UPDATE

app.py

@@ -104,17 +104,44 @@ async def generate_text(request: RequestModel):
         # 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
+
+    return {"summary_text_2": generated_text}
+@app.post("/generate2/")
+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=0.9,
+        # max_tokens=1024, 
+        stream=True
+    )
+  
+    generated_text = ""
+    for chunk in completion:
+        if chunk.choices[0].delta.content is not None:
+            generated_text += chunk.choices[0].delta.content
+
+    return {"summary_text_2": generated_text}
+
+@app.post("/generate3/")
+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": instructions_par_defaut  + request.text}],
+        temperature=0.2,
+        top_p=0.9,
+        # max_tokens=1024, 
+        stream=True
+    )
+  
     generated_text = ""
     for chunk in completion:
         if chunk.choices[0].delta.content is not None: