Create text_inspector_tool.py
Browse files- text_inspector_tool.py +122 -0
text_inspector_tool.py
ADDED
|
@@ -0,0 +1,122 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from typing import Optional
|
| 2 |
+
|
| 3 |
+
from smolagents import Tool
|
| 4 |
+
from smolagents.models import MessageRole, Model
|
| 5 |
+
|
| 6 |
+
from .mdconvert import MarkdownConverter
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
class TextInspectorTool(Tool):
|
| 10 |
+
name = "inspect_file_as_text"
|
| 11 |
+
description = """
|
| 12 |
+
You cannot load files yourself: instead call this tool to read a file as markdown text and ask questions about it.
|
| 13 |
+
This tool handles the following file extensions: [".html", ".htm", ".xlsx", ".pptx", ".wav", ".mp3", ".m4a", ".flac", ".pdf", ".docx"], and all other types of text files. IT DOES NOT HANDLE IMAGES."""
|
| 14 |
+
|
| 15 |
+
inputs = {
|
| 16 |
+
"file_path": {
|
| 17 |
+
"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 an HTML webpage: use the web_search tool instead!",
|
| 18 |
+
"type": "string",
|
| 19 |
+
},
|
| 20 |
+
"question": {
|
| 21 |
+
"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.",
|
| 22 |
+
"type": "string",
|
| 23 |
+
"nullable": True,
|
| 24 |
+
},
|
| 25 |
+
}
|
| 26 |
+
output_type = "string"
|
| 27 |
+
md_converter = MarkdownConverter()
|
| 28 |
+
|
| 29 |
+
def __init__(self, model: Model, text_limit: int):
|
| 30 |
+
super().__init__()
|
| 31 |
+
self.model = model
|
| 32 |
+
self.text_limit = text_limit
|
| 33 |
+
|
| 34 |
+
def forward_initial_exam_mode(self, file_path, question):
|
| 35 |
+
result = self.md_converter.convert(file_path)
|
| 36 |
+
|
| 37 |
+
if file_path[-4:] in [".png", ".jpg"]:
|
| 38 |
+
raise Exception("Cannot use inspect_file_as_text tool with images: use visualizer instead!")
|
| 39 |
+
|
| 40 |
+
if ".zip" in file_path:
|
| 41 |
+
return result.text_content
|
| 42 |
+
|
| 43 |
+
if not question:
|
| 44 |
+
return result.text_content
|
| 45 |
+
|
| 46 |
+
if len(result.text_content) < 4000:
|
| 47 |
+
return "Document content: " + result.text_content
|
| 48 |
+
|
| 49 |
+
messages = [
|
| 50 |
+
{
|
| 51 |
+
"role": MessageRole.SYSTEM,
|
| 52 |
+
"content": [
|
| 53 |
+
{
|
| 54 |
+
"type": "text",
|
| 55 |
+
"text": "Here is a file:\n### "
|
| 56 |
+
+ str(result.title)
|
| 57 |
+
+ "\n\n"
|
| 58 |
+
+ result.text_content[: self.text_limit],
|
| 59 |
+
}
|
| 60 |
+
],
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"role": MessageRole.USER,
|
| 64 |
+
"content": [
|
| 65 |
+
{
|
| 66 |
+
"type": "text",
|
| 67 |
+
"text": "Now please write a short, 5 sentence caption for this document, that could help someone asking this question: "
|
| 68 |
+
+ question
|
| 69 |
+
+ "\n\nDon't answer the question yourself! Just provide useful notes on the document",
|
| 70 |
+
}
|
| 71 |
+
],
|
| 72 |
+
},
|
| 73 |
+
]
|
| 74 |
+
return self.model(messages).content
|
| 75 |
+
|
| 76 |
+
def forward(self, file_path, question: Optional[str] = None) -> str:
|
| 77 |
+
result = self.md_converter.convert(file_path)
|
| 78 |
+
|
| 79 |
+
if file_path[-4:] in [".png", ".jpg"]:
|
| 80 |
+
raise Exception("Cannot use inspect_file_as_text tool with images: use visualizer instead!")
|
| 81 |
+
|
| 82 |
+
if ".zip" in file_path:
|
| 83 |
+
return result.text_content
|
| 84 |
+
|
| 85 |
+
if not question:
|
| 86 |
+
return result.text_content
|
| 87 |
+
|
| 88 |
+
messages = [
|
| 89 |
+
{
|
| 90 |
+
"role": MessageRole.SYSTEM,
|
| 91 |
+
"content": [
|
| 92 |
+
{
|
| 93 |
+
"type": "text",
|
| 94 |
+
"text": "You will have to write a short caption for this file, then answer this question:"
|
| 95 |
+
+ question,
|
| 96 |
+
}
|
| 97 |
+
],
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"role": MessageRole.USER,
|
| 101 |
+
"content": [
|
| 102 |
+
{
|
| 103 |
+
"type": "text",
|
| 104 |
+
"text": "Here is the complete file:\n### "
|
| 105 |
+
+ str(result.title)
|
| 106 |
+
+ "\n\n"
|
| 107 |
+
+ result.text_content[: self.text_limit],
|
| 108 |
+
}
|
| 109 |
+
],
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"role": MessageRole.USER,
|
| 113 |
+
"content": [
|
| 114 |
+
{
|
| 115 |
+
"type": "text",
|
| 116 |
+
"text": "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'."
|
| 117 |
+
+ question,
|
| 118 |
+
}
|
| 119 |
+
],
|
| 120 |
+
},
|
| 121 |
+
]
|
| 122 |
+
return self.model(messages).content
|