Trending repositories for topic information-retrieval

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Retrieval and Retrieval-augmented LLMs

:mag: LLM 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 ...

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

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

Harness LLMs with Multi-Agent Programming

Efficient Retrieval Augmentation and Generation Framework

MTEB: Massive Text Embedding Benchmark

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

Topic Modelling for Humans

Fetches system/theme information in terminal for Linux desktop screenshots.

Apache Lucene open-source search software

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

A Collection of BM25 Algorithms in Python

Effortlessly extract information from unstructured data with this library, utilizing advanced AI techniques. Compose AI in customizable pipelines and diverse sources for your projects.

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

Effortlessly extract information from unstructured data with this library, utilizing advanced AI techniques. Compose AI in customizable pipelines and diverse sources for your projects.

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Elevate user interactions with ChatFAQ: your open-source chatbot solution, offering the full spectrum of ChatGPT capabilities. AI + LLM + CMS

A simple username osint tool built in go

Efficient Retrieval Augmentation and Generation Framework

Harness LLMs with Multi-Agent Programming

cuVS - a library for vector search and clustering on the GPU

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

Retrieval and Retrieval-augmented LLMs

🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

MTEB: Massive Text Embedding Benchmark

A Python Search Engine for Humans 🥸

🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

Generative Representational Instruction Tuning

A Collection of BM25 Algorithms in Python

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Official Kubernetes operator for Apache Solr

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

:mag: LLM 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 ...

Retrieval and Retrieval-augmented LLMs

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

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...

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

Harness LLMs with Multi-Agent Programming

MTEB: Massive Text Embedding Benchmark

Efficient Retrieval Augmentation and Generation Framework

Topic Modelling for Humans

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Apache Lucene open-source search software

Generative Representational Instruction Tuning

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Fetches system/theme information in terminal for Linux desktop screenshots.

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

Effortlessly extract information from unstructured data with this library, utilizing advanced AI techniques. Compose AI in customizable pipelines and diverse sources for your projects.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

cuVS - a library for vector search and clustering on the GPU

Content-Based Image Retrieval (CBIR) using Faiss (Facebook) and many different feature extraction methods ( VGG16, ResNet50, Local Binary Pattern, RGBHistogram)

Minimalist web-searching app with an AI assistant that runs directly from your browser. Uses Web-LLM, Ratchet-ML, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

Elevate user interactions with ChatFAQ: your open-source chatbot solution, offering the full spectrum of ChatGPT capabilities. AI + LLM + CMS

Generative Representational Instruction Tuning

Efficient Retrieval Augmentation and Generation Framework

Retrieval and Retrieval-augmented LLMs

Harness LLMs with Multi-Agent Programming

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

pytrec_eval is an Information Retrieval evaluation tool for Python, based on the popular trec_eval.

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

MTEB: Massive Text Embedding Benchmark

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

A simple username osint tool built in go

Codes for papers on Large Language Models Personalization (LaMP)

🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Retrieval and Retrieval-augmented LLMs

:mag: LLM 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 ...

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

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...

Harness LLMs with Multi-Agent Programming

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

MTEB: Massive Text Embedding Benchmark

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

Topic Modelling for Humans

Efficient Retrieval Augmentation and Generation Framework

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

Comprehensive and timely academic information on federated learning (papers, frameworks, datasets, tutorials, workshops)

Apache Lucene open-source search software

Fetches system/theme information in terminal for Linux desktop screenshots.

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Up to 200x Faster Inner Products and Vector Similarity — for Python, JavaScript, Rust, C, and Swift, supporting f64, f32, f16 real & complex, i8, and binary vectors using SIMD for both x86 AVX2 & AVX-...

Generative Representational Instruction Tuning

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

cuVS - a library for vector search and clustering on the GPU

Minimalist web-searching app with an AI assistant that runs directly from your browser. Uses Web-LLM, Ratchet-ML, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

Content-Based Image Retrieval (CBIR) using Faiss (Facebook) and many different feature extraction methods ( VGG16, ResNet50, Local Binary Pattern, RGBHistogram)

An Extensible Framework for Retrieval-Augmented LLM Applications: Learning Relevance Beyond Simple Similarity.

Effortlessly extract information from unstructured data with this library, utilizing advanced AI techniques. Compose AI in customizable pipelines and diverse sources for your projects.

Harness LLMs with Multi-Agent Programming

Elevate user interactions with ChatFAQ: your open-source chatbot solution, offering the full spectrum of ChatGPT capabilities. AI + LLM + CMS

The idea is to calculate the similarity between the resume and the job description and then return the resumes with the highest similarity score.

Codes for papers on Large Language Models Personalization (LaMP)

Generative Representational Instruction Tuning

Retrieval and Retrieval-augmented LLMs

🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.

Explore LangChain and build powerful chatbots that interact with your own data. Gain insights into document loading, splitting, retrieval, question answering, and more.

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Open-Source Evaluation for GenAI Application Pipelines

Efficient Retrieval Augmentation and Generation Framework

MTEB: Massive Text Embedding Benchmark

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Retrieval and Retrieval-augmented LLMs

Generative Representational Instruction Tuning

AgentSearch is a framework for powering search agents and enabling customizable local search.

Train and Infer Powerful Sentence Embeddings with AnglE | 🔥 SOTA on STS and MTEB Leaderboard

Open-Source Evaluation for GenAI Application Pipelines

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

This is the repository for our paper "INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning"

🍁 Sycamore is an LLM-powered search and analytics platform for unstructured data.

Explore LangChain and build powerful chatbots that interact with your own data. Gain insights into document loading, splitting, retrieval, question answering, and more.

cuVS - a library for vector search and clustering on the GPU

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

Minimalist web-searching app with an AI assistant that runs directly from your browser. Uses Web-LLM, Ratchet-ML, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

CLIPMH:CLIP Multi-modal Hashing

SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 languages, generated using PaLM 2 and summarize-then-ask promptin...

An Extensible Framework for Retrieval-Augmented LLM Applications: Learning Relevance Beyond Simple Similarity.

[CIKM 2023] This is the code repo for our CIKM‘23 paper "Text Matching Improves Sequential Recommendation by Reducing Popularity Biases".

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

Retrieval and Retrieval-augmented LLMs

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

:mag: LLM 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 ...

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

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

Up to 10x faster strings for C, C++, Python, Rust, and Swift, leveraging SWAR and SIMD on Arm Neon and x86 AVX2 & AVX-512-capable chips to accelerate search, sort, edit distances, alignment scores, et...

Harness LLMs with Multi-Agent Programming

Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

MTEB: Massive Text Embedding Benchmark

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

Topic Modelling for Humans

Efficient Retrieval Augmentation and Generation Framework

Up to 200x Faster Inner Products and Vector Similarity — for Python, JavaScript, Rust, C, and Swift, supporting f64, f32, f16 real & complex, i8, and binary vectors using SIMD for both x86 AVX2 & AVX-...

Apache Lucene open-source search software

Comprehensive and timely academic information on federated learning (papers, frameworks, datasets, tutorials, workshops)

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Track any ip address with IP-Tracer. IP-Tracer is developed for Linux and Termux. you can retrieve any ip address information using IP-Tracer.

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

Up to 10x faster strings for C, C++, Python, Rust, and Swift, leveraging SWAR and SIMD on Arm Neon and x86 AVX2 & AVX-512-capable chips to accelerate search, sort, edit distances, alignment scores, et...

Up to 200x Faster Inner Products and Vector Similarity — for Python, JavaScript, Rust, C, and Swift, supporting f64, f32, f16 real & complex, i8, and binary vectors using SIMD for both x86 AVX2 & AVX-...

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases

cuVS - a library for vector search and clustering on the GPU

Minimalist web-searching app with an AI assistant that runs directly from your browser. Uses Web-LLM, Ratchet-ML, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

Generative Representational Instruction Tuning

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

Efficient Retrieval Augmentation and Generation Framework

MTEB: Massive Text Embedding Benchmark

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

🔎 SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.

No description

[ICCV 2023] - Composed Image Retrieval on Common Objects in context (CIRCO) dataset

The idea is to calculate the similarity between the resume and the job description and then return the resumes with the highest similarity score.

Effortlessly extract information from unstructured data with this library, utilizing advanced AI techniques. Compose AI in customizable pipelines and diverse sources for your projects.

This app allows users to easily query a PDF document using OpenAI's GPT-3 language model in Google Colab, utilizing Google Drive for storage.

Codebase for RetroMAE and beyond.

Content-Based Image Retrieval (CBIR) using Faiss (Facebook) and many different feature extraction methods ( VGG16, ResNet50, Local Binary Pattern, RGBHistogram)

SWIM-IR is a Synthetic Wikipedia-based Multilingual Information Retrieval training set with 28 million query-passage pairs spanning 33 languages, generated using PaLM 2 and summarize-then-ask promptin...