Spaces:
Sleeping
Sleeping
| 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) |