Spaces:
Sleeping
Sleeping
File size: 4,616 Bytes
8ad9e26 8ba98ee 8ad9e26 5cb0bc3 8ad9e26 8ba98ee 8ad9e26 5cb0bc3 8ad9e26 5cb0bc3 8ad9e26 5cb0bc3 8ad9e26 |
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 |
from __future__ import annotations
import logging
from llama_index import Prompt
from typing import List, Tuple
import mdtex2html
from gradio_client import utils as client_utils
from modules.presets import *
from modules.llama_func import *
from modules.config import render_latex
def compact_text_chunks(self, prompt: Prompt, text_chunks: List[str]) -> List[str]:
logging.debug("Compacting text chunks...🚀🚀🚀")
combined_str = [c.strip() for c in text_chunks if c.strip()]
combined_str = [f"[{index+1}] {c}" for index, c in enumerate(combined_str)]
combined_str = "\n\n".join(combined_str)
# resplit based on self.max_chunk_overlap
text_splitter = self.get_text_splitter_given_prompt(prompt, 1, padding=1)
return text_splitter.split_text(combined_str)
def postprocess(
self,
y: List[List[str | Tuple[str] | Tuple[str, str] | None] | Tuple],
) -> List[List[str | Dict | None]]:
"""
Parameters:
y: List of lists representing the message and response pairs. Each message and response should be a string, which may be in Markdown format. It can also be a tuple whose first element is a string filepath or URL to an image/video/audio, and second (optional) element is the alt text, in which case the media file is displayed. It can also be None, in which case that message is not displayed.
Returns:
List of lists representing the message and response. Each message and response will be a string of HTML, or a dictionary with media information. Or None if the message is not to be displayed.
"""
if y is None:
return []
processed_messages = []
for message_pair in y:
assert isinstance(
message_pair, (tuple, list)
), f"Expected a list of lists or list of tuples. Received: {message_pair}"
assert (
len(message_pair) == 2
), f"Expected a list of lists of length 2 or list of tuples of length 2. Received: {message_pair}"
processed_messages.append(
[
self._postprocess_chat_messages(message_pair[0], "user"),
self._postprocess_chat_messages(message_pair[1], "bot"),
]
)
return processed_messages
def postprocess_chat_messages(
self, chat_message: str | Tuple | List | None, message_type: str
) -> str | Dict | None:
if chat_message is None:
return None
elif isinstance(chat_message, (tuple, list)):
filepath = chat_message[0]
mime_type = client_utils.get_mimetype(filepath)
filepath = self.make_temp_copy_if_needed(filepath)
return {
"name": filepath,
"mime_type": mime_type,
"alt_text": chat_message[1] if len(chat_message) > 1 else None,
"data": None, # These last two fields are filled in by the frontend
"is_file": True,
}
elif isinstance(chat_message, str):
if message_type == "bot":
if not detect_converted_mark(chat_message):
chat_message = convert_mdtext(chat_message)
elif message_type == "user":
if not detect_converted_mark(chat_message):
chat_message = convert_asis(chat_message)
return chat_message
else:
raise ValueError(f"Invalid message for Chatbot component: {chat_message}")
with open("./assets/custom.js", "r", encoding="utf-8") as f, \
open("./assets/external-scripts.js", "r", encoding="utf-8") as f1:
customJS = f.read()
externalScripts = f1.read()
def reload_javascript():
print("Reloading javascript...")
js = f'<script>{customJS}</script><script async>{externalScripts}</script>'
if render_latex:
js += """\
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-MML-AM_CHTML"></script>
<script type="text/x-mathjax-config">MathJax.Hub.Config({skipStartupTypeset: false, tex2jax: {inlineMath: [['$','$'], ['\\(','\\)']],displayMath: [['$$','$$'], ['\\[','\\]']]}});</script>
"""
def template_response(*args, **kwargs):
res = GradioTemplateResponseOriginal(*args, **kwargs)
res.body = res.body.replace(b'</html>', f'{js}</html>'.encode("utf8"))
res.init_headers()
return res
gr.routes.templates.TemplateResponse = template_response
GradioTemplateResponseOriginal = gr.routes.templates.TemplateResponse |