https://github.com/eggplants/dlsite-recommendation-llm
Recommend DLSite voice works with LLM
https://github.com/eggplants/dlsite-recommendation-llm
Last synced: about 1 year ago
JSON representation
Recommend DLSite voice works with LLM
- Host: GitHub
- URL: https://github.com/eggplants/dlsite-recommendation-llm
- Owner: eggplants
- License: mit
- Created: 2024-02-13T18:16:08.000Z (over 2 years ago)
- Default Branch: master
- Last Pushed: 2024-11-09T17:16:58.000Z (over 1 year ago)
- Last Synced: 2024-11-30T17:47:36.722Z (over 1 year ago)
- Language: Python
- Homepage: https://dlsite-recommendation-llm.onrender.com
- Size: 1.77 MB
- Stars: 5
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# dlsite-recommendation-llm
[](
) [](
) [](
) [](
)
Reimplementation of , but for [DLsite](https://www.dlsite.com/) voice works!
## Deployment
[![Deploy to Render]](https://render.com/deploy?repo=https://github.com/eggplants/dlsite-recommendation-llm)
[![Website]](https://drl.egpl.dev)

[Deploy to Render]:
[Website]:
## Configuration
You have to copy existing `.env.example` file to `.env` file and fill in to run in local.
- `PINECONE_API_KEY`: Pinecone [API key](https://docs.pinecone.io/docs/projects#api-keys)
- `PINECONE_INDEX`: Pinecone [index](https://docs.pinecone.io/docs/indexes) name
- `PINECONE_ENV`: [Pod environment](https://docs.pinecone.io/docs/indexes#pod-environments) to host index DB
- `OPENAI_API_KEY`: OpenAI [API key](https://platform.openai.com/docs/quickstart/account-setup)
- `OPENAI_API_MODEL`: OpenAI [model](https://platform.openai.com/docs/models/models)
- `OPENAI_API_TEMPERATURE`: OpenAI API [sampling temperature](https://platform.openai.com/docs/api-reference/audio/createTranscription#audio-createtranscription-temperature) (to put it simply, it is randomness)
## How to run
You can fetch data from DLsite with [eggplants/dojinvoice_db](https://github.com/eggplants/dojinvoice_db).
```bash
# Setup deps
poetry shell
poetry install
# Convert SQLite db to CSV file
python scripts/convert_db_to_csv.py
# Create vector data from CSV data and upload to Pinecone
python scripts/add_doc_to_index.py
# Launch Streamlit server
drl
```