https://github.com/allrivertosea/deepseek-rag-mindtree
Mindtree enables fast, accurate, and explainable retrieval of information from PDFs, DOCX, and TXT files using DeepSeek-7B, BM25, FAISS, Neural Reranking (Cross-Encoder), GraphRAG, and Chat History Integration.
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (5.9%) to scientific vocabulary
Repository
Mindtree enables fast, accurate, and explainable retrieval of information from PDFs, DOCX, and TXT files using DeepSeek-7B, BM25, FAISS, Neural Reranking (Cross-Encoder), GraphRAG, and Chat History Integration.
Basic Info
- Host: GitHub
- Owner: allrivertosea
- License: mit
- Language: Python
- Default Branch: main
- Size: 233 KB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
DeepSeek-RAG-Mindtree
Mindtree-RAG leverages DeepSeek-R1:7B, BM25, FAISS, Neural Reranking (Cross-Encoder), GraphRAG, and Chat History Integration to efficiently retrieve information from PDFs, DOCX, and TXT files with speed, accuracy, and explainability.
Clone the Repository & Install Dependencies
git clone https://github.com/allrivertosea/DeepSeek-RAG-Mindtree.git
cd DeepSeek-RAG-Mindtree
conda create --name mindtree python=3.10
activate mindtree
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
Download model
Download Ollama → https://ollama.com/
ollama pull deepseek-r1:7b
ollama pull nomic-embed-text
Run
streamlit run app.py
http://localhost:8501
Owner
- Login: allrivertosea
- Kind: user
- Repositories: 1
- Profile: https://github.com/allrivertosea
GitHub Events
Total
- Watch event: 1
- Push event: 4
- Create event: 2
Last Year
- Watch event: 1
- Push event: 4
- Create event: 2
Dependencies
- PyMuPDF >=1.23.8
- docx2txt >=0.8
- faiss-cpu >=1.7.4
- langchain-community >=0.0.16
- langchain-core >=0.1.17
- langchain-ollama >=0.0.1
- networkx >=3.2.1
- numpy >=1.24.0
- pandas >=2.1.0
- pydantic >=2.5.3
- pypdf >=3.17.1
- rank-bm25 >=0.2.2
- requests >=2.31.0
- sentence-transformers >=2.2.2
- spacy >=3.7.2
- streamlit >=1.31.0
- torch >=2.1.0
- tqdm >=4.66.1