RAG-Powered Financial Query Assistant for JPMorgan Chase documents with Hybrid Search, Docker support, and Streamlit UI
-
Updated
Jul 7, 2026 - Python
#
bge-embeddings
Here are 30 public repositories matching this topic...
A production-ready, embeddable AI chatbot widget built with Cloudflare Workers that can be integrated into any website with a single script tag. Features real-time streaming responses, RAG-powered FAQ answers, session persistence, and dark/light mode support.
serverless customer-support server-sent-events kv shadow-dom semantic-search real-time-streaming rag cloudflare-workers workers-kv faq-chatbot ai-assistant vectorize workers-ai llama3 bge-embeddings embeddable-widget website-assistant knowledge-based-search ai-chatbot-widget
-
Updated
Aug 11, 2026 - JavaScript
An enterprise-grade, full-stack AI travel planner which provides data-driven itineraries for Lucknow, India and showcases production-ready architecture, combining a FastAPI backend with a Streamlit frontend. It leverages an advanced agentic RAG system, context-aware responses by integrating a local knowledge base with live, external APIs.
docker production-ready cloud-deployment rag fastapi groq streamlit vector-database open-meteo render-deployment langchain chromadb external-api-integration rag-chatbot huggingface-embeddings agentic-ai bge-embeddings llm-applications ragas-evaluation
-
Updated
Jul 9, 2026 - Python
AI/ML Engineer Portfolio | Japanese RAG Production System (FastAPI + real evaluation) | Credit Card Fraud Detection (XGBoost + SHAP + Docker) | Japanese Sentiment Analysis (BERT) | Open to mid-level AI/ML roles (India & Japan)
docker portfolio data-science python3 churn-prediction fraud-detection rag fastapi streamlit rag-pipeline bge-m3 bge-embeddings machne-learning ragas-evaluation japanese-bert
-
Updated
Jul 26, 2026 - HTML
A Graph-Augmented Retrieval Framework for Indian Legal Judgments using Structure-Aware Chunking, Region-Aware Metadata Extraction, Bipartite Citation Graphs, and Hybrid Dense-Graph Ranking.
machine-learning cuda-toolkit ndcg-evaluation pymupdf wilcoxon-test citation-graph indian-legal-judgements legalbert graphrag bge-embeddings all-minilm inlegalbert indian-kanoon legal-judgements
-
Updated
Jul 17, 2026 - Jupyter Notebook
Production-grade RAG Document Intelligence Platform — LangGraph Adaptive RAG + CRAG, LangSmith observability, RAGAS evaluation,Qdrant hybrid search (BGE dense + BM42 sparse + RRF), jinaai/jina-reranker-v1-tiny-en re-ranking, FastAPI + Docker
reranking rag pydantic fastapi rrf crag llm jinaai hybrid-retrieval qdrant-vector-database bge-embeddings ragas-evaluation jina-ai
-
Updated
Jun 9, 2026 - Python
Production-grade fashion recommendation platform using SigLIP (vision) + BGE (text) embeddings, FAISS HNSW, RRF fusion, and LLaMA 3.3-70B outfit styling. FastAPI + React + Supabase. 44k+ products.
react python pytorch recommendation-system llama multimodal faiss hnsw fastapi groq supabase fashion-recommender cloudflare-r2 render-deployment generative-ai siglip bge-embeddings
-
Updated
May 17, 2026 - Python
基于 BGE (BAAI General Embedding) 模型构建的高性能文本向量化服务，使用 FastAPI 提供 RESTful 接口，支持 ONNX模型的转换和推理加速。
-
Updated
Dec 27, 2025 - Python
Citation-grounded RAG system translating clinical guidelines into safe, trustworthy patient guidance.
testing safety evaluation-metrics mongodb-atlas rag pydantic fastapi qdrant-vector-database bge-embeddings docling gaurdrails
-
Updated
Aug 20, 2026 - HTML
Hybrid RAG–based e‑commerce agent for H&M products on the CLI, runnable both in the cloud with OpenAI and locally with Ollama.
-
Updated
Mar 10, 2026 - Python
PerfectPick is an AI-powered smartphone recommendation system built with Flask and Postgres for session management, AstraDB for vector storage, and hybrid retrieval using BM25 and BGE embeddings. Deployed on GCP with Docker and Kubernetes, integrated with Prometheus and Grafana for scalable, production-grade performance and MLOps observability.
python docker kubernetes flask machine-learning information-retrieval ai grafana postgresql gcp prometheus recommender-system cloud-deployment bm25 mlops vector-database hybrid-search astradb langchain bge-embeddings
-
Updated
Nov 5, 2025 - Python
A Retrieval-Augmented Generation (RAG) chatbot that lets you upload any PDF and ask questions, powered by Groq + Llama 3.3, LangChain, and FAISS.
python python3 artificial-intelligence question-answering llama gradio faiss rag langchain pdf-chatbot groq-api bge-embeddings
-
Updated
May 28, 2026 - Python
Local-first knowledge-graph memory layer for AI agents — what Mem0 charges for: 4-way RRF + L2 maintenance + bilingual classifier, one local SQLite. usearch f16 runs it on $10/year VPS.
ai memory sqlite mcp knowledge-graph hermes bilingual rag local-first ai-agent bge-embeddings sqlite-vec agent-memory mem0-alternative
-
Updated
Aug 16, 2026 - Python
Mini project for NLP: FineTuned a BGE encoder using domain specific data and then paired it with a finetuned BERT uncased model for QnA retrieval for getting top3 relevant answers.
-
Updated
Jun 10, 2026 - Python
TechReg Analyst is a production-grade Retrieval-Augmented Generation (RAG) system that answers complex queries over FIA Formula 1 Technical Regulations using FAISS-based retrieval, cross-encoder re-ranking, and grounded LLM generation.
python nlp information-retrieval llama faiss rag vector-search groq streamlit sentence-transformers cross-encoder llm langchain retrieval-augmented-generation bge-embeddings
-
Updated
May 3, 2026 - Python
A conversational chatbot that remembers context and retrieves external information using Retrieval-Augmented Generation (RAG) with LangChain, ChromaDB, local BGE embeddings, and Google Gemini 2.5 Flash.
-
Updated
May 18, 2026 - Python
📚 AI-powered Research Paper Question Answering System using a Manual Retrieval-Augmented Generation (RAG) Pipeline.
python nlp machine-learning ai transformers bge question-answering semantic-search research-paper bert rag streamlit hugging-face retrieval-augmented-generation bge-embeddings manual-rag
-
Updated
Jul 2, 2026 - Python
A local RAG playground with Go, Ollama, BGE, PostgreSQL and pgvector.
-
Updated
May 8, 2026 - Go
RAG system that you can test the method in each step and decide what way is better approach for your data
semantic hyde rag minilm dense-retrieval llm rerank bge-embeddings contextual-chunks recursive-chunking hybrid-re
-
Updated
Jun 30, 2026 - Python
This repository stores the pre-built LlamaIndex vector index used by FinRAG. It contains document chunks and embeddings created with pdfplumber, Hugging Face’s BGE model, and LlamaIndex, allowing the main app to load the index without rebuilding it.
embeddings document-retrieval rag huggingface sematic-search vector-store llamaindex vector-index bge-embeddings financial-documents
-
Updated
Jul 15, 2026
Improve this page
Add a description, image, and links to the bge-embeddings topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the bge-embeddings topic, visit your repo's landing page and select "manage topics."