Fix error Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

README.md

@@ -173,7 +173,7 @@ headers = {"api-key": AZURE_API_KEY, "Content-Type": "application/json"}
 payload = {
     "model": "gpt-5",
     "messages": [{"role": "user", "content": prompt}],
-    "max_tokens": 512,
+    "max_completion_tokens": 512,
     "temperature": 0.7,
     "top_p": 0.95,
 }
@@ -508,7 +508,7 @@ Then edit `data/config.json`:
     "llm": {
         "endpoint_url": "https://<your-resource>.openai.azure.com/openai/deployments/<your-deployment>/chat/completions?api-version=2024-12-01-preview",
         "model": "gpt-5",
-        "max_tokens": 512,
+        "max_completion_tokens": 512,
         "temperature": 0.7,
         "top_p": 0.95
     }

app.py

@@ -75,7 +75,7 @@ EMBEDDING_MODEL_NAME = _config["embedding"]["model"]
 # LLM (Azure OpenAI)
 LLM_ENDPOINT_URL = _config["llm"]["endpoint_url"]
 LLM_MODEL_NAME = _config["llm"]["model"]
-LLM_MAX_TOKENS = _config["llm"].get("max_tokens", 512)
+LLM_MAX_TOKENS = _config["llm"].get("max_completion_tokens", 512)
 LLM_TEMPERATURE = _config["llm"].get("temperature", 0.7)
 LLM_TOP_P = _config["llm"].get("top_p", 0.95)
 
@@ -270,7 +270,7 @@ def call_llm(prompt: str) -> str:
     payload = {
         "model": LLM_MODEL_NAME,
         "messages": [{"role": "user", "content": prompt}],
-        "max_tokens": LLM_MAX_TOKENS,
+        "max_completion_tokens": LLM_MAX_TOKENS,
         "temperature": LLM_TEMPERATURE,
         "top_p": LLM_TOP_P,
     }

config.json

@@ -1,13 +1,14 @@
 {
     "embedding": {
-        "endpoint_url": "https://hackathon-eiffel-2026-apim.azure-api.net/ai/models/openai/deployments/text-embedding-3/embeddings?api-version=2024-12-01-preview",
-        "model": "text-embedding-3"
+        "endpoint_url": "https://hackathon-eiffel-2026-apim.azure-api.net/ai/openai/deployments/text-embedding-3-small/embeddings?api-version=2024-12-01-preview",
+        "model": "text-embedding-3-small"
     },
     "llm": {
-        "endpoint_url": "https://hackathon-eiffel-2026-apim.azure-api.net/ai/models/openai/deployments/gpt-5/chat/completions?api-version=2024-12-01-preview",
-        "model": "gpt-5",
-        "max_tokens": 512,
+        "endpoint_url": "https://hackathon-eiffel-2026-apim.azure-api.net/ai/openai/deployments/gpt-5.1/chat/completions?api-version=2024-12-01-preview",
+        "model": "gpt-5.1",
+        "max_completion_tokens": 512,
         "temperature": 0.7,
         "top_p": 0.95
     }
+
 }