feat(semantic_search): support local OpenAI-compatible embedding servers (#22)

Adds a LocalEmbedder that targets any OpenAI-compatible embedding
endpoint (Ollama, llama.cpp, vLLM, LM Studio, ...). Zero new
Python dependencies — reuses the existing openai SDK with a
custom base_url. Defaults to Ollama at http://localhost:11434/v1
with nomic-embed-text @ 768 dims; override via env vars for other
servers/models (e.g. bge-m3 @ 1024 dims for better Turkish).

Refactors the shared encode/similarity logic into a private base
class so OpenRouterEmbedder and LocalEmbedder don't duplicate ~50
lines. OpenRouter keeps its ranking headers; local sends none.

Adds get_embedder() factory selecting the provider based on
EMBEDDING_PROVIDER (local) or OPENROUTER_API_KEY presence, and
is_semantic_search_available() that returns True for either path.
mcp_server_main now uses these so the semantic_search tool is
exposed when only a local server is configured.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

semantic_search/__init__.py

@@ -1,7 +1,23 @@
 # semantic_search/__init__.py
 
-from .embedder import OpenRouterEmbedder, is_openrouter_available
+from .embedder import (
+    OpenRouterEmbedder,
+    LocalEmbedder,
+    get_embedder,
+    is_openrouter_available,
+    is_local_embedding_configured,
+    is_semantic_search_available,
+)
 from .vector_store import VectorStore
 from .processor import DocumentProcessor
 
-__all__ = ['OpenRouterEmbedder', 'is_openrouter_available', 'VectorStore', 'DocumentProcessor']
+__all__ = [
+    'OpenRouterEmbedder',
+    'LocalEmbedder',
+    'get_embedder',
+    'is_openrouter_available',
+    'is_local_embedding_configured',
+    'is_semantic_search_available',
+    'VectorStore',
+    'DocumentProcessor',
+]