Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/samalba/dagger-chatbot
AI Chatbot that helps you learn how to use Dagger
https://github.com/samalba/dagger-chatbot
ai chatbot dagger langchain ollama python
Last synced: 7 days ago
JSON representation
AI Chatbot that helps you learn how to use Dagger
- Host: GitHub
- URL: https://github.com/samalba/dagger-chatbot
- Owner: samalba
- License: apache-2.0
- Created: 2023-07-30T01:09:09.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-08-23T16:46:27.000Z (about 1 year ago)
- Last Synced: 2024-08-02T18:40:22.295Z (3 months ago)
- Topics: ai, chatbot, dagger, langchain, ollama, python
- Language: Python
- Homepage:
- Size: 38.1 KB
- Stars: 28
- Watchers: 2
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# dagger-chatbot
Chatbot that understands Dagger pipelines and can help you using Dagger.
It's an alternative to reading documentation.
Tech used:
- Langchain
- Ollama
- Dagger Python SDK## Install dependencies
First, install the local python dependencies.
Run the following commands in a shell:
```shell
python3 -m venv venv && source ./venv/bin/activate
pip install -r requirements.txt
```Then you need to make sure you have [Ollama](https://ollama.ai/) up and running.
If you're not using the MacOS app and you built from the binary, open a shell and run the following command:
```shell
ollama serve
```## Generate assets
Several assets are needed for the chatbot to run:
- Fetch the documentation markdown files from the Dagger git repository
- Sanitize them (strip useless characters), split them into documents
- Tokenize the documents using an embedding model
- Store the tokenized documents into vector db (Chroma)How to generate the assets:
```shell
dagger run ./dagger_pipeline.py
```## Run the chatbot
Example:
```shell
./app.py
Ask me anything about Dagger: How to integrate Dagger with Github actions?
```