Correct folder placement done.

Author: Salman Mohammed

plugins/tool_search/in_mem_embeddings/README.md

@@ -14,6 +14,24 @@ Optionally, for high-quality embeddings:
 pip install utcp-in-mem-embeddings[embedding]
 ```
 
+Or install the required dependencies directly:
+
+```bash
+pip install "sentence-transformers>=2.2.0" "torch>=1.9.0"
+```
+
+## Why are sentence-transformers and torch needed?
+
+While the plugin works without these packages (using a simple character frequency-based fallback), installing them provides significant benefits:
+
+- **Enhanced Semantic Understanding**: The `sentence-transformers` package provides pre-trained models that convert text into high-quality vector embeddings, capturing the semantic meaning of text rather than just keywords.
+
+- **Better Search Results**: With these packages installed, the search can understand conceptual similarity between queries and tools, even when they don't share exact keywords.
+
+- **Performance**: The default model (all-MiniLM-L6-v2) offers a good balance between quality and performance for semantic search applications.
+
+- **Fallback Mechanism**: Without these packages, the plugin automatically falls back to a simpler text similarity method, which works but with reduced accuracy.
+
 ## How it works
 
 When installed, this package exposes an entry point under `utcp.plugins` so the UTCP core can auto-discover and register the `in_mem_embeddings` strategy.

plugins/tool_search/in_mem_embeddings/test_integration.py

@@ -67,8 +67,15 @@ async def test_integration():
         ]
 
         # Create repository
-        repo = InMemToolRepository(tools)
+        repo = InMemToolRepository()
 
+        # Create a manual and add it to the repository
+        from utcp.data.utcp_manual import UtcpManual
+        manual = UtcpManual(tools=tools)
+        manual_call_template = CallTemplate(name="test_manual", description="Test manual", call_template_type="default")
+        await repo.save_manual(manual_call_template, manual)
+       
+
         # Test search
         results = await strategy.search_tools(repo, "cooking", limit=1)
         print(f"   ✅ Search completed, found {len(results)} results")