File size: 5,588 Bytes
6e969ba
 
 
 
 
acc0c63
a88d27d
bf65701
5d39a3e
6e969ba
 
9103f91
 
5d39a3e
6e969ba
988a5cb
 
2e67686
e12378e
 
49e8bc7
2e67686
 
 
 
 
 
 
133f625
e12378e
2e67686
e12378e
988a5cb
 
 
 
6e969ba
aef72ef
6e969ba
 
 
 
 
29b3073
bf65701
5e39c57
 
29b3073
 
10369ed
29b3073
 
 
 
 
 
 
 
 
6e969ba
5d39a3e
 
 
 
 
a260e6a
5d39a3e
 
 
 
 
 
 
 
a260e6a
5d39a3e
 
 
 
4c38937
9103f91
 
 
 
4c38937
d3f3e34
34128f5
f8850ff
 
 
a88d27d
f8850ff
 
a06050e
9103f91
 
db9b250
8d8fc5c
a88d27d
 
 
 
f8850ff
 
 
 
 
 
a260e6a
 
 
a88d27d
f8850ff
a260e6a
 
 
 
 
 
 
55c04e3
0d44617
a260e6a
 
 
 
 
 
 
 
 
 
 
 
5751846
a260e6a
 
 
 
 
 
55c04e3
29b3073
 
a260e6a
9337711
 
 
 
 
 
 
6e969ba
f6ff404
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
import streamlit as st
import openai
import os
import base64
import glob
import json
import mistune
import pytz

from datetime import datetime
from openai import ChatCompletion
from xml.etree import ElementTree as ET
from bs4 import BeautifulSoup

openai.api_key = os.getenv('OPENAI_KEY')
st.set_page_config(
    page_title="GPT Streamlit Document Reasoner",
    layout="wide")

menu = ["txt", "htm", "md", "py"]
choice = st.sidebar.selectbox("Choose output file type to save results", menu)
choicePrefix = "Output and download file set to "
if choice == "txt":
     st.sidebar.write(choicePrefix + "Text file.")
elif choice == "htm":
     st.sidebar.write(choicePrefix + "HTML5.")
elif choice == "md":
     st.sidebar.write(choicePrefix + "Markdown.")
elif choice == "py":
     st.sidebar.write(choicePrefix + "Python Code.")

max_length = st.sidebar.slider("Max document length", min_value=1000, max_value=32000, value=2000, step=1000)

def truncate_document(document, length):
    return document[:length]

def chat_with_model(prompts):
    model = "gpt-3.5-turbo"
    conversation = [{'role': 'system', 'content': 'You are a helpful assistant.'}]
    conversation.extend([{'role': 'user', 'content': prompt} for prompt in prompts])
    response = openai.ChatCompletion.create(model=model, messages=conversation)
    return response['choices'][0]['message']['content']

def generate_filename(prompt, file_type):
    central = pytz.timezone('US/Central')
    safe_date_time = datetime.now(central).strftime("%m%d_%I%M")  
    safe_prompt = "".join(x for x in prompt if x.isalnum())[:28]
    return f"{safe_date_time}_{safe_prompt}.{file_type}"

def create_file(filename, prompt, response):
    if filename.endswith(".txt"):
        with open(filename, 'w') as file:
            file.write(f"Prompt:\n{prompt}\nResponse:\n{response}")
    elif filename.endswith(".htm"):
        with open(filename, 'w') as file:
            file.write(f"<h1>Prompt:</h1> <p>{prompt}</p> <h1>Response:</h1> <p>{response}</p>")
    elif filename.endswith(".md"):
        with open(filename, 'w') as file:
            file.write(f"# Prompt:\n{prompt}\n# Response:\n{response}")

def get_table_download_link(file_path):
    with open(file_path, 'r') as file:
        data = file.read()
    b64 = base64.b64encode(data.encode()).decode()  
    file_name = os.path.basename(file_path)
    ext = os.path.splitext(file_name)[1]  # get the file extension

    if ext == '.txt':
        mime_type = 'text/plain'
    elif ext == '.htm':
        mime_type = 'text/html'
    elif ext == '.md':
        mime_type = 'text/markdown'
    else:
        mime_type = 'application/octet-stream'  # general binary data type

    href = f'<a href="data:{mime_type};base64,{b64}" target="_blank" download="{file_name}">{file_name}</a>'
    return href

def CompressXML(xml_text):
    root = ET.fromstring(xml_text)
    for elem in list(root.iter()):
        if isinstance(elem.tag, str) and 'Comment' in elem.tag:
            elem.parent.remove(elem)
    return ET.tostring(root, encoding='unicode', method="xml")
    
def read_file_content(file,max_length):
    if file.type == "application/json":
        content = json.load(file)
        return str(content)
    elif file.type == "text/html" or file.type == "text/htm":
        content = BeautifulSoup(file, "html.parser")
        return content.text
    elif file.type == "application/xml" or file.type == "text/xml":
        tree = ET.parse(file)
        root = tree.getroot()
        xml = CompressXML(ET.tostring(root, encoding='unicode'))
        return xml
    elif file.type == "text/markdown" or file.type == "text/md":
        md = mistune.create_markdown()
        content = md(file.read().decode())
        return content
    elif file.type == "text/plain":
        return file.getvalue().decode()
    else:
        return ""

def main():
    prompts = ['']
    file_content = ""
    user_prompt = st.text_area("Your question:", '', height=100)
    uploaded_file = st.file_uploader("Choose a file", type=["xml", "json", "html", "htm", "md", "txt"])

    if user_prompt:
        prompts.append(user_prompt)

    if uploaded_file is not None:
        file_content = read_file_content(uploaded_file, max_length)
        prompts.append(file_content)

    if st.button('πŸ’¬ Chat'):
        st.write('Thinking and Reasoning with your inputs...')
        total_input = "".join(prompts)

        if len(total_input) > 4000:
            chunks = [total_input[i:i + max_length] for i in range(0, len(total_input), max_length)]
            responses = []
            for chunk in chunks:
                responses.append(chat_with_model([chunk]))
            response = "\n".join(responses)
        else:
            response = chat_with_model(prompts)
        st.write('Response:')
        st.write(response)
        
        filename = generate_filename(user_prompt, choice)
        create_file(filename, user_prompt, response)
        st.sidebar.markdown(get_table_download_link(filename), unsafe_allow_html=True)
    
    if len(file_content) > 0:
        st.markdown(f"**File Content Added:**\n{file_content}")
    
    all_files = glob.glob("*.txt") + glob.glob("*.htm") + glob.glob("*.md")
    for file in all_files:
        col1, col2 = st.sidebar.columns([4,1])  # adjust the ratio as needed
        with col1:
            st.markdown(get_table_download_link(file), unsafe_allow_html=True)
        with col2:
            if st.button("πŸ—‘", key=file):
                os.remove(file)
                st.experimental_rerun()

if __name__ == "__main__":
    main()