change

app.py

@@ -81,29 +81,29 @@ class RequestModel(BaseModel):
 @app.post("/generate/")
 async def generate_text(request: RequestModel):
     # Créer la requête pour l'API NVIDIA
-    completion = client.chat.completions.create(
-        model="meta/llama-3.1-8b-instruct", 
-        messages=[{"role": "user", "content": default_prompt + request.text}],
-        temperature=0.2,
-        top_p=0.7,
-        max_tokens=1024,
-        stream=True
-    )
-    # response = ollama.chat(
-    #     model="llama3",
-    #     messages=[
-    #         {
-    #             "role": "user",
-    #             "content": default_prompt + request.text,
-    #         },
-    #     ],
+    # completion = client.chat.completions.create(
+    #     model="meta/llama-3.1-8b-instruct", 
+    #     messages=[{"role": "user", "content": default_prompt + request.text}],
+    #     temperature=0.2,
+    #     top_p=0.7,
+    #     max_tokens=1024,
+    #     stream=True
     # )
+    response = ollama.chat(
+        model="llama3",
+        messages=[
+            {
+                "role": "user",
+                "content": default_prompt + request.text,
+            },
+        ],
+    )
     # Générer le texte en temps réel
     
-    generated_text = ""
-    for chunk in completion:
-        if chunk.choices[0].delta.content is not None:
-            generated_text += chunk.choices[0].delta.content
+    generated_text = response["message"]["content"]
+    # for chunk in completion:
+    #     if chunk.choices[0].delta.content is not None:
+    #         generated_text += chunk.choices[0].delta.content
 
     return {"generated_text": generated_text}
 if __name__ == "__main__":