# akarshvyas/ai-video-assistant- architecture

> Architecture diagram of the GitHub repository akarshvyas/ai-video-assistant-, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/akarshvyas/ai-video-assistant-
- Repository: https://github.com/akarshvyas/ai-video-assistant-

## Overview

This is an AI video/meeting assistant with a Streamlit interface and a CLI workflow. Users provide a YouTube URL or local media file; the CLI converts and chunks its audio, transcribes it, then generates a title, summary, action items, decisions, and open questions, and builds transcript-grounded chat. The Streamlit app also invokes analysis and chat components. The graph preserves the distinct ingestion, transcription, analysis, and retrieval stages. Source excerpts show the CLI orchestration and key UI calls; omitted UI lines limit evidence for its ingestion and transcription wiring.

Main entry points: [`main.py`](https://github.com/akarshvyas/ai-video-assistant-/blob/main/main.py) (CLI pipeline), [`core/rag_engine.py`](https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/rag_engine.py) (RAG question answering), [`app.py`](https://github.com/akarshvyas/ai-video-assistant-/blob/main/app.py) (Streamlit workflow), [`core/transcriber.py`](https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/transcriber.py) (Transcription)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_ingestion["Media ingestion"]
  node_media["Audio preparation<br/>[audio_processor.py]"]
  node_youtube["YouTube"]
end

subgraph group_speech["Transcription"]
  node_transcriber["Transcription<br/>[transcriber.py]"]
  node_whisper["Whisper model"]
  node_sarvam["Sarvam API"]
end

subgraph group_analysis["Meeting analysis"]
  node_ui["Streamlit workflow<br/>[app.py]"]
  node_pipeline["CLI pipeline<br/>[main.py]"]
  node_meeting_outputs["Title and summary<br/>[summarizer.py]"]
  node_extractor["Meeting insights<br/>[extractor.py]"]
end

subgraph group_chat["Transcript chat"]
  node_rag["RAG question answering<br/>[rag_engine.py]"]
  node_vectors[("Transcript vector store<br/>[vector_store.py]")]
  node_mistral["Mistral service"]
  node_answer["Chat response"]
end

node_user(("User"))
node_streamlit["Streamlit app"]
node_cli(("CLI user"))

node_user -->|"uses"| node_streamlit
node_streamlit -->|"runs"| node_ui
node_cli -->|"starts"| node_pipeline
node_pipeline -->|"processes input"| node_media
node_media -->|"downloads audio"| node_youtube
node_pipeline -->|"transcribes chunks"| node_transcriber
node_transcriber -->|"transcribes locally"| node_whisper
node_transcriber -->|"sends audio"| node_sarvam
node_pipeline -->|"generates title and summary"| node_meeting_outputs
node_pipeline -->|"extracts insights"| node_extractor
node_pipeline -->|"builds chat chain"| node_rag
node_ui -->|"generates title and summary"| node_meeting_outputs
node_ui -->|"extracts insights"| node_extractor
node_ui -->|"builds and queries"| node_rag
node_rag -->|"builds and retrieves"| node_vectors
node_rag -.->|"invokes model"| node_mistral
node_rag -->|"returns answer"| node_answer

click node_ui "https://github.com/akarshvyas/ai-video-assistant-/blob/main/app.py"
click node_pipeline "https://github.com/akarshvyas/ai-video-assistant-/blob/main/main.py"
click node_media "https://github.com/akarshvyas/ai-video-assistant-/blob/main/utils/audio_processor.py"
click node_transcriber "https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/transcriber.py"
click node_meeting_outputs "https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/summarizer.py"
click node_extractor "https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/extractor.py"
click node_rag "https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/rag_engine.py"
click node_vectors "https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/vector_store.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_media,node_youtube,node_user,node_cli toneBlue
class node_transcriber,node_whisper,node_sarvam toneAmber
class node_ui,node_pipeline,node_meeting_outputs,node_extractor toneMint
class node_rag,node_vectors,node_mistral,node_answer toneRose
class node_streamlit toneIndigo
```

## Components

### Media ingestion

- [Audio preparation](https://github.com/akarshvyas/ai-video-assistant-/blob/main/utils/audio_processor.py): `utils/audio_processor.py`
- **YouTube**

### Transcription

- [Transcription](https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/transcriber.py): `core/transcriber.py`
- **Whisper model**
- **Sarvam API**

### Meeting analysis

- [Streamlit workflow](https://github.com/akarshvyas/ai-video-assistant-/blob/main/app.py): `app.py`
- [CLI pipeline](https://github.com/akarshvyas/ai-video-assistant-/blob/main/main.py): `main.py`
- [Title and summary](https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/summarizer.py): `core/summarizer.py`
- [Meeting insights](https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/extractor.py): `core/extractor.py`

### Transcript chat

- [RAG question answering](https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/rag_engine.py): `core/rag_engine.py`
- [Transcript vector store](https://github.com/akarshvyas/ai-video-assistant-/blob/main/core/vector_store.py): `core/vector_store.py`
- **Mistral service**
- **Chat response**

### Other components

- **User**
- **Streamlit app**
- **CLI user**

## Connections

- User → Streamlit app: uses
- Streamlit app → Streamlit workflow: runs (evidence: `app.py`)
- CLI user → CLI pipeline: starts (evidence: `main.py`)
- CLI pipeline → Audio preparation: processes input (evidence: `main.py`)
- Audio preparation → YouTube: downloads audio (evidence: `utils/audio_processor.py`)
- CLI pipeline → Transcription: transcribes chunks (evidence: `main.py`)
- Transcription → Whisper model: transcribes locally (evidence: `core/transcriber.py`)
- Transcription → Sarvam API: sends audio (evidence: `core/transcriber.py`)
- CLI pipeline → Title and summary: generates title and summary (evidence: `main.py`)
- CLI pipeline → Meeting insights: extracts insights (evidence: `main.py`)
- CLI pipeline → RAG question answering: builds chat chain (evidence: `main.py`)
- Streamlit workflow → Title and summary: generates title and summary (evidence: `app.py`)
- Streamlit workflow → Meeting insights: extracts insights (evidence: `app.py`)
- Streamlit workflow → RAG question answering: builds and queries (evidence: `app.py`)
- RAG question answering → Transcript vector store: builds and retrieves (evidence: `core/rag_engine.py`)
- RAG question answering → Mistral service: invokes model
- RAG question answering → Chat response: returns answer (evidence: `core/rag_engine.py`)
