File size: 6,256 Bytes
153f125
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98fa13f
153f125
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98fa13f
153f125
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
import pandas as pd
from langchain_community.tools import DuckDuckGoSearchRun, TavilySearchResults
from langchain_core.tools import tool
from langchain.schema import HumanMessage, AIMessage, SystemMessage
from langchain_google_genai import ChatGoogleGenerativeAI
import base64

#LLMs
google_llm = ChatGoogleGenerativeAI(model='gemini-2.0-flash-lite')

#IMAGE_TOOLS
@tool
def extract_text(img_path: str) -> str:
    """
    Extract text from an image file using a multimodal model.

    Args:
        img_path: A local image file path (strings).

    Returns:
        A single string containing the concatenated text extracted from each image.
    """
    all_text = ""
    try:
       
        # Read image and encode as base64
        with open(img_path, "rb") as image_file:
            image_bytes = image_file.read()

        image_base64 = base64.b64encode(image_bytes).decode("utf-8")

        # Prepare the prompt including the base64 image data
        message = [
            HumanMessage(
                content=[
                    {
                        "type": "text",
                        "text": (
                            "Extract all the text from this image. "
                            "Return only the extracted text, no explanations."
                        ),
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/png;base64,{image_base64}"
                        },
                    },
                ]
            )
        ]

        # Call the vision-capable model
        response = google_llm.invoke(message)

        # Append extracted text
        all_text += response.content + "\n\n"

        return all_text.strip()
    except Exception as e:
        # You can choose whether to raise or just return an empty string / error message
        error_msg = f"Error extracting text: {str(e)}"
        print(error_msg)
        return ""

@tool
def describe_image(img_path: str) -> str:
    """
    Takes an image file path or URL and returns a detailed description of the image.

    Args:
        image_path_or_url (str): Local file path or URL to the image.

    Returns:
        str: A detailed description of the image content.
    """
    all_text = ""
    try:
       
        # Read image and encode as base64
        with open(img_path, "rb") as image_file:
            image_bytes = image_file.read()

        image_base64 = base64.b64encode(image_bytes).decode("utf-8")

        # Prepare the prompt including the base64 image data
        message = [
            HumanMessage(
                content=[
                    {
                        "type": "text",
                        "text": (
                            "Provide a detailed description from this image. "
                            "Return descriptive text only."
                        ),
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": f"data:image/png;base64,{image_base64}"
                        },
                    },
                ]
            )
        ]

        # Call the vision-capable model
        response = google_llm.invoke(message)

        # Append extracted text
        all_text += response.content + "\n\n"

        return all_text.strip()
    except Exception as e:
        # You can choose whether to raise or just return an empty string / error message
        error_msg = f"Error extracting text: {str(e)}"
        print(error_msg)
        return ""

#AUDIO_TOOLS
@tool 
def transcribe_audio(audio_path: str) -> str:
    """
    Transcribe audio from a file using a multimodal model.

    Args:
        audio_path: A local audio file path (strings).

    Returns:
        A single string containing the transcribed text.
    """
    all_text = ""
    try:
        # Read audio and encode as base64
        with open(audio_path, "rb") as audio_file:
            audio_bytes = audio_file.read()

        audio_base64 = base64.b64encode(audio_bytes).decode()

        # Prepare the prompt including the base64 image data
        message = [
            HumanMessage(
                content=[
                    {
                        "type": "text",
                        "text": (
                            "Transcribe the following audio input:"
                        ),
                    },
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": audio_base64,
                            "format": "wav"
                        },
                    },
                ]
            )
        ]

        # Call the vision-capable model
        response = google_llm.invoke(message)

        # Append extracted text
        all_text += response.content + "\n\n"
        return all_text.strip()
    
    except Exception as e:
        # You can choose whether to raise or just return an empty string / error message
        error_msg = f"Error transcribing audio: {str(e)}"
        print(error_msg)
        return ""

#WEB_SEARCH_TOOL
@tool
def web_search(query: str) -> str:
    """Perform a web search and return the top 5 results."""
    #search_tool = DuckDuckGoSearchRun()
    search_tool = TavilySearchResults(searxch_depth='basic')
    result = search_tool.invoke(query)
    return result

#FILE_PARSE_TOOL
@tool
def read_file(file_path: str) -> str:
    """
    Reads a text based file and returns its content as a string.

    Args:
        file_path (str): The path to the file.

    Returns:
        str: The content of the file.
    """
    if file_path.endswith('.txt'):
        with open(file_path, 'r') as file:
            return file.read()
    elif file_path.endswith('.csv'):
        return pd.read_csv(file_path).to_string()
    elif file_path.endswith('.xlsx'):
        return pd.read_excel(file_path).to_string()
    elif file_path.endswith('.py'):
        with open(file_path, 'r') as file:
            return file.read()
    else:
        raise ValueError("Unsupported file format. Only .txt, .csv, and .xlsx are supported.")