document-search

This open source chatbot project lets you create a chatbot that uses your own data to answer questions, thanks to the power of the OpenAI GPT-3.5 model.

python machine-learning ai chatbot python3 openai gpt knowledge-base document-search contextual-chatbot chatgpt chatgpt-api openai-chatgpt llama-index

UpdatedJul 13, 2023
Python

poloclub /mememo

Star105

A JavaScript library that brings vector search and RAG to your browser!

browser image-search document-search rag vector-search vector-database llm gen-ai

UpdatedAug 15, 2024
TypeScript

capjamesg /jamesql

Sponsor

Star83

An in-memory NoSQL database implemented in Python.

python nosql nosql-database web-search document-search

UpdatedFeb 10, 2025
Python

kcubeterm /achoz

Star80

Search through all your personal data efficiently like web search.

search-engine crawler websearch filesearch document-search

UpdatedJan 31, 2023
Python

daac-tools /find-simdoc

Star60

Finding all pairs of similar documents time- and memory-efficiently

UpdatedMar 13, 2025
Rust

deepsense-ai /ragbits

Star58

Building blocks for rapid development of GenAI applications

evaluation document-search rag guardrails llms prompt-management ragstack rag-optimization

UpdatedMar 22, 2025
Python

neuml /cord19q

Star56

COVID-19 Open Research Dataset (CORD-19) Analysis

python search nlp machine-learning medical scientific-papers document-search covid-19

UpdatedNov 20, 2022
Python

zayedrais /DocumentSearchEngine

Star53

Document Search Engine project with TF-IDF abd Google universal sentence encoder model

python data-science machine-learning deep-learning tensorflow text-analysis semantic-search-engine tensorflow-tutorials tfidf semantic-search tensorflow-models text-search document-similarity document-search juypter tfidf-text-analysis text-semantic-similarity universal-sentence-encoder tfidf-vectorizer python-text-analysis

UpdatedMay 1, 2023
Jupyter Notebook

teilomillet /raggo

Star47

A lightweight, production-ready RAG (Retrieval Augmented Generation) library in Go.

golang ai embeddings openai question-answering document-search rag vector-search milvus vector-database llm chromadb retrieval-augmented-generation

UpdatedNov 23, 2024
Go

infinilabs /coco-server

Star42

🥥 Coco AI Server - Search, Connect, Collaborate, AI-powered enterprise search, all in one space.

launcher collaboration raycast semantic-search enterprise-search desktop-search ai-search document-search rag ai-assistant cloud-search workspace-search enterprise-assistant glean-opensource-alternative

UpdatedMar 21, 2025
TypeScript

jankovicsandras /plpgsql_bm25

Star40

BM25 search implemented in PL/pgSQL

search postgres postgresql plpgsql bm25 okapi text-search document-search bm25okapi

UpdatedMar 10, 2025
Jupyter Notebook

jankovicsandras /bm25opt

Star19

faster BM25 search algorithms in Python

python3 bag-of-words bm25 text-search document-search bm25plus bm25okapi bm25l

UpdatedNov 14, 2024
Jupyter Notebook

easonlai /chatbot_with_pdf_streamlit

Star15

This code example shows how to make a chatbot for semantic search over documents using Streamlit, LangChain, and various vector databases. The chatbot lets users ask questions and get answers from a document collection. The code is in Python and can be customized for different scenarios and data.

python azure openai chroma embedding-models semantic-search pinecone vector-similarity document-search vector-search streamlit vector-database azure-cognitive-search gpt-3 azure-openai langchain gpt-35-turbo langchain-python

UpdatedSep 3, 2023
Jupyter Notebook

kyr0 /clientside-search

Sponsor

Star10

A highly efficient, isomorphic, full-featured, multilingual text search engine library, providing full-text search, fuzzy matching, phonetic scoring, document indexing and more, with micro JSON state hydration/dehydration in-browser and server-side.

nodejs multilingual search-engine browser trie fuzzy-matching full-text-search lucene tf-idf client-side phonetics text-processing bk-tree bm25 text-search document-search damerau-levenshtein-distance document-indexing state-hydration

UpdatedJul 21, 2023
TypeScript

lekt9 /alBERT-launcher

Star8

AI-powered file launcher and semantic search assistant. Like Spotlight/Alfred but with advanced AI capabilities for understanding context and meaning. Features local processing, privacy-first design, and seamless integration with your workflow.

electron macos search-engine alfred privacy typescript ai local spotlight desktop semantic-search document-search productivity-tool vector-search llm local-ai ollama