Update agent.py
Browse files
agent.py
CHANGED
|
@@ -52,43 +52,11 @@ class BasicAgent():
|
|
| 52 |
|
| 53 |
|
| 54 |
def assistant(self, state: AgentState):
|
| 55 |
-
|
| 56 |
-
extract_text(img_path: str) -> str:
|
| 57 |
-
Extract text from an image file using a multimodal model.
|
| 58 |
-
|
| 59 |
-
Args:
|
| 60 |
-
img_path: A url pointing to an image (e.g., PNG, JPEG).
|
| 61 |
-
|
| 62 |
-
Returns:
|
| 63 |
-
A single string containing the concatenated text extracted from each image.
|
| 64 |
-
|
| 65 |
-
search_tool(query: str) -> str:
|
| 66 |
-
Search the web using the DuckDuckGoSearchRun to perform a search query and return a summarized textual result.
|
| 67 |
-
|
| 68 |
-
Args:
|
| 69 |
-
query: A string representing the search query.
|
| 70 |
-
|
| 71 |
-
Returns:
|
| 72 |
-
A single string containing the search result or summary.
|
| 73 |
-
|
| 74 |
-
describe_image(img_path: str, query: str) -> str:
|
| 75 |
-
Generate a detailed description of an image using a multimodal model.
|
| 76 |
-
This function reads a image from an url, encodes it, and sends it to a
|
| 77 |
-
vision-capable language model to obtain a comprehensive, natural language
|
| 78 |
-
description of the image's content, including its objects, actions, and context,
|
| 79 |
-
following a specific query.
|
| 80 |
-
|
| 81 |
-
Args:
|
| 82 |
-
img_path: A url pointing to an image (e.g., PNG, JPEG).
|
| 83 |
-
query: Information to extract from the image
|
| 84 |
-
|
| 85 |
-
Returns:
|
| 86 |
-
A single string containing a detailed, human-readable description of the image.
|
| 87 |
-
"""
|
| 88 |
sys_msg = SystemMessage(content=f"""
|
| 89 |
You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER].
|
| 90 |
YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
|
| 91 |
-
|
| 92 |
|
| 93 |
return {
|
| 94 |
"messages": [self.chat_with_tools.invoke([sys_msg] + state["messages"])],
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
def assistant(self, state: AgentState):
|
| 55 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 56 |
sys_msg = SystemMessage(content=f"""
|
| 57 |
You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER].
|
| 58 |
YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
|
| 59 |
+
""")
|
| 60 |
|
| 61 |
return {
|
| 62 |
"messages": [self.chat_with_tools.invoke([sys_msg] + state["messages"])],
|