Update app.py

app.py

@@ -227,11 +227,19 @@ def StreamLLMChatResponse(prompt):
     except:
         st.write('Llama model is asleep. Starting up now on A10 - please give 5 minutes then retry as KEDA scales up from zero to activate running container(s).')
 
-# 4. Run query with payload
-def query(payload):
-    response = requests.post(API_URL, headers=headers, json=payload)
-    st.markdown(response.json())
+def query(filename):
+    with open(filename, "rb") as f:
+        data = f.read
+    st.write('Posting request to model ' + API_URL_IE)
+    response = requests.post(API_URL_IE, headers=headers, data=data)
     return response.json()
+    
+# 4. Run query with payload
+#def query(payload):
+#    response = requests.post(API_URL, headers=headers, json=payload)
+#    st.markdown(response.json())
+#    return response.json()
+    
 def get_output(prompt):
     return query({"inputs": prompt})
 
@@ -518,8 +526,8 @@ def get_zip_download_link(zip_file):
 #API_URL_IE = "https://api-inference.huggingface.co/models/openai/whisper-small.en"
 # Latest small - 1/26
 API_URL_IE = "https://api-inference.huggingface.co/models/openai/whisper-small"
-MODEL2 = "openai/whisper-small.en"
-MODEL2_URL = "https://huggingface.co/openai/whisper-small.en"
+#MODEL2 = "openai/whisper-small.en"
+#MODEL2_URL = "https://huggingface.co/openai/whisper-small.en"
 
 HF_KEY = st.secrets['HF_KEY']
 headers = {
@@ -528,12 +536,7 @@ headers = {
 }
 
 #@st.cache_resource
-def query(filename):
-    with open(filename, "rb") as f:
-        data = f.read
-    st.write('Posting request to model ' + API_URL_IE)
-    response = requests.post(API_URL_IE, headers=headers, data=data)
-    return response.json()
+
 
 def generate_filename(prompt, file_type):
     central = pytz.timezone('US/Central')