TySS-Dev/ollama-ai-answers-searxng
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Making the code base easy to read and maintain and making it a oneline install

Browse Source
This commit is contained in:
Tyler
2026-05-17 13:54:54 -04:00
parent 15cfe47181
commit 01f5717b9f
9 changed files with 1489 additions and 828 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+116 -102
View File
@@ -1,32 +1,75 @@
<div align="center">
[![Main Repo](https://img.shields.io/badge/Main%20Repo-gits.tysstech.com-blue?logo=gitea)](https://git.tysstech.com/tyler/PacCrypt-Webapp)
[![Mirror Repo](https://img.shields.io/badge/Mirror%20Repo-github.com-blue?logo=github)](https://github.com/TySP-Dev/ollama-ai-answers-searxng)
# ollama-ai-answers-searxng
<div align="left">
**Local AI search overviews for SearXNG, powered by Ollama.**
# Ollama AI Answers Plugin for SearXNG
**Based on [ai-answers-searxng](https://github.com/cra88y/ai-answers-searxng) by [cra88y](https://github.com/cra88y)**
![Python](https://img.shields.io/badge/python-3.8%2B-blue?logo=python)
![License](https://img.shields.io/badge/license-MIT-green)
![SearXNG](https://img.shields.io/badge/SearXNG-compatible-orange?logo=searxng)
A SearXNG plugin that generates local AI overviews powered by Ollama, using search results as RAG context.
[![Mirror Repo](https://img.shields.io/badge/GitHub-TySP--Dev%2Follama--ai--answers--searxng-blue?logo=github)](https://github.com/TySP-Dev/ollama-ai-answers-searxng)
Features:
- Token-by-token UI streaming
- Clickable inline citations
- Interactive mode: continue summary, ask follow-ups, copy, or regenerate
- Simple response mode with no extras
- Internally called low-latency RAG for follow-ups (bypasses HTTP loopback)
- Native network integration via `searx.network` (respects proxy/SSL settings)
- Stateless conversation persistence/shareability via URL hash
- Model selector in the AI overview widget
- Does not slow down result loading
- One file install
</div>
## Installation
## One-line Install
Place `ollama_answers.py` into the `searx/plugins` directory of your SearXNG instance (or mount it in a container) and enable it in `settings.yml`:
```bash
bash <(curl -fsSL https://raw.githubusercontent.com/TySP-Dev/ollama-ai-answers-searxng/master/install.sh)
```
## Features
- AI Overview box at the top of every search result page
- Powered entirely by your local Ollama instance — no external API calls
- Page content fetching — enriches context beyond SearXNG snippets
- Model selector dropdown — switch models per-search without restarting
- Inline citations with clickable source links
- Citation footer listing all referenced sources
- Follow-up questions with conversation history
- Copy and Regenerate buttons
- Typewriter animation (granian-compatible buffered response)
- Ollama-only — no OpenAI, Gemini, or other provider bloat
## Requirements
- SearXNG installed via Docker Compose
- Ollama running and accessible from the SearXNG container
- Python 3.8+ (for `build.py` and `install.sh`)
- Docker + Docker Compose
## Install
### One-line (recommended)
```bash
bash <(curl -fsSL https://raw.githubusercontent.com/TySP-Dev/ollama-ai-answers-searxng/master/install.sh)
```
The script will clone the repo, build the plugin, detect your SearXNG Docker Compose installation, copy the plugin, update `docker-compose.yml` and `settings.yml`, and optionally restart SearXNG.
### Manual
```bash
git clone https://github.com/TySP-Dev/ollama-ai-answers-searxng
cd ollama-ai-answers-searxng
python3 build.py
bash install.sh
```
Or manually copy the built plugin and update your config:
```yaml
# docker-compose.yml — searxng service
environment:
- LLM_URL=http://ollama:11434/v1/chat/completions
- LLM_MODEL=qwen3.5:9b
volumes:
- ./plugins/ollama_answers.py:/usr/local/searxng/searx/plugins/ollama_answers.py:Z
```
```yaml
# settings.yml
plugins:
searx.plugins.ollama_answers.SXNGPlugin:
active: true
@@ -34,102 +77,73 @@ plugins:
## Configuration
Configure via environment variables.
All configuration is done via environment variables on the SearXNG container.
### Required
| Variable | Description | Default |
| Variable | Default | Description |
|---|---|---|
| `LLM_URL` | Ollama chat completions endpoint | `http://ollama:11434/v1/chat/completions` |
| `LLM_MODEL` | Model name as listed in Ollama | `qwen3.5:9b` |
| `LLM_URL` | `http://ollama:11434/v1/chat/completions` | Ollama endpoint |
| `LLM_MODEL` | `qwen3.5:9b` | Default model |
| `LLM_MAX_TOKENS` | `200` | Max response tokens |
| `LLM_TEMPERATURE` | `0.2` | Response temperature |
| `LLM_TABS` | `general,science,it,news` | Search tabs to show AI overview on |
| `LLM_QUESTION_MARK_REQUIRED` | `false` | Only trigger on queries ending with `?` |
| `LLM_INTERACTIVE` | `true` | Show copy/regenerate/follow-up UI |
| `LLM_SYSTEM_PROMPT` | *(built-in)* | Override the system prompt |
| `LLM_CONTEXT_DEEP_COUNT` | `5` | Results fetched for full page content |
| `LLM_CONTEXT_SHALLOW_COUNT` | `15` | Results used as headline-only context |
### Optional
## Project Structure
| Variable | Description | Default |
|---|---|---|
| `LLM_SYSTEM_PROMPT` | Overrides the default system prompt | `You are a direct, citation-accurate search synthesis engine.` |
| `LLM_MAX_TOKENS` | Max tokens in the AI response | `200` |
| `LLM_TEMPERATURE` | Sampling temperature | `0.2` |
| `LLM_CONTEXT_DEEP_COUNT` | Results used with full snippets | `5` |
| `LLM_CONTEXT_SHALLOW_COUNT` | Results with headlines only (breadth) | `15` |
| `LLM_TABS` | Comma-delimited tab whitelist | `general,science,it,news` |
| `LLM_INTERACTIVE` | Interactive UI mode (copy, regenerate, follow-up) | `true` |
| `LLM_QUESTION_MARK_REQUIRED` | Only trigger on queries containing `?` | `false` |
## How It Works
1. User performs a search
2. Results return server-side
3. `post_search` plugin hook fires
4. Token-optimized context is extracted from results
5. UI/logic shell injected into the standard answers object
6. Client-side script calls a signed endpoint (`/ai-stream`)
7. Ollama streams a response token-by-token in the UI
## Docker Compose Example
```yaml
services:
searxng:
environment:
- LLM_URL=http://ollama:11434/v1/chat/completions
- LLM_MODEL=qwen3.5:9b
volumes:
- ./ollama_answers.py:/usr/local/searxng/searx/plugins/ollama_answers.py
ollama:
image: ollama/ollama
volumes:
- ollama_data:/root/.ollama
volumes:
ollama_data:
```
ollama-ai-answers-searxng/
├── ollama_answers.py # Source plugin — reads UI from assets/
├── build.py # Assembles dist/ollama_answers.py (self-contained)
├── install.sh # Full automated Docker Compose installer
├── assets/
│ ├── ui.css # Interactive widget styles
│ ├── ui.html # Interactive widget HTML (copy/regen/follow-up bar)
│ └── ui.js # Frontend JS (typewriter, citations, streaming)
├── dist/ # Output of build.py — gitignored
│ └── ollama_answers.py # Self-contained, ready to deploy
├── dev/
│ └── dev.py # Local Flask dev server (no SearXNG required)
└── README.md
```
## Remote Ollama
If your Ollama instance is remote or behind a reverse proxy, set `LLM_URL` to the full endpoint and provide an API key if required. The plugin supports Bearer token auth and follows HTTP redirects.
```yaml
environment:
- LLM_URL=https://ollama.example.com/v1/chat/completions
- LLM_API_KEY=your-bearer-token
```
## Development — Dev Server
A standalone Flask dev server is included in `tests/dev.py`. It mocks the SearXNG plugin environment so you can test the full UI without a running SearXNG instance.
### Setup
## Development
```bash
pip install flask flask-babel certifi
# Edit source files
vim ollama_answers.py
vim assets/ui.css
# Build dist file for deployment
python3 build.py
# Deploy to server
cp dist/ollama_answers.py ~/searxng/plugins/ollama_answers.py
cd ~/searxng && docker compose up -d --force-recreate core
# Run local dev server
PYTHONPATH=. python3 dev/dev.py
```
### Run
```bash
python tests/dev.py
```
Then open [http://127.0.0.1:5000/](http://127.0.0.1:5000/) in your browser.
The dev server mocks the SearXNG plugin environment so you can test the full UI without a running SearXNG instance. Open [http://127.0.0.1:5000/](http://127.0.0.1:5000/) after starting it.
> **Note:** Use `127.0.0.1:5000`, not `localhost:5000` — macOS AirPlay Receiver can occupy the IPv6 loopback on port 5000.
### Usage
## How It Works
- Type a query in the search bar and hit **Search** to trigger an AI overview.
- Expand **Ollama Configuration** at the top to change the endpoint URL or Bearer token for the current session. Click **Apply** to save and re-run the current query.
- The model selector in the AI overview widget (loaded from `/ai-models`) shows all models available on the configured Ollama server and persists your choice in the session URL.
1. User searches on SearXNG
2. `post_search` hook fires after results are fetched
3. Top result URLs are fetched in parallel for full page content
4. Context is assembled from page content + snippets + infoboxes
5. A signed token is generated and injected into the page
6. The browser POSTs to `/ai-stream` with the token and context
7. The server calls Ollama with the enriched context
8. The response is returned as JSON and animated with a typewriter effect
9. Citations are rendered inline and collected in a footer
### Environment Variables (dev)
## License
The dev reads the same variables as the plugin:
```bash
LLM_URL=http://localhost:11434/v1/chat/completions \
LLM_MODEL=qwen3.5:9b \
python tests/dev.py
```
Or export them before running. Any values set in the config panel at runtime take priority for that session.
MIT License