Duplicate from cogcorp/askexpert

.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: Askexpert
+emoji: 👁
+colorFrom: blue
+colorTo: red
+sdk: gradio
+sdk_version: 3.29.0
+app_file: app.py
+pinned: false
+duplicated_from: cogcorp/askexpert
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,121 @@
+import gradio as gr
+from PyPDF2 import PdfReader
+import zipfile
+import os
+import io
+import nltk
+import openai
+import time
+import subprocess
+import sys
+from sentence_transformers import SentenceTransformer, util
+
+# install required libraries
+subprocess.check_call([sys.executable, "-m", "pip", "install", "-r", "requirements.txt"])
+
+def install(package):
+    subprocess.check_call([sys.executable, "-m", "pip", "install", package])
+
+# Install PyTorch, transformers, and sentence-transformers
+install("torch")
+install("transformers")
+install("sentence-transformers")
+
+# download required NLTK data packages
+nltk.download('punkt')
+
+# Put your OpenAI API key here
+openai.api_key = os.getenv('OpenAPI')
+
+# Create a cache dictionary
+cache = {}
+
+# Load the pre-trained model
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def create_persona(text):
+    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 an expert at summarizing content to provide a factual persona."},
+                    {"role": "user", "content": f"Create a persona based on this Cognitive Corp provides workplace optimization via a cognitive workplace which can be defined as an environment where cutting-edge technology, such as artificial intelligence and machine learning, is leveraged and this text: {text}"},
+                ]
+            )
+            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 second before retrying
+                continue
+            else:
+                return str(e)  # return the exception message after the last attempt
+
+def call_openai_api(persona, user_prompt, additional_facts):
+    max_retries = 5
+    for attempt in range(max_retries):
+        try:
+            response = openai.ChatCompletion.create(
+                model="gpt-3.5-turbo",
+                messages=[
+                    {"role": "system", "content": f"You are {persona}"},
+                    {"role": "user", "content": f"""Ignore all previous instructions. As {persona}
+ You are James Waddell, you wrote this paper: optimizing the workplace through technology. 
+Here are some additional facts: {additional_facts}. Now, provide short factual answers as James, focus on the additional facts if provided: {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 second before retrying
+                continue
+            else:
+                return str(e)  # return the exception message after the last attempt
+
+def extract_persona_from_pdf(pdf_file):
+    with open(pdf_file, 'rb') as f:
+        pdf = PdfReader(f)
+        aggregated_text = ''
+        for page in pdf.pages:
+            aggregated_text += page.extract_text()
+    return create_persona(aggregated_text)
+
+# Extract the persona from the persona.pdf file
+persona = extract_persona_from_pdf('persona.pdf')
+
+def pdf_to_text(pdf_file_io, user_prompt, persona):
+    aggregated_text = ''
+    pdf = PdfReader(pdf_file_io)
+    for page in pdf.pages:
+        aggregated_text += page.extract_text()
+    cache[pdf_file_io] = aggregated_text
+
+    query_embedding = model.encode(user_prompt, convert_to_tensor=True)
+    text_embedding = model.encode(aggregated_text, convert_to_tensor=True)
+    cosine_scores = util.pytorch_cos_sim(query_embedding, text_embedding)
+
+    if cosine_scores[0][0] > 0.5:
+        additional_facts = "Direct answer from author's knoweledge: " + user_prompt
+    else:
+        additional_facts = "No additional information to add."
+
+    answer = call_openai_api(persona, user_prompt, additional_facts)
+    return answer
+
+def ask_expert(user_prompt):
+    with zipfile.ZipFile("documents.zip", 'r') as z:
+        for filename in z.namelist():
+            if filename.endswith('.pdf'):
+                pdf_file_data = z.read(filename)
+                pdf_file_io = io.BytesIO(pdf_file_data)
+                result = pdf_to_text(pdf_file_io, user_prompt, persona)
+    return result
+
+iface = gr.Interface(
+    fn=ask_expert, 
+    inputs=gr.inputs.Textbox(lines=1, placeholder="Enter a question or prompt for the Author", label="User Prompt"), 
+    outputs=gr.outputs.Textbox(label="Cognitive Agent Response")
+)
+iface.launch()
+

documents.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cc19cef8472fb9b6967032b7dcdc18f643de1847436709f105bea6c60dfd2a
+size 2664989

persona.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffb423c87bc2f24036e7b254d1699ed9f8ae9b8179fc980ec441d7d1d189cac
+size 645110

requirements.txt

@@ -0,0 +1,9 @@
+PyPDF2
+numpy
+nltk
+scikit-learn
+tensorflow>=2.0.0
+tensorflow-hub
+openai
+gradio
+sentence-transformers