embeddings

Edge compatible PDF.ai Chat with any PDF document You can ask questions, get summaries, find information, and more. Built with Pinecone, OpenAI, Langchain, Nextjs13, TypeScript, Clerk Auth, Drizzle ORM for edge runtime environment, Shadcn UI.

A project to show howto use SpringAI with Ollama to chat with the documents in a library. Documents are stored in a normal/vector database. The AI is used to create embeddings from documents that are stored in the vector database. The vector database is used to query for the nearest document. That document is used by the AI to generate the answer.

Anthropic's Contextual Retrieval implementation with visual chunk comparison. Preview context enrichment before/after embedding.

Knowledge for GPTScript

Rust-based retrieval system with hybrid search (vector + BM25), async ingestion, and gRPC-first API

A hex-native embedded database for Go. Morton keys, native ring scans, seams (contradictions), MVCC, provenance, and optional HNSW embeddings. Built from scratch for lattice-addressed memory.

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

LightweightEmbeddings is a fast, free, and unlimited API service for multilingual embeddings and reranking, with support for both text and images and guaranteed uptime.

Embed anything.

High-performance infrastructure libraries built in Rust, with seamless bindings for Python, Node.js, and WebAssembly.

Fine-tuning black-box OpenAI embedding models

Edge Vector search engine with Vulkan GPU acceleration, hierarchical indexing (HRM2), and native LangChain integration. Gaussian splat-based architecture for similarity search on resource-constrained devices.

Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, Windsurf. Temporal decay, contradiction detection, knowledge graph, autonomous consolidation. Backed by the YantrikDB Rust engine. Install: pip install yantrikdb-mcp.

Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.

One Mac process. Many models. Real speed. Multi-model LLM serving with prefix reuse, MTP acceleration, and OpenAI APIs — built for Apple Silicon, measured against mlx-lm and llama.cpp.

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

An application that enable the users to upload PDF files and ask questions regarding their content using Retrieval Augmented Generation (RAG)

GraphRAG over any codebase — a Neo4j knowledge graph of code entities plus a 3072-dim vector index, bridged so one natural-language query walks structure and ranks by meaning. Python · Neo4j · OpenAI embeddings · Streamlit · Docker. Hybrid semantic + structural code search.

Using langchain framework created some useful Ai applications.

ContextQA - The open-source tool for data-driven conversations