Supports audio transcription

app.py

@@ -1,3 +1,4 @@
+from smolagents import tool
 import re
 import os
 import gradio as gr
@@ -26,8 +27,10 @@ from smolagents import (
     DuckDuckGoSearchTool,
     FinalAnswerTool,
     OpenAIServerModel,
-    ToolCallingAgent
+    ToolCallingAgent,
 )
+#from smolagents.tools.transcriber import TranscriberTool
+
 from pypdf import PdfReader
 
 # Load environment variables from .env file
@@ -546,6 +549,45 @@ def load_text_file(file_path: str, detect_format: bool = True) -> str:
         return f"Error reading file: {str(e)}"
     
 
+@tool
+def transcribe_with_whisper(audio_path: str) -> str:
+    """
+    Transcribes audio using OpenAI's Whisper model.
+    
+    Args:
+        audio_path: Path to the audio file to transcribe
+        
+    Returns:
+        The transcribed text
+    """
+
+    if not os.path.exists(audio_path):
+        return f"Error: Audio file not found at {audio_path}"
+
+    # Try with faster-whisper if available, fall back to whisper
+    try:
+        try:
+            # Try with faster-whisper first (it's faster)
+            from faster_whisper import WhisperModel
+
+            model = WhisperModel("medium.en", device="cpu")
+            segments, info = model.transcribe(audio_path)
+
+            transcript = " ".join([segment.text for segment in segments])
+            return transcript
+
+        except ImportError:
+            # Fall back to original whisper
+            #import whisper
+
+            #model = whisper.load_model("small")
+            #result = model.transcribe(audio_path)
+            #return result["text"]
+            return "Failed to transcribe audio with faster-whisper"
+
+    except Exception as e:
+        return f"Error transcribing audio: {str(e)}"
+    
 
 class BasicAgent:
     def __init__(self):
@@ -715,6 +757,18 @@ class BasicAgent:
             #use_e2b_executor=True
         )
 
+        # Initialize the agent with the transcription tool
+        # self.transcriber_agent = CodeAgent(
+        #     model=reasoning_model,
+        #     tools=[],
+        #     add_base_tools=True,
+        #     name="transcriber_agent",
+        #     description="Transcribes audio file to text, i.e. take audio file and generates the the transcription of the audio.",
+        #     # Add any imports your agent might need
+        #     additional_authorized_imports=["pandas", "numpy"],
+        #     max_steps=5
+        # )
+
         # Define the Manager Agent
         # This agent manages tasks and delegates to other agents
         self.manager_agent = CodeAgent(
@@ -725,12 +779,14 @@ class BasicAgent:
                    load_xlsx_file_as_markdown,
                    query_wikipedia,
                    load_text_file,
+                   transcribe_with_whisper,
                    FinalAnswerTool()],
             # Specify the agents this manager oversees
             managed_agents=[self.web_search_specialist_agent,
                             self.reasoning_agent,
                             self.youtube_qa_agent,
                             self.python_code_executer],
+                            #self.transcriber_agent],
             name="manager_agent",  # Give the manager agent a name
             description="Manages tasks by delegating to other agents.",  # Describe its role
             additional_authorized_imports=[

poetry.lock

@@ -211,6 +211,59 @@ files = [
 [package.dependencies]
 cryptography = "*"
 
+[[package]]
+name = "av"
+version = "14.3.0"
+description = "Pythonic bindings for FFmpeg's libraries."
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "av-14.3.0-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:fb2fbd93685086c859748c147861dfb97ccf896dfbaa0141b8f15a1493d758e8"},
+    {file = "av-14.3.0-cp310-cp310-macosx_12_0_x86_64.whl", hash = "sha256:187fa564b130ac15b6ea7124c289be7fa8687d8e121d69b3000225cbff6414b0"},
+    {file = "av-14.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9c789487510e9630ce46610ecdb3b2271ec720b839282884c04950f3b8be65f2"},
+    {file = "av-14.3.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ca1711ef45fd711736125cb7e63e71dd9016127baae84c73cf0f08fb63d09a0b"},
+    {file = "av-14.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c69df85a9eb5d70709578954839dfe09fa952b177666fe963c96a052031eaee"},
+    {file = "av-14.3.0-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:bf000c608a15ae27c51c49142c3a2be0618bd7263cd804b1bfa30dd55460b3a0"},
+    {file = "av-14.3.0-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:bc723464d8ee806b5ac5a3915244019080e22ed55283884c729b336806483a62"},
+    {file = "av-14.3.0-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:d8e36dea941f3e1e7f3791c758cf52c392472cf36c51da19fd7288ab94b5d0e2"},
+    {file = "av-14.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:18680276d534b327e108d08ab8b35da1500696a4f1ce9658c4324028cfb4641e"},
+    {file = "av-14.3.0-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c3c6aa31553de2578ca7424ce05803c0672525d0cef542495f47c5a923466dcc"},
+    {file = "av-14.3.0-cp311-cp311-macosx_12_0_x86_64.whl", hash = "sha256:5bc930153f945f858c2aca98b8a4fa7265f93d6015729dbb6b780b58ce26325c"},
+    {file = "av-14.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:943d46a1a93f1282abaeec0d1c62698104958865c30df9478f48a6aef7328eb8"},
+    {file = "av-14.3.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:8485965f71c84f15cf597e5e5e1731e076d967fc519e074f6f7737a26f3fd89b"},
+    {file = "av-14.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b64f9410121548ca3ce4283d9f42dbaadfc2af508810bafea1f0fa745d2a9dee"},
+    {file = "av-14.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8de6a2b6964d68897249dd41cdb99ca21a59e2907f378dc7e56268a9b6b3a5a8"},
+    {file = "av-14.3.0-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:5f901aaaf9f59119717ae37924ff81f9a4e2405177e5acf5176335b37dba41ba"},
+    {file = "av-14.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:655fe073fa0c97abada8991d362bdb2cc09b021666ca94b82820c64e11fd9f13"},
+    {file = "av-14.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:5135318ffa86241d5370b6d1711aedf6a0c9bea181e52d9eb69d545358183be5"},
+    {file = "av-14.3.0-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:8250680e4e17c404008005b60937248712e9c621689bbc647577d8e2eaa00a66"},
+    {file = "av-14.3.0-cp312-cp312-macosx_12_0_x86_64.whl", hash = "sha256:349aa6ef529daaede95f37e9825c6e36fddb15906b27938d9e22dcdca2e1f648"},
+    {file = "av-14.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f953a9c999add37b953cb3ad4ef3744d3d4eee50ef1ffeb10cb1f2e6e2cbc088"},
+    {file = "av-14.3.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1eaefb47d2ee178adfcedb9a70678b1a340a6670262d06ffa476da9c7d315aef"},
+    {file = "av-14.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e3b7ca97af1eb3e41e7971a0eb75c1375f73b89ff54afb6d8bf431107160855"},
+    {file = "av-14.3.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:e2a0404ac4bfa984528538fb7edeb4793091a5cc6883a473d13cb82c505b62e0"},
+    {file = "av-14.3.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:2ceb45e998184231bcc99a14f91f4265d959e6b804fe9054728e9855214b2ad5"},
+    {file = "av-14.3.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:f87df669f49d5202f3933dc94e606353f5c5f9a709a1c0823b3f6d6333560bd7"},
+    {file = "av-14.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:90ef006bc334fff31d5e839368bcd8c6345959749a980ce6f7a8a5fa2c8396e7"},
+    {file = "av-14.3.0-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:0ec9ed764acbbcc590f30891abdb792c2917e13c91c407751f01ff3d2f957672"},
+    {file = "av-14.3.0-cp313-cp313-macosx_12_0_x86_64.whl", hash = "sha256:5c886dcbc7d2f6b6c88e0bea061b268895265d1ec8593e1fd2c69c9795225b9d"},
+    {file = "av-14.3.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:acfd2f6d66b3587131060cba58c007028784ba26d1615d43e0d4afdc37d5945a"},
+    {file = "av-14.3.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ffee262ea4bf016a3e48ce75716ca23adef89cf0d7a55618423fe63bc5986ac2"},
+    {file = "av-14.3.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9d68e5dd7a1b7373bbdbd82fa85b97d5aed4441d145c3938ba1fe3d78637bb05"},
+    {file = "av-14.3.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:dd2d8fc3d514305fa979363298bf600fa7f48abfb827baa9baf1a49520291a62"},
+    {file = "av-14.3.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:96d19099b3867fac67dfe2bb29fd15ef41f1f508d2ec711d1f081e505a9a8d04"},
+    {file = "av-14.3.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:15dc4a7c916620b733613661ceb7a186f141a0fc98608dfbafacdc794a7cd665"},
+    {file = "av-14.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:f930faa2e6f6a46d55bc67545b81f5b22bd52975679c1de0f871fc9f8ca95711"},
+    {file = "av-14.3.0-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:a395d5cea24e9fe73ee81dc7f8acc1eb36eb7d0305e757cd7f31bdafcdb86664"},
+    {file = "av-14.3.0-cp39-cp39-macosx_12_0_x86_64.whl", hash = "sha256:cee53b155e61ed620b95898f50113ae2cfe70c0c6ec9fbe787cddd350dd9fda8"},
+    {file = "av-14.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1acebc51364f170543b339144890ef274d00f258816064639617a1f4636e01e3"},
+    {file = "av-14.3.0-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a0fb86853f1e2fb4afc9cdb13b4d2326a480a7b61486760b44461eabfd771e3a"},
+    {file = "av-14.3.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c2e80b867ead4d8d3440a1e582430937ad547c2b92e2050e7d276bfc06021a77"},
+    {file = "av-14.3.0-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:267780e1b8af93bb586a5e26c5f690541d9e2b0558e5046b9fbd02d313106abc"},
+    {file = "av-14.3.0-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:a3d43d4e46e83cffc11fd28c6a67d4443d23076562b296d320f5720492d7be2a"},
+]
+
 [[package]]
 name = "beautifulsoup4"
 version = "4.13.4"
@@ -457,6 +510,24 @@ files = [
     {file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
 ]
 
+[[package]]
+name = "coloredlogs"
+version = "15.0.1"
+description = "Colored terminal output for Python's logging module"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+groups = ["main"]
+files = [
+    {file = "coloredlogs-15.0.1-py2.py3-none-any.whl", hash = "sha256:612ee75c546f53e92e70049c9dbfcc18c935a2b9a53b66085ce9ef6a6e5c0934"},
+    {file = "coloredlogs-15.0.1.tar.gz", hash = "sha256:7c991aa71a4577af2f82600d8f8f3a89f936baeaf9b50a9c197da014e5bf16b0"},
+]
+
+[package.dependencies]
+humanfriendly = ">=9.1"
+
+[package.extras]
+cron = ["capturer (>=2.4)"]
+
 [[package]]
 name = "cryptography"
 version = "44.0.2"
@@ -515,6 +586,46 @@ ssh = ["bcrypt (>=3.1.5)"]
 test = ["certifi (>=2024)", "cryptography-vectors (==44.0.2)", "pretend (>=0.7)", "pytest (>=7.4.0)", "pytest-benchmark (>=4.0)", "pytest-cov (>=2.10.1)", "pytest-xdist (>=3.5.0)"]
 test-randomorder = ["pytest-randomly"]
 
+[[package]]
+name = "ctranslate2"
+version = "4.6.0"
+description = "Fast inference engine for Transformer models"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "ctranslate2-4.6.0-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:aeadeb7fd11f37ec96b40952402ce35ee7d214b09e1634fb11934f7d5e4ad1d7"},
+    {file = "ctranslate2-4.6.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b5da5eee549db5137e9082fa7b479bd8bf273d9a961afdf3f8ecff2527fdf71e"},
+    {file = "ctranslate2-4.6.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6ed15383afc9d4e448d4090389f06c141a5ce1510e610c1aa7021332cfbc97f1"},
+    {file = "ctranslate2-4.6.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0ac5a714890e9f5f6876005c8a8fb2bdf9bec88437c38ff3efd71bd65333519d"},
+    {file = "ctranslate2-4.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:f99502996361f7dc35f00b95a01e414c8d8ff75b8a58da97e378ceb5560689ae"},
+    {file = "ctranslate2-4.6.0-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:2f80538ce0f619540499b505747179ee5e86a5c9b80361c1582f7c725d660509"},
+    {file = "ctranslate2-4.6.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:00097c52bf6be97f753e39bc7399f23bdf9803df942094b8cecdd8432f0335d5"},
+    {file = "ctranslate2-4.6.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9f4691a66cb7b9ffb04ebff4291055c20223449a6534c4a52b7432b0853946d0"},
+    {file = "ctranslate2-4.6.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:79e4f2e8ea7f24797c80e0f4593d30447ef8da9036ebb4402b7f6c54687b7a46"},
+    {file = "ctranslate2-4.6.0-cp311-cp311-win_amd64.whl", hash = "sha256:865649cebae240fe8c5b3e868354ea6c611d2ec17f335848caf890fca6c62d71"},
+    {file = "ctranslate2-4.6.0-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:ff3ad05010857d450ee40fd9c28a33c10215a7180e189151e378ed2d19be8a57"},
+    {file = "ctranslate2-4.6.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:78a844c633b6d450b20adac296f7f60ac2a67f2c76e510a83c8916835dc13f04"},
+    {file = "ctranslate2-4.6.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:44bf4b973ea985b80696093e11e9c72909aee55b35abb749428333822c70ce68"},
+    {file = "ctranslate2-4.6.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:06b2ca5c2905b540dd833a0b75d912ec9acc18d33a2dc4f85f12032851659a0d"},
+    {file = "ctranslate2-4.6.0-cp312-cp312-win_amd64.whl", hash = "sha256:511cdf810a5bf6a2cec735799e5cd47966e63f8f7688fdee1b97fed621abda00"},
+    {file = "ctranslate2-4.6.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:6283ffe63831b980282ff64ab845c62c7ef771f2ce06cb34825fd7578818bf07"},
+    {file = "ctranslate2-4.6.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:2ebaae12ade184a235569235a875cf03d53b07732342f93b96ae76ef02c31961"},
+    {file = "ctranslate2-4.6.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a719cd765ec10fe20f9a866093e777a000fd926a0bf235c7921f12c84befb443"},
+    {file = "ctranslate2-4.6.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:039aa6cc3ed662931a60dec0be28abeaaceb3cc6f476060b8017a7a39a54a9f6"},
+    {file = "ctranslate2-4.6.0-cp313-cp313-win_amd64.whl", hash = "sha256:af555c75cb9a9cc6c385f38680b92fa426761cf690e4479b1e962e2b17e02972"},
+    {file = "ctranslate2-4.6.0-cp39-cp39-macosx_10_13_x86_64.whl", hash = "sha256:9bf6b954ca9a2d82d5d0f701eaf980c00ef58998aea71ce0b1c4f9ed3cc66c4d"},
+    {file = "ctranslate2-4.6.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:fbee3bc08f63b263b942631f1d49af9c27851ce1796ac8f69aa6c1048513878f"},
+    {file = "ctranslate2-4.6.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bc3c4c9ab59de1f05e78d0c37dc4cce58b55ed7760d0e12dc3de51d4b647cd02"},
+    {file = "ctranslate2-4.6.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f88fb05d6d22d702ecb2bb6eb236b77e0c55a6b577d4116bb697c6f509aa98c0"},
+    {file = "ctranslate2-4.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:3bf04cb9d1990b97a122137410dc6e93c7e24683f243218ef334afc0f5f6c030"},
+]
+
+[package.dependencies]
+numpy = "*"
+pyyaml = ">=5.3,<7"
+setuptools = "*"
+
 [[package]]
 name = "datasets"
 version = "3.5.1"
@@ -652,6 +763,30 @@ typing-extensions = ">=4.8.0"
 all = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.5)", "httpx (>=0.23.0)", "itsdangerous (>=1.1.0)", "jinja2 (>=3.1.5)", "orjson (>=3.2.1)", "pydantic-extra-types (>=2.0.0)", "pydantic-settings (>=2.0.0)", "python-multipart (>=0.0.18)", "pyyaml (>=5.3.1)", "ujson (>=4.0.1,!=4.0.2,!=4.1.0,!=4.2.0,!=4.3.0,!=5.0.0,!=5.1.0)", "uvicorn[standard] (>=0.12.0)"]
 standard = ["email-validator (>=2.0.0)", "fastapi-cli[standard] (>=0.0.5)", "httpx (>=0.23.0)", "jinja2 (>=3.1.5)", "python-multipart (>=0.0.18)", "uvicorn[standard] (>=0.12.0)"]
 
+[[package]]
+name = "faster-whisper"
+version = "1.1.1"
+description = "Faster Whisper transcription with CTranslate2"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "faster-whisper-1.1.1.tar.gz", hash = "sha256:50d27571970c1be0c2b2680a2593d5d12f9f5d2f10484f242a1afbe7cb946604"},
+    {file = "faster_whisper-1.1.1-py3-none-any.whl", hash = "sha256:5808dc334fb64fb4336921450abccfe5e313a859b31ba61def0ac7f639383d90"},
+]
+
+[package.dependencies]
+av = ">=11"
+ctranslate2 = ">=4.0,<5"
+huggingface-hub = ">=0.13"
+onnxruntime = ">=1.14,<2"
+tokenizers = ">=0.13,<1"
+tqdm = "*"
+
+[package.extras]
+conversion = ["transformers[torch] (>=4.23)"]
+dev = ["black (==23.*)", "flake8 (==6.*)", "isort (==5.*)", "pytest (==7.*)"]
+
 [[package]]
 name = "ffmpy"
 version = "0.3.2"
@@ -680,6 +815,18 @@ docs = ["furo (>=2024.8.6)", "sphinx (>=8.1.3)", "sphinx-autodoc-typehints (>=3)
 testing = ["covdefaults (>=2.3)", "coverage (>=7.6.10)", "diff-cover (>=9.2.1)", "pytest (>=8.3.4)", "pytest-asyncio (>=0.25.2)", "pytest-cov (>=6)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.28.1)"]
 typing = ["typing-extensions (>=4.12.2)"]
 
+[[package]]
+name = "flatbuffers"
+version = "25.2.10"
+description = "The FlatBuffers serialization format for Python"
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "flatbuffers-25.2.10-py2.py3-none-any.whl", hash = "sha256:ebba5f4d5ea615af3f7fd70fc310636fbb2bbd1f566ac0a23d98dd412de50051"},
+    {file = "flatbuffers-25.2.10.tar.gz", hash = "sha256:97e451377a41262f8d9bd4295cc836133415cc03d8cb966410a4af92eb00d26e"},
+]
+
 [[package]]
 name = "frozenlist"
 version = "1.6.0"
@@ -1083,6 +1230,21 @@ testing = ["InquirerPy (==0.3.4)", "Jinja2", "Pillow", "aiohttp", "fastapi", "gr
 torch = ["safetensors[torch]", "torch"]
 typing = ["types-PyYAML", "types-requests", "types-simplejson", "types-toml", "types-tqdm", "types-urllib3", "typing-extensions (>=4.8.0)"]
 
+[[package]]
+name = "humanfriendly"
+version = "10.0"
+description = "Human friendly output for text interfaces using Python"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+groups = ["main"]
+files = [
+    {file = "humanfriendly-10.0-py2.py3-none-any.whl", hash = "sha256:1697e1a8a8f550fd43c2865cd84542fc175a61dcb779b6fee18cf6b6ccba1477"},
+    {file = "humanfriendly-10.0.tar.gz", hash = "sha256:6b0b831ce8f15f7300721aa49829fc4e83921a9a301cc7f606be6686a2288ddc"},
+]
+
+[package.dependencies]
+pyreadline3 = {version = "*", markers = "sys_platform == \"win32\" and python_version >= \"3.8\""}
+
 [[package]]
 name = "idna"
 version = "3.10"
@@ -1574,6 +1736,24 @@ files = [
     {file = "mdurl-0.1.2.tar.gz", hash = "sha256:bb413d29f5eea38f31dd4754dd7377d4465116fb207585f97bf925588687c1ba"},
 ]
 
+[[package]]
+name = "mpmath"
+version = "1.3.0"
+description = "Python library for arbitrary-precision floating-point arithmetic"
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "mpmath-1.3.0-py3-none-any.whl", hash = "sha256:a0b2b9fe80bbcd81a6647ff13108738cfb482d481d826cc0e02f5b35e5c88d2c"},
+    {file = "mpmath-1.3.0.tar.gz", hash = "sha256:7a28eb2a9774d00c7bc92411c19a89209d5da7c4c9a9e227be8330a23a25b91f"},
+]
+
+[package.extras]
+develop = ["codecov", "pycodestyle", "pytest (>=4.6)", "pytest-cov", "wheel"]
+docs = ["sphinx"]
+gmpy = ["gmpy2 (>=2.1.0a4)"]
+tests = ["pytest (>=4.6)"]
+
 [[package]]
 name = "multidict"
 version = "6.4.3"
@@ -1778,6 +1958,42 @@ files = [
     {file = "numpy-2.2.5.tar.gz", hash = "sha256:a9c0d994680cd991b1cb772e8b297340085466a6fe964bc9d4e80f5e2f43c291"},
 ]
 
+[[package]]
+name = "onnxruntime"
+version = "1.21.1"
+description = "ONNX Runtime is a runtime accelerator for Machine Learning models"
+optional = false
+python-versions = ">=3.10"
+groups = ["main"]
+files = [
+    {file = "onnxruntime-1.21.1-cp310-cp310-macosx_13_0_universal2.whl", hash = "sha256:daedb5d33d8963062a25f4a3c788262074587f685a19478ef759a911b4b12c25"},
+    {file = "onnxruntime-1.21.1-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3a402f9bda0b1cc791d9cf31d23c471e8189a55369b49ef2b9d0854eb11d22c4"},
+    {file = "onnxruntime-1.21.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:15656a2d0126f4f66295381e39c8812a6d845ccb1bb1f7bf6dd0a46d7d602e7f"},
+    {file = "onnxruntime-1.21.1-cp310-cp310-win_amd64.whl", hash = "sha256:79bbedfd1263065532967a2132fb365a27ffe5f7ed962e16fec55cca741f72aa"},
+    {file = "onnxruntime-1.21.1-cp311-cp311-macosx_13_0_universal2.whl", hash = "sha256:8bee9b5ba7b88ae7bfccb4f97bbe1b4bae801b0fb05d686b28a722cb27c89931"},
+    {file = "onnxruntime-1.21.1-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:4b6a29a1767b92d543091349f5397a1c7619eaca746cd1bc47f8b4ec5a9f1a6c"},
+    {file = "onnxruntime-1.21.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:982dcc04a6688e1af9e3da1d4ef2bdeb11417cf3f8dde81f8f721043c1919a4f"},
+    {file = "onnxruntime-1.21.1-cp311-cp311-win_amd64.whl", hash = "sha256:2b6052c04b9125319293abb9bdcce40e806db3e097f15b82242d4cd72d81fd0c"},
+    {file = "onnxruntime-1.21.1-cp312-cp312-macosx_13_0_universal2.whl", hash = "sha256:f615c05869a523a94d0a4de1f0936d0199a473cf104d630fc26174bebd5759bd"},
+    {file = "onnxruntime-1.21.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:79dfb1f47386c4edd115b21015354b2f05f5566c40c98606251f15a64add3cbe"},
+    {file = "onnxruntime-1.21.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:2742935d6610fe0f58e1995018d9db7e8239d0201d9ebbdb7964a61386b5390a"},
+    {file = "onnxruntime-1.21.1-cp312-cp312-win_amd64.whl", hash = "sha256:a7afdb3fcb162f5536225e13c2b245018068964b1d0eee05303ea6823ca6785e"},
+    {file = "onnxruntime-1.21.1-cp313-cp313-macosx_13_0_universal2.whl", hash = "sha256:ed4f9771233a92edcab9f11f537702371d450fe6cd79a727b672d37b9dab0cde"},
+    {file = "onnxruntime-1.21.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:1bc100fd1f4f95258e7d0f7068ec69dec2a47cc693f745eec9cf4561ee8d952a"},
+    {file = "onnxruntime-1.21.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0fea0d2b98eecf4bebe01f7ce9a265a5d72b3050e9098063bfe65fa2b0633a8e"},
+    {file = "onnxruntime-1.21.1-cp313-cp313-win_amd64.whl", hash = "sha256:da606061b9ed1b05b63a37be38c2014679a3e725903f58036ffd626df45c0e47"},
+    {file = "onnxruntime-1.21.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:94674315d40d521952bfc28007ce9b6728e87753e1f18d243c8cd953f25903b8"},
+    {file = "onnxruntime-1.21.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5c9e4571ff5b2a5d377d414bc85cd9450ba233a9a92f766493874f1093976453"},
+]
+
+[package.dependencies]
+coloredlogs = "*"
+flatbuffers = "*"
+numpy = ">=1.21.6"
+packaging = "*"
+protobuf = "*"
+sympy = "*"
+
 [[package]]
 name = "openai"
 version = "1.77.0"
@@ -2245,6 +2461,25 @@ files = [
     {file = "propcache-0.3.1.tar.gz", hash = "sha256:40d980c33765359098837527e18eddefc9a24cea5b45e078a7f3bb5b032c6ecf"},
 ]
 
+[[package]]
+name = "protobuf"
+version = "6.30.2"
+description = ""
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "protobuf-6.30.2-cp310-abi3-win32.whl", hash = "sha256:b12ef7df7b9329886e66404bef5e9ce6a26b54069d7f7436a0853ccdeb91c103"},
+    {file = "protobuf-6.30.2-cp310-abi3-win_amd64.whl", hash = "sha256:7653c99774f73fe6b9301b87da52af0e69783a2e371e8b599b3e9cb4da4b12b9"},
+    {file = "protobuf-6.30.2-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:0eb523c550a66a09a0c20f86dd554afbf4d32b02af34ae53d93268c1f73bc65b"},
+    {file = "protobuf-6.30.2-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:50f32cc9fd9cb09c783ebc275611b4f19dfdfb68d1ee55d2f0c7fa040df96815"},
+    {file = "protobuf-6.30.2-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:4f6c687ae8efae6cf6093389a596548214467778146b7245e886f35e1485315d"},
+    {file = "protobuf-6.30.2-cp39-cp39-win32.whl", hash = "sha256:524afedc03b31b15586ca7f64d877a98b184f007180ce25183d1a5cb230ee72b"},
+    {file = "protobuf-6.30.2-cp39-cp39-win_amd64.whl", hash = "sha256:acec579c39c88bd8fbbacab1b8052c793efe83a0a5bd99db4a31423a25c0a0e2"},
+    {file = "protobuf-6.30.2-py3-none-any.whl", hash = "sha256:ae86b030e69a98e08c77beab574cbcb9fff6d031d57209f574a5aea1445f4b51"},
+    {file = "protobuf-6.30.2.tar.gz", hash = "sha256:35c859ae076d8c56054c25b59e5e59638d86545ed6e2b6efac6be0b6ea3ba048"},
+]
+
 [[package]]
 name = "pyarrow"
 version = "20.0.0"
@@ -2525,6 +2760,22 @@ docs = ["myst_parser", "sphinx", "sphinx_rtd_theme"]
 full = ["Pillow (>=8.0.0)", "cryptography"]
 image = ["Pillow (>=8.0.0)"]
 
+[[package]]
+name = "pyreadline3"
+version = "3.5.4"
+description = "A python implementation of GNU readline."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+markers = "sys_platform == \"win32\""
+files = [
+    {file = "pyreadline3-3.5.4-py3-none-any.whl", hash = "sha256:eaf8e6cc3c49bcccf145fc6067ba8643d1df34d604a1ec0eccbf7a18e6d3fae6"},
+    {file = "pyreadline3-3.5.4.tar.gz", hash = "sha256:8d57d53039a1c75adba8e50dd3d992b28143480816187ea5efbd5c78e6c885b7"},
+]
+
+[package.extras]
+dev = ["build", "flake8", "mypy", "pytest", "twine"]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"
@@ -3007,6 +3258,27 @@ files = [
 dev = ["Django (>=1.11)", "check-manifest", "colorama (<=0.4.1)", "coverage", "flake8", "nose2", "readme-renderer (<25.0)", "tox", "wheel", "zest.releaser[recommended]"]
 doc = ["Sphinx", "sphinx-rtd-theme"]
 
+[[package]]
+name = "setuptools"
+version = "80.3.1"
+description = "Easily download, build, install, upgrade, and uninstall Python packages"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "setuptools-80.3.1-py3-none-any.whl", hash = "sha256:ea8e00d7992054c4c592aeb892f6ad51fe1b4d90cc6947cc45c45717c40ec537"},
+    {file = "setuptools-80.3.1.tar.gz", hash = "sha256:31e2c58dbb67c99c289f51c16d899afedae292b978f8051efaf6262d8212f927"},
+]
+
+[package.extras]
+check = ["pytest-checkdocs (>=2.4)", "pytest-ruff (>=0.2.1)", "ruff (>=0.8.0)"]
+core = ["importlib_metadata (>=6)", "jaraco.functools (>=4)", "jaraco.text (>=3.7)", "more_itertools", "more_itertools (>=8.8)", "packaging (>=24.2)", "platformdirs (>=4.2.2)", "tomli (>=2.0.1)", "wheel (>=0.43.0)"]
+cover = ["pytest-cov"]
+doc = ["furo", "jaraco.packaging (>=9.3)", "jaraco.tidelift (>=1.4)", "pygments-github-lexers (==0.0.5)", "pyproject-hooks (!=1.1)", "rst.linker (>=1.9)", "sphinx (>=3.5)", "sphinx-favicon", "sphinx-inline-tabs", "sphinx-lint", "sphinx-notfound-page (>=1,<2)", "sphinx-reredirects", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
+enabler = ["pytest-enabler (>=2.2)"]
+test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.7.2)", "jaraco.test (>=5.5)", "packaging (>=24.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-home (>=0.5)", "pytest-perf", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"]
+type = ["importlib_metadata (>=7.0.2)", "jaraco.develop (>=7.21)", "mypy (==1.14.*)", "pytest-mypy"]
+
 [[package]]
 name = "shellingham"
 version = "1.5.4"
@@ -3117,6 +3389,24 @@ anyio = ">=3.6.2,<5"
 [package.extras]
 full = ["httpx (>=0.27.0,<0.29.0)", "itsdangerous", "jinja2", "python-multipart (>=0.0.18)", "pyyaml"]
 
+[[package]]
+name = "sympy"
+version = "1.14.0"
+description = "Computer algebra system (CAS) in Python"
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "sympy-1.14.0-py3-none-any.whl", hash = "sha256:e091cc3e99d2141a0ba2847328f5479b05d94a6635cb96148ccb3f34671bd8f5"},
+    {file = "sympy-1.14.0.tar.gz", hash = "sha256:d3d3fe8df1e5a0b42f0e7bdf50541697dbe7d23746e894990c030e2b05e72517"},
+]
+
+[package.dependencies]
+mpmath = ">=1.1.0,<1.4"
+
+[package.extras]
+dev = ["hypothesis (>=6.70.0)", "pytest (>=7.1.0)"]
+
 [[package]]
 name = "tiktoken"
 version = "0.9.0"
@@ -3713,4 +4003,4 @@ type = ["pytest-mypy"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.12,<3.13"
-content-hash = "e29835a62bb0b14f8ba9524f2c6c9a58128a40946e4e719dd9f8864a98aa3820"
+content-hash = "64a242457369382ca1d12cb4459589bfaa7294a2163d40713d3d202689f9e613"

pyproject.toml

@@ -8,7 +8,7 @@ authors = [
 readme = "README.md"
 requires-python = ">=3.12,<3.13"
 dependencies = [
-    "smolagents[litellm] (>=1.14.0,<2.0.0)",
+    "smolagents[litellm,toolkit] (>=1.14.0,<2.0.0)",
     "gradio[oauth] (>=5.27.0,<6.0.0)",
     "requests (>=2.32.3,<3.0.0)",
     "pandas (>=2.2.3,<3.0.0)",
@@ -21,6 +21,7 @@ dependencies = [
     "wikipedia (>=1.4.0,<2.0.0)",
     "openai (>=1.77.0,<2.0.0)",
     "youtube-transcript-api (>=1.0.3,<2.0.0)",
+    "faster-whisper (>=1.1.1,<2.0.0)",
 ]