Feature/prompt templates and lmstudio sdk

docs/configuration-guide.md

@@ -158,6 +158,95 @@ builder.build_index("./indexes/my-notes", chunks)
 
 `embedding_options` is persisted to the index `meta.json`, so subsequent `LeannSearcher` or `LeannChat` sessions automatically reuse the same provider settings (the embedding server manager forwards them to the provider for you).
 
+## Optional Embedding Features
+
+### Task-Specific Prompt Templates
+
+Some embedding models are trained with task-specific prompts to differentiate between documents and queries. The most notable example is **Google's EmbeddingGemma**, which requires different prompts depending on the use case:
+
+- **Indexing documents**: `"title: none | text: "`
+- **Search queries**: `"task: search result | query: "`
+
+LEANN supports automatic prompt prepending via the `--embedding-prompt-template` flag:
+
+```bash
+# Build index with EmbeddingGemma (via LM Studio or Ollama)
+leann build my-docs \
+  --docs ./documents \
+  --embedding-mode openai \
+  --embedding-model text-embedding-embeddinggemma-300m-qat \
+  --embedding-api-base http://localhost:1234/v1 \
+  --embedding-prompt-template "title: none | text: " \
+  --force
+
+# Search with query-specific prompt
+leann search my-docs \
+  --query "What is quantum computing?" \
+  --embedding-prompt-template "task: search result | query: "
+```
+
+**Important Notes:**
+- **Only use with compatible models**: EmbeddingGemma and similar task-specific models
+- **NOT for regular models**: Adding prompts to models like `nomic-embed-text`, `text-embedding-3-small`, or `bge-base-en-v1.5` will corrupt embeddings
+- **Template is saved**: Build-time templates are saved to `.meta.json` for reference
+- **Flexible prompts**: You can use any prompt string, or leave it empty (`""`)
+
+**Python API:**
+```python
+from leann.api import LeannBuilder
+
+builder = LeannBuilder(
+    embedding_mode="openai",
+    embedding_model="text-embedding-embeddinggemma-300m-qat",
+    embedding_options={
+        "base_url": "http://localhost:1234/v1",
+        "api_key": "lm-studio",
+        "prompt_template": "title: none | text: ",
+    },
+)
+builder.build_index("./indexes/my-docs", chunks)
+```
+
+**References:**
+- [HuggingFace Blog: EmbeddingGemma](https://huggingface.co/blog/embeddinggemma) - Technical details
+
+### LM Studio Auto-Detection (Optional)
+
+When using LM Studio with the OpenAI-compatible API, LEANN can optionally auto-detect model context lengths via the LM Studio SDK. This eliminates manual configuration for token limits.
+
+**Prerequisites:**
+```bash
+# Install Node.js (if not already installed)
+# Then install the LM Studio SDK globally
+npm install -g @lmstudio/sdk
+```
+
+**How it works:**
+1. LEANN detects LM Studio URLs (`:1234`, `lmstudio` in URL)
+2. Queries model metadata via Node.js subprocess
+3. Automatically unloads model after query (respects your JIT auto-evict settings)
+4. Falls back to static registry if SDK unavailable
+
+**No configuration needed** - it works automatically when SDK is installed:
+
+```bash
+leann build my-docs \
+  --docs ./documents \
+  --embedding-mode openai \
+  --embedding-model text-embedding-nomic-embed-text-v1.5 \
+  --embedding-api-base http://localhost:1234/v1
+  # Context length auto-detected if SDK available
+  # Falls back to registry (2048) if not
+```
+
+**Benefits:**
+- ✅ Automatic token limit detection
+- ✅ Respects LM Studio JIT auto-evict settings
+- ✅ No manual registry maintenance
+- ✅ Graceful fallback if SDK unavailable
+
+**Note:** This is completely optional. LEANN works perfectly fine without the SDK using the built-in token limit registry.
+
 ## Index Selection: Matching Your Scale
 
 ### HNSW (Hierarchical Navigable Small World)

docs/faq.md

@@ -8,3 +8,51 @@ You can speed up the process by using a lightweight embedding model. Add this to
 --embedding-model sentence-transformers/all-MiniLM-L6-v2
 ```
 **Model sizes:** `all-MiniLM-L6-v2` (30M parameters), `facebook/contriever` (~100M parameters), `Qwen3-0.6B` (600M parameters)
+
+## 2. When should I use prompt templates?
+
+**Use prompt templates ONLY with task-specific embedding models** like Google's EmbeddingGemma. These models are specially trained to use different prompts for documents vs queries.
+
+**DO NOT use with regular models** like `nomic-embed-text`, `text-embedding-3-small`, or `bge-base-en-v1.5` - adding prompts to these models will corrupt the embeddings.
+
+**Example usage with EmbeddingGemma:**
+```bash
+# Build with document prompt
+leann build my-docs --embedding-prompt-template "title: none | text: "
+
+# Search with query prompt
+leann search my-docs --query "your question" --embedding-prompt-template "task: search result | query: "
+```
+
+See the [Configuration Guide: Task-Specific Prompt Templates](configuration-guide.md#task-specific-prompt-templates) for detailed usage.
+
+## 3. Why is LM Studio loading multiple copies of my model?
+
+This was fixed in recent versions. LEANN now properly unloads models after querying metadata, respecting your LM Studio JIT auto-evict settings.
+
+**If you still see duplicates:**
+- Update to the latest LEANN version
+- Restart LM Studio to clear loaded models
+- Check that you have JIT auto-evict enabled in LM Studio settings
+
+**How it works now:**
+1. LEANN loads model temporarily to get context length
+2. Immediately unloads after query
+3. LM Studio JIT loads model on-demand for actual embeddings
+4. Auto-evicts per your settings
+
+## 4. Do I need Node.js and @lmstudio/sdk?
+
+**No, it's completely optional.** LEANN works perfectly fine without them using a built-in token limit registry.
+
+**Benefits if you install it:**
+- Automatic context length detection for LM Studio models
+- No manual registry maintenance
+- Always gets accurate token limits from the model itself
+
+**To install (optional):**
+```bash
+npm install -g @lmstudio/sdk
+```
+
+See [Configuration Guide: LM Studio Auto-Detection](configuration-guide.md#lm-studio-auto-detection-optional) for details.

packages/leann-core/src/leann/api.py

@@ -916,6 +916,7 @@ def search(
         metadata_filters: Optional[dict[str, dict[str, Union[str, int, float, bool, list]]]] = None,
         batch_size: int = 0,
         use_grep: bool = False,
+        provider_options: Optional[dict[str, Any]] = None,
         **kwargs,
     ) -> list[SearchResult]:
         """
@@ -979,10 +980,24 @@ def search(
 
         start_time = time.time()
 
+        # Extract query template from stored embedding_options with fallback chain:
+        # 1. Check provider_options override (highest priority)
+        # 2. Check query_prompt_template (new format)
+        # 3. Check prompt_template (old format for backward compat)
+        # 4. None (no template)
+        query_template = None
+        if provider_options and "prompt_template" in provider_options:
+            query_template = provider_options["prompt_template"]
+        elif "query_prompt_template" in self.embedding_options:
+            query_template = self.embedding_options["query_prompt_template"]
+        elif "prompt_template" in self.embedding_options:
+            query_template = self.embedding_options["prompt_template"]
+
         query_embedding = self.backend_impl.compute_query_embedding(
             query,
             use_server_if_available=recompute_embeddings,
             zmq_port=zmq_port,
+            query_template=query_template,
         )
         logger.info(f"  Generated embedding shape: {query_embedding.shape}")
         embedding_time = time.time() - start_time

packages/leann-core/src/leann/cli.py

@@ -144,6 +144,18 @@ def create_parser(self) -> argparse.ArgumentParser:
             default=None,
             help="API key for embedding service (defaults to OPENAI_API_KEY)",
         )
+        build_parser.add_argument(
+            "--embedding-prompt-template",
+            type=str,
+            default=None,
+            help="Prompt template to prepend to all texts for embedding (e.g., 'query: ' for search)",
+        )
+        build_parser.add_argument(
+            "--query-prompt-template",
+            type=str,
+            default=None,
+            help="Prompt template for queries (different from build template for task-specific models)",
+        )
         build_parser.add_argument(
             "--force", "-f", action="store_true", help="Force rebuild existing index"
         )
@@ -260,6 +272,12 @@ def create_parser(self) -> argparse.ArgumentParser:
             action="store_true",
             help="Display file paths and metadata in search results",
         )
+        search_parser.add_argument(
+            "--embedding-prompt-template",
+            type=str,
+            default=None,
+            help="Prompt template to prepend to query for embedding (e.g., 'query: ' for search)",
+        )
 
         # Ask command
         ask_parser = subparsers.add_parser("ask", help="Ask questions")
@@ -1398,6 +1416,14 @@ async def build_index(self, args):
             resolved_embedding_key = resolve_openai_api_key(args.embedding_api_key)
             if resolved_embedding_key:
                 embedding_options["api_key"] = resolved_embedding_key
+        if args.query_prompt_template:
+            # New format: separate templates
+            if args.embedding_prompt_template:
+                embedding_options["build_prompt_template"] = args.embedding_prompt_template
+            embedding_options["query_prompt_template"] = args.query_prompt_template
+        elif args.embedding_prompt_template:
+            # Old format: single template (backward compat)
+            embedding_options["prompt_template"] = args.embedding_prompt_template
 
         builder = LeannBuilder(
             backend_name=args.backend_name,