chore: nettoyage .gitignore - retrait venv, __pycache__, .env, data, logs, modèles du tracking

core/llm.py

@@ -22,7 +22,6 @@ class LLMManager:
         self.model_name = model_name
         self.base_url = base_url or os.environ.get("OLLAMA_BASE_URL", "http://localhost:11434")
         self.temperature = temperature
-        self._lock = asyncio.Lock()
     
     def build_payload(
         self,
@@ -51,60 +50,59 @@ class LLMManager:
     
     async def call_llama(self, payload: Dict[str, Any]) -> str:
         """Call Ollama Generate API and stream response."""
-        async with self._lock:
-            try:
-                # Automatic payload conversion for legacy compatibility (e.g. from moderation.py)
-                ollama_payload = {
-                    "model": payload.get("model", self.model_name),
-                    "prompt": payload["prompt"],
-                    "system": payload.get("system", payload.get("system_prompt", "Tu es une IA serviable.")),
-                    "stream": True,  # Streaming pour voir la réponse en direct
-                    "think": False,  # Désactive le reasoning GPT-OSS
-                    "format": "",
-                    "options": {
-                        "temperature": payload.get("temperature", self.temperature),
-                        "num_ctx": payload.get("n_ctx", 16384),
-                        "num_predict": payload.get("max_tokens") or payload.get("num_predict", 8192),
-                        "repeat_penalty": payload.get("repeat_penalty") or payload.get("repeat_last_n", 1.2),
-                        "stop": payload.get("stop", [])
-                    }
+        try:
+            # Automatic payload conversion for legacy compatibility (e.g. from moderation.py)
+            ollama_payload = {
+                "model": payload.get("model", self.model_name),
+                "prompt": payload["prompt"],
+                "system": payload.get("system", payload.get("system_prompt", "Tu es une IA serviable.")),
+                "stream": True,  # Streaming pour voir la réponse en direct
+                "think": False,  # Désactive le reasoning GPT-OSS
+                "format": "",
+                "options": {
+                    "temperature": payload.get("temperature", self.temperature),
+                    "num_ctx": payload.get("n_ctx", 16384),
+                    "num_predict": payload.get("max_tokens") or payload.get("num_predict", 8192),
+                    "repeat_penalty": payload.get("repeat_penalty") or payload.get("repeat_last_n", 1.2),
+                    "stop": payload.get("stop", [])
                 }
+            }
 
-                accumulated_reply = ""
-                api_url = f"{self.base_url}/api/generate"
+            accumulated_reply = ""
+            api_url = f"{self.base_url}/api/generate"
+            
+            # Build headers with optional API key
+            headers = {}
+            api_key = os.environ.get("OLLAMA_API_KEY", "")
+            if api_key:
+                headers["Authorization"] = f"Bearer {api_key}"
+
+            async with aiohttp.ClientSession() as session:
+                async with session.post(api_url, json=ollama_payload, headers=headers) as response:
+                    if response.status != 200:
+                        err_text = await response.text()
+                        logger.error(f"Ollama API Error ({response.status}): {err_text}")
+                        return ""
+
+                    # Streaming en direct dans le terminal
+                    async for line in response.content:
+                        if line:
+                            try:
+                                chunk = json.loads(line)
+                                resp = chunk.get("response", "")
+                                if resp:
+                                    accumulated_reply += resp
+                                    print(resp, end="", flush=True)
+                                if chunk.get("done"):
+                                    break
+                            except json.JSONDecodeError:
+                                continue
+                    print()
+                    return accumulated_reply.strip()
                 
-                # Build headers with optional API key
-                headers = {}
-                api_key = os.environ.get("OLLAMA_API_KEY", "")
-                if api_key:
-                    headers["Authorization"] = f"Bearer {api_key}"
-
-                async with aiohttp.ClientSession() as session:
-                    async with session.post(api_url, json=ollama_payload, headers=headers) as response:
-                        if response.status != 200:
-                            err_text = await response.text()
-                            logger.error(f"Ollama API Error ({response.status}): {err_text}")
-                            return ""
-
-                        # Streaming en direct dans le terminal
-                        async for line in response.content:
-                            if line:
-                                try:
-                                    chunk = json.loads(line)
-                                    resp = chunk.get("response", "")
-                                    if resp:
-                                        accumulated_reply += resp
-                                        print(resp, end="", flush=True)
-                                    if chunk.get("done"):
-                                        break
-                                except json.JSONDecodeError:
-                                    continue
-                        print()
-                        return accumulated_reply.strip()
-                
-            except Exception as e:
-                logger.error(f"Error calling Ollama: {e}")
-                return ""
+        except Exception as e:
+            logger.error(f"Error calling Ollama: {e}")
+            return ""
 
     async def close_session(self):
         pass