# kathirvbk/ai-meet architecture

> Architecture diagram of the GitHub repository kathirvbk/ai-meet, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-05). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/kathirvbk/ai-meet
- Repository: https://github.com/kathirvbk/ai-meet

## Overview

MeetMind’s principal workflow accepts a meeting recording or transcript, processes speech into speaker-aware text, runs a validation-loop agent to produce minutes and action items, and stores meeting records for later access. The FastAPI service also exposes history, administration, and meeting Q&A; the React frontend provides the user-facing meeting and management screens. The README describes a Streamlit UI, but the supplied tree instead contains a React frontend and FastAPI server, so the graph follows the files present. Some subsystem links rely on the README or SOURCE INDEX; unsampled implementation details are not inferred.

Main entry points: [`api_server.py`](https://github.com/kathirvbk/ai-meet/blob/master/api_server.py) (API server), [`services/transcript_service.py`](https://github.com/kathirvbk/ai-meet/blob/master/services/transcript_service.py) (Transcript pipeline), [`graph/workflow.py`](https://github.com/kathirvbk/ai-meet/blob/master/graph/workflow.py) (Agent workflow), [`agents/validator.py`](https://github.com/kathirvbk/ai-meet/blob/master/agents/validator.py) (Output validation)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_client["Web client"]
  node_react["React app<br/>[App.jsx]"]
  node_meeting_views["Meeting screens"]
  node_admin_views["Admin screens<br/>[AdminPanel.jsx]"]
  node_api_client["API client<br/>[api.js]"]
end

subgraph group_api["API and services"]
  node_fastapi["API server<br/>[api_server.py]"]
  node_history["Meeting history<br/>[history_service.py]"]
  node_admin["Admin services<br/>[admin_service.py]"]
  node_models["Relational models<br/>[models.py]"]
  node_pdf["PDF export<br/>[pdf_service.py]"]
end

subgraph group_speech["Speech processing"]
  node_audio["Audio processing<br/>[audio_processor.py]"]
  node_stt["Speech recognition<br/>[speech_to_text.py]"]
  node_diarization["Speaker diarization"]
  node_speaker_names["Speaker naming"]
  node_reconstruction["Transcript reconstruction"]
  node_transcript["Transcript pipeline"]
end

subgraph group_agents["Minutes workflow"]
  node_workflow["Agent workflow<br/>[workflow.py]"]
  node_analyzer["Meeting analysis"]
  node_extractor["Action extraction"]
  node_validator["Output validation<br/>[validator.py]"]
  node_reanalyzer["Error correction<br/>[reanalyzer.py]"]
  node_mom["Minutes generation<br/>[mom_generator.py]"]
end

subgraph group_knowledge["Meeting knowledge"]
  node_rag_chain["Club Q&amp;A<br/>[rag_chain.py]"]
  node_retriever["Meeting retrieval<br/>[retriever.py]"]
  node_vector_store[("Vector store<br/>[vector_store.py]")]
end

node_user(("Club user"))
node_llm["Groq AI services"]

node_user -->|"uses"| node_react
node_react -->|"routes to"| node_meeting_views
node_react -->|"routes to"| node_admin_views
node_meeting_views -->|"calls"| node_api_client
node_admin_views -->|"calls"| node_api_client
node_api_client -.->|"HTTP requests"| node_fastapi
node_fastapi -->|"invokes"| node_transcript
node_fastapi -->|"invokes"| node_workflow
node_fastapi -->|"invokes"| node_history
node_fastapi -->|"queries"| node_rag_chain
node_fastapi -->|"invokes"| node_admin
node_history -->|"persists records"| node_models
node_admin -->|"uses"| node_models
node_transcript -->|"converts and chunks"| node_audio
node_transcript -->|"transcribes"| node_stt
node_transcript -->|"identifies speakers"| node_diarization
node_transcript -->|"detects names"| node_speaker_names
node_transcript -->|"reconstructs text"| node_reconstruction
node_workflow -->|"dispatches"| node_analyzer
node_workflow -->|"dispatches"| node_extractor
node_workflow -->|"dispatches"| node_validator
node_workflow -->|"dispatches"| node_reanalyzer
node_workflow -->|"dispatches"| node_mom
node_analyzer -->|"then extracts"| node_extractor
node_extractor -->|"then validates"| node_validator
node_validator -->|"retries errors"| node_reanalyzer
node_reanalyzer -->|"revalidates"| node_validator
node_validator -->|"continues when valid"| node_mom
node_mom -.->|"generates minutes"| node_llm
node_rag_chain -->|"retrieves context"| node_retriever
node_retriever -->|"searches"| node_vector_store
node_vector_store -.->|"embeds records"| node_llm
node_rag_chain -->|"generates answers"| node_llm
node_user -.->|"downloads minutes"| node_pdf

click node_react "https://github.com/kathirvbk/ai-meet/blob/master/frontend/src/App.jsx"
click node_meeting_views "https://github.com/kathirvbk/ai-meet/tree/master/frontend/src/pages"
click node_admin_views "https://github.com/kathirvbk/ai-meet/blob/master/frontend/src/pages/AdminPanel.jsx"
click node_api_client "https://github.com/kathirvbk/ai-meet/blob/master/frontend/src/utils/api.js"
click node_fastapi "https://github.com/kathirvbk/ai-meet/blob/master/api_server.py"
click node_history "https://github.com/kathirvbk/ai-meet/blob/master/services/history_service.py"
click node_admin "https://github.com/kathirvbk/ai-meet/blob/master/services/admin_service.py"
click node_models "https://github.com/kathirvbk/ai-meet/blob/master/database/models.py"
click node_audio "https://github.com/kathirvbk/ai-meet/blob/master/services/audio_processor.py"
click node_stt "https://github.com/kathirvbk/ai-meet/blob/master/services/speech_to_text.py"
click node_diarization "https://github.com/kathirvbk/ai-meet/blob/master/services/speaker_diarization.py"
click node_speaker_names "https://github.com/kathirvbk/ai-meet/blob/master/services/speaker_name_detector.py"
click node_reconstruction "https://github.com/kathirvbk/ai-meet/blob/master/services/transcript_reconstructor.py"
click node_transcript "https://github.com/kathirvbk/ai-meet/blob/master/services/transcript_service.py"
click node_workflow "https://github.com/kathirvbk/ai-meet/blob/master/graph/workflow.py"
click node_analyzer "https://github.com/kathirvbk/ai-meet/blob/master/agents/meeting_analyzer.py"
click node_extractor "https://github.com/kathirvbk/ai-meet/blob/master/agents/action_extractor.py"
click node_validator "https://github.com/kathirvbk/ai-meet/blob/master/agents/validator.py"
click node_reanalyzer "https://github.com/kathirvbk/ai-meet/blob/master/agents/reanalyzer.py"
click node_mom "https://github.com/kathirvbk/ai-meet/blob/master/agents/mom_generator.py"
click node_rag_chain "https://github.com/kathirvbk/ai-meet/blob/master/rag/rag_chain.py"
click node_retriever "https://github.com/kathirvbk/ai-meet/blob/master/rag/retriever.py"
click node_vector_store "https://github.com/kathirvbk/ai-meet/blob/master/rag/vector_store.py"
click node_pdf "https://github.com/kathirvbk/ai-meet/blob/master/services/pdf_service.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_react,node_meeting_views,node_admin_views,node_api_client,node_user toneBlue
class node_fastapi,node_history,node_admin,node_models,node_pdf toneAmber
class node_audio,node_stt,node_diarization,node_speaker_names,node_reconstruction,node_transcript toneMint
class node_workflow,node_analyzer,node_extractor,node_validator,node_reanalyzer,node_mom toneRose
class node_rag_chain,node_retriever,node_vector_store,node_llm toneIndigo
```

## Components

### Web client

- [React app](https://github.com/kathirvbk/ai-meet/blob/master/frontend/src/App.jsx): `frontend/src/App.jsx`
- [Meeting screens](https://github.com/kathirvbk/ai-meet/tree/master/frontend/src/pages): `frontend/src/pages`
- [Admin screens](https://github.com/kathirvbk/ai-meet/blob/master/frontend/src/pages/AdminPanel.jsx): `frontend/src/pages/AdminPanel.jsx`
- [API client](https://github.com/kathirvbk/ai-meet/blob/master/frontend/src/utils/api.js): `frontend/src/utils/api.js`

### API and services

- [API server](https://github.com/kathirvbk/ai-meet/blob/master/api_server.py): `api_server.py`
- [Meeting history](https://github.com/kathirvbk/ai-meet/blob/master/services/history_service.py): `services/history_service.py`
- [Admin services](https://github.com/kathirvbk/ai-meet/blob/master/services/admin_service.py): `services/admin_service.py`
- [Relational models](https://github.com/kathirvbk/ai-meet/blob/master/database/models.py): `database/models.py`
- [PDF export](https://github.com/kathirvbk/ai-meet/blob/master/services/pdf_service.py): `services/pdf_service.py`

### Speech processing

- [Audio processing](https://github.com/kathirvbk/ai-meet/blob/master/services/audio_processor.py): `services/audio_processor.py`
- [Speech recognition](https://github.com/kathirvbk/ai-meet/blob/master/services/speech_to_text.py): `services/speech_to_text.py`
- [Speaker diarization](https://github.com/kathirvbk/ai-meet/blob/master/services/speaker_diarization.py): `services/speaker_diarization.py`
- [Speaker naming](https://github.com/kathirvbk/ai-meet/blob/master/services/speaker_name_detector.py): `services/speaker_name_detector.py`
- [Transcript reconstruction](https://github.com/kathirvbk/ai-meet/blob/master/services/transcript_reconstructor.py): `services/transcript_reconstructor.py`
- [Transcript pipeline](https://github.com/kathirvbk/ai-meet/blob/master/services/transcript_service.py): `services/transcript_service.py`

### Minutes workflow

- [Agent workflow](https://github.com/kathirvbk/ai-meet/blob/master/graph/workflow.py): `graph/workflow.py`
- [Meeting analysis](https://github.com/kathirvbk/ai-meet/blob/master/agents/meeting_analyzer.py): `agents/meeting_analyzer.py`
- [Action extraction](https://github.com/kathirvbk/ai-meet/blob/master/agents/action_extractor.py): `agents/action_extractor.py`
- [Output validation](https://github.com/kathirvbk/ai-meet/blob/master/agents/validator.py): `agents/validator.py`
- [Error correction](https://github.com/kathirvbk/ai-meet/blob/master/agents/reanalyzer.py): `agents/reanalyzer.py`
- [Minutes generation](https://github.com/kathirvbk/ai-meet/blob/master/agents/mom_generator.py): `agents/mom_generator.py`

### Meeting knowledge

- [Club Q&A](https://github.com/kathirvbk/ai-meet/blob/master/rag/rag_chain.py): `rag/rag_chain.py`
- [Meeting retrieval](https://github.com/kathirvbk/ai-meet/blob/master/rag/retriever.py): `rag/retriever.py`
- [Vector store](https://github.com/kathirvbk/ai-meet/blob/master/rag/vector_store.py): `rag/vector_store.py`

### Other components

- **Club user**
- **Groq AI services**

## Connections

- Club user → React app: uses (evidence: `README.md`)
- React app → Meeting screens: routes to (evidence: `frontend/src/App.jsx`)
- React app → Admin screens: routes to (evidence: `frontend/src/App.jsx`)
- Meeting screens → API client: calls (evidence: `frontend/src/pages/MeetingDetails.jsx`)
- Admin screens → API client: calls (evidence: `frontend/src/pages/AdminPanel.jsx`)
- API client → API server: HTTP requests
- API server → Transcript pipeline: invokes (evidence: `api_server.py`)
- API server → Agent workflow: invokes (evidence: `api_server.py`)
- API server → Meeting history: invokes (evidence: `api_server.py`)
- API server → Club Q&A: queries (evidence: `api_server.py`)
- API server → Admin services: invokes (evidence: `api_server.py`)
- Meeting history → Relational models: persists records (evidence: `services/history_service.py`)
- Admin services → Relational models: uses (evidence: `services/admin_service.py`)
- Transcript pipeline → Audio processing: converts and chunks (evidence: `services/transcript_service.py`)
- Transcript pipeline → Speech recognition: transcribes (evidence: `services/transcript_service.py`)
- Transcript pipeline → Speaker diarization: identifies speakers (evidence: `services/transcript_service.py`)
- Transcript pipeline → Speaker naming: detects names (evidence: `services/transcript_service.py`)
- Transcript pipeline → Transcript reconstruction: reconstructs text (evidence: `services/transcript_service.py`)
- Agent workflow → Meeting analysis: dispatches (evidence: `graph/workflow.py`)
- Agent workflow → Action extraction: dispatches (evidence: `graph/workflow.py`)
- Agent workflow → Output validation: dispatches (evidence: `graph/workflow.py`)
- Agent workflow → Error correction: dispatches (evidence: `graph/workflow.py`)
- Agent workflow → Minutes generation: dispatches (evidence: `graph/workflow.py`)
- Meeting analysis → Action extraction: then extracts (evidence: `README.md`)
- Action extraction → Output validation: then validates (evidence: `README.md`)
- Output validation → Error correction: retries errors (evidence: `README.md`)
- Error correction → Output validation: revalidates (evidence: `graph/workflow.py`)
- Output validation → Minutes generation: continues when valid (evidence: `README.md`)
- Minutes generation → Groq AI services: generates minutes
- Club Q&A → Meeting retrieval: retrieves context (evidence: `rag/rag_chain.py`)
- Meeting retrieval → Vector store: searches (evidence: `rag/retriever.py`)
- Vector store → Groq AI services: embeds records
- Club Q&A → Groq AI services: generates answers (evidence: `rag/rag_chain.py`)
- Club user → PDF export: downloads minutes
