https://github.com/bentoml/rag-tutorials
a series of tutorials implementing rag service with BentoML and LlamaIndex
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 (14.7%) to scientific vocabulary
Repository
a series of tutorials implementing rag service with BentoML and LlamaIndex
Basic Info
- Host: GitHub
- Owner: bentoml
- Language: Python
- Default Branch: main
- Size: 318 KB
Statistics
- Stars: 47
- Watchers: 4
- Forks: 9
- Open Issues: 3
- Releases: 0
Metadata Files
README.md
Self-Hosted RAG Web Service with BentoML
This is a BentoML example project, containing a series of tutorials where we build a complete self-hosted Retrieval-Augmented Generation (RAG) application, step-by-step.
This project will guide you through setting up a RAG service that uses vector-based search and large language models (LLMs) to answer queries using documents as a knowledge base. Our ultimate goal is to create a system that can scale efficiently and handle complex queries with high performance.
See here for a full list of BentoML example projects.
Project overview
This repository contains a series of five tutorials designed to progressively build a RAG system with custom embedding and language models as well as a vector database.
- Building a Simple RAG System using LlamaIndex: Set up a basic RAG system that runs locally on your machine using LlamaIndex. This serves as a foundational step, familiarizing you with the basic components of a RAG system.
- Transforming a Local RAG into a BentoML Web Service: Convert the local script into a web service by setting up a basic API service using BentoML.
- Integrating a Custom Embedding Service: Replace the default OpenAI embedding model used in the RAG system with a custom model.
- Integrating a Custom LLM: Replace the default OpenAI question-answering part in the RAG system with a custom LLM.
- Integrating Milvus Vector Database: Implement Milvus to manage the documentation index for better scalability and performance.
Set up the environment
To begin, clone the entire project.
bash
git clone https://github.com/bentoml/rag-tutorials.git
cd rag-tutorials
Next, set up the Python environment required for running the tutorials:
```bash
Recommend Python 3.11
python3 -m venv rag-bentoml && . rag-bentoml/bin/activate && pip install -r requirement.txt ```
Get started
Each tutorial is self-contained and includes instructions on setting up and running the components discussed. Start with the first tutorial and proceed through each to build upon the previous steps. By the end of the series, you will have a better understanding of how to build a RAG system using modern technologies and custom integrations.
Have fun!
Owner
- Name: BentoML
- Login: bentoml
- Kind: organization
- Location: San Francisco
- Website: https://bentoml.com
- Twitter: bentomlai
- Repositories: 76
- Profile: https://github.com/bentoml
The most flexible way to serve AI models in production
GitHub Events
Total
- Watch event: 20
- Push event: 1
- Fork event: 4
Last Year
- Watch event: 20
- Push event: 1
- Fork event: 4
Issues and Pull Requests
Last synced: over 1 year ago
All Time
- Total issues: 3
- Total pull requests: 7
- Average time to close issues: about 22 hours
- Average time to close pull requests: 20 days
- Total issue authors: 3
- Total pull request authors: 2
- Average comments per issue: 0.33
- Average comments per pull request: 0.14
- Merged pull requests: 7
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 3
- Pull requests: 7
- Average time to close issues: about 22 hours
- Average time to close pull requests: 20 days
- Issue authors: 3
- Pull request authors: 2
- Average comments per issue: 0.33
- Average comments per pull request: 0.14
- Merged pull requests: 7
- Bot issues: 0
- Bot pull requests: 0
Top Authors
Issue Authors
- Prajval108 (1)
- ahmedkotb98 (1)
- andysingal (1)
Pull Request Authors
- Sherlock113 (9)
- larme (1)