Merge pull request #164 from ggozad/feat/lm_studio

Support LMStudio

CHANGELOG.md

@@ -1,6 +1,13 @@
 # Changelog
 ## [Unreleased]
 
+### Added
+
+- **LM Studio Provider**: Added support for LM Studio as a provider for embeddings and QA/research models
+  - Configure with `provider: lm_studio` in embeddings, QA, or research model settings
+  - Supports thinking control for reasoning models (gpt-oss, etc.)
+  - Default base URL: `http://localhost:1234`
+
 ### Fixed
 
 - **Configuration**: Fixed `init-config` command generating invalid configuration files (#165)

README.md

@@ -7,8 +7,8 @@ Retrieval-Augmented Generation (RAG) library built on LanceDB.
 ## Features
 
 - **Local LanceDB**: No external servers required, supports also LanceDB cloud storage, S3, Google Cloud & Azure
-- **Multiple embedding providers**: Ollama, VoyageAI, OpenAI, vLLM
+- **Multiple embedding providers**: Ollama, LM Studio, VoyageAI, OpenAI, vLLM
-- **Multiple QA providers**: Any provider/model supported by Pydantic AI
+- **Multiple QA providers**: Any provider/model supported by Pydantic AI (Ollama, LM Studio, OpenAI, Anthropic, etc.)
 - **Native hybrid search**: Vector + full-text search with native LanceDB RRF reranking
 - **Reranking**: Default search result reranking with MixedBread AI, Cohere, Zero Entropy, or vLLM
 - **Question answering**: Built-in QA agents on your documents

docs/configuration/providers.md

@@ -59,6 +59,7 @@ See the [Pydantic AI thinking documentation](https://ai.pydantic.dev/thinking/)
 - **Bedrock**: Claude, OpenAI, and Qwen models
 - **Ollama**: Models supporting reasoning (gpt-oss, etc.)
 - **vLLM**: Models supporting reasoning (gpt-oss, etc.)
+- **LM Studio**: Models supporting reasoning (gpt-oss, etc.)
 
 **When to use:**
 - Disable for simple queries, RAG workflows, speed-critical applications
@@ -148,6 +149,23 @@ providers:
 
 **Note:** You need to run a vLLM server separately with an embedding model loaded.
 
+### LM Studio
+
+[LM Studio](https://lmstudio.ai/) provides a local OpenAI-compatible API server for running models:
+
+```yaml
+embeddings:
+  provider: lm_studio
+  model: text-embedding-qwen3-embedding-4b
+  vector_dim: 2560
+
+providers:
+  lm_studio:
+    base_url: http://localhost:1234
+```
+
+**Note:** LM Studio must be running with an embedding model loaded. The default URL is `http://localhost:1234`.
+
 ## Question Answering Providers
 
 Configure which LLM provider to use for question answering. Any provider and model supported by [Pydantic AI](https://ai.pydantic.dev/models/) can be used.
@@ -226,6 +244,29 @@ providers:
 
 **Note:** You need to run a vLLM server separately with a model that supports tool calling loaded. Consult the specific model's documentation for proper vLLM serving configuration.
 
+### LM Studio
+
+Use LM Studio for local question answering and research:
+
+```yaml
+qa:
+  model:
+    provider: lm_studio
+    name: openai/gpt-oss-20b
+    enable_thinking: false
+
+research:
+  model:
+    provider: lm_studio
+    name: openai/gpt-oss-20b
+
+providers:
+  lm_studio:
+    base_url: http://localhost:1234
+```
+
+**Note:** LM Studio must be running with a chat model that supports tool calling loaded.
+
 ### Other Providers
 
 Any provider supported by Pydantic AI can be used. Examples:

haiku_rag_slim/haiku/rag/config/__init__.py

@@ -11,6 +11,7 @@ from haiku.rag.config.models import (
     ConversionOptions,
     EmbeddingsConfig,
     LanceDBConfig,
+    LMStudioConfig,
     MonitorConfig,
     OllamaConfig,
     ProcessingConfig,
@@ -36,6 +37,7 @@ __all__ = [
     "ResearchConfig",
     "ProcessingConfig",
     "OllamaConfig",
+    "LMStudioConfig",
     "VLLMConfig",
     "ProvidersConfig",
     "find_config_file",

haiku_rag_slim/haiku/rag/config/models.py

@@ -135,9 +135,14 @@ class DoclingServeConfig(BaseModel):
     timeout: int = 300
 
 
+class LMStudioConfig(BaseModel):
+    base_url: str = "http://localhost:1234"
+
+
 class ProvidersConfig(BaseModel):
     ollama: OllamaConfig = Field(default_factory=OllamaConfig)
     vllm: VLLMConfig = Field(default_factory=VLLMConfig)
+    lm_studio: LMStudioConfig = Field(default_factory=LMStudioConfig)
     docling_serve: DoclingServeConfig = Field(default_factory=DoclingServeConfig)
 
 

haiku_rag_slim/haiku/rag/embeddings/__init__.py

@@ -46,4 +46,11 @@ def get_embedder(config: AppConfig = Config) -> EmbedderBase:
             config.embeddings.model, config.embeddings.vector_dim, config
         )
 
+    if config.embeddings.provider == "lm_studio":
+        from haiku.rag.embeddings.lm_studio import Embedder as LMStudioEmbedder
+
+        return LMStudioEmbedder(
+            config.embeddings.model, config.embeddings.vector_dim, config
+        )
+
     raise ValueError(f"Unsupported embedding provider: {config.embeddings.provider}")

haiku_rag_slim/haiku/rag/embeddings/lm_studio.py

@@ -0,0 +1,28 @@
+from typing import overload
+
+from openai import AsyncOpenAI
+
+from haiku.rag.embeddings.base import EmbedderBase
+
+
+class Embedder(EmbedderBase):
+    @overload
+    async def embed(self, text: str) -> list[float]: ...
+
+    @overload
+    async def embed(self, text: list[str]) -> list[list[float]]: ...
+
+    async def embed(self, text: str | list[str]) -> list[float] | list[list[float]]:
+        client = AsyncOpenAI(
+            base_url=f"{self._config.providers.lm_studio.base_url}/v1", api_key="dummy"
+        )
+        if not text:
+            return []
+        response = await client.embeddings.create(
+            model=self._model,
+            input=text,
+        )
+        if isinstance(text, str):
+            return response.data[0].embedding
+        else:
+            return [item.embedding for item in response.data]

haiku_rag_slim/haiku/rag/utils.py

@@ -233,6 +233,29 @@ def get_model(
             settings=vllm_settings,
         )
 
+    elif provider == "lm_studio":
+        model_settings = None
+
+        # Apply thinking control for gpt-oss
+        if model == "gpt-oss" and model_config.enable_thinking is not None:
+            if model_config.enable_thinking is False:
+                model_settings = OpenAIChatModelSettings(openai_reasoning_effort="low")
+            else:
+                model_settings = OpenAIChatModelSettings(openai_reasoning_effort="high")
+
+        model_settings = apply_common_settings(
+            model_settings, OpenAIChatModelSettings, model_config
+        )
+
+        return OpenAIChatModel(
+            model_name=model,
+            provider=OpenAIProvider(
+                base_url=f"{app_config.providers.lm_studio.base_url}/v1",
+                api_key="dummy",
+            ),
+            settings=model_settings,
+        )
+
     else:
         # For any other provider, use string format and let Pydantic AI handle it
         return f"{provider}:{model}"

tests/test_embedder_config.py

@@ -3,6 +3,7 @@ import pytest
 from haiku.rag.config import (
     AppConfig,
     EmbeddingsConfig,
+    LMStudioConfig,
     OllamaConfig,
     ProvidersConfig,
     VLLMConfig,
@@ -71,6 +72,28 @@ def test_openai_embedder_uses_config():
     assert embedder._config == custom_config
 
 
+def test_lm_studio_embedder_uses_config():
+    """Test that lm_studio embedder uses the config passed to get_embedder."""
+    custom_config = AppConfig(
+        embeddings=EmbeddingsConfig(
+            provider="lm_studio",
+            model="custom-lm-studio-model",
+            vector_dim=1024,
+        ),
+        providers=ProvidersConfig(
+            lm_studio=LMStudioConfig(base_url="http://custom-lmstudio:5678"),
+        ),
+    )
+
+    embedder = get_embedder(custom_config)
+
+    assert embedder._model == "custom-lm-studio-model"
+    assert embedder._vector_dim == 1024
+    assert (
+        embedder._config.providers.lm_studio.base_url == "http://custom-lmstudio:5678"
+    )
+
+
 @pytest.mark.skipif(
     True, reason="VoyageAI is an optional dependency, may not be installed"
 )