Fix: build_models resolves separate AsyncOpenAI clients for judge and embedding models

Previously, only the judge_model's profile was looked up and its AsyncOpenAI

client was shared with embedding_factory. When embedding_model has a different

base_url/api_key (e.g. Qwen3-Embedding-4B on SiliconFlow vs gpt-5 on another

gateway), the embedding calls silently used the wrong URL, causing 402/404 errors.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

rag_eval/metrics/factory.py

@@ -98,19 +98,26 @@ def build_models(
 ) -> tuple[Any, Any]:
     """Create the LLM and embedding clients required by the selected RAGAS metrics.
 
-    Dynamically resolves connection settings from the stored LLM Profiles first
-    (matched by model name), falling back to .env settings when no profile matches.
+    Resolves connection settings independently for the judge LLM and the embedding
+    model by looking up each in the stored LLM Profiles (matched by model name).
+    This allows judge_model and embedding_model to use different gateways / API keys.
+    Falls back to .env settings when no matching profile is found.
     """
-    client_kwargs = _resolve_openai_client_kwargs(judge_model, settings)
-    client = AsyncOpenAI(**client_kwargs)
+    llm_kwargs = _resolve_openai_client_kwargs(judge_model, settings)
+    emb_kwargs = _resolve_openai_client_kwargs(embedding_model, settings)
+
+    llm_client = AsyncOpenAI(**llm_kwargs)
+    # Only allocate a second client when the embedding model needs different settings.
+    emb_client = AsyncOpenAI(**emb_kwargs) if emb_kwargs != llm_kwargs else llm_client
+
     # RAGAS structured-output judge calls can be truncated by the upstream default
     # 1024 completion budget, especially for faithfulness and GPT-5 family models.
     llm = llm_factory(
         judge_model,
-        client=client,
+        client=llm_client,
         max_tokens=max(1, int(settings.ragas_llm_max_tokens)),
     )
-    embeddings = embedding_factory(provider="openai", model=embedding_model, client=client)
+    embeddings = embedding_factory(provider="openai", model=embedding_model, client=emb_client)
     return llm, embeddings