saberbud/PocketFlow-Tutorial-Codebase-Knowledge
1
0
Fork 0
mirror of https://github.com/The-Pocket/PocketFlow-Tutorial-Codebase-Knowledge.git synced 2026-08-29 16:40:32 +08:00
Code Issues Packages Projects Releases Wiki Activity

switch provider based on environment variables

Browse Source
This commit is contained in:
Mark Van de Vyver
2025-10-24 04:59:32 +11:00
parent b597bb9d3b
commit c6eaaffd7b
2 changed files with 81 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -8
View File
@@ -86,14 +86,7 @@ This is a tutorial project of [Pocket Flow](https://github.com/The-Pocket/Pocket
pip install -r requirements.txt
```
4. Set up LLM in [`utils/call_llm.py`](./utils/call_llm.py) by providing credentials. By default, you can use the [AI Studio key](https://aistudio.google.com/app/apikey) with this client for Gemini Pro 2.5:
```python
client = genai.Client(
api_key=os.getenv("GEMINI_API_KEY", "your-api_key"),
)
```
4. Set up LLM in [`utils/call_llm.py`](./utils/call_llm.py) by providing credentials. To do so, you can put the values in a `.env` file. By default, you can use the AI Studio key with this client for Gemini Pro 2.5 by setting the `GEMINI_API_KEY` environment variable. If you want to use another LLM, you can set the `LLM_PROVIDER` environment variable (e.g. `XAI`), and then set the model, url, and API key (e.g. `XAI_MODEL`, `XAI_URL`,`XAI_API_KEY`). If using Ollama, the url is `http://localhost:11434/` and the API key can be omitted.
You can use your own models. We highly recommend the latest models with thinking capabilities (Claude 3.7 with thinking, O1). You can verify that it is correctly set up by running:
```bash
python utils/call_llm.py