Update app.py

app.py

@@ -1,61 +1,60 @@
+from omegaconf import OmegaConf
+from query import VectaraQuery
+import os
+
+from PIL import Image
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+# """
+# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+# """
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+# def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p):
+#     messages = [{"role": "system", "content": system_message}]
+
+#     for val in history:
+#         if val[0]:
+#             messages.append({"role": "user", "content": val[0]})
+#         if val[1]:
+#             messages.append({"role": "assistant", "content": val[1]})
+
+#     messages.append({"role": "user", "content": message})
 
+#     response = ""
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+#     for message in client.chat_completion(messages, max_tokens=max_tokens, stream=True, temperature=temperature, top_p=top_p):
+#         token = message.choices[0].delta.content
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+#         response += token
+#         yield response
 
-    messages.append({"role": "user", "content": message})
+corpus_ids = str(os.environ['corpus_ids']).split(',')
+cfg = OmegaConf.create({
+    'customer_id': str(os.environ['customer_id']),
+    'corpus_ids': corpus_ids,
+    'api_key': str(os.environ['api_key']),
+    'title': os.environ['title'],
+    'description': os.environ['description'],
+    'source_data_desc': os.environ['source_data_desc'],
+    'streaming': isTrue(os.environ.get('streaming', False)),
+    'prompt_name': os.environ.get('prompt_name', None)
+})
 
-    response = ""
+def random_fun(message, history):
+    return message + '!'
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
 
-        response += token
-        yield response
+demo = gr.ChatInterface(random_fun, title = cfg.title, description = cfg.description)
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
 demo = gr.ChatInterface(
     respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+    
 )