Fixing typos

Reviewed-on: #4

.gitignore

@@ -3,7 +3,7 @@ __pycache__/
 *$py.class
 venv/
 .env
+dev/.env
 .idea/
 .vscode/
 .agent/
-dist/

README.md

@@ -1,83 +1,81 @@
 <div align="center">
 
-# ollama-ai-answers-searxng
+[![Main Repo](https://img.shields.io/badge/Main%20Repo-git.tysstech.com-blue?logo=gitea)](https://git.tysstech.com/TySS-Dev/ollama-ai-answers-searxng)
-
+[![Mirror Repo](https://img.shields.io/badge/Mirror%20Repo-github.com-blue?logo=github)](https://github.com/TySP-Dev/ollama-ai-answers-searxng)
-**Local AI search overviews for SearXNG, powered by Ollama.**
-
-![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)
-
-[![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)
 
 </div>
 
-## One-line Install
+# Ollama AI Answers Plugin for SearXNG
+**Based on [ai-answers-searxng](https://github.com/cra88y/ai-answers-searxng) by [cra88y](https://github.com/cra88y)**
 
-```bash
+A SearXNG plugin that generates local AI overviews powered by Ollama, using search results as RAG context.
-bash <(curl -fsSL https://raw.githubusercontent.com/TySP-Dev/ollama-ai-answers-searxng/master/install.sh)
-```
 
-## Features
+## Features:
 
-- AI Overview box at the top of every search result page
+- Inline numbered citations
-- Powered entirely by your local Ollama instance — no external API calls
+- Interactive mode - Continue summary, ask follow-ups, copy, or regenerate
-- Page content fetching — enriches context beyond SearXNG snippets
+- Overview of ranked results with prompts based on detected query intent:
-- Model selector dropdown — switch models per-search without restarting
+  - `How To` `Technical` `Factual` `Comparison` `Opinion` `Current` `Local` `Geneal`
-- Inline citations with clickable source links
+- Internally called RAG for follow-ups
-- Citation footer listing all referenced sources
+- Native network integration via `searx.network`
-- Follow-up questions with conversation history
+- Stateless conversation presistence/shareability via URL hash
-- Copy and Regenerate buttons
+- Ollama model selector
-- Typewriter animation (granian-compatible buffered response)
+- Feeds fetched results to Ollama without slowing down SearXNG  results
-- Ollama-only — no OpenAI, Gemini, or other provider bloat
+- Real-time streaming via Valkey (No waiting for a completed response)
-
+- TF-IDF result ranking before being sent to Ollama
-## Requirements
+- Smart chunking - Pages are split into 512-token segments and highest-scoring chunk per page used for context
-
+- Conversation memory - 30-minute cross-search conversation history via Valkey for follow-up questions
-- SearXNG installed via Docker Compose
+- Markdown support
-- Ollama running and accessible from the SearXNG container
+- Intent emoji badge showing what intent prompt was used 
-- Python 3.8+ (for `build.py` and `install.sh`)
-- Docker + Docker Compose
 
 ## Install
 
-### One-line (recommended)
+1. Download the plugin:
 
-```bash
+   ### Main repo (Gitea)
-bash <(curl -fsSL https://raw.githubusercontent.com/TySP-Dev/ollama-ai-answers-searxng/master/install.sh)
+   ```bash
-```
+   curl -o ollama_answers.py https://git.tysstech.com/TySS-Dev/ollama-ai-answers-searxng/raw/branch/main/ollama_answers.py
+   ```
 
-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.
+   ### Mirror repo (Github):
+   ```bash
+   curl -o ollama_answers.py https://raw.githubusercontent.com/TySP-Dev/ollama-ai-answers-searxng/main/ollama_answers.py
+   ```
 
-### Manual
+3. Copy to your SearXNG plugins directory:
+   ```bash
+   cp ollama_answers.py path_to/searxng/plugins/ollama_answers.py
+   ```
 
-```bash
+4. Add the volume mount to your `docker-compose.yml` under the searxng service:
-git clone https://github.com/TySP-Dev/ollama-ai-answers-searxng
+   ```yaml
-cd ollama-ai-answers-searxng
+   volumes:
-python3 build.py
+     - ./plugins/ollama_answers.py:/usr/local/searxng/searx/plugins/ollama_answers.py:Z
-bash install.sh
+   ```
-```
 
-Or manually copy the built plugin and update your config:
+5. Add environment variables to `docker-compose.yml`:
-
+   ```yaml
-```yaml
+   environment:
-# docker-compose.yml — searxng service
-environment:
      - LLM_URL=http://ollama:11434/v1/chat/completions
      - LLM_MODEL=qwen3.5:9b
-volumes:
+     - VALKEY_HOST=searxng-valkey
-  - ./plugins/ollama_answers.py:/usr/local/searxng/searx/plugins/ollama_answers.py:Z
+   ```
-```
 
-```yaml
+6. Add to `settings.yml` plugins section:
-# settings.yml
+   ```yaml
-plugins:
+   plugins:
      searx.plugins.ollama_answers.SXNGPlugin:
        active: true
-```
+   ```
+
+7. Restart SearXNG:
+   ```bash
+   docker compose up -d --force-recreate core
+   ```
 
 ## Configuration
 
-All configuration is done via environment variables on the SearXNG container.
+Configure via environment variables.
 
 | Variable | Default | Description |
 |---|---|---|
@@ -85,65 +83,187 @@ All configuration is done via environment variables on the SearXNG container.
 | `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_TABS` | `general,science,it,news` | Tabs to show AI overview on |
-| `LLM_QUESTION_MARK_REQUIRED` | `false` | Only trigger on queries ending with `?` |
+| `LLM_QUESTION_MARK_REQUIRED` | `false` | Only trigger on queries with `?` |
-| `LLM_INTERACTIVE` | `true` | Show copy/regenerate/follow-up UI |
+| `LLM_INTERACTIVE` | `true` | Show copy/regen/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_DEEP_COUNT` | `5` | Full-content results to fetch |
-| `LLM_CONTEXT_SHALLOW_COUNT` | `15` | Results used as headline-only context |
+| `LLM_CONTEXT_SHALLOW_COUNT` | `15` | Headline-only results |
+| `VALKEY_HOST` | `searxng-valkey` | Valkey container hostname |
+| `VALKEY_PORT` | `6379` | Valkey port |
+
+## 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
+
+## Known Issues
+
+- [ ] Update README with all updates
+
+- [x] When asking a follow up question the previous output disappears
+
+- [x] Parts of the UI are not theme aware resulting in a unpolished look when not using a dark theme
+
+- [x] When SearXNG provides a info blob for a search it appears on top of the overview i.e. `Wikipedia` or `Linux` 
+
+For any issues not stated here please create an issue ticket on [Gitea](https://git.tysstech.com/TySS-Dev/ollama-ai-answers-searxng/issues) or [GitHub](https://github.com/TySP-Dev/ollama-ai-answers-searxng/issues) and add the `bug` tag.
+
+## Roadmap
+
+### Dev Server
+
+- [x] Stream viewer — show tokens arriving in real time in the debug panel as they come out of Valkey, so you can see exactly what the LLM is generating chunk by chunk
+
+- [x] TF-IDF score visualizer — show a table of which URLs were fetched, their scores, and which chunks were selected for context
+
+- [ ] Intent detection display — show what intent was detected and which system prompt was used for each query
+
+- [ ] Saved queries — save/load test queries so you can quickly re-run the same set of searches after making changes to the plugin
+
+- [ ] A/B model comparison — run the same query against two different models simultaneously and show both responses side by side
+
+- [ ] Response time breakdown — show how long each phase took: SearXNG fetch, page fetching, TF-IDF scoring, LLM stream start, stream complete
+
+- [ ] Context inspector — show the full assembled context string that gets sent to the LLM, so you can see exactly what it's working with
+
+- [ ] Prompt viewer — show the full system prompt + user prompt that gets sent to Ollama
+
+- [ ] Export button — copy the full context + prompt + response as a JSON blob for bug reports
+
+- [ ] Per-intent system prompt editor — edit the system prompts for each intent type live without restarting
+
+- [ ] Token counter — show estimated token count of the context being sent
+
+### Plugin
+
+- [ ] Working on feature plans
+
+## Architecture
+
+```
+┌─────────────────────────────────────────────────────┐
+│                   Browser                           │
+│  POST /ai-stream → GET /ai-status/{id} (poll 150ms) │
+└────────────────┬────────────────────────────────────┘
+                 │
+┌────────────────▼────────────────────────────────────┐
+│              SearXNG + Plugin                       │
+│                                                     │
+│  post_search()                                      │
+│    → _enrich_results()  ← ThreadPoolExecutor        │
+│      → _fetch_page_text() × 5 parallel              │
+│      → _chunk_text() + _tfidf_score()               │
+│      → rerank by score                              │
+│    → _assemble_context()                            │
+│    → inject AI Overview HTML + JS                   │
+│                                                     │
+│  /ai-stream                                         │
+│    → validate token                                 │
+│    → _detect_intent() → select system prompt        │
+│    → _load_conversation() from Valkey               │
+│    → launch stream_to_valkey() thread               │
+│    → return {job_id} immediately                    │
+│                                                     │
+│  stream_to_valkey() [background thread]             │
+│    → Ollama stream=True                             │
+│    → RPUSH tokens to Valkey                         │
+│    → RPUSH __DONE__ when complete                   │
+│                                                     │
+│  /ai-status/{job_id}                                │
+│    → LRANGE chunks from offset                      │
+│    → return {chunks, done}                          │
+└────────────────┬────────────────────────────────────┘
+                 │
+┌────────────────▼────────────────────────────────────┐
+│                  Valkey                             │
+│  ai:job:{id}:chunks  (list, TTL 120s)               │
+│  ai:job:{id}:status  (string, TTL 120s)             │
+│  ai:conv:{session}   (JSON, TTL 1800s)              │
+└─────────────────────────────────────────────────────┘
+```
+
+## Docker Compose Example
+
+```yaml
+services:
+  searxng:
+    environment:
+      - LLM_URL=http://ollama:11434/v1/chat/completions
+      - LLM_MODEL=qwen3.5:9b
+      - VALKEY_HOST=searxng-valkey
+    volumes:
+      - ./ollama_answers.py:/usr/local/searxng/searx/plugins/ollama_answers.py
+
+  ollama:
+    image: ollama/ollama
+    volumes:
+      - ollama_data:/root/.ollama
+
+volumes:
+  ollama_data:
+```
+
+## 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
+```
 
 ## Project Structure
 
 ```
 ollama-ai-answers-searxng/
-├── ollama_answers.py      # Source plugin — reads UI from assets/
+├── ollama_answers.py      # single plugin file — all logic here
-├── build.py               # Assembles dist/ollama_answers.py (self-contained)
+├── README.md
-├── install.sh             # Full automated Docker Compose installer
+├── requirements.txt       # flask, flask-babel (for local dev only)
-├── assets/
+└── tests/
-│   ├── ui.css             # Interactive widget styles
+    └── dev.py             # local dev server
-│   ├── 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
 ```
 
-## Development
+## 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
 
 ```bash
-# Edit source files
+pip install flask flask-babel certifi
-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
 ```
 
-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.
+### Run
+
+```bash
+python tests/dev.py
+```
+
+Then open [http://127.0.0.1:5000/](http://127.0.0.1:5000/) in your browser.
 
 > **Note:** Use `127.0.0.1:5000`, not `localhost:5000` — macOS AirPlay Receiver can occupy the IPv6 loopback on port 5000.
 
-## How It Works
+### Usage
 
-1. User searches on SearXNG
+- Type a query in the search bar and hit **Search** to trigger an AI overview.
-2. `post_search` hook fires after results are fetched
+- 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.
-3. Top result URLs are fetched in parallel for full page content
+- 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.
-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
 
-## License
+### Environment Variables (dev)
 
-MIT License
+The dev server 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.

assets/ui.css

@@ -1,134 +0,0 @@
-@keyframes sxng-fade-in-up {
-    0% { opacity: 0; transform: translateY(10px); }
-    100% { opacity: 1; transform: translateY(0); }
-}
-.sxng-footer {
-    display: flex;
-    align-items: center;
-    gap: 0.5rem;
-    margin-top: 1rem;
-    opacity: 0;
-    animation: sxng-fade-in-up 0.5s ease-out forwards;
-}
-.sxng-btn {
-    display: inline-flex;
-    align-items: center;
-    justify-content: center;
-    width: 32px;
-    height: 32px;
-    padding: 0;
-    border: none;
-    border-radius: 4px;
-    background: var(--color-sidebar-bg, #424247);
-    color: var(--color-search-url, #bbb);
-    cursor: pointer;
-    vertical-align: middle;
-    line-height: 1.4;
-}
-.sxng-btn:hover {
-    background: var(--color-search-url, #303033);
-    color: var(--color-sidebar-bg, #bbb);
-}
-.sxng-btn svg { width: 18px; height: 18px; fill: currentColor; }
-.sxng-input-wrapper {
-    flex-grow: 1;
-    display: flex;
-    height: 32px;
-    align-items: center;
-    margin: 0 0.5rem;
-    position: relative;
-}
-.sxng-input {
-    width: 100%;
-    height: -webkit-fill-available;
-    background: var(--color-sidebar-bg, #424247);
-    border: none;
-    color: var(--color-base-font, #cdd6f4);
-    font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, Helvetica, Arial, sans-serif;
-    font-size: 0.78em;
-    padding: 3px 8px;
-    border-radius: 4px;
-    line-height: 1.4;
-    vertical-align: middle;
-}
-.sxng-input:focus { outline: none; }
-.sxng-input::placeholder { color: var(--color-base-font, #333); opacity: 0.35; }
-.sxng-input-line {
-    position: absolute;
-    bottom: 0;
-    left: 0;
-    width: 0;
-    height: 1px;
-    background: var(--color-result-link, #5e81ac);
-    transition: width 0.3s ease;
-}
-.sxng-input:focus + .sxng-input-line { width: 100%; }
-.sxng-user-msg {
-    display: block;
-    width: fit-content;
-    max-width: 80%;
-    margin: 0.75rem 0 0.75rem auto;
-    padding: 0.25rem 0.6rem 0.25rem 0;
-    border-right: 2px solid var(--color-result-link, #5e81ac);
-    text-align: right;
-    font-size: 0.85rem;
-    line-height: 1.4;
-    opacity: 0.55;
-    animation: sxng-fade-in-up 0.3s ease-out forwards;
-}
-.sxng-input-wrapper:focus-within { 
-    opacity: 1; 
-    color: var(--color-result-link, #5e81ac); 
-    background: var(--color-base-background-hover, rgba(0,0,0,0.05)) !important;
-}
-.sxng-model-select {
-    appearance: none;
-    -webkit-appearance: none;
-    background: url("data:image/svg+xml;charset=UTF-8,%3C%3Fxml%20version%3D%221.0%22%20encoding%3D%22UTF-8%22%3F%3E%0A%3Csvg%20xmlns%3D%22http%3A%2F%2Fwww.w3.org%2F2000%2Fsvg%22%20viewBox%3D%220%200%20512%20512%22%3E%0A%3Cg%20fill%3D%22%23aaa%22%3E%0A%3Cpolygon%20points%3D%22128%2C192%20256%2C320%20384%2C192%22%2F%3E%3C%2Fg%3E%0A%3C%2Fsvg%3E") calc(100% + 2rem) / 1rem no-repeat content-box border-box;
-    background-color: #424247;
-    text-overflow: ellipsis;
-    border-width: 0 2rem 0 0;
-    border-color: transparent;
-    border-radius: 5px;
-    outline: none;
-    height: 32px;
-    color: var(--color-search-url, #bbb);
-    font-size: .9rem;
-    padding: 1px 10px 1px 10px !important;
-    margin: 0;
-    cursor: pointer;
-    display: none;
-    max-width: 8rem;
-    vertical-align: middle;
-}
-.sxng-model-select:hover {
-    background-color: #303033;
-    color: var(--color-search-url, #bbb);
-}
-.sxng-reasoning {
-    margin: 0.5rem 0; padding: 0.5rem;
-    border-left: 2px solid var(--color-result-link, #5e81ac);
-    background: var(--color-base-background-hover, rgba(0,0,0,0.03));
-    font-size: 0.85rem; opacity: 0.7; transition: opacity 0.2s;
-}
-.sxng-reasoning:hover { opacity: 1; }
-.sxng-reasoning summary { cursor: pointer; font-weight: bold; color: var(--color-result-link, #5e81ac); }
-.sxng-thought-content { margin-top: 0.5rem; white-space: pre-wrap; font-family: monospace; }
-.sxng-citation-footer {
-    margin-top: 0.75rem;
-    padding-top: 0.5rem;
-    border-top: 1px solid var(--color-sidebar-bg, #424247);
-    display: flex;
-    flex-wrap: wrap;
-    gap: 0.4rem 0.75rem;
-}
-.sxng-citation-item a {
-    font-size: 0.75em;
-    color: var(--color-result-link, #5e81ac);
-    text-decoration: none;
-    opacity: 0.75;
-}
-.sxng-citation-item a:hover {
-    opacity: 1;
-    text-decoration: underline;
-}

assets/ui.html

@@ -1,13 +0,0 @@
-<div id="sxng-footer" class="sxng-footer" style="display:none;">
-    <button class="sxng-btn" id="btn-copy" title="Copy to clipboard">
-        <svg viewBox="0 0 24 24"><path d="M16 1H4C2.9 1 2 1.9 2 3V17H4V3H16V1M19 5H8C6.9 5 6 5.9 6 7V21C6 22.1 6.9 23 8 23H19C20.1 23 21 22.1 21 21V7C21 5.9 20.1 5 19 5M19 21H8V7H19V21Z"/></svg>
-    </button>
-    <button class="sxng-btn" id="btn-regen" title="Regenerate answer">
-        <svg viewBox="0 0 24 24"><path d="M17.65 6.35C16.2 4.9 14.21 4 12 4C7.58 4 4.01 7.58 4.01 12C4.01 16.42 7.58 20 12 20C15.73 20 18.84 17.45 19.73 14H17.65C16.83 16.33 14.61 18 12 18C8.69 18 6 15.31 6 12C6 8.69 8.69 6 12 6C13.66 6 15.14 6.69 16.22 7.78L13 11H20V4L17.65 6.35Z"/></svg>
-    </button>
-    <form id="sxng-action-form" class="sxng-input-wrapper" onsubmit="event.preventDefault();">
-        <input type="text" id="sxng-action-input" class="sxng-input" placeholder="Ask..." aria-label="Ask follow-up" autocomplete="off">
-        <div class="sxng-input-line"></div>
-        </button>
-    </form>
-</div>

assets/ui.js

@@ -1,566 +0,0 @@
-// === FRONTEND_JS_TEMPLATE ===
-(async () => {
-    const is_interactive = __IS_INTERACTIVE__;
-    const q_init = __JS_Q__;
-    const lang_init = __JS_LANG__;
-    let urls = __JS_URLS__;
-    const b64_init = __B64_CONTEXT__;
-    const tk_init = __TK__;
-    const script_root = __SCRIPT_ROOT__;
-    const model_init = __MODEL_INIT__;
-    const conversation = {
-        originalQuery: q_init,
-        originalContext: new TextDecoder().decode(Uint8Array.from(atob(b64_init), c => c.charCodeAt(0))),
-        originalSources: [...urls],
-        turns: [{role: 'user', content: q_init, ts: Date.now()}]
-    };
-    const box = document.getElementById('sxng-stream-box');
-    const data = document.getElementById('sxng-stream-data');
-    const wrapper = box.closest('.answer');
-    if (wrapper) wrapper.style.display = 'none';
-    let restored = false;
-    let isStreaming = false;
-    
-    __CITATION_HELPER_JS__
-
-    __INTERACTIVE_JS_INIT__
-
-    function synthesizeQuery(original, followup) {
-        const cleanOrig = original.replace(/^(what|how|why|when|where|who|which|is|are|can|does|do)(\s+(is|are|do|does|can|to|a|an|the))?\s+/i, '');
-        const origWords = cleanOrig.split(' ').slice(0, 12);
-        return `${origWords.join(' ')} ${followup}`.trim();
-    }
-
-    __STREAM_FN_SIG__ {
-        if (isStreaming) {
-            console.warn('[AI Answers] Stream already in progress, ignoring duplicate call');
-            return;
-        }
-        
-        isStreaming = true;
-        try {
-            const ctx = auxContext || conversation.originalContext;
-            if (wrapper) wrapper.style.display = '';
-            box.style.display = 'block';
-
-            const controller = new AbortController();
-            let timeoutId = setTimeout(() => controller.abort(), 60000);
-            const finalQ = __STREAM_Q__;
-            
-            const _selMdl = (document.getElementById('sxng-model-select') || {value: ''}).value;
-            const bodyObj = { q: finalQ, lang: lang_init, context: ctx, tk: tk_init, model: _selMdl__STREAM_BODY__ };
-            const res = await fetch(script_root + '/ai-stream', {
-                method: 'POST',
-                headers: { 'Content-Type': 'application/json' },
-                body: JSON.stringify(bodyObj),
-                signal: controller.signal
-            });
-
-            clearTimeout(timeoutId);
-            if (!res.ok) {
-                const errSpan = document.createElement('span');
-                errSpan.style.color = '#bf616a';
-                errSpan.textContent = "Error: " + res.statusText;
-                data.appendChild(errSpan);
-                return;
-            }
-
-            const respJson = await res.json();
-
-            if (respJson.error) {
-                const cursorErr = data.querySelector('.sxng-cursor');
-                if (cursorErr) cursorErr.remove();
-                const errSpan = document.createElement('span');
-                errSpan.style.color = '#bf616a';
-                errSpan.textContent = "⚠️ " + respJson.error;
-                data.appendChild(errSpan);
-                return;
-            }
-
-            const fullText = (respJson.text || '').trim();
-
-            if (!fullText) {
-                const cursorErr = data.querySelector('.sxng-cursor');
-                if (cursorErr) cursorErr.remove();
-                const errSpan = document.createElement('span');
-                errSpan.style.color = '#bf616a';
-                errSpan.textContent = 'No response received. Check API configuration and server logs.';
-                data.appendChild(errSpan);
-                return;
-            }
-
-            let mainText = fullText;
-            const thinkMatch = mainText.match(/^<think>([\s\S]*?)<\/think>\s*/);
-            if (thinkMatch) {
-                const cursorTh = data.querySelector('.sxng-cursor');
-                const details = document.createElement('details');
-                details.className = 'sxng-reasoning';
-                details.innerHTML = '<summary>Thought Process</summary>';
-                const thoughtDiv = document.createElement('div');
-                thoughtDiv.className = 'sxng-thought-content';
-                thoughtDiv.textContent = thinkMatch[1];
-                details.appendChild(thoughtDiv);
-                if (cursorTh) cursorTh.before(details);
-                else data.appendChild(details);
-                mainText = mainText.substring(thinkMatch[0].length);
-            }
-
-            let cursor = data.querySelector('.sxng-cursor');
-            if (!cursor) {
-                cursor = document.createElement('span');
-                cursor.className = 'sxng-cursor';
-                data.appendChild(cursor);
-            }
-
-            let buffer = '';
-            const flushBuffer = (force = false) => {
-                if (!buffer) return;
-                
-                if (force) {
-                    const fragment = renderCitations(buffer, urls);
-                    if (cursor) cursor.before(fragment);
-                    else data.appendChild(fragment);
-                    buffer = '';
-                    return;
-                }
-
-                while (true) {
-                    const match = buffer.match(/(\[\d+(?:,\s*\d+)*\])/);
-                    
-                    if (!match) break;
-                    
-                    const preText = buffer.substring(0, match.index);
-                    if (preText) {
-                        const s = document.createElement('span');
-                        s.className = 'sxng-chunk';
-                        s.textContent = preText;
-                        cursor.before(s);
-                    }
-
-                    const citationText = match[0];
-                    const fragment = renderCitations(citationText, urls);
-                    cursor.before(fragment);
-
-                    buffer = buffer.substring(match.index + match[0].length);
-                }
-
-                const openIdx = buffer.lastIndexOf('[');
-                if (openIdx === -1) {
-                    if (buffer) {
-                        const s = document.createElement('span');
-                        s.className = 'sxng-chunk';
-                        s.textContent = buffer;
-                        cursor.before(s);
-                        buffer = '';
-                    }
-                } else {
-                    const safeChunk = buffer.substring(0, openIdx);
-                    if (safeChunk) {
-                        const s = document.createElement('span');
-                        s.className = 'sxng-chunk';
-                        s.textContent = safeChunk;
-                        cursor.before(s);
-                    }
-                    buffer = buffer.substring(openIdx);
-                    
-                    if (buffer.length > 50) {
-                        const s = document.createElement('span');
-                        s.className = 'sxng-chunk';
-                        s.textContent = buffer[0];
-                        cursor.before(s);
-                        buffer = buffer.substring(1);
-                    }
-                }
-            };
-
-            let twPos = 0;
-            const twBatch = 4;
-            await new Promise(resolve => {
-                function twTick() {
-                    if (twPos >= mainText.length) {
-                        flushBuffer(true);
-                        resolve();
-                        return;
-                    }
-                    const end = Math.min(twPos + twBatch, mainText.length);
-                    buffer += mainText.substring(twPos, end);
-                    twPos = end;
-                    flushBuffer(false);
-                    setTimeout(twTick, 8);
-                }
-                twTick();
-            });
-
-            if (cursor) cursor.remove();
-
-            let last = data.lastChild;
-            while (last) {
-                if (last.textContent && last.textContent.trim().length === 0) {
-                    const prev = last.previousSibling;
-                    last.remove();
-                    last = prev;
-                } else {
-                    if (last.textContent) last.textContent = last.textContent.trimEnd();
-                    break;
-                }
-            }
-
-            renderCitationFooter(mainText, urls, data);
-
-            const collectedResponse = mainText;
-
-            __INTERACTIVE_JS_COMPLETE__
-
-            if (collectedResponse) {
-                conversation.turns.push({role: 'assistant', content: collectedResponse.trim(), ts: Date.now()});
-            }
-            
-            // Save state if this was an initial generation or a regeneration
-            if (arguments.length === 0 && typeof updateState === 'function') {
-                updateState();
-            }
-
-        } catch (e) {
-            console.error('[AI Answers] Fatal stream exception:', e);
-            const errSpan = document.createElement('span');
-            errSpan.style.cssText = 'color: #bf616a; font-weight: bold; display: block; margin-top: 0.5rem;';
-            
-            if (e.name === 'AbortError') {
-                errSpan.textContent = "⚠️ Connection to AI provider timed out.";
-            } else {
-                errSpan.textContent = "⚠️ AI Widget encountered a fatal error. Check browser console.";
-            }
-            
-            if (data) {
-                const cursor = data.querySelector('.sxng-cursor');
-                if (cursor) cursor.remove();
-                data.appendChild(errSpan);
-            }
-        } finally {
-            isStreaming = false;
-        }
-    }
-
-    if (!restored) startStream();
-})();
-// === CITATION_HELPER_JS ===
-function renderCitations(text, urls) {
-    const fragment = document.createDocumentFragment();
-    const re = /\[(\d{1,2}(?:\s*,\s*\d{1,2})*)\]/g;
-    let lastIdx = 0;
-    const matches = [...text.matchAll(re)];
-
-    matches.forEach(match => {
-        if (match.index > lastIdx) {
-            const s = document.createElement('span');
-            s.className = 'sxng-chunk';
-            s.textContent = text.substring(lastIdx, match.index);
-            fragment.appendChild(s);
-        }
-        match[1].split(/\s*,\s*/).forEach(n => {
-            const idx = parseInt(n.trim());
-            if (idx >= 1 && idx <= urls.length) {
-                const url = urls[idx-1];
-                if (url) {
-                    const a = document.createElement('a');
-                    a.href = url;
-                    a.target = '_blank';
-                    a.style.cssText = 'text-decoration:none;color:var(--color-result-link);font-weight:bold;';
-                    a.textContent = `[${n.trim()}]`;
-                    a.className = 'sxng-chunk';
-                    fragment.appendChild(a);
-                } else {
-                    const s = document.createElement('span');
-                    s.className = 'sxng-chunk';
-                    s.textContent = `[${n.trim()}]`;
-                    fragment.appendChild(s);
-                }
-            } else {
-                const s = document.createElement('span');
-                s.className = 'sxng-chunk';
-                s.textContent = `[${n.trim()}]`;
-                fragment.appendChild(s);
-            }
-        });
-        lastIdx = match.index + match[0].length;
-    });
-
-    if (lastIdx < text.length) {
-        const s = document.createElement('span');
-        s.className = 'sxng-chunk';
-        // Preserve whitespace by not trimming
-        s.textContent = text.substring(lastIdx);
-        fragment.appendChild(s);
-    }
-    return fragment;
-}
-
-function renderCitationFooter(textContent, urls, container) {
-    const re = /\[(\d{1,2}(?:\s*,\s*\d{1,2})*)\]/g;
-    const usedIndices = new Set();
-    let m;
-    while ((m = re.exec(textContent)) !== null) {
-        m[1].split(/\s*,\s*/).forEach(n => {
-            const idx = parseInt(n.trim());
-            if (idx >= 1 && idx <= urls.length && urls[idx - 1]) {
-                usedIndices.add(idx);
-            }
-        });
-    }
-    if (usedIndices.size === 0) return;
-    const sorted = [...usedIndices].sort((a, b) => a - b);
-    const footer = document.createElement('div');
-    footer.className = 'sxng-citation-footer';
-    sorted.forEach(n => {
-        const url = urls[n - 1];
-        if (!url) return;
-        let domain;
-        try { domain = new URL(url).hostname.replace('www.', ''); } catch(e) { domain = url; }
-        const item = document.createElement('span');
-        item.className = 'sxng-citation-item';
-        const a = document.createElement('a');
-        a.href = url;
-        a.target = '_blank';
-        a.textContent = `[${n}] ${domain}`;
-        item.appendChild(a);
-        footer.appendChild(item);
-    });
-    container.appendChild(footer);
-}
-// === INTERACTIVE_JS ===
-const footer = document.getElementById('sxng-footer');
-const input = document.getElementById('sxng-action-input');
-if (typeof model_init !== 'undefined' && model_init) {
-    const _ms = document.getElementById('sxng-model-select');
-    if (_ms) {
-        const _o = document.createElement('option');
-        _o.value = model_init;
-        _o.textContent = model_init;
-        _o.selected = true;
-        _ms.appendChild(_o);
-    }
-}
-if (window.getComputedStyle && box) {
-    try {
-        const docStyles = getComputedStyle(document.documentElement);
-        let accent = docStyles.getPropertyValue('--color-result-link').trim();
-        if (!accent) {
-            const a = document.createElement('a');
-            document.body.appendChild(a);
-            accent = getComputedStyle(a).color;
-            document.body.removeChild(a);
-        }
-        if (accent) {
-            box.style.setProperty('--color-result-link', accent);
-            box.style.setProperty('--sxng-ai-accent', accent);
-        }
-    } catch(e) {}
-}
-
-// conversation saved as base64 URL fragment.
-const updateState = () => {
-    try {
-        let state = {
-            t: conversation.turns.map(t => ({
-                r: t.role === 'user' ? 'u' : 'a',
-                c: t.content.replace(/\s+/g, ' ').trim()
-            })),
-            u: urls
-        };
-        const encodeB64 = (obj) => {
-            const u8 = new TextEncoder().encode(JSON.stringify(obj));
-            let bin = '';
-            // Use a loop to avoid RangeError: Maximum call stack size exceeded
-            for (let i = 0; i < u8.byteLength; i++) {
-                bin += String.fromCharCode(u8[i]);
-            }
-            return btoa(bin);
-        };
-
-        let b64 = encodeB64(state);
-        while (b64.length > 2000 && state.t.length > 2) {
-            state.t.splice(1, 2); // Delete in Q&A pairs
-            b64 = encodeB64(state);
-        }
-
-        history.replaceState(null, null, '#ai=' + b64);
-    } catch(e) {}
-};
-
-if (location.hash.includes('ai=')) {
-    try {
-        const b64 = location.hash.split('ai=')[1];
-        const uint8 = new Uint8Array(atob(b64).split('').map(c => c.charCodeAt(0)));
-        const json = new TextDecoder().decode(uint8);
-        const state = JSON.parse(json);
-        if (state.t && state.t.length > 0) {
-            // Restore URLs for citation indexing
-            if (state.u && Array.isArray(state.u)) {
-                urls = state.u;
-            }
-
-            conversation.turns = state.t.map(t => ({
-                role: t.r === 'u' ? 'user' : 'assistant',
-                content: t.c.trim(),
-                ts: 0
-            }));
-
-            const injectCitations = (text) => {
-                return renderCitations(text, urls);
-            };
-
-            data.innerHTML = '';
-            conversation.turns.forEach((turn, i) => {
-                if (turn.role === 'user') {
-                    if (turn.content !== conversation.originalQuery) {
-                        const u = document.createElement('span');
-                        u.className = 'sxng-user-msg';
-                        u.textContent = turn.content;
-                        data.appendChild(u);
-                        const clr = document.createElement('div');
-                        clr.style.clear = 'both';
-                        data.appendChild(clr);
-                    }
-                } else {
-                    data.appendChild(injectCitations(turn.content));
-                }
-            });
-            box.style.display = 'block';
-            if(wrapper) wrapper.style.display = '';
-            if(footer && is_interactive) footer.style.display = 'flex';
-            restored = true;
-        }
-    } catch(e) { console.warn('Restore failed', e); }
-}
-document.getElementById('btn-copy').onclick = async (e) => {
-    const btn = e.currentTarget;
-    const originalContent = btn.innerHTML;
-    const text = Array.from(data.childNodes)
-        .filter(n => n.nodeType === 3 || n.tagName === 'SPAN')
-        .map(n => n.textContent)
-        .join('');
-    await navigator.clipboard.writeText(text);
-    btn.innerHTML = '<svg viewBox="0 0 24 24" style="color:#a3be8c;"><path d="M9 16.17L4.83 12L3.41 13.41L9 19L21 7L19.59 5.59L9 16.17Z"/></svg>';
-    setTimeout(() => btn.innerHTML = originalContent, 2000);
-};
-
-document.getElementById('btn-regen').onclick = async () => {
-    data.innerHTML = '<span class="sxng-cursor"></span>';
-    footer.style.display = 'none';
-
-    if (conversation.turns.length > 0 && conversation.turns[conversation.turns.length - 1].role === 'assistant') {
-        conversation.turns.pop();
-    }
-
-    updateState();
-
-    if (conversation.turns.length <= 1) {
-        await startStream();
-    } else {
-        const val = conversation.turns[conversation.turns.length - 1].content;
-        const currentText = conversation.turns.slice(0, -1).slice(-6)
-            .map(t => (t.role === 'user' ? 'Q' : 'A') + ': ' + t.content)
-            .join('\\n\\n');
-        await startStream(val, currentText);
-    }
-    updateState();
-};
-
-const handleAction = async (e) => {
-    if (e) e.preventDefault();
-    const val = input.value.trim();
-
-    conversation.turns.push({role: 'user', content: val, ts: Date.now()});
-    updateState();
-
-    const currentText = conversation.turns.slice(0, -1).slice(-6)
-        .map(t => (t.role === 'user' ? 'Q' : 'A') + ': ' + t.content)
-        .join('\\n\\n');
-
-    input.value = '';
-    input.blur();
-    footer.style.display = 'none';
-
-    if (val) {
-        const cursor = data.querySelector('.sxng-cursor');
-        if (cursor) cursor.remove();
-        const userMsg = document.createElement('span');
-        userMsg.className = 'sxng-user-msg';
-        userMsg.textContent = val;
-        data.appendChild(userMsg);
-        const clr = document.createElement('div');
-        clr.style.clear = 'both';
-        data.appendChild(clr);
-
-        const newCursor = document.createElement('span');
-        newCursor.className = 'sxng-cursor';
-        data.appendChild(newCursor);
-
-        const synthesized = synthesizeQuery(q_init, val);
-        let auxContext = null;
-        try {
-            const auxData = await fetch(script_root + '/ai-auxiliary-search', {
-                method: 'POST',
-                headers: {'Content-Type': 'application/json'},
-                body: JSON.stringify({query: synthesized, lang: lang_init, offset: urls.length, tk: tk_init})
-            }).then(r => r.json());
-            if (auxData.context) {
-                const originalBackground = conversation.originalContext.substring(0, 1500);
-                auxContext = `FRESH SOURCES (most relevant):\\n${auxData.context}\\n\\nBACKGROUND (for reference):\\n${originalBackground}`;
-                if (auxData.new_urls && Array.isArray(auxData.new_urls)) {
-                    urls = urls.concat(auxData.new_urls);
-                }
-            }
-        } catch (err) {}
-
-        await startStream(val, currentText, auxContext);
-        updateState();
-    } else {
-        const cursor = data.querySelector('.sxng-cursor');
-        if (cursor) cursor.remove();
-        data.appendChild(document.createElement('br'));
-        data.appendChild(document.createElement('br'));
-        const newCursor = document.createElement('span');
-        newCursor.className = 'sxng-cursor';
-        data.appendChild(newCursor);
-        await startStream("Continue", currentText);
-        updateState();
-    }
-};
-
-document.getElementById('sxng-action-form').onsubmit = handleAction;
-input.onfocus = () => {
-    setTimeout(() => {
-        input.scrollIntoView({behavior: 'smooth', block: 'center'});
-    }, 300);
-};
-
-(function fetchModels() {
-    const _msel2 = document.getElementById('sxng-model-select');
-    if (!_msel2) return;
-    const _modelsUrl = script_root + '/ai-models?tk=' + encodeURIComponent(tk_init);
-    console.log('[AI Answers] Fetching models from', _modelsUrl);
-    fetch(_modelsUrl)
-        .then(r => r.ok ? r.json() : Promise.reject('HTTP ' + r.status))
-        .then(d => {
-            const models = (d && d.models && d.models.length > 0) ? d.models : [model_init];
-            const _cur = _msel2.value || model_init;
-            _msel2.innerHTML = '';
-            models.forEach(m => {
-                const o = document.createElement('option');
-                o.value = m; o.textContent = m;
-                if (m === _cur) o.selected = true;
-                _msel2.appendChild(o);
-            });
-            _msel2.style.display = 'inline-block';
-        })
-        .catch(() => {
-            if (model_init) {
-                const o = document.createElement('option');
-                o.value = model_init; o.textContent = model_init;
-                o.selected = true;
-                _msel2.appendChild(o);
-                _msel2.style.display = 'inline-block';
-            }
-        });
-})();

build.py

@@ -1,63 +0,0 @@
-#!/usr/bin/env python3
-"""Build dist/ollama_answers.py by inlining assets as Python string constants."""
-import os
-import re
-
-ROOT = os.path.dirname(os.path.abspath(__file__))
-ASSETS = os.path.join(ROOT, 'assets')
-SRC = os.path.join(ROOT, 'ollama_answers.py')
-DIST_DIR = os.path.join(ROOT, 'dist')
-DIST = os.path.join(DIST_DIR, 'ollama_answers.py')
-
-
-def read(path):
-    with open(path, encoding='utf-8') as f:
-        return f.read()
-
-
-def main():
-    css = read(os.path.join(ASSETS, 'ui.css'))
-    html = read(os.path.join(ASSETS, 'ui.html'))
-    js_raw = read(os.path.join(ASSETS, 'ui.js'))
-
-    frontend_js = js_raw.split('// === CITATION_HELPER_JS ===')[0].replace('// === FRONTEND_JS_TEMPLATE ===', '').strip()
-    citation_js = js_raw.split('// === CITATION_HELPER_JS ===')[1].split('// === INTERACTIVE_JS ===')[0].strip()
-    interactive_js = js_raw.split('// === INTERACTIVE_JS ===')[1].strip()
-
-    src = read(SRC)
-
-    asset_block = '''\
-# UI assets
-_ASSETS = os.path.join(os.path.dirname(__file__), 'assets')
-INTERACTIVE_CSS = open(os.path.join(_ASSETS, 'ui.css')).read()
-INTERACTIVE_HTML = open(os.path.join(_ASSETS, 'ui.html')).read()
-_js_raw = open(os.path.join(_ASSETS, 'ui.js')).read()
-FRONTEND_JS_TEMPLATE = _js_raw.split('// === CITATION_HELPER_JS ===')[0].replace('// === FRONTEND_JS_TEMPLATE ===', '').strip()
-CITATION_HELPER_JS = _js_raw.split('// === CITATION_HELPER_JS ===')[1].split('// === INTERACTIVE_JS ===')[0].strip()
-INTERACTIVE_JS = _js_raw.split('// === INTERACTIVE_JS ===')[1].strip()'''
-
-    inline_block = (
-        '# UI assets\n'
-        'INTERACTIVE_CSS = """\\\n' + css.replace('\\', '\\\\') + '\n"""\n'
-        'INTERACTIVE_HTML = """\\\n' + html.replace('\\', '\\\\') + '\n"""\n'
-        'FRONTEND_JS_TEMPLATE = r"""\\\n' + frontend_js + '\n"""\n'
-        'CITATION_HELPER_JS = r"""\\\n' + citation_js + '\n"""\n'
-        'INTERACTIVE_JS = r"""\\\n' + interactive_js + '\n"""\n'
-    )
-
-    if asset_block not in src:
-        print('ERROR: Could not locate the asset-loading block in ollama_answers.py')
-        raise SystemExit(1)
-
-    dist_src = src.replace(asset_block, inline_block)
-    dist_src = '# AUTO-GENERATED by build.py — do not edit directly\n' + dist_src
-
-    os.makedirs(DIST_DIR, exist_ok=True)
-    with open(DIST, 'w', encoding='utf-8') as f:
-        f.write(dist_src)
-
-    print('Built dist/ollama_answers.py successfully')
-
-
-if __name__ == '__main__':
-    main()

dev/.env.example

@@ -0,0 +1,39 @@
+# AI Answers Plugin — Dev Server Config
+# Copy this to .env and fill in your values
+# .env is gitignored and never committed
+
+# Ollama endpoint (required)
+LLM_URL=http://localhost:11434/v1/chat/completions
+
+# Default model
+LLM_MODEL=qwen3.5:9b
+
+# Max response tokens
+LLM_MAX_TOKENS=200
+
+# Response temperature (0.0 - 2.0)
+LLM_TEMPERATURE=0.2
+
+# Bearer token for authenticated LLM endpoints
+# Leave empty if no Bearer token is needed for your server
+LLM_API_KEY=
+
+# Live SearXNG instance for real search results
+# Leave empty to use mock results
+SEARXNG_URL=
+
+# Valkey for streaming (required)
+# Start with: docker run -d --name dev-valkey -p 6379:6379 valkey/valkey:9-alpine
+VALKEY_HOST=localhost
+VALKEY_PORT=6379
+
+# Dev server host and port
+DEV_HOST=127.0.0.1
+DEV_PORT=5000
+
+# Plugin settings
+LLM_INTERACTIVE=true
+LLM_QUESTION_MARK_REQUIRED=false
+LLM_TABS=general,science,it,news
+LLM_CONTEXT_DEEP_COUNT=5
+LLM_CONTEXT_SHALLOW_COUNT=15

install.sh

@@ -1,242 +0,0 @@
-#!/usr/bin/env bash
-set -e
-
-REPO_URL="https://github.com/TySP-Dev/ollama-ai-answers-searxng"
-REPO_DIR="/tmp/ollama-ai-answers-searxng"
-
-# ============================================================
-echo "=== Step 1: Clone or update repo ==="
-# ============================================================
-if [ -d "$REPO_DIR/.git" ]; then
-    echo "Repository already exists — pulling latest changes..."
-    git -C "$REPO_DIR" pull
-else
-    git clone "$REPO_URL" "$REPO_DIR"
-fi
-cd "$REPO_DIR"
-
-# ============================================================
-echo "=== Step 2: Build dist file ==="
-# ============================================================
-if ! python3 build.py; then
-    echo "ERROR: build.py failed"
-    exit 1
-fi
-
-# ============================================================
-echo "=== Step 3: Detect SearXNG Docker Compose installation ==="
-# ============================================================
-CANDIDATES=(
-    "$HOME/searxng/docker-compose.yml"
-    "$HOME/docker/searxng/docker-compose.yml"
-    "/opt/searxng/docker-compose.yml"
-    "/etc/searxng/docker-compose.yml"
-)
-
-FOUND=()
-for f in "${CANDIDATES[@]}"; do
-    if [ -f "$f" ] && grep -q "searxng" "$f" 2>/dev/null; then
-        FOUND+=("$f")
-    fi
-done
-
-# Also do a broader search
-while IFS= read -r f; do
-    # Avoid duplicates
-    already=false
-    for existing in "${FOUND[@]}"; do
-        [ "$f" = "$existing" ] && already=true && break
-    done
-    $already || FOUND+=("$f")
-done < <(find "$HOME" -maxdepth 6 -name "docker-compose.yml" -exec grep -l "searxng" {} \; 2>/dev/null)
-
-if [ ${#FOUND[@]} -eq 0 ]; then
-    echo "ERROR: No docker-compose.yml containing 'searxng' was found."
-    echo "Please set COMPOSE_FILE manually and re-run."
-    exit 1
-elif [ ${#FOUND[@]} -eq 1 ]; then
-    COMPOSE_FILE="${FOUND[0]}"
-    echo "Found: $COMPOSE_FILE"
-else
-    echo "Multiple docker-compose.yml files found:"
-    for i in "${!FOUND[@]}"; do
-        echo "  [$((i+1))] ${FOUND[$i]}"
-    done
-    read -rp "Select a file [1-${#FOUND[@]}]: " choice
-    idx=$((choice - 1))
-    if [ "$idx" -lt 0 ] || [ "$idx" -ge "${#FOUND[@]}" ]; then
-        echo "ERROR: Invalid selection"
-        exit 1
-    fi
-    COMPOSE_FILE="${FOUND[$idx]}"
-fi
-
-COMPOSE_DIR="$(dirname "$COMPOSE_FILE")"
-echo "Using: $COMPOSE_FILE"
-
-# ============================================================
-echo "=== Step 4: Create plugins directory ==="
-# ============================================================
-PLUGINS_DIR="$COMPOSE_DIR/plugins"
-mkdir -p "$PLUGINS_DIR"
-echo "Plugins directory: $PLUGINS_DIR"
-
-# ============================================================
-echo "=== Step 5: Copy built plugin ==="
-# ============================================================
-cp dist/ollama_answers.py "$PLUGINS_DIR/ollama_answers.py"
-echo "Plugin installed to $PLUGINS_DIR/ollama_answers.py"
-
-# ============================================================
-echo "=== Step 6: Update docker-compose.yml volume mount ==="
-# ============================================================
-python3 - "$COMPOSE_FILE" <<'PYEOF'
-import re, sys
-compose_file = sys.argv[1]
-content = open(compose_file).read()
-mount = '      - ./plugins/ollama_answers.py:/usr/local/searxng/searx/plugins/ollama_answers.py:Z'
-if 'ollama_answers.py' not in content:
-    content = re.sub(
-        r'(volumes:(?:\n\s+- [^\n]+)*)',
-        lambda m: m.group(0) + '\n' + mount,
-        content, count=1
-    )
-    open(compose_file, 'w').write(content)
-    print('Added volume mount to docker-compose.yml')
-else:
-    print('Volume mount already present')
-PYEOF
-
-# ============================================================
-echo "=== Step 7: Find and update settings.yml ==="
-# ============================================================
-SETTINGS_CANDIDATES=(
-    "$COMPOSE_DIR/core-config/settings.yml"
-    "$COMPOSE_DIR/config/settings.yml"
-    "$COMPOSE_DIR/searxng/settings.yml"
-)
-
-SETTINGS_FOUND=()
-for f in "${SETTINGS_CANDIDATES[@]}"; do
-    [ -f "$f" ] && SETTINGS_FOUND+=("$f")
-done
-
-# Broader search within COMPOSE_DIR
-while IFS= read -r f; do
-    already=false
-    for existing in "${SETTINGS_FOUND[@]}"; do
-        [ "$f" = "$existing" ] && already=true && break
-    done
-    $already || SETTINGS_FOUND+=("$f")
-done < <(find "$COMPOSE_DIR" -name "settings.yml" 2>/dev/null | head -5)
-
-if [ ${#SETTINGS_FOUND[@]} -eq 0 ]; then
-    echo "WARNING: settings.yml not found. Add this manually:"
-    echo ""
-    echo "  plugins:"
-    echo "    searx.plugins.ollama_answers.SXNGPlugin:"
-    echo "      active: true"
-    echo ""
-    SETTINGS_FILE=""
-elif [ ${#SETTINGS_FOUND[@]} -eq 1 ]; then
-    SETTINGS_FILE="${SETTINGS_FOUND[0]}"
-    echo "Found: $SETTINGS_FILE"
-else
-    echo "Multiple settings.yml files found:"
-    for i in "${!SETTINGS_FOUND[@]}"; do
-        echo "  [$((i+1))] ${SETTINGS_FOUND[$i]}"
-    done
-    read -rp "Select a file [1-${#SETTINGS_FOUND[@]}]: " schoice
-    sidx=$((schoice - 1))
-    if [ "$sidx" -lt 0 ] || [ "$sidx" -ge "${#SETTINGS_FOUND[@]}" ]; then
-        echo "ERROR: Invalid selection"
-        exit 1
-    fi
-    SETTINGS_FILE="${SETTINGS_FOUND[$sidx]}"
-fi
-
-if [ -n "$SETTINGS_FILE" ]; then
-    python3 - "$SETTINGS_FILE" <<'PYEOF'
-import sys
-settings_file = sys.argv[1]
-content = open(settings_file).read()
-entry = 'searx.plugins.ollama_answers.SXNGPlugin:\n    active: true'
-if 'ollama_answers' not in content:
-    if 'plugins:' in content:
-        content = content.replace('plugins:', 'plugins:\n\n  ' + entry, 1)
-    else:
-        content += '\nplugins:\n\n  ' + entry + '\n'
-    open(settings_file, 'w').write(content)
-    print('Added plugin entry to settings.yml')
-else:
-    print('Plugin entry already present')
-PYEOF
-fi
-
-# ============================================================
-echo "=== Step 8: Configure environment variables ==="
-# ============================================================
-python3 - "$COMPOSE_FILE" <<'PYEOF'
-import sys
-compose_file = sys.argv[1]
-content = open(compose_file).read()
-has_llm_url = 'LLM_URL' in content
-has_llm_model = 'LLM_MODEL' in content
-sys.exit(0 if (has_llm_url and has_llm_model) else 1)
-PYEOF
-ENV_ALREADY=$?
-
-if [ $ENV_ALREADY -eq 0 ]; then
-    echo "LLM_URL and LLM_MODEL already present in docker-compose.yml"
-else
-    read -rp "Enter Ollama URL (default: http://ollama:11434/v1/chat/completions): " llm_url
-    llm_url="${llm_url:-http://ollama:11434/v1/chat/completions}"
-
-    read -rp "Enter model name (default: qwen3.5:9b): " llm_model
-    llm_model="${llm_model:-qwen3.5:9b}"
-
-    python3 - "$COMPOSE_FILE" "$llm_url" "$llm_model" <<'PYEOF'
-import re, sys
-compose_file, llm_url, llm_model = sys.argv[1], sys.argv[2], sys.argv[3]
-content = open(compose_file).read()
-env_lines = f'      - LLM_URL={llm_url}\n      - LLM_MODEL={llm_model}'
-if 'LLM_URL' not in content:
-    content = re.sub(
-        r'(environment:(?:\n\s+- [^\n]+)*)',
-        lambda m: m.group(0) + '\n' + env_lines,
-        content, count=1
-    )
-    open(compose_file, 'w').write(content)
-    print(f'Added LLM_URL={llm_url} and LLM_MODEL={llm_model} to docker-compose.yml')
-else:
-    print('LLM_URL already present, skipping')
-PYEOF
-fi
-
-# ============================================================
-echo "=== Step 9: Restart SearXNG ==="
-# ============================================================
-read -rp "Restart SearXNG now? (y/n): " restart_choice
-if [[ "$restart_choice" =~ ^[Yy]$ ]]; then
-    echo "Restarting SearXNG..."
-    cd "$COMPOSE_DIR"
-    docker compose up -d --force-recreate core
-    echo "SearXNG restarted."
-else
-    echo "Skipping restart. Run manually:"
-    echo "  cd \"$COMPOSE_DIR\" && docker compose up -d --force-recreate core"
-fi
-
-# ============================================================
-echo ""
-echo "=== Installation complete ==="
-echo ""
-echo "Summary:"
-echo "  Plugin:   $PLUGINS_DIR/ollama_answers.py"
-echo "  Compose:  $COMPOSE_FILE"
-[ -n "$SETTINGS_FILE" ] && echo "  Settings: $SETTINGS_FILE"
-echo ""
-echo "Environment variables to verify in docker-compose.yml:"
-echo "  LLM_URL    — Ollama endpoint"
-echo "  LLM_MODEL  — Model name (e.g. qwen3.5:9b)"
-echo ""

requirements.txt

@@ -1,3 +1,5 @@
 flask
 flask-babel
 certifi
+python-dotenv
+valkey

tests/dev.py

@@ -1,346 +0,0 @@
-import sys
-import os
-sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-import logging
-from types import ModuleType
-from flask import Flask, request, redirect
-
-logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
-os.environ.setdefault('LLM_URL', 'http://localhost:11434/v1/chat/completions')
-
-# SearXNG module mocks
-searx = ModuleType("searx")
-searx_plugins = ModuleType("searx.plugins")
-searx_results = ModuleType("searx.result_types")
-
-class MockPlugin:
-    def __init__(self, cfg):
-        self.active = getattr(cfg, 'active', True)
-
-class MockPluginInfo:
-    def __init__(self, **kwargs):
-        self.meta = kwargs
-
-class MockEngineResults:
-    def __init__(self):
-        self.types = ModuleType("types")
-        self.types.Answer = lambda *args, **kwargs: kwargs.get('answer', args[0] if args else "")
-        self._results = []
-    
-    def add(self, res):
-        self._results.append(res)
-
-searx_plugins.Plugin = MockPlugin
-searx_plugins.PluginInfo = MockPluginInfo
-searx_results.EngineResults = MockEngineResults
-
-searx.settings = {'server': {'secret_key': 'demo-secret'}}
-searx.network = ModuleType("searx.network")
-
-sys.modules["searx"] = searx
-sys.modules["searx.plugins"] = searx_plugins
-sys.modules["searx.result_types"] = searx_results
-
-# Network module mock
-searx_network = ModuleType("searx.network")
-def mock_network_call(method, url, **kwargs):
-    import http.client, ssl, json
-    from urllib.parse import urlparse
-    
-    parsed = urlparse(url)
-    port = parsed.port or (443 if parsed.scheme=='https' else 80)
-    target = f"{parsed.hostname}:{port}"
-    
-    if parsed.scheme == 'https':
-        conn = http.client.HTTPSConnection(target, timeout=30, context=ssl.create_default_context())
-    else:
-        conn = http.client.HTTPConnection(target, timeout=30)
-    
-    headers = kwargs.get('headers', {})
-    body = None
-    if kwargs.get('json'):
-        body = json.dumps(kwargs['json'])
-    elif kwargs.get('data'):
-        body = kwargs['data']
-
-    path = parsed.path
-    if parsed.query:
-        path += f"?{parsed.query}"
-    
-    if kwargs.get('params'):
-        from urllib.parse import urlencode
-        query_str = urlencode(kwargs['params'])
-        if '?' in path:
-            path += f"&{query_str}"
-        else:
-            path += f"?{query_str}"
-
-    conn.request(method, path, body=body, headers=headers)
-    return conn.getresponse()
-
-def mock_stream(method, url, **kwargs):
-    res = mock_network_call(method, url, **kwargs)
-    
-    class MockResponse:
-        def __init__(self, r):
-            self.status_code = r.status
-            self.text = "Mock Response" # Stub
-            self._r = r
-    
-    def generator():
-        while True:
-            chunk = res.read(128)
-            if not chunk: break
-            yield chunk
-
-    return MockResponse(res), generator()
-
-def mock_get(url, **kwargs):
-    import json
-    res = mock_network_call('GET', url, **kwargs)
-    
-    class MockResponse:
-        def __init__(self, r):
-            self.status_code = r.status
-            self._content = r.read()
-            self.text = self._content.decode('utf-8')
-        
-        def json(self):
-            return json.loads(self.text)
-            
-    return MockResponse(res)
-
-searx_network.stream = mock_stream
-searx_network.get = mock_get
-sys.modules["searx.network"] = searx_network
-
-from ollama_answers import SXNGPlugin
-from flask_babel import Babel
-
-app = Flask(__name__)
-babel = Babel(app)
-
-class MockConfig:
-    active = True
-
-plugin = SXNGPlugin(MockConfig())
-plugin.init(app)
-
-@app.route("/config", methods=["POST"])
-def update_config():
-    url = request.form.get("url", "").strip()
-    bearer = request.form.get("bearer", "").strip()
-    model = request.form.get("model", "").strip()
-    query = request.form.get("q", "")
-    if url:
-        plugin.endpoint_url = url
-    plugin.api_key = bearer if bearer else "ollama"
-    if model:
-        plugin.model = model
-    redirect_q = f"?q={query}" if query else ""
-    return redirect(f"/{redirect_q}")
-
-
-@app.route("/search")
-def mock_search():
-    query = request.args.get("q", "")
-    format_type = request.args.get("format", "html")
-    
-    if format_type != "json":
-        return "Demo only supports JSON format", 400
-    
-    results = [
-        {"title": f"Result 1 for: {query}", "content": f"This is simulated content about {query}. It contains relevant information.", "url": f"https://example.com/1/{query.replace(' ', '-')}", "publishedDate": "2026-01-18"},
-        {"title": f"Result 2 for: {query}", "content": f"Additional information regarding {query}. More context and details.", "url": f"https://example.com/2/{query.replace(' ', '-')}", "publishedDate": "2026-01-17"},
-        {"title": f"Result 3 for: {query}", "content": f"Further reading on {query}. Expert analysis.", "url": f"https://example.com/3/{query.replace(' ', '-')}", "publishedDate": "2026-01-16"},
-    ]
-    
-    return {
-        "results": results,
-        "infoboxes": [],
-        "answers": [],
-        "suggestions": [f"{query} explained", f"{query} tutorial"]
-    }
-
-@app.route("/")
-def index():
-    query = request.args.get("q", "why is the sky blue")
-    
-    class MockSearchQuery:
-        pageno = 1
-        lang = 'en'
-        categories = ['general']
-    MockSearchQuery.query = query
-    
-    class MockSearch:
-        search_query = MockSearchQuery()
-        class MockResultContainer:
-            def __init__(self):
-                self.answers = set()
-
-            def get_ordered_results(self):
-                base_results = [
-                    {"title": "Wikipedia", "content": "The sky appears blue due to Rayleigh scattering of sunlight. When sunlight enters the atmosphere, it collides with gas molecules and scatters in all directions. Blue light scatters more than other colors because it travels in shorter waves.", "url": "https://en.wikipedia.org/wiki/Rayleigh_scattering", "publishedDate": "2026-01-15"},
-                    {"title": "NASA Science", "content": "Shorter blue wavelengths scatter more than longer red wavelengths. This phenomenon, discovered by Lord Rayleigh in the 1870s, explains why we see a blue sky during the day.", "url": "https://science.nasa.gov/blue-sky", "publishedDate": "2026-01-10"},
-                    {"title": "Physics Today", "content": "The atmosphere acts as a filter, scattering blue light in all directions while letting other colors pass through more directly.", "url": "https://physicstoday.org/atmosphere", "publishedDate": "2026-01-01"},
-                    {"title": "Scientific American", "content": "At sunset, light travels through more atmosphere, scattering away the blue and leaving reds and oranges.", "url": "https://scientificamerican.com/sunset", "publishedDate": "2025-12-20"},
-                    {"title": "National Geographic", "content": "Ocean color also results from light scattering and absorption by water molecules.", "url": "https://nationalgeographic.com/ocean-blue", "publishedDate": "2025-12-15"},
-                ]
-                broad_results = [
-                    {"title": "MIT OpenCourseWare: Atmospheric Physics", "content": "Course materials.", "url": "https://ocw.mit.edu/physics"},
-                    {"title": "NOAA: Understanding the Atmosphere", "content": "Educational resource.", "url": "https://noaa.gov/atmosphere"},
-                    {"title": "BBC Science: Why is the sky blue?", "content": "Explainer article.", "url": "https://bbc.com/science/sky"},
-                    {"title": "Khan Academy: Light and Color", "content": "Video lesson.", "url": "https://khanacademy.org/light"},
-                    {"title": "HowStuffWorks: Rayleigh Scattering", "content": "Detailed explanation.", "url": "https://howstuffworks.com/rayleigh"},
-                    {"title": "Physics Stack Exchange: Sky color discussion", "content": "Q&A thread.", "url": "https://physics.stackexchange.com/sky"},
-                    {"title": "Quora: Atmospheric optics explained", "content": "Community answers.", "url": "https://quora.com/atmosphere"},
-                ]
-                if 'quantum' in query.lower():
-                    return [
-                        {"title": "IBM Quantum", "content": "Quantum computers rely on qubits, which can represent 0, 1, or both via superposition. They solve complex problems faster.", "url": "https://www.ibm.com/quantum", "publishedDate": "2026-01-15"},
-                        {"title": "Nature Physics", "content": "Entanglement allows qubits to be correlated instantly across distances. This is key for quantum cryptography and teleportation.", "url": "https://nature.com/articles/quantum", "publishedDate": "2026-01-10"},
-                        {"title": "Wikipedia", "content": "Quantum computing uses quantum mechanics. Major applications include drug discovery and materials science.", "url": "https://en.wikipedia.org/wiki/Quantum_computing", "publishedDate": "2025-12-01"}
-                    ] + broad_results
-                return base_results + broad_results
-        result_container = MockResultContainer()
-
-    search = MockSearch()
-    plugin.post_search(None, search)
-    
-    injection_html = ""
-    if search.result_container.answers:
-        injection_html = list(search.result_container.answers)[0]
-    
-    bearer_display = plugin.api_key if plugin.api_key != "ollama" else ""
-    return f"""
-    <!DOCTYPE html>
-    <html lang="en">
-    <head>
-        <meta charset="UTF-8">
-        <title>AI Answers Demo</title>
-        <style>
-            body {{
-                font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
-                padding: 2rem;
-                max-width: 800px;
-                margin: 0 auto;
-                background: #2e3440;
-                color: #eceff4;
-            }}
-            :root {{
-                --color-result-border: #3b4252;
-                --color-result-description: #d8dee9;
-                --color-base-font: #88c0d0;
-                --color-result-link: #81a1c1;
-            }}
-            .meta {{ color: #81a1c1; font-size: 0.9rem; }}
-            hr {{ border-color: #4c566a; }}
-            a {{ color: #88c0d0; }}
-            .config-panel {{
-                background: #3b4252;
-                border-radius: 6px;
-                padding: 1rem 1.25rem;
-                margin-bottom: 1.25rem;
-            }}
-            .config-panel summary {{
-                cursor: pointer;
-                font-size: 0.85rem;
-                color: #81a1c1;
-                user-select: none;
-            }}
-            .config-panel summary:hover {{ color: #88c0d0; }}
-            .config-row {{
-                display: flex;
-                flex-direction: column;
-                gap: 0.5rem;
-                margin-top: 0.75rem;
-            }}
-            .config-row label {{
-                font-size: 0.8rem;
-                color: #81a1c1;
-            }}
-            .config-row input {{
-                background: #2e3440;
-                border: 1px solid #4c566a;
-                border-radius: 4px;
-                color: #eceff4;
-                font-size: 0.85rem;
-                padding: 0.4rem 0.6rem;
-                width: 100%;
-                box-sizing: border-box;
-            }}
-            .config-row input:focus {{ outline: none; border-color: #81a1c1; }}
-            .config-btn {{
-                margin-top: 0.75rem;
-                background: #4c566a;
-                border: none;
-                border-radius: 4px;
-                color: #eceff4;
-                cursor: pointer;
-                font-size: 0.85rem;
-                padding: 0.4rem 1rem;
-            }}
-            .config-btn:hover {{ background: #5e81ac; }}
-            .search-row {{
-                display: flex;
-                gap: 0.5rem;
-                margin-bottom: 1.25rem;
-            }}
-            .search-row input {{
-                flex: 1;
-                background: #3b4252;
-                border: 1px solid #4c566a;
-                border-radius: 4px;
-                color: #eceff4;
-                font-size: 0.95rem;
-                padding: 0.45rem 0.75rem;
-            }}
-            .search-row input:focus {{ outline: none; border-color: #81a1c1; }}
-            .search-row button {{
-                background: #5e81ac;
-                border: none;
-                border-radius: 4px;
-                color: #eceff4;
-                cursor: pointer;
-                font-size: 0.9rem;
-                padding: 0.45rem 1rem;
-            }}
-            .search-row button:hover {{ background: #81a1c1; }}
-        </style>
-    </head>
-    <body>
-        <details class="config-panel" {'open' if not bearer_display and 'localhost' in plugin.endpoint_url else ''}>
-            <summary>&#9881; Ollama Configuration</summary>
-            <form method="POST" action="/config">
-                <input type="hidden" name="q" value="{query}">
-                <div class="config-row">
-                    <label>Endpoint URL</label>
-                    <input type="text" name="url" value="{plugin.endpoint_url}" placeholder="http://localhost:11434/v1/chat/completions">
-                </div>
-                <div class="config-row">
-                    <label>Bearer Token <span style="opacity:0.5;">(optional)</span></label>
-                    <input type="text" name="bearer" value="{bearer_display}" placeholder="Leave empty if not required">
-                </div>
-                <button type="submit" class="config-btn">Apply</button>
-            </form>
-        </details>
-
-        <form class="search-row" method="GET" action="/">
-            <input type="text" name="q" value="{query}" placeholder="Ask something...">
-            <button type="submit">Search</button>
-        </form>
-
-        <p class="meta">Model: <strong>{plugin.model}</strong></p>
-        <hr>
-        {injection_html if injection_html else '<p style="color:#f66;">No response — check your Ollama endpoint and token above.</p>'}
-    </body>
-    </html>
-    """
-
-if __name__ == "__main__":
-    print("AI Answers - Demo\n")
-    print(f"  Endpoint: {plugin.endpoint_url}")
-    print(f"  Model:    {plugin.model or 'N/A'}")
-    print(f"  Mode:     {'interactive' if plugin.interactive else 'simple'}")
-    print(f"\n  http://localhost:5000/?q=why+is+the+sky+blue\n")
-    app.run(debug=False, port=5000)