Update app.py

app.py

@@ -1,53 +1,54 @@
 import os
 os.system('pip install transformers')
 os.system('pip install datasets')
-os.system('pip install gradio')
-os.system('pip install minijinja')
-os.system('pip install PyMuPDF')
 
 import gradio as gr
 from huggingface_hub import InferenceClient
 from transformers import pipeline
 from datasets import load_dataset
-import fitz  # PyMuPDF
-
-client = InferenceClient()
 
 dataset = load_dataset("ibunescu/qa_legal_dataset_train")
 
-def score_argument_from_outcome(outcome, argument):
-    prosecutor_score = 0
-    if "Prosecutor" in outcome:
-        prosecutor_score = outcome.count("Prosecutor") * 2
-        if "won" in outcome and "Prosecutor" in outcome:
-            prosecutor_score += 10
-    return prosecutor_score
-
-def chat_between_bots(system_message1, system_message2, max_tokens, temperature, top_p, history1, history2, shared_history, message):
-    response1, history1 = list(respond(message, history1, system_message1, max_tokens, temperature, top_p))[-1]
-    response2, history2 = list(respond(message, history2, system_message2, max_tokens, temperature, top_p))[-1]
-    
-    return response1, response2, history1, history2, shared_history
+# Use a pipeline as a high-level helper
+pipe = pipeline("fill-mask", model="nlpaueb/legal-bert-base-uncased")
+
+"""
+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 extract_text_from_pdf(pdf_file):
-    text = ""
-    doc = fitz.open(pdf_file)
-    for page in doc:
-        text += page.get_text()
-    return text
+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})
 
-def ask_about_pdf(pdf_text, question):
-    prompt = f"PDF Content: {pdf_text}\n\nQuestion: {question}\n\nAnswer:"
     response = ""
+
     for message in client.chat_completion(
-        [{"role": "system", "content": "You are a legal expert answering questions based on the PDF content provided."},
-         {"role": "user", "content": prompt}],
-        max_tokens=512,
+        messages,
+        max_tokens=max_tokens,
         stream=True,
-        temperature=0.6,
-        top_p=0.95,
+        temperature=temperature,
+        top_p=top_p,
     ):
         token = message.choices[0].delta.content
+
+        response += token
+        yield response
+        token = message.choices[0].delta.content
         if token is not None:
             response += token
     return response