add groq

app.py

@@ -3,9 +3,16 @@ import faster_whisper
 import gradio as gr
 from dotenv import load_dotenv
 from huggingface_hub import InferenceClient
+from groq import Groq
 
 # Load API key dari .env
 load_dotenv()
+GROQ_API_KEY = os.getenv("GROQ_API_KEY")
+
+if not GROQ_API_KEY:
+    raise ValueError("GROQ API NOT FOUND!")
+gclient = Groq(api_key=GROQ_API_KEY)
+
 HF_API_KEY = os.getenv("HF_API_KEY")
 
 if not HF_API_KEY:
@@ -28,6 +35,24 @@ MODEL_OPTIONS = [
 ]
 
 
+def chat_with_groq(message):
+    """Handles conversation with Groq LLM."""
+    response = gclient.chat.completions.create(
+        model="deepseek-r1-distill-llama-70b",
+        messages=[
+            {
+                "role": "system",
+                "content": "You are a customer service assistant. Follow instructions and reply in Indonesian.",
+            },
+            {"role": "user", "content": message},
+        ],
+        temperature=1.0,
+        max_tokens=2048,
+        max_retries=2,
+    )
+    return response.choices[0].message["content"]  # Extract response text
+
+
 def save_to_file(content, filename):
     with open(filename, "w", encoding="utf-8") as file:
         file.write(content)
@@ -65,10 +90,11 @@ def generate_soap_summary(transcription_text, selected_model):
     messages = [
         {"role": "user", "content": template.format(dialogue=transcription_text)}
     ]
-    response = huggingface_client.chat.completions.create(
-        model=selected_model, messages=messages, max_tokens=1000, stream=False
-    )
-    soap = response.choices[0].message.content.strip()
+    # response = huggingface_client.chat.completions.create(
+    #     model=selected_model, messages=messages, max_tokens=1000, stream=False
+    # )
+    # soap = response.choices[0].message.content.strip()
+    soap = chat_with_groq(messages)
     return soap, save_to_file(soap, "soap_summary.txt")
 
 

requirements.txt

@@ -2,3 +2,4 @@ faster_whisper==1.1.1
 gradio==5.17.0
 huggingface_hub==0.28.1
 python-dotenv==1.0.1
+groq