Add LangSearch web search tool for small model knowledge augmentation

Dockerfile

@@ -63,8 +63,9 @@ RUN python3 -m venv /opt/venv \
   && rm -rf /root/.cache/pip
 
 COPY download_model.py /app/download_model.py
+COPY search_tool.py /app/search_tool.py
 COPY start.sh /app/start.sh
-RUN chmod +x /app/start.sh \
+RUN chmod +x /app/start.sh /app/search_tool.py \
   && mkdir -p /data/models /data/hf-cache \
   && chown -R 65532:65532 /app || true
 

README.md

@@ -31,6 +31,7 @@ Optional tuning variables:
 - `CACHE_TYPE_K`: KV cache type for keys, default `q8_0`
 - `CACHE_TYPE_V`: KV cache type for values, default `q8_0`
 - `REASONING`: reasoning mode, accepts `True`, `False`, or `auto` and maps to llama.cpp `--reasoning`
+- `LANGSEARCH_API_KEY`: optional API key for LangSearch web search tool (free tier: 1 req/sec, 60/min, 1000/day)
 - `PARALLEL`: optional override for concurrent prompt decode slots
 - `PORT`: listen port, default `7860`
 
@@ -50,6 +51,28 @@ The Docker image uses a multi-stage build on Ubuntu 24.04. The builder stage ins
 
 Model downloads and HF cache live on the `/data` bucket so restarts do not redownload the model.
 
+## Web Search Tool
+
+If `LANGSEARCH_API_KEY` is set, use the search tool to augment small model knowledge:
+
+```bash
+python3 /app/search_tool.py "query" [count] [summary] [freshness]
+```
+
+Examples:
+```bash
+python3 /app/search_tool.py "latest AI news" 5 true noLimit
+python3 /app/search_tool.py "Python 3.13 release" 3 false oneWeek
+```
+
+Parameters:
+- `query`: search string (required)
+- `count`: max results 1-10 (default: 5)
+- `summary`: include summaries (default: true)
+- `freshness`: `oneDay`, `oneWeek`, `oneMonth`, `oneYear`, `noLimit` (default: `noLimit`)
+
+Output is JSON with search results, URLs, snippets, and optional summaries.
+
 ## curl examples
 
 ```bash

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub>=0.24,<1
+huggingface_hub>=0.24,<1
+requests>=2.31,<3

search_tool.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+
+import os
+import sys
+import json
+import requests
+
+
+def search(query: str, count: int = 5, summary: bool = True, freshness: str = "noLimit") -> dict:
+    api_key = os.environ.get("LANGSEARCH_API_KEY", "").strip()
+    if not api_key:
+        raise SystemExit("LANGSEARCH_API_KEY environment variable not set")
+    
+    url = "https://api.langsearch.com/v1/web-search"
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json"
+    }
+    payload = {
+        "query": query,
+        "freshness": freshness,
+        "summary": summary,
+        "count": min(count, 10)
+    }
+    
+    try:
+        response = requests.post(url, headers=headers, json=payload, timeout=30)
+        response.raise_for_status()
+        data = response.json()
+        
+        if data.get("code") == 200:
+            results = []
+            web_pages = data.get("data", {}).get("webPages", {}).get("value", [])
+            for page in web_pages:
+                results.append({
+                    "name": page.get("name", ""),
+                    "url": page.get("url", ""),
+                    "snippet": page.get("snippet", ""),
+                    "summary": page.get("summary", "") if summary else ""
+                })
+            return {"success": True, "query": query, "results": results}
+        else:
+            return {"success": False, "error": data.get("msg", "Unknown error")}
+    
+    except requests.RequestException as e:
+        return {"success": False, "error": str(e)}
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: search_tool.py '<query>' [count] [summary] [freshness]")
+        print("Example: search_tool.py 'Apple M4 chip' 5 true noLimit")
+        sys.exit(1)
+    
+    query = sys.argv[1]
+    count = int(sys.argv[2]) if len(sys.argv) > 2 else 5
+    summary = sys.argv[3].lower() == "true" if len(sys.argv) > 3 else True
+    freshness = sys.argv[4] if len(sys.argv) > 4 else "noLimit"
+    
+    result = search(query, count, summary, freshness)
+    print(json.dumps(result, indent=2))