Duplicate from cogcorp/assignment1

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: ExpertChat
+emoji: 👀
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+duplicated_from: cogcorp/assignment1
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,89 @@
+import gradio as gr
+from PyPDF2 import PdfReader
+import zipfile
+import os
+import io
+import nltk
+import openai
+import time
+
+
+import pip
+import subprocess
+import sys 
+
+# install required libraries
+subprocess.check_call([sys.executable, "-m", "pip", "install", "-r", "requirements.txt"])
+
+# download required NLTK data packages
+nltk.download('punkt')
+nltk.download('all')  # or any other packages your project depends on
+
+
+
+
+
+
+
+
+# Put your OpenAI API key here
+openai.api_key = os.getenv('OpenAPI') 
+
+def call_openai_api(text, user_prompt):
+    max_retries = 5
+    for attempt in range(max_retries):
+        try:
+            response = openai.ChatCompletion.create(
+                model="gpt-3.5-turbo",
+                messages=[
+                    {"role": "system", "content": "You are a research assistant. Provide factual short answers to your prompts. The user will provide reference data followed by instructions."},
+                    {"role": "user", "content": f"{text}\n\n{user_prompt}"},
+                ]
+            )
+            return response['choices'][0]['message']['content']
+        except Exception as e:
+            if attempt < max_retries - 1:  # if it's not the last attempt
+                time.sleep(1)  # wait for 1 seconds before retrying
+                continue
+            else:
+                return str(e)  # return the exception message after the last attempt
+
+def pdf_to_text(file, user_prompt):
+    z = zipfile.ZipFile(file.name, 'r')
+    texts = []
+    for filename in z.namelist():
+        if filename.endswith('.pdf'):
+            pdf_file_data = z.read(filename)
+            pdf_file_io = io.BytesIO(pdf_file_data)
+            pdf = PdfReader(pdf_file_io)
+            text = ''
+            for page in pdf.pages:
+                text += page.extract_text()
+            # Tokenize text
+            tokens = nltk.word_tokenize(text)
+            # If tokens are more than 2000, split into chunks
+            if len(tokens) > 2000:
+                for i in range(0, len(tokens), 2000):
+                    chunk = tokens[i:i + 2000]
+                    chunk_str = ' '.join(chunk)
+                    # Using OpenAI API
+                    response = call_openai_api(chunk_str, user_prompt)
+                    texts.append(response)
+            else:
+                # Using OpenAI API
+                response = call_openai_api(text, user_prompt)
+                texts.append(response)
+    return '\n'.join(texts)
+
+iface = gr.Interface(
+    fn=pdf_to_text, 
+    inputs=[
+        gr.inputs.File(label="PDF File (Upload a Zip file containing ONLY PDF files)"),
+        gr.inputs.Textbox(label="User Prompt (Enter a prompt to guide the AI's responses)")
+    ], 
+    outputs=gr.outputs.Textbox(label="Cognitive Agent Response"),
+    title="Ask An Expert Proof Of Concept",
+    description="This app extracts knowledge from the uploaded Zip files. Using a Cognitive Agent you can interact with that knowledge."
+)
+iface.launch(share=False)
+

requirements.txt

@@ -0,0 +1,5 @@
+PyMuPDF
+openai
+gradio
+PyPDF2
+nltk