# dhrumilprajapati03/voice-chat-assistant architecture

> Architecture diagram of the GitHub repository dhrumilprajapati03/voice-chat-assistant, 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/dhrumilprajapati03/voice-chat-assistant
- Repository: https://github.com/dhrumilprajapati03/voice-chat-assistant

## Overview

Academy Assistant serves text and voice questions about courses, fees, schedules and academy documents. Users enter through the Gradio UI or FastAPI endpoints; the pipeline classifies and records text, handles greetings directly, and otherwise asks a session-aware agent. Voice requests add speech recognition before text handling and speech synthesis afterward. The agent can consult document retrieval and read-only academy SQL. History is stored separately from the agent’s in-memory conversational checkpoint. The source excerpts support the main runtime calls; ingestion details and database schema behavior are less fully shown.

Main entry points: [`app/pipeline.py`](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/pipeline.py) (Conversation pipeline), [`tools/agent.py`](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/agent.py) (Agent orchestration), [`app/main.py`](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/main.py) (FastAPI endpoints), [`tools/db.py`](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/db.py) (Chat history access)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interaction["User interaction"]
  node_ui["Gradio chat UI<br/>[ui.py]"]
  node_api["FastAPI endpoints<br/>[main.py]"]
end

subgraph group_conversation["Conversation runtime"]
  node_pipeline["Conversation pipeline<br/>[pipeline.py]"]
  node_intent["Intent classifier<br/>[intent.py]"]
  node_stt["Speech recognition<br/>[stt.py]"]
  node_tts["Speech synthesis<br/>[tts.py]"]
  node_agent["Agent orchestration<br/>[agent.py]"]
end

subgraph group_knowledge["Knowledge access"]
  node_ragtool["Document search tool<br/>[rag.py]"]
  node_vectorstore[("Chroma document index<br/>[rag.py]")]
  node_ingest["Document ingestion<br/>[ingest.py]"]
  node_documents["Academy source documents"]
  node_sqltool["Academy SQL tool<br/>[sql_tool.py]"]
end

subgraph group_persistence["State and storage"]
  node_history["Chat history access<br/>[db.py]"]
  node_database[("Academy database<br/>[schema.sql]")]
  node_memory["Agent session memory<br/>[agent.py]"]
end

node_user(("Academy user"))
node_groq{{"Groq language model"}}

node_user -->|"uses"| node_ui
node_ui -->|"sends chat and voice"| node_api
node_user -->|"submits requests"| node_api
node_api -->|"dispatches chat"| node_pipeline
node_api -->|"loads history"| node_history
node_pipeline -->|"classifies text"| node_intent
node_pipeline -->|"saves messages"| node_history
node_pipeline -->|"asks agent"| node_agent
node_pipeline -->|"transcribes audio"| node_stt
node_pipeline -->|"synthesizes reply"| node_tts
node_agent -->|"generates replies"| node_groq
node_agent -->|"calls document search"| node_ragtool
node_agent -->|"calls SQL tool"| node_sqltool
node_ragtool -->|"searches documents"| node_vectorstore
node_ingest -.->|"builds index"| node_vectorstore
node_documents -.->|"provides sources"| node_ingest
node_sqltool -->|"queries"| node_database
node_history -->|"reads and writes"| node_database
node_agent -->|"checkpoints sessions"| node_memory

click node_ui "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/ui.py"
click node_api "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/main.py"
click node_pipeline "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/pipeline.py"
click node_intent "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/intent.py"
click node_stt "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/stt.py"
click node_tts "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/tts.py"
click node_agent "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/agent.py"
click node_ragtool "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/rag.py"
click node_vectorstore "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/rag.py"
click node_ingest "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/Scripts/ingest.py"
click node_documents "https://github.com/dhrumilprajapati03/voice-chat-assistant/tree/master/data"
click node_sqltool "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/sql_tool.py"
click node_history "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/db.py"
click node_database "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/db/schema.sql"
click node_memory "https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/agent.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_ui,node_api,node_user toneBlue
class node_pipeline,node_intent,node_stt,node_tts,node_agent toneAmber
class node_ragtool,node_vectorstore,node_ingest,node_documents,node_sqltool toneMint
class node_history,node_database,node_memory toneRose
class node_groq toneIndigo
```

## Components

### User interaction

- [Gradio chat UI](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/ui.py): `app/ui.py`
- [FastAPI endpoints](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/main.py): `app/main.py`

### Conversation runtime

- [Conversation pipeline](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/app/pipeline.py): `app/pipeline.py`
- [Intent classifier](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/intent.py): `tools/intent.py`
- [Speech recognition](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/stt.py): `tools/stt.py`
- [Speech synthesis](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/tts.py): `tools/tts.py`
- [Agent orchestration](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/agent.py): `tools/agent.py`

### Knowledge access

- [Document search tool](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/rag.py): `tools/rag.py`
- [Chroma document index](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/rag.py): `tools/rag.py`
- [Document ingestion](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/Scripts/ingest.py): `Scripts/ingest.py`
- [Academy source documents](https://github.com/dhrumilprajapati03/voice-chat-assistant/tree/master/data): `data`
- [Academy SQL tool](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/sql_tool.py): `tools/sql_tool.py`

### State and storage

- [Chat history access](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/db.py): `tools/db.py`
- [Academy database](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/db/schema.sql): `db/schema.sql`
- [Agent session memory](https://github.com/dhrumilprajapati03/voice-chat-assistant/blob/master/tools/agent.py): `tools/agent.py`

### Other components

- **Academy user**
- **Groq language model**

## Connections

- Academy user → Gradio chat UI: uses (evidence: `app/ui.py`)
- Gradio chat UI → FastAPI endpoints: sends chat and voice (evidence: `app/ui.py`)
- Academy user → FastAPI endpoints: submits requests (evidence: `app/main.py`)
- FastAPI endpoints → Conversation pipeline: dispatches chat (evidence: `app/main.py`)
- FastAPI endpoints → Chat history access: loads history (evidence: `app/main.py`)
- Conversation pipeline → Intent classifier: classifies text (evidence: `app/pipeline.py`)
- Conversation pipeline → Chat history access: saves messages (evidence: `app/pipeline.py`)
- Conversation pipeline → Agent orchestration: asks agent (evidence: `app/pipeline.py`)
- Conversation pipeline → Speech recognition: transcribes audio (evidence: `app/pipeline.py`)
- Conversation pipeline → Speech synthesis: synthesizes reply (evidence: `app/pipeline.py`)
- Agent orchestration → Groq language model: generates replies (evidence: `tools/agent.py`)
- Agent orchestration → Document search tool: calls document search (evidence: `tools/agent.py`)
- Agent orchestration → Academy SQL tool: calls SQL tool (evidence: `tools/agent.py`)
- Document search tool → Chroma document index: searches documents (evidence: `tools/rag.py`)
- Document ingestion → Chroma document index: builds index (evidence: `Scripts/ingest.py`)
- Academy source documents → Document ingestion: provides sources
- Academy SQL tool → Academy database: queries (evidence: `tools/sql_tool.py`)
- Chat history access → Academy database: reads and writes (evidence: `tools/db.py`)
- Agent orchestration → Agent session memory: checkpoints sessions (evidence: `tools/agent.py`)
