From 3141c91023fb1700150bf084e08f41a2728a4c61 Mon Sep 17 00:00:00 2001
From: Yiorgis Gozadinos <ggozadinos@gmail.com>
Date: Wed, 24 Dec 2025 12:33:44 +0200
Subject: [PATCH] Add base_url to ModelConfig and EmbeddingModelConfig.
 Deprecate vllm and lm_studio configs, now through open ai

---
 haiku_rag_slim/haiku/rag/config/models.py |  6 ++-
 haiku_rag_slim/haiku/rag/utils.py         | 61 +++++------------------
 2 files changed, 17 insertions(+), 50 deletions(-)

diff --git a/haiku_rag_slim/haiku/rag/config/models.py b/haiku_rag_slim/haiku/rag/config/models.py
index 7048de89..2e6c5e1e 100644
--- a/haiku_rag_slim/haiku/rag/config/models.py
+++ b/haiku_rag_slim/haiku/rag/config/models.py
@@ -12,6 +12,7 @@ class ModelConfig(BaseModel):
     Attributes:
         provider: Model provider (ollama, openai, anthropic, etc.)
         name: Model name/identifier
+        base_url: Optional base URL for OpenAI-compatible servers (vLLM, LM Studio, etc.)
         enable_thinking: Control reasoning behavior (true/false/None for default)
         temperature: Sampling temperature (0.0 to 1.0+)
         max_tokens: Maximum tokens to generate
@@ -19,6 +20,7 @@ class ModelConfig(BaseModel):
 
     provider: str = "ollama"
     name: str = "gpt-oss"
+    base_url: str | None = None
 
     enable_thinking: bool | None = None
     temperature: float | None = None
@@ -29,14 +31,16 @@ class EmbeddingModelConfig(BaseModel):
     """Configuration for an embedding model.
 
     Attributes:
-        provider: Model provider (ollama, openai, voyageai, vllm, lm_studio)
+        provider: Model provider (ollama, openai, voyageai, cohere, sentence-transformers)
         name: Model name/identifier
         vector_dim: Vector dimensions produced by the model
+        base_url: Optional base URL for OpenAI-compatible servers (vLLM, LM Studio, etc.)
     """
 
     provider: str = "ollama"
     name: str = "qwen3-embedding:4b"
     vector_dim: int = 2560
+    base_url: str | None = None
 
 
 class StorageConfig(BaseModel):
diff --git a/haiku_rag_slim/haiku/rag/utils.py b/haiku_rag_slim/haiku/rag/utils.py
index 2b8b3fd8..67c15d6b 100644
--- a/haiku_rag_slim/haiku/rag/utils.py
+++ b/haiku_rag_slim/haiku/rag/utils.py
@@ -135,11 +135,12 @@ def get_model(
             model_settings, OpenAIChatModelSettings, model_config
         )
 
+        # Use model-level base_url if set, otherwise fall back to providers config
+        base_url = model_config.base_url or f"{app_config.providers.ollama.base_url}/v1"
+
         return OpenAIChatModel(
             model_name=model,
-            provider=OllamaProvider(
-                base_url=f"{app_config.providers.ollama.base_url}/v1"
-            ),
+            provider=OllamaProvider(base_url=base_url),
             settings=model_settings,
         )
 
@@ -159,6 +160,14 @@ def get_model(
             openai_settings, OpenAIChatModelSettings, model_config
         )
 
+        # Use model-level base_url if set (for vLLM, LM Studio, etc.)
+        if model_config.base_url:
+            return OpenAIChatModel(
+                model_name=model,
+                provider=OpenAIProvider(base_url=model_config.base_url),
+                settings=openai_settings,
+            )
+
         return OpenAIChatModel(model_name=model, settings=openai_settings)
 
     elif provider == "anthropic":
@@ -264,52 +273,6 @@ def get_model(
 
         return BedrockConverseModel(model_name=model, settings=bedrock_settings)
 
-    elif provider == "vllm":
-        vllm_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:
-                vllm_settings = OpenAIChatModelSettings(openai_reasoning_effort="low")
-            else:
-                vllm_settings = OpenAIChatModelSettings(openai_reasoning_effort="high")
-
-        vllm_settings = apply_common_settings(
-            vllm_settings, OpenAIChatModelSettings, model_config
-        )
-
-        return OpenAIChatModel(
-            model_name=model,
-            provider=OpenAIProvider(
-                base_url=f"{app_config.providers.vllm.research_base_url or app_config.providers.vllm.qa_base_url}/v1",
-                api_key="none",
-            ),
-            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}"