Trending repositories for topic semantic-search
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
Chatbot for documentation, that allows you to chat with your data. Privately deployable, provides AI knowledge sharing and integrates knowledge into your AI workflow
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a c...
A compute framework for building Search, RAG, Recommendations and Analytics over complex structured & unstructured data.
Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
Here you can find all the Tutorials for Haystack 📓
RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
Easily compute clip embeddings and build a clip retrieval system with them
A curated list of Generative AI tools, works, models, and references
Platform for building AI that can learn and answer questions over federated data.
A compute framework for building Search, RAG, Recommendations and Analytics over complex structured & unstructured data.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
Here you can find all the Tutorials for Haystack 📓
Efficient Retrieval Augmentation and Generation Framework
Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a c...
Chatbot for documentation, that allows you to chat with your data. Privately deployable, provides AI knowledge sharing and integrates knowledge into your AI workflow
Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.
Easily compute clip embeddings and build a clip retrieval system with them
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
A curated list of Generative AI tools, works, models, and references
A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a c...
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
A compute framework for building Search, RAG, Recommendations and Analytics over complex structured & unstructured data.
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Chatbot for documentation, that allows you to chat with your data. Privately deployable, provides AI knowledge sharing and integrates knowledge into your AI workflow
Platform for building AI that can learn and answer questions over federated data.
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
A curated list of Generative AI tools, works, models, and references
Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.
Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
Easily compute clip embeddings and build a clip retrieval system with them
Jupyter Notebooks to help you get hands-on with Pinecone vector databases
A compute framework for building Search, RAG, Recommendations and Analytics over complex structured & unstructured data.
NNV(No-Named.V) is a high-level project where we take on the challenge of deploying a all-in-one database from scratch to production. Join me on this journey!
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
Real-time on-device text-to-image and image-to-image Semantic Search with video stream capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
Here you can find all the Tutorials for Haystack 📓
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine
See how to augment LLMs with real-time data for dynamic, context-aware apps - Rag + Agents + GraphRAG.
Hybrid search engine, combining best features of text and semantic search worlds
🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Framework for enhancing LLMs for RAG tasks using fine-tuning.
🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.
Efficient Retrieval Augmentation and Generation Framework
RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C...
A curated list of Generative AI tools, works, models, and references
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a c...
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a c...
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
A compute framework for building Search, RAG, Recommendations and Analytics over complex structured & unstructured data.
Platform for building AI that can learn and answer questions over federated data.
Chatbot for documentation, that allows you to chat with your data. Privately deployable, provides AI knowledge sharing and integrates knowledge into your AI workflow
NNV(No-Named.V) is a high-level project where we take on the challenge of deploying a all-in-one database from scratch to production. Join me on this journey!
A curated list of Generative AI tools, works, models, and references
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.
RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
NNV(No-Named.V) is a high-level project where we take on the challenge of deploying a all-in-one database from scratch to production. Join me on this journey!
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
A compute framework for building Search, RAG, Recommendations and Analytics over complex structured & unstructured data.
See how to augment LLMs with real-time data for dynamic, context-aware apps - Rag + Agents + GraphRAG.
🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.
Go library for embedded vector search and semantic embeddings using llama.cpp
Real-time on-device text-to-image and image-to-image Semantic Search with video stream capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
Here you can find all the Tutorials for Haystack 📓
SemanticPDF: Drag, Drop, Semantic Search - SemanticPDF is a simple, privacy-focused application that makes it easy to upload a PDF file and perform a semantic search on contents.
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C...
Semantic Search demo featuring UForm, USearch, UCall, and StreamLit, to visual and retrieve from image datasets, similar to "CLIP Retrieval"
🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
Open-source ecosystem for building AI-powered conversational solutions using RAG, agents, FSMs, and LLMs.
Harness the power of Retrieval-Augmented Generation with the Personal AI Assistant, an innovative tool designed to extract and synthesize information from web and PDF sources efficiently. This cutting...
Hybrid search engine, combining best features of text and semantic search worlds
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C...
Go library for embedded vector search and semantic embeddings using llama.cpp
A cutting-edge search engine project tailored specifically for the AI product
Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.
A blazing-fast semantic search React component. Match by meaning, not just by letters. Search as you type without waiting (no debounce needed). Rank by cosine similarity.
NNV(No-Named.V) is a high-level project where we take on the challenge of deploying a all-in-one database from scratch to production. Join me on this journey!
See how to augment LLMs with real-time data for dynamic, context-aware apps - Rag + Agents + GraphRAG.
UI widget for adding semantic search to your React UI in just a few lines of code
CLIP-Finder enables semantic offline searches of images from gallery photos using natural language descriptions or the camera. Built on Apple's MobileCLIP-S0 architecture, it ensures optimal performan...
Vector search over tweets from the tweet archive using OpenAI embeddings and LanceDB
SemanticPDF: Drag, Drop, Semantic Search - SemanticPDF is a simple, privacy-focused application that makes it easy to upload a PDF file and perform a semantic search on contents.
Your AI Powered Enterprise Knowledge Partner. Designed to be used at scale from ingesting large amounts of documents formats such as pdfs, docx, xlsx, png, jpgs, tiff, mp3, mp4, jpeg. Integrates with ...
Kubernetes operator for producing vector embeddings based on source code repositories.
AI-powered semantic search engine for emojis in 50+ languages, developed in Python
Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by Prithivi Da, For PRs and Collaboration checkout the readme.
21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
Platform for building AI that can learn and answer questions over federated data.
A lightning-fast search API that fits effortlessly into your apps, websites, and workflow
AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. W...
Open Source alternative to Algolia + Pinecone and an Easier-to-Use alternative to ElasticSearch ⚡ 🔍 ✨ Fast, typo tolerant, in-memory fuzzy Search Engine for building delightful search experiences
Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.
💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows
Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a c...
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Chatbot for documentation, that allows you to chat with your data. Privately deployable, provides AI knowledge sharing and integrates knowledge into your AI workflow
Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍
A curated list of Generative AI tools, works, models, and references
RAG architecture: index and query any data using LLM and natural language, track sources, show citations, asynchronous memory patterns.
Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai
A compute framework for building Search, RAG, Recommendations and Analytics over complex structured & unstructured data.
Jupyter Notebooks to help you get hands-on with Pinecone vector databases
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C...
Go library for embedded vector search and semantic embeddings using llama.cpp
Hybrid search engine, combining best features of text and semantic search worlds
CLIP-Finder enables semantic offline searches of images from gallery photos using natural language descriptions or the camera. Built on Apple's MobileCLIP-S0 architecture, it ensures optimal performan...
SemanticPDF: Drag, Drop, Semantic Search - SemanticPDF is a simple, privacy-focused application that makes it easy to upload a PDF file and perform a semantic search on contents.
Real-time on-device text-to-image and image-to-image Semantic Search with video stream capture using USearch & UForm AI Swift SDKs for Apple devices 🍏
Superduper: Build end-to-end AI applications and agent workflows on your existing data infrastructure and preferred tools - without migrating your data.
SQL Server connector for Semantic Kernel plugin and Kernel Memory
Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by Prithivi Da, For PRs and Collaboration checkout the readme.
NNV(No-Named.V) is a high-level project where we take on the challenge of deploying a all-in-one database from scratch to production. Join me on this journey!
🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI ...
Offline semantic Text-to-Image and Image-to-Image search on Android powered by quantized state-of-the-art vision-language pretrained CLIP model and ONNX Runtime inference engine
21 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/
SemanticFinder - frontend-only live semantic search with transformers.js
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
Open-source ecosystem for building AI-powered conversational solutions using RAG, agents, FSMs, and LLMs.
Efficient Retrieval Augmentation and Generation Framework
Semantic Search demo featuring UForm, USearch, UCall, and StreamLit, to visual and retrieve from image datasets, similar to "CLIP Retrieval"
This repository features three demos that can be effortlessly integrated into your AWS environment. They serve as a practical guide to leveraging AWS services for crafting a sophisticated Large Langua...