jamesf/Perplexica
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add Serper API as an alternative search provider option for faster speeds and no rate limitations from Google

Browse source
This commit is contained in:
Roger M 2024-04-29 19:44:53 +01:00
parent ab6cda690f
commit 4cd0778094
12 changed files with 137 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -65,8 +65,8 @@ There are mainly 2 ways of installing Perplexica - With Docker, Without Docker.
- `OPENAI`: Your OpenAI API key. **You only need to fill this if you wish to use OpenAI's models**.
- `OLLAMA`: Your Ollama API URL. You should enter it as `http://host.docker.internal:PORT_NUMBER`. If you installed Ollama on port 11434, use `http://host.docker.internal:11434`. For other ports, adjust accordingly. **You need to fill this if you wish to use Ollama's models instead of OpenAI's**.
**Note**: You can change these and use different models after running Perplexica as well from the settings page.
**Note**: You can change these and use different models after running Perplexica as well from the settings page.
- `SERPER`: The Serper API key, if you prefer not to run SearxNG and want faster search speeds, as well as avoiding rate limitations by Google. You can create a free key allowing up to 2,500 queries [here](https://serper.dev/).
- `SIMILARITY_MEASURE`: The similarity measure to use (This is filled by default; you can leave it as is if you are unsure about it.)
5. Ensure you are in the directory containing the `docker-compose.yaml` file and execute: