Search

More Filters

Show More
Add Listing
Go Back

chipper

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Chipper is a developer-focused, self-hosted toolkit for building and running retrieval-augmented generation (RAG) pipelines and knowledge-enabled model workflows. It provides a lightweight, modular architecture with both a web interface and a CLI so you can ingest documents, split and embed content, index vectors, run queries, and combine retrieval with local or remote language models. The project also functions as a proxy for Ollama, enabling third-party Ollama clients to use server-side retrieval, prompt overrides, and model selection. Chipper is containerized for easy deployment and is built on Haystack, Ollama, Hugging Face, ElasticSearch, Docker, TailwindCSS and related tooling. The project began as a private local RAG tool to preserve author privacy and evolved into an extensible service for experimentation and teaching.

Links

Stars
466
App URL
https://github.com/TilmanGriesel/chipper
Github Repository
https://github.com/TilmanGriesel/chipper/blob/main/README.md

App Details

Features
Chipper includes local and cloud model support allowing use of Ollama for on-prem inference or Hugging Face APIs for remote models. It integrates with ElasticSearch for scalable vector storage and retrieval. Document chunking and structured splitting are provided to prepare content for embeddings. Built-in web scraping and audio transcription tools let you extract new sources and convert audio to text. The project ships with both a lightweight offline web UI and a CLI. It is fully dockerized for container deployment. Additional features include customizable RAG pipelines, an Ollama API proxy with API key and bearer token authentication, Edge TTS client-side speech synthesis, and support for distributed processing and Haystack chat generators.
Use Cases
Chipper helps developers, educators, and tinkerers create private, reproducible RAG workflows without relying on cloud chat services. It centralizes document ingestion, embeddings, and indexing so models can answer queries with grounded context. The Ollama proxy capability lets existing Ollama clients gain server-side retrieval, model selection and prompt overrides, effectively turning Chipper into a shared knowledge backend. Dockerization simplifies deployment and the offline web UI and CLI provide accessible ways to experiment and teach. Features like audio transcription, web scraping, and distributed chaining make it practical to collect and scale knowledge sources. The README notes it is a personal, non-production project and invites contribution and experimentation.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*