update transcribe_audio tool

agent.py

@@ -7,19 +7,9 @@ from typing import List, TypedDict, Annotated, Optional
 
 from langchain.tools import tool
 from langchain_community.document_loaders import (
-    CSVLoader,
-    YoutubeLoader,
-    PyPDFLoader
+    CSVLoader, PyPDFLoader, YoutubeLoader
 )
-from langchain_community.document_loaders.blob_loaders.youtube_audio import (
-    YoutubeAudioLoader,
-)
-from langchain_community.document_loaders.generic import GenericLoader
-from langchain_community.document_loaders.parsers.audio import (
-    OpenAIWhisperParser,
-    OpenAIWhisperParserLocal,
-)
-
+from langchain_community.document_loaders import AssemblyAIAudioTranscriptLoader
 from langchain.chat_models import init_chat_model
 from langchain.agents import initialize_agent, AgentType
 from langchain_community.retrievers import BM25Retriever
@@ -124,16 +114,6 @@ def read_spreadsheet(spreadsheet_path: str) -> str:
     except Exception as e:
         return f"Error reading spreadsheet: {e}"
 
-@tool
-def transcribe_audio(audio_path: str) -> str:
-    """Transcribe audio file (e.g., MP3) using Whisper."""
-    try:
-        docs = AudioLoader(audio_path).load()
-        transcripts = WhisperLoader().load(docs)
-        return "\n".join(doc.page_content for doc in transcripts)
-    except Exception as e:
-        return f"Error transcribing audio: {e}"
-
 @tool
 def youtube_transcript_tool(video_url: str) -> str:
     """Download the transcript of a YouTube video using LangChain YoutubeLoader."""
@@ -155,7 +135,17 @@ def youtube_transcript_api(video_url_or_id: str) -> str:
     except Exception as e:
         return f"Error fetching transcript via API: {e}"
 
+@tool
+def transcribe_audio(audio_path: str) -> str:
+    """Transcribe audio file (e.g., MP3) using AssemblyAI."""
+    try:
 
+        loader = AssemblyAIAudioTranscriptLoader(file_path=audio_path)
+        docs = loader.load()
+        return "\n".join(doc.page_content for doc in docs)
+    except Exception as e:
+        return f"Error transcribing audio: {e}"
+    
     
 #o3_mini = init_chat_model("openai:o3-mini", temperature=0)
 #claude_sonnet = init_chat_model(anthropic:claude-3-5-sonnet-latest", temperature=0)
@@ -202,8 +192,8 @@ class MyAgent:
                 loader = PyPDFLoader(path)
                 self.docs.extend(loader.load())
             elif ext in [".mp3", ".wav"]:
-                audio_docs = AudioLoader(path).load()
-                self.docs.extend(WhisperLoader().load(audio_docs))
+                loader = AssemblyAIAudioTranscriptLoader(file_path=path)
+                self.docs.extend(loader.load())
             elif "youtube" in path:
                 loader = YoutubeLoader.from_youtube_url(path)
                 self.docs.extend(loader.load())
@@ -280,8 +270,5 @@ class MyAgent:
         return state
 
 
-# CLI entrypoint
-if __name__ == "__main__":
-    import fire
-    fire.Fire(MyAgent)
+