Add Audio Input for Performance Reviews

[archie-ai-code-explain-pr-review[bot]]

• Enable users to provide audio input for their performance reviews and self-reviews, in addition to the existing text-based input.
• Use the streamlit-audio-recorder library to allow audio recording in the app.
• Implement the convert_speech_to_text function using the Whisper model on the Groq library to convert the audio to text.
• Update the ReviewRequest and SelfReviewRequest models to include an optional audio_review field, and use this input for generating the review and self-review.
• Update the review generation logic in app.py to handle the new audio_review field.

[greptile-apps[bot]]

Implementation Steps

1. Install streamlit-audio-recorder:

   pip install streamlit-audio-recorder

2. Update ReviewRequest and SelfReviewRequest Models:

   # In review.py and self_review.py
   class ReviewRequest(BaseModel):
      your_role: str
      candidate_role: str
      perf_question: Optional[str] = None
      your_review: str
      audio_review: Optional[bytes] = None  # Add this line
      llm_type: str
      user_api_key: str
      model_size: str = "small"
   
   class SelfReviewRequest(BaseModel):
      text_dump: str
      questions: List[str]
      instructions: Optional[str] = None
      audio_review: Optional[bytes] = None  # Add this line
      llm_type: str
      user_api_key: str
      model_size: str = "medium"

3. Implement convert_speech_to_text Function:

   # In llm.py
   from groq import Whisper
   
   def convert_speech_to_text(audio_data: bytes) -> str:
      whisper = Whisper(api_key=GROQ_API_KEY)
      return whisper.transcribe(audio_data)

4. Update app.py for Audio Input:

   import streamlit as st
   from streamlit_audio_recorder import audio_recorder
   from review import ReviewRequest, generate_review, DEFAULT_QUESTIONS
   from self_review import SelfReviewRequest, generate_self_review
   from llm import convert_speech_to_text
   
   # Add audio recorder to the UI
   audio_data = audio_recorder()
   
   if review_type == "Performance Review":
      # Existing code...
      if st.button('Generate Performance Review'):
          if not user_api_key:
              st.error("Please enter your API key in the sidebar.")
          elif not your_role or not candidate_role or not your_review:
              st.error("Please fill in all required fields.")
          else:
              try:
                  questions = perf_question.split('\n') if perf_question else DEFAULT_QUESTIONS.split('\n')
                  audio_text = convert_speech_to_text(audio_data) if audio_data else None
                  review_request = ReviewRequest(
                      your_role=your_role,
                      candidate_role=candidate_role,
                      perf_question="\n".join(questions),
                      your_review=your_review,
                      audio_review=audio_text,
                      llm_type=llm_type,
                      user_api_key=user_api_key,
                      model_size=model_size
                  )
                  review = generate_review(**review_request.model_dump())
                  for qa in review:
                      st.markdown(f"**{qa['question']}**")
                      st.markdown(qa['answer'])
                      st.markdown("---")
              except Exception as e:
                  st.error(f"An error occurred: {str(e)}")
   
   else:  # Self-Review
      # Existing code...
      if st.button('Generate Self-Review'):
          if not user_api_key:
              st.error("Please enter your API key in the sidebar.")
          elif not text_dump or not questions:
              st.error("Please provide both the text dump and questions.")
          else:
              try:
                  question_list = [q.strip() for q in questions.split('\n') if q.strip()]
                  audio_text = convert_speech_to_text(audio_data) if audio_data else None
                  self_review_request = SelfReviewRequest(
                      text_dump=text_dump,
                      questions=question_list,
                      instructions=instructions if instructions else None,
                      audio_review=audio_text,
                      llm_type=llm_type,
                      user_api_key=user_api_key,
                      model_size=model_size
                  )
                  self_review = generate_self_review(**self_review_request.model_dump())
                  for qa in self_review:
                      st.markdown(f"**{qa['question']}**")
                      st.markdown(qa['answer'])
                      st.markdown("---")
              except Exception as e:
                  st.error(f"An error occurred: {str(e)}")

   }

References

/app.py /review.py /self_review.py /llm.py

#### About Greptile

This response provides a starting point for your research, not a precise solution. Help us improve! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. [Ask Greptile](https://app.greptile.com/chat/github/ajitesh123/perf-review-ai/main) · [Edit Issue Bot Settings](https://app.greptile.com/apps/github)