ag2 0.4b1__py3-none-any.whl → 0.4.1__py3-none-any.whl

autogen/agentchat/contrib/captainagent/tools/data_analysis/calculate_skewness_and_kurtosis.py

@@ -0,0 +1,29 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def calculate_skewness_and_kurtosis(csv_file: str, column_name: str) -> tuple:
+    """
+    Calculate the skewness and kurtosis of a specified column in a CSV file. The kurtosis is calculated using the Fisher definition.
+    The two metrics are computed using scipy.stats functions.
+
+    Args:
+    csv_file (str): The path to the CSV file.
+    column_name (str): The name of the column to calculate skewness and kurtosis for.
+
+    Returns:
+    tuple: (skewness, kurtosis)
+    """
+    import pandas as pd
+    from scipy.stats import kurtosis, skew
+
+    # Read the CSV file into a pandas DataFrame
+    df = pd.read_csv(csv_file)
+
+    # Extract the specified column
+    column = df[column_name]
+
+    # Calculate the skewness and kurtosis
+    skewness = skew(column)
+    kurt = kurtosis(column)
+
+    return skewness, kurt

autogen/agentchat/contrib/captainagent/tools/data_analysis/detect_outlier_iqr.py

@@ -0,0 +1,29 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def detect_outlier_iqr(csv_file: str, column_name: str):
+    """
+    Detect outliers in a specified column of a CSV file using the IQR method.
+
+    Args:
+    csv_file (str): The path to the CSV file.
+    column_name (str): The name of the column to detect outliers in.
+
+    Returns:
+    list: A list of row indices that correspond to the outliers.
+    """
+    import pandas as pd
+
+    # Read the CSV file into a pandas DataFrame
+    df = pd.read_csv(csv_file)
+
+    # Calculate the quartiles and IQR for the specified column
+    q1 = df[column_name].quantile(0.25)
+    q3 = df[column_name].quantile(0.75)
+    iqr = q3 - q1
+
+    # Find the outliers based on the defined criteria
+    outliers = df[(df[column_name] < q1 - 1.5 * iqr) | (df[column_name] > q3 + 1.5 * iqr)]
+
+    # Return the row indices of the outliers
+    return outliers.index.tolist()

autogen/agentchat/contrib/captainagent/tools/data_analysis/detect_outlier_zscore.py

@@ -0,0 +1,29 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def detect_outlier_zscore(csv_file, column_name, threshold=3):
+    """
+    Detect outliers in a CSV file based on a specified column. The outliers are determined by calculating the z-score of the data points in the column.
+
+    Args:
+    csv_file (str): The path to the CSV file.
+    column_name (str): The name of the column to calculate z-scores for.
+    threshold (float, optional): The threshold value for determining outliers. By default set to 3.
+
+    Returns:
+    list: A list of row indices where the z-score is above the threshold.
+    """
+    import numpy as np
+    import pandas as pd
+
+    # Read the CSV file into a pandas DataFrame
+    df = pd.read_csv(csv_file)
+
+    # Calculate the z-score for the specified column
+    z_scores = np.abs((df[column_name] - df[column_name].mean()) / df[column_name].std())
+
+    # Find the row indices where the z-score is above the threshold
+    outlier_indices = np.where(z_scores > threshold)[0]
+
+    # Return the row indices of the outliers
+    return outlier_indices

autogen/agentchat/contrib/captainagent/tools/data_analysis/explore_csv.py

@@ -0,0 +1,22 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def explore_csv(file_path, num_lines=5):
+    """
+    Reads a CSV file and prints the column names, shape, data types, and the first few lines of data.
+
+    Args:
+        file_path (str): The path to the CSV file.
+        num_lines (int, optional): The number of lines to print. Defaults to 5.
+    """
+    import pandas as pd
+
+    df = pd.read_csv(file_path)
+    header = df.columns
+    print("Columns:")
+    print(", ".join(header))
+    print("Shape:", df.shape)
+    print("Data Types:")
+    print(df.dtypes)
+    print("First", num_lines, "lines:")
+    print(df.head(num_lines))

autogen/agentchat/contrib/captainagent/tools/data_analysis/shapiro_wilk_test.py

@@ -0,0 +1,31 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["pandas", "scipy"])
+def shapiro_wilk_test(csv_file, column_name):
+    """
+    Perform the Shapiro-Wilk test on a specified column of a CSV file.
+
+    Args:
+    csv_file (str): The path to the CSV file.
+    column_name (str): The name of the column to perform the test on.
+
+    Returns:
+    float: The p-value resulting from the Shapiro-Wilk test.
+    """
+    import pandas as pd
+    from scipy.stats import shapiro
+
+    # Read the CSV file into a pandas DataFrame
+    df = pd.read_csv(csv_file)
+
+    # Extract the specified column as a numpy array
+    column_data = df[column_name].values
+
+    # Perform the Shapiro-Wilk test
+    _, p_value = shapiro(column_data)
+
+    return p_value

autogen/agentchat/contrib/captainagent/tools/information_retrieval/arxiv_download.py

@@ -0,0 +1,26 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+import arxiv
+
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["arxiv"], ["arxiv"])
+def arxiv_download(id_list: list, download_dir="./"):
+    """
+    Downloads PDF files from ArXiv based on a list of arxiv paper IDs.
+
+    Args:
+        id_list (list): A list of paper IDs to download. e.g. [2302.00006v1]
+        download_dir (str, optional): The directory to save the downloaded PDF files. Defaults to './'.
+
+    Returns:
+        list: A list of paths to the downloaded PDF files.
+    """
+    paths = []
+    for paper in arxiv.Client().results(arxiv.Search(id_list=id_list)):
+        path = paper.download_pdf(download_dir, filename=paper.get_short_id() + ".pdf")
+        paths.append(path)
+        print("Paper id:", paper.get_short_id(), "Downloaded to:", path)
+    return paths

autogen/agentchat/contrib/captainagent/tools/information_retrieval/arxiv_search.py

@@ -0,0 +1,55 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+import arxiv
+
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["arxiv"], ["arxiv"])
+def arxiv_search(query, max_results=10, sortby="relevance"):
+    """
+    Search for articles on arXiv based on the given query.
+
+    Args:
+        query (str): The search query.
+        max_results (int, optional): The maximum number of results to retrieve. Defaults to 10.
+        sortby (str, optional): The sorting criterion for the search results. Can be 'relevance' or 'submittedDate'. Defaults to 'relevance'.
+
+    Returns:
+        list: A list of dictionaries containing information about the search results. Each dictionary contains the following keys:
+            - 'title': The title of the article.
+            - 'authors': The authors of the article.
+            - 'summary': The summary of the article.
+            - 'entry_id': The entry ID of the article.
+            - 'doi': The DOI of the article (If applicable).
+            - 'published': The publication date of the article in the format 'Y-M'.
+    """
+
+    def get_author(r):
+        return ", ".join(a.name for a in r.authors)
+
+    criterion = {"relevance": arxiv.SortCriterion.Relevance, "submittedDate": arxiv.SortCriterion.SubmittedDate}[sortby]
+
+    client = arxiv.Client()
+    search = arxiv.Search(query=query, max_results=max_results, sort_by=criterion)
+    res = []
+    results = client.results(search)
+    for r in results:
+        print("Entry id:", r.entry_id)
+        print("Title:", r.title)
+        print("Authors:", get_author(r))
+        print("DOI:", r.doi)
+        print("Published:", r.published.strftime("%Y-%m"))
+        # print("Summary:", r.summary)
+        res.append(
+            {
+                "title": r.title,
+                "authors": get_author(r),
+                "summary": r.summary,
+                "entry_id": r.entry_id,
+                "doi": r.doi,
+                "published": r.published.strftime("%Y-%m"),
+            }
+        )
+    return res

autogen/agentchat/contrib/captainagent/tools/information_retrieval/extract_pdf_image.py

@@ -0,0 +1,54 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+import os
+
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["PyMuPDF"], ["os"])
+def extract_pdf_image(pdf_path: str, output_dir: str, page_number=None):
+    """
+    Extracts images from a PDF file and saves them to the specified output directory.
+
+    Args:
+        pdf_path (str): The path to the PDF file.
+        output_dir (str): The directory to save the extracted images.
+        page_number (int, optional): The page number to extract images from. If not provided, extract images from all pages.
+    """
+    import fitz  # PyMuPDF library
+
+    # Open the PDF file
+    doc = fitz.open(pdf_path)
+
+    # Create the output directory if it doesn't exist
+    os.makedirs(output_dir, exist_ok=True)
+
+    # Extract images from the PDF file
+    images = []
+    if page_number is not None:
+        page = doc[page_number - 1]  # Adjust page number to 0-based index
+        for img in page.get_images():
+            xref = img[0]
+            base_image = doc.extract_image(xref)
+            image_bytes = base_image["image"]
+            images.append(image_bytes)
+    else:
+        for page in doc:
+            for img in page.get_images():
+                xref = img[0]
+                base_image = doc.extract_image(xref)
+                image_bytes = base_image["image"]
+                images.append(image_bytes)
+
+    # Save the extracted images
+    for i, image_bytes in enumerate(images):
+        image_path = os.path.join(output_dir, f"image_{i}.png")
+        with open(image_path, "wb") as f:
+            f.write(image_bytes)
+
+    # Print the total number of images saved
+    print(f"Saved a total of {len(images)} images")
+
+    # Close the PDF file
+    doc.close()

autogen/agentchat/contrib/captainagent/tools/information_retrieval/extract_pdf_text.py

@@ -0,0 +1,39 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["PyMuPDF"])
+def extract_pdf_text(pdf_path, page_number=None):
+    """
+    Extracts text from a specified page or the entire PDF file.
+
+    Args:
+        pdf_path (str): The path to the PDF file.
+        page_number (int, optional): The page number to extract (starting from 0). If not provided,
+            the function will extract text from the entire PDF file.
+
+    Returns:
+        str: The extracted text.
+    """
+    import fitz
+
+    # Open the PDF file
+    doc = fitz.open(pdf_path)
+
+    # Extract text from the entire PDF file or a specific page
+    text = ""
+    if page_number is None:
+        # Extract content from the entire PDF file
+        for page in doc:
+            text += page.get_text()
+    else:
+        # Extract content from a specific page
+        page = doc[page_number]
+        text = page.get_text()
+
+    # Close the PDF file
+    doc.close()
+
+    return text

autogen/agentchat/contrib/captainagent/tools/information_retrieval/get_wikipedia_text.py

@@ -0,0 +1,22 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def get_wikipedia_text(title):
+    """
+    Retrieves the text content of a Wikipedia page. It does not support tables and other complex formatting.
+
+    Args:
+        title (str): The title of the Wikipedia page.
+
+    Returns:
+        str or None: The text content of the Wikipedia page if it exists, None otherwise.
+    """
+    import wikipediaapi
+
+    wiki_wiki = wikipediaapi.Wikipedia("Mozilla/5.0 (merlin@example.com)", "en")
+    page = wiki_wiki.page(title)
+
+    if page.exists():
+        return page.text
+    else:
+        return None

autogen/agentchat/contrib/captainagent/tools/information_retrieval/get_youtube_caption.py

@@ -0,0 +1,35 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+# alternative api: https://rapidapi.com/omarmhaimdat/api/youtube-v2
+
+
+def get_youtube_caption(videoId):
+    """
+    Retrieves the captions for a YouTube video.
+
+    Args:
+        videoId (str): The ID of the YouTube video.
+
+    Returns:
+        str: The captions of the YouTube video in text format.
+
+    Raises:
+        KeyError: If the RAPID_API_KEY environment variable is not set.
+    """
+    import os
+
+    import requests
+
+    RAPID_API_KEY = os.environ["RAPID_API_KEY"]
+    video_url = f"https://www.youtube.com/watch?v={videoId}"
+    url = "https://youtube-transcript3.p.rapidapi.com/api/transcript-with-url"
+
+    querystring = {"url": video_url, "lang": "en", "flat_text": "true"}
+
+    headers = {"X-RapidAPI-Key": RAPID_API_KEY, "X-RapidAPI-Host": "youtube-transcript3.p.rapidapi.com"}
+
+    response = requests.get(url, headers=headers, params=querystring)
+    response = response.json()
+    print(response)
+    return response["transcript"]

autogen/agentchat/contrib/captainagent/tools/information_retrieval/image_qa.py

@@ -0,0 +1,61 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+import os
+
+from PIL import Image
+
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["transformers", "torch"], ["transformers", "torch", "PIL", "os"])
+def image_qa(image, question, ckpt="Salesforce/blip-vqa-base"):
+    """
+    Perform question answering on an image using a pre-trained VQA model.
+
+    Args:
+        image (Union[str, Image.Image]): The image to perform question answering on. It can be either file path to the image or a PIL Image object.
+        question: The question to ask about the image.
+
+    Returns:
+        dict: The generated answer text.
+    """
+    import torch
+    from transformers import BlipForQuestionAnswering, BlipProcessor
+
+    def image_processing(img):
+        if isinstance(img, Image.Image):
+            return img.convert("RGB")
+        elif isinstance(img, str):
+            if os.path.exists(img):
+                return Image.open(img).convert("RGB")
+            else:
+                full_path = img
+                if os.path.exists(full_path):
+                    return Image.open(full_path).convert("RGB")
+                else:
+                    raise FileNotFoundError
+
+    def text_processing(file_path):
+        # Check the file extension
+        if file_path.endswith(".txt"):
+            with open(file_path, "r") as file:
+                content = file.read()
+        else:
+            # if the file is not .txt, then it is a string, directly return the string
+            return file_path
+        return content
+
+    image = image_processing(image)
+    question = text_processing(question)
+
+    processor = BlipProcessor.from_pretrained(ckpt)
+    model = BlipForQuestionAnswering.from_pretrained(ckpt, torch_dtype=torch.float16).to("cuda")
+
+    raw_image = image
+
+    inputs = processor(raw_image, question, return_tensors="pt").to("cuda", torch.float16)
+    out = model.generate(**inputs)
+    result_formatted = processor.decode(out[0], skip_special_tokens=True)
+
+    return result_formatted

autogen/agentchat/contrib/captainagent/tools/information_retrieval/optical_character_recognition.py

@@ -0,0 +1,62 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+import os
+
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["easyocr"], ["os"])
+def optical_character_recognition(image):
+    """
+    Perform optical character recognition (OCR) on the given image.
+
+    Args:
+        image (Union[str, Image.Image]): The image to perform OCR on. It can be either a file path or an Image object.
+
+    Returns:
+        str: The extracted text from the image.
+
+    Raises:
+        FileNotFoundError: If the image file path does not exist.
+    """
+    import io
+
+    import easyocr
+    from PIL import Image
+
+    def image_processing(img):
+        if isinstance(img, Image.Image):
+            return img.convert("RGB")
+        elif isinstance(img, str):
+            if os.path.exists(img):
+                return Image.open(img).convert("RGB")
+            else:
+                full_path = img
+                if os.path.exists(full_path):
+                    return Image.open(full_path).convert("RGB")
+                else:
+                    raise FileNotFoundError
+
+    reader = easyocr.Reader(["en"])  # Load the OCR model into memory
+
+    if isinstance(image, str):
+        # If image is a path, use it directly
+        if not os.path.exists(image):
+            raise FileNotFoundError
+        image_path_or_bytes = image
+    else:
+        # If image is an Image object, convert it to a bytes stream
+        buffer = io.BytesIO()
+        image = image_processing(image)  # Process the image if needed
+        image.save(buffer, format="JPEG")
+        buffer.seek(0)
+        image_path_or_bytes = buffer
+
+    # Read text from the image or image path
+    result = reader.readtext(image_path_or_bytes)
+
+    # Extract only the text from the result
+    result_text = [text for _, text, _ in result]
+
+    return ", ".join(result_text)

autogen/agentchat/contrib/captainagent/tools/information_retrieval/perform_web_search.py

@@ -0,0 +1,48 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def perform_web_search(query, count=10, offset=0):
+    """
+    Perform a web search using Bing API.
+
+    Args:
+        query (str): The search query.
+        count (int, optional): Number of search results to retrieve. Defaults to 10.
+        offset (int, optional): Offset of the first search result. Defaults to 0.
+
+    Returns:
+        The name, URL and snippet of each search result.
+    """
+    import os
+
+    import requests
+
+    # Get the Bing API key from the environment variable
+    bing_api_key = os.getenv("BING_API_KEY")
+
+    # Check if the API key is available
+    if not bing_api_key:
+        raise ValueError("Bing API key not found in environment variable")
+
+    # Set up the API request
+    url = "https://api.bing.microsoft.com/v7.0/search"
+    headers = {
+        "Ocp-Apim-Subscription-Key": bing_api_key,
+    }
+    params = {
+        "q": query,
+        "count": count,  # Number of search results to retrieve
+        "offset": offset,  # Offset of the first search result
+    }
+
+    # Send the API request
+    response = requests.get(url, headers=headers, params=params)
+    response.raise_for_status()
+
+    # Process the search results
+    search_results = response.json()
+    for index, result in enumerate(search_results["webPages"]["value"]):
+        print(f"Search Result {index+1}:")
+        print(result["name"])
+        print(result["url"])
+        print(result["snippet"])

autogen/agentchat/contrib/captainagent/tools/information_retrieval/scrape_wikipedia_tables.py

@@ -0,0 +1,34 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def scrape_wikipedia_tables(url: str, header_keyword: str):
+    """
+    Scrapes Wikipedia tables based on a given URL and header keyword.
+
+    Args:
+        url: The URL of the Wikipedia page to scrape.
+        header_keyword: The keyword to search for in the headers of the page.
+
+    Returns:
+        list: A list of lists representing the scraped table data. Each inner list represents a row in the table,
+              with each element representing a cell value.
+    """
+    import requests
+    from bs4 import BeautifulSoup
+
+    response = requests.get(url)
+    response.raise_for_status()
+    soup = BeautifulSoup(response.content, "html.parser")
+    headers = soup.find_all(["h1", "h2", "h3", "h4", "h5", "h6"])
+    data = []
+    for header in headers:
+        if header_keyword.lower() in header.text.lower():
+            table = header.find_next_sibling("table", class_="wikitable")
+            if table:
+                rows = table.find_all("tr")
+                for row in rows:
+                    cols = row.find_all(["th", "td"])
+                    cols = [ele.text.strip() for ele in cols]
+                    data.append([ele for ele in cols if ele])
+                break
+    return data

autogen/agentchat/contrib/captainagent/tools/information_retrieval/transcribe_audio_file.py

@@ -0,0 +1,22 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["openai-whisper"])
+def transcribe_audio_file(file_path):
+    """
+    Transcribes the audio file located at the given file path.
+
+    Args:
+        file_path (str): The path to the audio file.
+
+    Returns:
+        str: The transcribed text from the audio file.
+    """
+    import whisper
+
+    model = whisper.load_model("base")
+    result = model.transcribe(file_path)
+    return result["text"]

autogen/agentchat/contrib/captainagent/tools/information_retrieval/youtube_download.py

@@ -0,0 +1,36 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+def youtube_download(url: str):
+    """
+    Downloads a YouTube video and returns the download link.
+
+    Args:
+        url: The URL of the YouTube video.
+
+    Returns:
+        str: The download link for the audio.
+    """
+    import os
+
+    import requests
+
+    endpoint = "https://youtube-mp3-downloader2.p.rapidapi.com/ytmp3/ytmp3/"
+
+    querystring = {"url": url}
+
+    headers = {
+        "X-RapidAPI-Key": os.environ.get("RAPIDAPI_KEY"),
+        "X-RapidAPI-Host": "youtube-mp3-downloader2.p.rapidapi.com",
+    }
+
+    response = requests.get(endpoint, headers=headers, params=querystring)
+    response = response.json()
+
+    if "link" in response:
+        return response["link"]
+    else:
+        print("Error: Unable to retrieve download link.")
+        print(response)
+        # or you can return an error message
+        # return "Error: Unable to retrieve download link."

autogen/agentchat/contrib/captainagent/tools/math/calculate_circle_area_from_diameter.py

@@ -0,0 +1,22 @@
+# Copyright (c) 2023 - 2024, Owners of https://github.com/ag2ai
+#
+# SPDX-License-Identifier: Apache-2.0
+from autogen.coding.func_with_reqs import with_requirements
+
+
+@with_requirements(["sympy"])
+def calculate_circle_area_from_diameter(diameter):
+    """
+    Calculate the area of a circle given its diameter.
+
+    Args:
+    diameter (float): The diameter of the circle.
+
+    Returns:
+    float: The area of the circle.
+    """
+    from sympy import pi
+
+    radius = diameter / 2
+    area = pi * radius**2
+    return area