Stop using static chunk sizes. A lightweight, production-ready RAG ingestion toolkit. Uses Docling for layout-aware parsing and applies smart heuristics for optimal chunking (PDF vs Code vs MD). Extracted from a production RAG platform
☆71Mar 15, 2026Updated 5 months ago
Alternatives and similar repositories for smart-ingest-kit
Users that are interested in smart-ingest-kit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A simple CPU only OCR for pdf/images/word/excel to markdown. With streamlit.☆52Jan 26, 2026Updated 7 months ago
- A Docker-powered RAG system that understands the difference between code and prose. Ingest your codebase and documentation, then query th…☆354Mar 14, 2026Updated 5 months ago
- A Python CLI to test, benchmark, and find the best RAG chunking strategy for your Markdown documents.☆117Jan 18, 2026Updated 7 months ago
- An opinionated, "speed" and "usability" focused agentic TUI with a built-in MCP registry/plugin system.☆33Apr 14, 2026Updated 4 months ago
- Exploring retrieval systems for language models☆14Aug 7, 2026Updated 3 weeks ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- pdfLLM is a completely open source, proof of concept RAG app.☆188Sep 1, 2025Updated last year
- A simple streamlit app to play with qwen3-2b-VL to perform OCR. Dockerized set up, tested with 3060 12 GB.☆32Nov 23, 2025Updated 9 months ago
- Enterprise-grade Retrieval-Augmented Generation system with microservices architecture.☆23Mar 15, 2026Updated 5 months ago
- High-performance batched Top-K selection for CPU inference. Up to 80x faster than PyTorch, optimized for LLM sampling with AVX2 SIMD.☆18Mar 20, 2026Updated 5 months ago
- Token-aware, LangChain-compatible semantic chunker with PDF, markdown, and layout support☆13Jun 28, 2025Updated last year
- REFRAG: LLM-powered representations for better RAG retrieval. Improve precision, reduce context size, same speed.☆31Dec 29, 2025Updated 8 months ago
- The easiest possible implementation of an MCP server and client. Set up a server or a client in 2 lines of code.☆22Jul 5, 2025Updated last year
- Privacy-focused, self-hosted RAG assistant for querying codebases with local or cloud LLMs.☆21Aug 13, 2026Updated 2 weeks ago
- SmartRAG is a privacy-first multimodal RAG system that lets you chat intelligently with your documents, images, and audio. Upload PDFs, W…☆112Apr 6, 2026Updated 4 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Professional RAG development skills for Claude Code - audit, evaluate, optimize, and scaffold RAG pipelines☆34Jan 18, 2026Updated 7 months ago
- An opinionated development framework for building production-ready AI agents with LangGraph. It grounds AI coding assistants (Cursor, Win…☆23May 20, 2026Updated 3 months ago
- Elixir library to generate Ecto migrations from a PostgreSQL schema SQL file. Uses NimbleParsec and macro-style code generation.☆18Dec 12, 2025Updated 8 months ago
- An example repo full of Douglas Adams quotes☆16Mar 12, 2024Updated 2 years ago
- PipesHub is an open-source fully extensible AI context layer that unifies your business data for explainable enterprise search and agenti…☆3,703Updated this week
- ☆16Feb 3, 2026Updated 6 months ago
- A fully local, zero-API, zero-finetune multi-agent AI architecture that makes an 8B base model perform high level model reasoning, resear…☆34Nov 25, 2025Updated 9 months ago
- MCP server that allows Claude to have a voice.☆14May 5, 2025Updated last year
- A Python package for zero-shot text anonymization using Transformer-based NER models.☆84Dec 16, 2025Updated 8 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Validated, private, shareable knowledge-graph memory for AI — per-tenant, write-gated, PostgreSQL-authoritative, served over MCP.☆19Aug 15, 2026Updated 2 weeks ago
- Cut LLM costs by up to 80% and unlock sub-millisecond responses with intelligent semantic caching.A drop-in, provider-agnostic LLM proxy …☆400Aug 18, 2026Updated 2 weeks ago
- Save context for what matters. The last agent you'll ever need.☆33Sep 25, 2025Updated 11 months ago
- This is more like a QA system☆16Jul 20, 2026Updated last month
- Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling p…☆587Updated this week
- Development tool for Model Context Protocol servers☆13Apr 23, 2025Updated last year
- ☆28Jun 22, 2025Updated last year
- A Developmental AI That Learns Like a Child☆29Mar 29, 2026Updated 5 months ago
- Middleware for AI Agents that verifies grounding and prevents hallucinations. Returns structured retry suggestions for self-correction.☆51Dec 11, 2025Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Coordinate skills between Codex, Copilot, and Claude Code. Validates, analyzes, and syncs skills, subagents, commands, and configuration …☆69Jun 18, 2026Updated 2 months ago
- Local, cache-aware LLM usage and cost telemetry for OpenClaw.☆15Jul 27, 2026Updated last month
- Give your local LLM a real memory with a lightweight, fully local memory system. 100% offline and under your control.☆76Sep 16, 2025Updated 11 months ago
- An MCP server to help you "play with your documents" via Docling 🐥☆19Apr 5, 2025Updated last year
- Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside emb…☆45Updated this week
- This bridge integrates Ollama into any chat interface and lets you build your own multi-agent pipeline, including a built-in memory data…☆90Jun 29, 2026Updated 2 months ago
- ☆107Nov 27, 2024Updated last year