Update app.py

app.py

@@ -1,63 +1,94 @@
 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")
-
-
-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 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)",
-        ),
-    ],
-)
+import os
+from openai import OpenAI
+import time
+from PyPDF2 import PdfReader
+read_key = os.environ.get('passw_rr', None)
 
+assistant_id = os.environ.get('assist_id_rr_robot', None)
+client = OpenAI(organization=os.environ.get('AI_org', None), api_key=os.environ.get('AI_key', None))
 
+# Step 2: Create a Thread
+thread = client.beta.threads.create()
+print(thread.id)
+
+# plocka ut text från fil om sådan bifogas
+
+def pdf_to_text(pdf_file):
+  pdf_text = ''
+  pdf_reader = PdfReader(pdf_file)
+  for page in range(len(pdf_reader.pages)):
+    text = pdf_reader.pages[page].extract_text()
+    pdf_text = pdf_text + '\n' + text
+  return pdf_text
+
+def txt_to_text(text_file):
+  with open(text_file, 'r') as f:
+      txt_text = f.read()
+  return txt_text
+
+
+def read_file(file_path):
+  if file_path.endswith('.pdf'): # för pdf, ska jag läsa den eller bara kasta in i assistenten rakt av?
+    text = pdf_to_text(file_path)
+  if file_path.endswith('.txt'):
+    text = txt_to_text(file_path)
+  return text
+
+def main(query,history):
+
+  # Hämta fil-innehåll
+    file_content = ''
+    prompt = query["text"]
+    if len(query["files"]) > 0: #if "files" in message:
+        file_path = query["files"][0]
+        file_content = read_file(file_path)
+    
+    total_message = prompt + 'Text att analysera:\n' +  file_content
+    
+    # Step 3: Add a Message to a Thread
+    message = client.beta.threads.messages.create(
+        thread_id=thread.id,
+        role="user",
+        content=total_message
+    )
+
+    # Step 4: Run the Assistant
+    run = client.beta.threads.runs.create(
+        thread_id=thread.id,
+        assistant_id=assistant_id,
+    )
+
+    while True:
+        # Wait for 5 seconds
+        time.sleep(5)
+
+        # Retrieve the run status
+        run_status = client.beta.threads.runs.retrieve(
+            thread_id=thread.id,
+            run_id=run.id
+        )
+
+        # If run is completed, get messages
+        if run_status.status == 'completed':
+            messages = client.beta.threads.messages.list(
+                thread_id=thread.id
+            )
+            response = ""
+            # Loop through messages and print content based on role
+            for msg in messages.data:
+                role = msg.role
+                content = msg.content[0].text.value
+                response += f"{role.capitalize()}: {content}\n\n"
+                break
+            return response
+        else:
+            continue
+
+# Create a Gradio Interface
 if __name__ == "__main__":
-    demo.launch()
+    iface = gr.ChatInterface(fn=main,
+                         #    examples=[{"text": "Skulle du kunna peka på svagheter och styrkor i en konsekvensutredning?", "files": []}],
+                             title="RR-robot (Proof of concept)",
+                             multimodal=True,
+                             description="Jag hjälper dig att analysera konsekvensutredningar").launch(auth=("user", read_key)) #multimodal=True