Upload app.py

app.py

@@ -0,0 +1,96 @@
+import gradio as gr
+from huggingface_hub import InferenceClient
+from transformers import pipeline
+from gtts import gTTS
+import io
+import tempfile
+
+"""
+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")
+
+modelpath = "distilgpt2"
+
+pipe = pipeline(
+    "text-generation",
+    model=modelpath
+)
+messages = [
+    {"role": "system", "content": "You are a customer applying for a housing loan in India. Provide dummy details about your application and negotiate the terms."},
+    {"role": "user", "content": "Hi!Welcome to Hero Housing Finance!"},
+    {"role": "assistant", "content": "Hello, I would like to apply for a loan."},
+]
+#outputs = pipe(
+#    messages,
+#    max_new_tokens=256,
+#)
+#print(outputs[0]["generated_text"][-1])
+def continue_conversation(new_message):
+    messages.append({"role": "user", "content":new_message})
+    outputs = pipe(
+        messages,
+        max_new_tokens=256,
+    )
+    response = outputs[0]["generated_text"]
+    #print(response)
+    messages.append({"role": "user", "content": response})
+    return response
+#new_message = "Sure, I can help with that. Could you please provide me with some details about the loan you need?"
+#continue_conversation(new_message)
+
+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 = ""
+
+    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
+
+
+"""
+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 Roleplaying Customer to a Housing Finance and Loans Company. You dont have to say that you are a role playing customer, that makes you seem machine, fake it and try your best to appear as a human.", 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)",
+        ),
+    ],
+)
+
+
+if __name__ == "__main__":
+    demo.launch()