File size: 5,796 Bytes
4602937
fada25c
4615482
4602937
fada25c
 
4602937
2b44908
 
fada25c
2b44908
fada25c
 
2b44908
 
fada25c
 
 
 
 
 
 
 
3430157
fada25c
 
 
 
2b44908
fada25c
 
 
2b44908
 
 
fada25c
 
 
 
 
 
 
6dd9499
fada25c
 
 
6dd9499
 
 
 
 
 
fada25c
 
 
 
 
 
 
 
6dd9499
 
 
 
 
 
 
 
fada25c
 
2b44908
fada25c
2b44908
fada25c
2b44908
fada25c
6dd9499
 
fada25c
2b44908
 
 
fada25c
 
 
6dd9499
ddc78b4
6dd9499
 
fada25c
448c3da
0a5200d
 
5f6f331
 
 
 
0a5200d
5f6f331
 
 
0a5200d
 
 
 
448c3da
0a5200d
 
448c3da
 
0a5200d
448c3da
0a5200d
 
 
 
448c3da
 
5f6f331
 
448c3da
 
 
 
 
 
 
 
5f6f331
 
 
 
0a5200d
 
448c3da
0a5200d
 
 
 
5f6f331
 
0a5200d
5f6f331
0a5200d
 
 
 
 
 
 
 
 
 
 
 
5f6f331
0a5200d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f6f331
 
448c3da
 
0a5200d
5f6f331
448c3da
 
 
 
 
0a5200d
 
 
 
 
448c3da
5f6f331
0a5200d
 
448c3da
 
 
 
0a5200d
 
 
 
1740daa
448c3da
0a5200d
 
 
 
5f6f331
 
448c3da
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
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
from dotenv import load_dotenv
import gradio as gr
import os
from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate, Settings
from llama_index.llms.huggingface import HuggingFaceInferenceAPI
from llama_index.embeddings.huggingface import HuggingFaceEmbedding
from sentence_transformers import SentenceTransformer

# Load environment variables
load_dotenv()

# Configure the Llama index settings
Settings.llm = HuggingFaceInferenceAPI(
    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
    context_window=3000,
    token=os.getenv("HF_TOKEN"),
    max_new_tokens=512,
    generate_kwargs={"temperature": 0.1},
)
Settings.embed_model = HuggingFaceEmbedding(
    model_name="BAAI/bge-small-en-v1.5"
)

# Define the directory for persistent storage and data
PERSIST_DIR = "db"
PDF_DIRECTORY = 'data'  # Changed to the directory containing PDFs

# Ensure directories exist
os.makedirs(PDF_DIRECTORY, exist_ok=True)
os.makedirs(PERSIST_DIR, exist_ok=True)

# Variable to store current chat conversation
current_chat_history = []

def data_ingestion_from_directory():
    # Use SimpleDirectoryReader on the directory containing the PDF files
    documents = SimpleDirectoryReader(PDF_DIRECTORY).load_data()
    storage_context = StorageContext.from_defaults()
    index = VectorStoreIndex.from_documents(documents)
    index.storage_context.persist(persist_dir=PERSIST_DIR)

def handle_query(query):
    chat_text_qa_msgs = [
        (
            "user",
            """
            You are now the RedFerns Tech chatbot. Your aim is to provide answers to the user based on the conversation flow only.
            {context_str}
            Question:
            {query_str}
            """
        )
    ]
    text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)

    # Load index from storage
    storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
    index = load_index_from_storage(storage_context)

    # Use chat history to enhance response
    context_str = ""
    for past_query, response in reversed(current_chat_history):
        if past_query.strip():
            context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"

    query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)
    answer = query_engine.query(query)

    if hasattr(answer, 'response'):
        response = answer.response
    elif isinstance(answer, dict) and 'response' in answer:
        response = answer['response']
    else:
        response = "Sorry, I couldn't find an answer."

    # Update current chat history
    current_chat_history.append((query, response))

    return response

# Example usage: Process PDF ingestion from directory
print("Processing PDF ingestion from directory:", PDF_DIRECTORY)
data_ingestion_from_directory()

# Define the function to handle predictions
def predict(message,history):
    response = handle_query(message)
    return response


# Create the chat interface with a custom layout function
css = '''
  /* Style the chat container */
  .gradio-container {
    display: flex;
    flex-direction: column;
    width: 450px;
    margin: 0 auto;
    padding: 20px;
    border: 1px solid #ddd;
    border-radius: 10px;
    background-color: #fff;
    box-shadow: 0 4px 8px rgba(0,0,0,0.1);
    position: relative;
    height: 600px; /* Adjust the height of the container */
  }

  /* Style the logo */
  .gradio-logo {
    display: flex;
    justify-content: center;
    margin-bottom: 20px;
  }

  .gradio-logo img {
    width: 100%;
    max-width: 300px;
  }

  /* Style the title */
  .gradio-title {
    text-align: center;
    font-weight: bold;
    font-size: 24px;
    margin-bottom: 20px;
    color: #4A90E2;
  }

  /* Style the chat history */
  .gradio-chat-history {
    flex: 1;
    overflow-y: auto;
    padding: 15px;
    border-bottom: 1px solid #ddd;
    background-color: #f9f9f9;
    border-radius: 5px;
    margin-bottom: 10px;
    max-height: 500px; /* Increase the height of the chat history */
  }

  /* Style the chat messages */
  .gradio-message {
    margin-bottom: 15px;
    display: flex;
    flex-direction: column; /* Stack messages vertically */
  }

  .gradio-message.user .gradio-message-content {
    background-color: #E1FFC7;
    align-self: flex-end;
    border: 1px solid #c3e6cb;
    border-radius: 15px 15px 0 15px;
    padding: 10px;
    font-size: 16px;
    margin-bottom: 5px;
    max-width: 80%;
  }

  .gradio-message.bot .gradio-message-content {
    background-color: #fff;
    align-self: flex-start;
    border: 1px solid #ced4da;
    border-radius: 15px 15px 15px 0;
    padding: 10px;
    font-size: 16px;
    margin-bottom: 5px;
    max-width: 80%;
  }

  .gradio-message-content {
    box-shadow: 0 2px 4px rgba(0,0,0,0.1);
  }

  /* Style the footer */
  .gradio-footer {
    display: flex;
    padding: 10px;
    border-top: 1px solid #ddd;
    background-color: #F8D7DA; /* Light red background color */
    position: absolute;
    bottom: 0;
    width: calc(100% - 40px); /* Adjust width to match container padding */
  }

  /* Remove Gradio footer */
  footer {
    display: none !important;
    background-color: #F8D7DA;
  }
'''

# Create a custom HTML block for the logo
logo_html = '''
<div class="gradio-logo">
  <img src="https://redfernstech.com/wp-content/uploads/2024/05/RedfernsLogo_FinalV1.0-3-2048x575.png" alt="Company Logo">
</div>
'''

# Create a Blocks layout with the custom HTML and ChatInterface
with gr.Blocks(theme=gr.themes.Monochrome(), fill_height=True,css=css) as demo:
    gr.HTML(logo_html)
    gr.ChatInterface(predict)

# Launch the interface
demo.launch()