Update app.py

app.py

@@ -1,64 +1,37 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+import os
+import re
+from dotenv import load_dotenv
+load_dotenv()
 
-"""
-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")
+from langchain.agents.openai_assistant import OpenAIAssistantRunnable
+from langchain.agents import AgentExecutor
 
+from langchain.schema import HumanMessage, AIMessage
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+import gradio
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+api_key = os.getenv('OPENAI_API_KEY')
+extractor_agent = os.getenv('ASSISTANT_ID_DECASTRO')
 
-    messages.append({"role": "user", "content": message})
+extractor_llm = OpenAIAssistantRunnable(assistant_id=extractor_agent, api_key=api_key, as_agent=True)
 
-    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
+def remove_citation(text):
+    # Define the regex pattern to match the citation format 【number†text】
+    pattern = r"【\d+†\w+】"
+    # Replace the pattern with an empty string
+    return re.sub(pattern, "📚", text)
 
-        response += token
-        yield response
+def predict(message, history):
+    history_langchain_format = []
+    for human, ai in history:
+        history_langchain_format.append(HumanMessage(content=human))
+        history_langchain_format.append(AIMessage(content=ai))
+    history_langchain_format.append(HumanMessage(content=message))
+    gpt_response = extractor_llm.invoke({"content": message})
+    output = gpt_response.return_values["output"]
+    non_cited_output = remove_citation(output)
+    return non_cited_output
 
-
-"""
-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)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+chat = gradio.ChatInterface(predict, title="Solution Specifier", description="testing for the time being")
+chat.launch(share=True)