, and retrieve embeddings☆73Updated last year
- EXPERIMENTAL – A library for language models to respond with GUI.☆64Updated last year
- The Typescript-first prompt engineering toolkit for working with chat based LLMs.☆109Updated last year
- GPU accelerated client-side embeddings for vector search, RAG etc.☆66Updated last year
- Run GGML models with Kubernetes.☆173Updated last year
- smol-podcaster is your podcast production agent 🎙️☆342Updated 7 months ago
- ✦ The intuitive python LLM framework☆172Updated 5 months ago
- 🐤 A minimal viable logger for Prompt/LLM Engineering. Use your IDE as Logging UI - a fast, simple, extensible, zero dependency Node.js l…☆128Updated last year
- Drive a browser with Cohere☆72Updated 2 years ago
- Wove is a tool for building long-running workflows with LLMs.☆111Updated 2 years ago
- ☆41Updated last year
- A Markdown-like syntax for writing prompts. Includes an in-editor playground.☆114Updated last year
- A langchain app to visualise a debate using Tree-of-Thought reasoning☆60Updated last year
- A pure TypeScript implementation of the HNSW algorithm for approximate nearest neighbour search.☆43Updated last year