pin models: parasail-qwen3-235b on Parasail, qwen2.5:14b locally

1 files changed, 9 insertions, 22 deletions

diff --git a/main.py b/main.py
index b6d57dc..d5c73ec 100644
--- a/main.py
+++ b/main.py
@@ -65,35 +65,22 @@ log.info("Connected as %s", client.email)
 # LLM client setup: Parasail primary, Ollama fallback
 # ---------------------------------------------------------------------------
 
+# Model config: big Qwen3 on Parasail, smaller local Qwen2.5 as fallback
+PARASAIL_MODEL = "parasail-qwen3-235b-a22b-instruct-2507"
+OLLAMA_MODEL = "qwen2.5:14b-instruct-q4_K_M"
+
+
 def _make_llm_client() -> tuple[OpenAI, str]:
     """Return (openai_client, model_name) for the best available backend."""
     parasail_key = os.environ.get("PARASAIL_API_KEY", "")
     if parasail_key:
-        log.info("Calling Parasail for LLM response")
-        # Prefer a small/fast model; fall back to Llama if unavailable
-        try:
-            r = requests.get(
-                "https://api.parasail.io/v1/models",
-                headers={"Authorization": f"Bearer {parasail_key}"},
-                timeout=8,
-            )
-            model_ids = [m["id"] for m in r.json().get("data", [])]
-            log.info("Parasail available models: %s", model_ids)
-            preferred = ["qwen3-4b", "meta-llama/Llama-3.1-8B-Instruct"]
-            model = next((m for m in preferred if m in model_ids), None)
-            if model is None and model_ids:
-                model = model_ids[0]
-            model = model or "meta-llama/Llama-3.1-8B-Instruct"
-        except Exception as e:
-            log.warning("Could not fetch Parasail models (%s); using default", e)
-            model = "meta-llama/Llama-3.1-8B-Instruct"
-
+        log.info("Using Parasail model: %s", PARASAIL_MODEL)
         c = OpenAI(api_key=parasail_key, base_url="https://api.parasail.io/v1")
-        return c, model
+        return c, PARASAIL_MODEL
 
-    log.info("Calling Ollama for LLM response")
+    log.info("Using Ollama model: %s", OLLAMA_MODEL)
     c = OpenAI(api_key="ollama", base_url="http://localhost:11434/v1")
-    return c, "qwen2.5:3b"
+    return c, OLLAMA_MODEL
 
 
 # ---------------------------------------------------------------------------