File size: 17,241 Bytes
d9e3edb | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | # import json
# import os
# import re
# import time
# from pathlib import Path
# from typing import Dict, List
# import requests
# import streamlit as st
# def extract_and_verify_url(string):
# """Extract the URL from the string and verify if it points to content."""
# url_pattern = re.compile(
# r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
# )
# match = url_pattern.search(string)
# if match:
# url = match.group()
# try:
# response = requests.head(url, allow_redirects=True, timeout=5)
# if response.status_code == 200:
# return {
# "url": url,
# "status": "Valid and content exists",
# "status_code": 200,
# }
# else:
# return {
# "url": url,
# "status": f"Invalid (HTTP {response.status_code})",
# "status_code": response.status_code,
# }
# except requests.RequestException as e:
# return {"url": url, "status": f"Error: {e}"}
# return {"url": "", "status": "No URL found"}
# def stream_data(data_val):
# for word in data_val.split(" "):
# yield word + " "
# time.sleep(0.02)
# def list_files_in_directory(directory):
# """List all files in the given directory."""
# try:
# return os.listdir(directory)
# except FileNotFoundError:
# return []
# def save_uploaded_file(uploaded_file, directory):
# """Save the uploaded file to the specified directory."""
# with open(os.path.join(directory, uploaded_file.name), "wb") as f:
# f.write(uploaded_file.getbuffer())
# return os.path.join(directory, uploaded_file.name)
# def call_rag_api(
# query: str,
# url: str,
# is_uploaded: bool = False,
# ) -> Dict:
# """Call the RAG API and get a response."""
# endpoint = f"http://127.0.0.1:8000/get-response"
# payload = {"query": query, "is_uploaded": is_uploaded, "url": url}
# try:
# response = requests.post(endpoint, json=payload)
# response.raise_for_status()
# result = response.json()
# print(type(result))
# print(result)
# return {
# "status": "success",
# "response": result["response"],
# "context": result["context"],
# "citations": result["citations"],
# }
# except requests.exceptions.RequestException as e:
# return {"status": "error", "message": str(e)}
# # Main Streamlit app
# def main():
# st.title("🤖 RAG Chat Assistant")
# # Sidebar inputs and actions
# with st.sidebar:
# st.header("📚 Document Control")
# # Input directory
# directory = st.text_input("Enter the directory path:", value="data")
# # Ensure directory exists
# Path(directory).mkdir(parents=True, exist_ok=True)
# # Display files in the directory
# st.subheader("Files in Directory")
# files = list_files_in_directory(directory)
# if files:
# st.write(files)
# else:
# st.write("No files found.")
# # Upload file
# st.subheader("Upload a File")
# uploaded_file = st.file_uploader(
# "Choose a file", type=["txt", "pdf", "doc", "docx", "mp3", "mp4"]
# )
# if uploaded_file:
# file_path = save_uploaded_file(uploaded_file, directory)
# with st.spinner:
# endpoint = f"http://127.0.0.1:8000/process-file"
# payload = {"file_path": file_path}
# result = requests.post(endpoint, json=payload)
# st.success(result["response"])
# st.success(f"File '{uploaded_file.name}' uploaded successfully!")
# # Delete a file
# st.subheader("Delete a File")
# if files:
# file_to_delete = st.selectbox("Select a file to delete:", options=files)
# if st.button("Delete File"):
# try:
# os.remove(os.path.join(directory, file_to_delete))
# st.success(f"File '{file_to_delete}' deleted successfully!")
# except Exception as e:
# st.error(f"Error deleting file: {e}")
# # Chat system status
# st.divider()
# st.markdown("### System Status")
# if uploaded_file:
# st.success("Document loaded")
# else:
# st.info("No document uploaded")
# # Initialize chat history
# if "messages" not in st.session_state:
# st.session_state.messages = []
# # Display chat messages in streaming manner
# chat_placeholder = st.container()
# for message in st.session_state.messages:
# with chat_placeholder.container():
# with st.chat_message(message["role"]):
# st.markdown(message["content"])
# if message["role"] == "assistant" and "context" in message:
# with st.expander("View source context"):
# st.info(message["context"])
# # Chat input
# if prompt := st.chat_input("Ask me anything about your documents..."):
# res = extract_and_verify_url(prompt)
# print(res)
# if res["url"] != None:
# print(res["url"])
# st.session_state.messages.append({"role": "user", "content": prompt})
# with chat_placeholder.container():
# with st.chat_message("user"):
# st.markdown(prompt)
# with chat_placeholder.container():
# with st.chat_message("assistant"):
# with st.spinner("Thinking..."):
# result = call_rag_api(
# url=res["url"],
# query=prompt,
# is_uploaded=uploaded_file is not None,
# )
# if result["status"] == "success":
# response_content = result["response"]
# context = result["context"]
# citations = result["citations"]
# # st.markdown(response_content)
# st.write_stream(stream_data(response_content))
# with st.expander("View source context"):
# st.json(citations)
# st.session_state.messages.append(
# {
# "role": "assistant",
# "content": response_content,
# "context": context,
# "citations": citations,
# }
# )
# else:
# st.error(
# f"Error: {result.get('message', 'Unknown error occurred')}"
# )
# if __name__ == "__main__":
# main()
import json
import os
import re
import time
from pathlib import Path
from typing import Dict, List
import requests
import streamlit as st
from streamlit_js_eval import streamlit_js_eval
def extract_and_verify_url(string):
"""Extract the URL from the string and verify if it points to content."""
url_pattern = re.compile(
r"http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\\(\\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+"
)
match = url_pattern.search(string)
if match:
url = match.group()
try:
response = requests.head(url, allow_redirects=True, timeout=5)
if response.status_code == 200:
return {
"url": url,
"status": "Valid and content exists",
"status_code": 200,
}
else:
return {
"url": url,
"status": f"Invalid (HTTP {response.status_code})",
"status_code": response.status_code,
}
except requests.RequestException as e:
return {"url": url, "status": f"Error: {e}"}
return {"url": "", "status": "No URL found"}
def stream_data(data_val):
for word in data_val.split(" "):
yield word + " "
time.sleep(0.02)
def list_files_in_directory(directory):
"""List all files in the given directory."""
try:
return os.listdir(directory)
except FileNotFoundError:
return []
def save_uploaded_file(uploaded_file, directory):
"""Save the uploaded file to the specified directory."""
with open(os.path.join(directory, uploaded_file.name), "wb") as f:
f.write(uploaded_file.getbuffer())
return os.path.join(directory, uploaded_file.name)
def call_rag_api(query: str, url: str, is_uploaded: bool = False) -> Dict:
"""Call the RAG API and get a response."""
endpoint = f"http://127.0.0.1:8000/get-response"
payload = {"query": query, "is_uploaded": is_uploaded, "url": url}
try:
response = requests.post(endpoint, json=payload)
response.raise_for_status()
result = response.json()
return {
"status": "success",
"response": result["response"],
"context": result["context"],
"citations": result["citations"],
}
except requests.exceptions.RequestException as e:
return {"status": "error", "message": str(e)}
def call_llm_api(query: str) -> Dict:
"""Call the LLM API for answering questions."""
endpoint = f"http://127.0.0.1:8000/llm-response"
payload = {"query": query}
try:
response = requests.post(endpoint, json=payload)
response.raise_for_status()
result = response.json()
return {"status": "success", "response": result["response"]}
except requests.exceptions.RequestException as e:
return {"status": "error", "message": str(e)}
# Main Streamlit app
def main():
st.title("🤖 Multi-Functional Chat Assistant")
# Sidebar inputs and actions
with st.sidebar:
# Chat functionality selection
mode = st.radio("Select Mode:", ["LLM Answering", "Web Search Agent", "RAG"])
st.header("📂 Document Control")
# Input directory
directory = st.text_input("Enter the directory path:", value="data")
# Ensure directory exists
Path(directory).mkdir(parents=True, exist_ok=True)
# Display files in the directory
st.subheader("Files in Directory")
files = list_files_in_directory(directory)
if files:
st.write(files)
else:
st.write("No files found.")
# Upload file
st.subheader("Upload a File")
uploaded_file = st.file_uploader(
"Choose a file", type=["txt", "pdf", "doc", "docx", "mp3", "mp4"]
)
if uploaded_file:
file_path = save_uploaded_file(uploaded_file, directory)
endpoint = f"http://127.0.0.1:8000/process-file"
payload = {"file_path": file_path}
with st.spinner("File is in process..."):
response = requests.post(endpoint, json=payload)
st.success(f"File '{uploaded_file.name}' uploaded successfully!")
time.sleep(3)
streamlit_js_eval(js_expressions="parent.window.location.reload()")
# Delete a file
st.subheader("Delete a File")
if files:
file_to_delete = st.selectbox("Select a file to delete:", options=files)
if st.button("Delete File"):
try:
payload = {"file_path": file_to_delete}
endpoint = f"http://127.0.0.1:8000/delete-file"
with st.spinner("File is deleting..."):
response = requests.post(endpoint, json=payload)
os.remove(os.path.join(directory, file_to_delete))
st.success(f"File '{file_to_delete}' deleted successfully!")
time.sleep(3)
streamlit_js_eval(js_expressions="parent.window.location.reload()")
except Exception as e:
st.error(f"Error deleting file: {e}")
# Chat system status
st.divider()
st.markdown("### System Status")
if uploaded_file:
st.success("Document loaded")
else:
st.info("No document uploaded")
# Initialize chat history
if "messages" not in st.session_state:
st.session_state.messages = []
# Display chat messages in streaming manner
chat_placeholder = st.container()
for message in st.session_state.messages:
with chat_placeholder.container():
with st.chat_message(message["role"]):
st.markdown(message["content"])
# # Chat functionality selection
# mode = st.radio("Select Mode:", ["LLM Answering", "Web Search Agent", "RAG"])
# Chat input
if prompt := st.chat_input("Ask me anything..."):
st.session_state.messages.append({"role": "user", "content": prompt})
with chat_placeholder.container():
with st.chat_message("user"):
st.markdown(prompt)
with chat_placeholder.container():
with st.chat_message("assistant"):
with st.spinner("Thinking..."):
citations = []
if mode == "LLM Answering":
result = call_llm_api(prompt)
if result["status"] == "success":
response_content = result.get("response", "")
st.write_stream(stream_data(response_content))
st.session_state.messages.append(
{"role": "assistant", "content": response_content}
)
else:
st.error(
f"Error: {result.get('message', 'Unknown error occurred')}"
)
elif mode == "Web Search Agent":
res = extract_and_verify_url(prompt)
result = call_rag_api(
url=res.get("url", ""),
query=prompt,
is_uploaded=uploaded_file is not None,
)
if result["status"] == "success":
response_content = result["response"]
context = result["context"]
citations = result["citations"]
# st.markdown(response_content)
st.write_stream(stream_data(response_content))
# with st.expander("View source context"):
# st.json(citations)
st.session_state.messages.append(
{
"role": "assistant",
"content": response_content,
"context": context,
"citations": citations,
}
)
else:
st.error(
f"Error: {result.get('message', 'Unknown error occurred')}"
)
elif mode == "RAG":
res = extract_and_verify_url(prompt)
result = call_rag_api(
url="None",
query=prompt,
is_uploaded=uploaded_file is not None,
)
if result["status"] == "success":
response_content = result["response"]
context = result["context"]
citations = result["citations"]
# st.markdown(response_content)
st.write_stream(stream_data(response_content))
# with st.expander("View source context"):
# st.json(citations)
st.session_state.messages.append(
{
"role": "assistant",
"content": response_content,
"context": context,
"citations": citations,
}
)
else:
st.error(
f"Error: {result.get('message', 'Unknown error occurred')}"
)
with st.expander("View source context"):
st.json(citations)
if __name__ == "__main__":
main()
|