puppetm4st3r / baai_m3_simple_server
This code sets up a simple yet robust server using FastAPI for handling asynchronous requests for embedding generation and reranking tasks using the BAAI M3 multilingual model.
☆58Updated 9 months ago
Alternatives and similar repositories for baai_m3_simple_server:
Users that are interested in baai_m3_simple_server are comparing it to the libraries listed below
- A fast, lightweight and easy-to-use Python library for splitting text into semantically meaningful chunks.☆239Updated this week
- Code for explaining and evaluating late chunking (chunked pooling)☆321Updated last month
- Official repo for "LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs".☆220Updated 5 months ago
- Open Source Text Embedding Models with OpenAI Compatible API☆145Updated 7 months ago
- ☆205Updated 2 months ago
- Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception☆111Updated 3 weeks ago
- Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on task…☆147Updated 4 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆130Updated 7 months ago
- Client Code Examples, Use Cases and Benchmarks for Enterprise h2oGPTe RAG-Based GenAI Platform☆82Updated this week
- An enterprise-grade AI retriever designed to streamline AI integration into your applications, ensuring cutting-edge accuracy.☆279Updated this week
- Fine-Tuning Embedding for RAG with Synthetic Data☆483Updated last year
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆200Updated 3 months ago
- TextEmbed is a REST API crafted for high-throughput and low-latency embedding inference. It accommodates a wide variety of embedding mode…☆22Updated 5 months ago
- ☆307Updated last year
- ☆57Updated 10 months ago
- RankLLM is a Python toolkit for reproducible information retrieval research using rerankers, with a focus on listwise reranking.☆402Updated this week
- AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark☆124Updated last month
- This repo is for handling Question Answering, especially for Multi-hop Question Answering☆67Updated last year
- ☆173Updated last week
- ☆74Updated last year
- Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, imp…☆171Updated 5 months ago
- Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cro…☆746Updated 2 months ago
- A Comprehensive Benchmark for Document Parsing and Evaluation☆230Updated this week
- Vision Document Retrieval (ViDoRe): Benchmark. Evaluation code for the ColPali paper.☆173Updated this week
- This repository implements the chain of verification paper by Meta AI☆162Updated last year
- [EMNLP 2024: Demo Oral] RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation☆286Updated 3 months ago
- Dense X Retrieval: What Retrieval Granularity Should We Use?☆145Updated last year
- Code for Husky, an open-source language agent that solves complex, multi-step reasoning tasks. Husky v1 addresses numerical, tabular and …☆335Updated 8 months ago
- A Python library to chunk/group your texts based on semantic similarity.☆93Updated 7 months ago
- Guideline following Large Language Model for Information Extraction☆340Updated 3 months ago