Spaces:
Sleeping
Sleeping
File size: 3,495 Bytes
ed20377 |
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 |
from dotenv import load_dotenv
from typing import Optional
from smolagents import InferenceClientModel, Tool
from app_tools.mdconvert import MarkdownConverter
load_dotenv()
text_limit = 70000
websurfer_llm_engine = InferenceClientModel(
model="meta-llama/Meta-Llama-3.1-70B-Instruct",
)
class TextInspectorTool(Tool):
name = "inspect_file_as_text"
description = """
You cannot load files yourself: instead call this tool to read a file as markdown text and ask questions about it.
This tool handles the following file extensions: [".html", ".htm", ".xlsx", ".pptx", ".wav", ".mp3", ".flac", ".pdf", ".docx"], and all other types of text files. IT DOES NOT HANDLE IMAGES."""
inputs = {
"question": {
"description": "[Optional]: Your question, as a natural language sentence. Provide as much context as possible. Do not pass this parameter if you just want to directly return the content of the file.",
"type": "string",
"nullable": True,
},
"file_path": {
"description": "The path to the file you want to read as text. Must be a '.something' file, like '.pdf'. If it is an image, use the visualizer tool instead! DO NOT USE THIS TOOL FOR A WEBPAGE: use the search tool instead!",
"type": "string",
},
}
output_type = "string"
md_converter = MarkdownConverter()
def forward_initial_exam_mode(self, file_path, question):
result = self.md_converter.convert(file_path)
if file_path[-4:] in ['.png', '.jpg']:
raise Exception("Cannot use inspect_file_as_text tool with images: use visualizer instead!")
if ".zip" in file_path:
return result.text_content
if not question:
return result.text_content
messages = [
{
"role": MessageRole.SYSTEM,
"content": "Here is a file:\n### "
+ str(result.title)
+ "\n\n"
+ result.text_content[:text_limit],
},
{
"role": MessageRole.USER,
"content": question,
},
]
return websurfer_llm_engine(messages)
def forward(self, file_path, question: Optional[str] = None) -> str:
result = self.md_converter.convert(file_path)
if file_path[-4:] in ['.png', '.jpg']:
raise Exception("Cannot use inspect_file_as_text tool with images: use visualizer instead!")
if ".zip" in file_path:
return result.text_content
if not question:
return result.text_content
messages = [
{
"role": MessageRole.SYSTEM,
"content": "You will have to write a short caption for this file, then answer this question:"
+ question,
},
{
"role": MessageRole.USER,
"content": "Here is the complete file:\n### "
+ str(result.title)
+ "\n\n"
+ result.text_content[:text_limit],
},
{
"role": MessageRole.USER,
"content": "Now answer the question below. Use these three headings: '1. Short answer', '2. Extremely detailed answer', '3. Additional Context on the document and question asked'."
+ question,
},
]
return websurfer_llm_engine(messages) |