https://github.com/pilarcode/rag_apis
🤖 Chatbot to recommend services from the api specification
https://github.com/pilarcode/rag_apis
azureopenai chromadb gradio langchain llm rag
Last synced: 12 months ago
JSON representation
🤖 Chatbot to recommend services from the api specification
- Host: GitHub
- URL: https://github.com/pilarcode/rag_apis
- Owner: pilarcode
- Created: 2023-12-30T18:06:17.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-02-20T20:31:55.000Z (almost 2 years ago)
- Last Synced: 2024-02-21T21:25:48.988Z (almost 2 years ago)
- Topics: azureopenai, chromadb, gradio, langchain, llm, rag
- Language: Python
- Homepage:
- Size: 1.22 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# QA chatbot
Chatbot to answer questions about api services.
# Data
Api specification about pets.
# Development
### Init repo
```bash
$ git init .
```
and link it to the cloud repo. e.g.:
```bash
$ git remote add origin https://github.com/pilarcode/rag_langchain.git
$ git branch -M main
$ git push -uf origin main
```
# Deployment
To generate the containerized app and run it on-prem or on a VM, follow these steps:
1. Build the Docker image:
```bash
docker build -t mrag .
```
2. Run the Docker container:
```bash
docker run -it -p 8046:8046 mrag
```
# Run
To interact with the assistant, open your browser. e.g., http://localhost:8046
# Implemented with this tools
* LangChain
* Gradio
* AzureOpenAI llm: gpt 3.5 turbo
* AzureOpenAI embeddings: text-embedding-ada-002
* Vector stores: Chroma
* Jupyter notebooks
* Python
# Tests
The user says hi and the smart assistant should offer assistance to the users
The user asks a question about a service in English
The user asks a question about a service in French