nath1295/LLMFlex
A python package for developing AI applications with local LLMs.
Supports multiple model formats (GGUF, GPTQ, AWQ, EXL2, PyTorch) and OpenAI API servers through a unified `LlmFactory` interface, enabling inference across different backends without code changes. Provides composable abstractions for RAG pipelines—embedding toolkits, FAISS vector databases, chat memory with long/short-term recall, and a ReAct agent framework—alongside Langchain compatibility for existing workflows. Includes a Streamlit interface for local chatbot deployment with function calling, document-based RAG, and configurable prompt templates for different model families.
150 stars and 43 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
150
Forks
20
Language
Python
License
MIT
Category
Last pushed
Jan 04, 2025
Monthly downloads
43
Commits (30d)
0
Dependencies
25
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/nath1295/LLMFlex"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
lancedb/vectordb-recipes
Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs
ErickWendel/neo4j-ai-experiments
Examples of my tutorial on how to use Neo4j for empowering AI RAG systems
Emirateyang/llm-agent
Java library to simplify the integration of LLMs
ISNE11/CheatSheet-LLM
Run local Large Language Models (LLMs) offline using Ollama – interact with textbooks and custom...
lisekarimi/lexo
🗯️LLM toolkit for RAG, tuning, agents, and more