296 skills found · Page 9 of 10
ruvnet / Contextual RetrevialThis Contextual Retrieval System enhances the accuracy and relevance of information retrieval by incorporating context into the search process. It leverages OpenAI's GPT-4 model, LlamaIndex, FastAPI, LiteLLM, and uses Supabase for both vector storage and document storage and management.
JustVugg / EasymemoryA 100% local memory layer for chatbots and agents with an MCP server for Claude, GPT, Gemini, and local models. It auto-saves conversations, ingests documents and markdown vaults, and provides hybrid retrieval (vector + keyword + graph) plus enterprise security (OAuth2, API keys, rate limiting, audit logs) and integrations (Slack import, Notion/GDr
vasilyaksenov / QCustomPlotQCustomPlot is a Qt C++ widget for plotting and data visualization. It has no further dependencies and is well documented. This plotting library focuses on making good looking, publication quality 2D plots, graphs and charts, as well as offering high performance for realtime visualization applications. Have a look at the Setting Up and the Basic Plotting tutorials to get started. QCustomPlot can export to various formats such as vectorized PDF files and rasterized images like PNG, JPG and BMP. QCustomPlot is the solution for displaying of realtime data inside the application as well as producing high quality plots for other media.
mominalix / Multi Tenant Retrieval Augmented Generation RAG SystemA production-grade Multi-Tenant Retrieval-Augmented Generation (RAG) System built with FastAPI, Qdrant, and Streamlit. This system provides secure, isolated RAG capabilities for multiple organizations with advanced document processing, vector search, and LLM integration.
neonsecret / AI Challenge LegalARLC 2026 Agentic RAG Legal Challenge — Legal QA pipeline for DIFC court documents. Hybrid BM25 + vector retrieval, cross-encoder reranking, answer-grounded page verification.
abeermohamed1 / Tweets Sentiment AnalysisTweets Sentiment Analysis Project to classify the the polarity of tweets either as ‘Positive’, ‘Negative’, and ‘Neutral' with high accuracy
tankyhsu / Nanobot VikingOpenViking knowledge base integration for nanobot — RAG augmentation, semantic search, vector embeddings, document indexing. Free models on SiliconFlow.
SimonGit0 / Circuit DrawingTool for easily drawing appealing electrical circuit diagrams as vector graphics. E.g. to use them in a PDF (LaTeX document).
mujtaba057 / LAW BOT Legal Strategy Companion AI For Case Studies Advice Law Insights #(Langchain-and-OpenAI-API-LLM-model vector databases ) Law Bot provides defense points on specific allegations against an individual mentioned in the uploaded documents using Langchain-and-OpenAI-API-LLM-model-and-embeddings-vector-database
0xAdafang / LuminAi BackendHigh-performance RAG engine built with Go and PostgreSQL. Handles intelligent document ingestion (PDF/URL), semantic vector search with pgvector, and adaptive bilingual AI responses.
MadsDoodle / HRGenieAn agentic HR automation system that generates personalized offer letters based on employee metadata, salary structure, and HR policy documents. Combines document parsing, intelligent chunking, vector-based retrieval, and LLM-powered generation via a simple chat interface.
robaita / Rag With OpenwebuiA Retrieval-Augmented Generation (RAG) system integrated with OpenWebUI for document querying. It processes documents, retrieves relevant information using a vector database, and generates accurate responses with DeepSeek-R1:14B. Ideal for resume screening, legal research, and technical documentation.
shekh-2810 / DocInferXDocInferX is a fully-local, privacy-focused document intelligence system. It ingests PDFs and images, performs OCR, cleans text, chunks content, embeds it into a vector database, and lets you chat with your documents offline using a lightweight LLM (Phi-2).
harishkotra / Gaia Pdf RagGaia PDF RAG is a Retrieval-Augmented Generation (RAG) application that allows users to ask questions about PDF documents using a local Gaia node and Qdrant vector database.
pyr0mind / AI Powered PDF Agent ProjectAI-PDF-Agent converts PDFs into queryable data using AI. Extracts text (PyMuPDF), generates embeddings, and answers questions via LLMs (OpenAI). Modular for custom vector databases (Pinecone/FAISS). Ideal for research/legal analysis. MIT-licensed. Clone, install dependencies, and query documents. Open-source contributions enhance preprocessing.
rahulreddythummala / A Secure And Dynamic Multi Keyword Ranked Search Scheme Over Encrypted Cloud Data• Here, a secure multi-keyword ranked search scheme over encrypted cloud data is presented using JAVA as the frontend technology and backend as MySQL.• Specifically, the vector space model and the widely-used “term frequency (TF) × inverse document frequency(IDF)” model are combined in the index construction and query generation to provide multi-keyword ranked search.• We construct a special tree-based index structure and propose a “Greedy Depth-first Search” algorithm to provide efficient multi-keyword ranked search. • The secure kNN algorithm is utilized to encrypt the index and query vectors, and to ensure accurate relevance score calculation between encrypted index and query vectors. • To resist different attacks in different threat models, we construct two secure search schemes: the basic dynamic multi-keyword ranked search (BDMRS) scheme in the known ciphertext model, and the enhanced dynamic multi-keyword ranked search (EDMRS) scheme in the known background model.
v-owen / SuperChatBotA low latency parser and chatbot engine leveraging Azure OpenAI Embeddings with 2 custom fine-tuned LLMs, achieving ultra-low 100ms delay via MongoDB Atlas Vector Search and Redis while storing the uploaded documents on AWS S3. Deployed the FastAPI and Streamlit images with Jenkins pipelines on Azure Container Apps, reducing 60% peak loads.
MohammedNasserAhmed / Arabic Pdf ChatArabic Chat with PDF is a user-friendly application that lets you interact with Arabic PDF documents. Powered by advanced language models, OCR, and vector search, it allows you to upload PDFs, ask questions, and receive accurate Arabic responses 🚀
mdzaheerjk / Knowledge Intelligence SystemThis project aims to build a RAG-based Knowledge Intelligence System that lets users upload, organize, search, and chat with internal documents via a conversational AI interface. It combines vector retrieval with an LLM to deliver accurate, context-aware answers grounded in user data, with an admin dashboard for content and usage management.
anshul1004 / InformationRetrievalPerforms tokenization, stemming, lemmatization, index creation, index compression and ranked retrieval of Cranfield documents
