remi/Perplexica
1
0
Fork 0
mirror of https://github.com/ItzCrazyKns/Perplexica.git synced 2025-10-22 15:28:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(app): update documentation

Browse Source
This commit is contained in:
ItzCrazyKns
2025-10-21 13:44:07 +05:30
parent 77672003ff
commit 3d950bac07
3 changed files with 173 additions and 60 deletions
Download Patch File Download Diff File Expand all files Collapse all files

83
README.md
View File

@@ -76,6 +76,34 @@ There are mainly 2 ways of installing Perplexica - With Docker, Without Docker.
### Getting Started with Docker (Recommended)
Perplexica can be easily run using Docker. Simply run the following command:
```bash
docker run -p 3000:3000 -p 8080:8080 --name perplexica itzcrazykns1337/perplexica:latest
```
This will pull and start the Perplexica container with the bundled SearxNG search engine. Once running, open your browser and navigate to http://localhost:3000. You can then configure your settings (API keys, models, etc.) directly in the setup screen.
**Note**: The image includes both Perplexica and SearxNG, so no additional setup is required.
#### Using Perplexica with Your Own SearxNG Instance
If you already have SearxNG running, you can use the standalone version of Perplexica:
```bash
docker run -p 3000:3000 -e SEARXNG_API_URL=http://your-searxng-url:8080 --name perplexica itzcrazykns1337/perplexica:standalone-latest
```
**Important**: Make sure your SearxNG instance has:
- JSON format enabled in the settings
- Wolfram Alpha search engine enabled
Replace `http://your-searxng-url:8080` with your actual SearxNG URL. Then configure your AI provider settings in the setup screen at http://localhost:3000.
#### Advanced Setup (Building from Source)
If you prefer to build from source or need more control:
1. Ensure Docker is installed and running on your system.
2. Clone the Perplexica repository:
@@ -85,39 +113,46 @@ There are mainly 2 ways of installing Perplexica - With Docker, Without Docker.
3. After cloning, navigate to the directory containing the project files.
4. Rename the `sample.config.toml` file to `config.toml`. For Docker setups, you need only fill in the following fields:
- `OPENAI`: Your OpenAI API key. **You only need to fill this if you wish to use OpenAI's models**.
- `CUSTOM_OPENAI`: Your OpenAI-API-compliant local server URL, model name, and API key. You should run your local server with host set to `0.0.0.0`, take note of which port number it is running on, and then use that port number to set `API_URL = http://host.docker.internal:PORT_NUMBER`. You must specify the model name, such as `MODEL_NAME = "unsloth/DeepSeek-R1-0528-Qwen3-8B-GGUF:Q4_K_XL"`. Finally, set `API_KEY` to the appropriate value. If you have not defined an API key, just put anything you want in-between the quotation marks: `API_KEY = "whatever-you-want-but-not-blank"` **You only need to configure these settings if you want to use a local OpenAI-compliant server, such as Llama.cpp's [`llama-server`](https://github.com/ggml-org/llama.cpp/blob/master/tools/server/README.md)**.
- `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**.
- `LEMONADE`: Your Lemonade API URL. Since Lemonade runs directly on your local machine (not in Docker), you should enter it as `http://host.docker.internal:PORT_NUMBER`. If you installed Lemonade on port 8000, use `http://host.docker.internal:8000`. For other ports, adjust accordingly. **You need to fill this if you wish to use Lemonade's models**.
- `GROQ`: Your Groq API key. **You only need to fill this if you wish to use Groq's hosted models**.`
- `ANTHROPIC`: Your Anthropic API key. **You only need to fill this if you wish to use Anthropic models**.
- `Gemini`: Your Gemini API key. **You only need to fill this if you wish to use Google's models**.
- `DEEPSEEK`: Your Deepseek API key. **Only needed if you want Deepseek models.**
- `AIMLAPI`: Your AI/ML API key. **Only needed if you want to use AI/ML API models and embeddings.**
**Note**: You can change these after starting Perplexica from the settings dialog.
- `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:
4. Build and run using Docker:
```bash
docker compose up -d
docker build -t perplexica .
docker run -p 3000:3000 -p 8080:8080 --name perplexica perplexica
```
6. Wait a few minutes for the setup to complete. You can access Perplexica at http://localhost:3000 in your web browser.
5. Access Perplexica at http://localhost:3000 and configure your settings in the setup screen.
**Note**: After the containers are built, you can start Perplexica directly from Docker without having to open a terminal.
### Non-Docker Installation
1. Install SearXNG and allow `JSON` format in the SearXNG settings.
2. Clone the repository and rename the `sample.config.toml` file to `config.toml` in the root directory. Ensure you complete all required fields in this file.
3. After populating the configuration run `npm i`.
4. Install the dependencies and then execute `npm run build`.
5. Finally, start the app by running `npm run start`
1. Install SearXNG and allow `JSON` format in the SearXNG settings. Make sure Wolfram Alpha search engine is also enabled.
2. Clone the repository:
```bash
git clone https://github.com/ItzCrazyKns/Perplexica.git
cd Perplexica
```
3. Install dependencies:
```bash
npm i
```
4. Build the application:
```bash
npm run build
```
5. Start the application:
```bash
npm run start
```
6. Open your browser and navigate to http://localhost:3000 to complete the setup and configure your settings (API keys, models, SearxNG URL, etc.) in the setup screen.
**Note**: Using Docker is recommended as it simplifies the setup process, especially for managing environment variables and dependencies.