# ferozewaris/multi-agent-intelligent-assistant architecture

> Architecture diagram of the GitHub repository ferozewaris/multi-agent-intelligent-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/ferozewaris/multi-agent-intelligent-assistant
- Repository: https://github.com/ferozewaris/multi-agent-intelligent-assistant

## Overview

Intelligent RAG System combines category-based PDF retrieval with structured-data analysis, exposed through a Streamlit chat UI and FastAPI. The documented ingestion path loads and splits categorized documents, embeds chunks, and stores them; queries are routed to RAG or DuckDB, then returned to the user. The graph includes the API, UI, indexing pipeline, model configuration, and MLflow tracking. Some UI routing and API indexing details are in omitted excerpts, so those links are marked unverified or omitted rather than asserted as observed calls.

Main entry points: [`src2/rag_chain.py`](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/rag_chain.py) (RAG Chain), [`src2/duckdb_agent.py`](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/duckdb_agent.py) (DuckDB Agent), [`src2/embed_documents.py`](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/embed_documents.py) (Document Indexer), [`src2/streamlit_app.py`](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/streamlit_app.py) (Streamlit Chat)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_interfaces["User Interfaces"]
  node_streamlit["Streamlit Chat<br/>[streamlit_app.py]"]
  node_fastapi["REST API<br/>[api.py]"]
end

subgraph group_documents["Document Retrieval"]
  node_indexer["Document Indexer<br/>[embed_documents.py]"]
  node_processor["PDF Processing"]
  node_embedding["Embedding Provider<br/>[embeddings.py]"]
  node_vectors[("Category Vector Store<br/>[vector_store.py]")]
  node_rag["RAG Chain<br/>[rag_chain.py]"]
  node_pdfs["Categorized PDFs"]
end

subgraph group_structured["Structured Data"]
  node_router["Agent Router<br/>[agent_router.py]"]
  node_duckagent["DuckDB Agent<br/>[duckdb_agent.py]"]
  node_duckdb[("DuckDB<br/>[duckdb_agent.py]")]
end

subgraph group_shared["Shared Services"]
  node_config["Runtime Configuration<br/>[config.py]"]
  node_mlflow["MLflow Tracking"]
end

node_user(("User"))
node_llm["Groq Chat Model"]
node_embedding_services["Embedding Services"]

node_user -->|"asks query"| node_streamlit
node_user -->|"sends request"| node_fastapi
node_streamlit -.->|"selects agent"| node_router
node_streamlit -->|"queries"| node_rag
node_streamlit -.->|"handles data query"| node_duckagent
node_fastapi -->|"queries"| node_rag
node_indexer -->|"loads and splits"| node_processor
node_pdfs -->|"provides PDFs"| node_processor
node_indexer -->|"initializes"| node_embedding
node_indexer -->|"adds chunks"| node_vectors
node_rag -->|"searches categories"| node_vectors
node_rag -.->|"uses embeddings"| node_embedding
node_router -->|"classifies query"| node_llm
node_duckagent -->|"executes SQL"| node_duckdb
node_duckagent -->|"generates SQL"| node_llm
node_duckagent -->|"summarizes results"| node_llm
node_rag -->|"generates answer"| node_llm
node_embedding -->|"creates vectors"| node_embedding_services
node_router -->|"logs routing"| node_mlflow
node_duckagent -->|"tracks queries"| node_mlflow
node_indexer -->|"tracks indexing"| node_mlflow
node_rag -.->|"tracks retrieval"| node_mlflow
node_config -->|"configures"| node_router
node_config -->|"configures"| node_embedding
node_config -->|"configures"| node_vectors

click node_streamlit "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/streamlit_app.py"
click node_fastapi "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/api.py"
click node_indexer "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/embed_documents.py"
click node_processor "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/document_processor.py"
click node_embedding "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/embeddings.py"
click node_vectors "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/vector_store.py"
click node_rag "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/rag_chain.py"
click node_router "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/agent_router.py"
click node_duckagent "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/duckdb_agent.py"
click node_duckdb "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/duckdb_agent.py"
click node_pdfs "https://github.com/ferozewaris/multi-agent-intelligent-assistant/tree/main/src2/data"
click node_config "https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/config.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_streamlit,node_fastapi,node_user toneBlue
class node_indexer,node_processor,node_embedding,node_vectors,node_rag,node_pdfs toneAmber
class node_router,node_duckagent,node_duckdb toneMint
class node_config,node_mlflow toneRose
class node_llm,node_embedding_services toneIndigo
```

## Components

### User Interfaces

- [Streamlit Chat](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/streamlit_app.py): `src2/streamlit_app.py`
- [REST API](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/api.py): `src2/api.py`

### Document Retrieval

- [Document Indexer](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/embed_documents.py): `src2/embed_documents.py`
- [PDF Processing](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/document_processor.py): `src2/document_processor.py`
- [Embedding Provider](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/embeddings.py): `src2/embeddings.py`
- [Category Vector Store](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/vector_store.py): `src2/vector_store.py`
- [RAG Chain](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/rag_chain.py): `src2/rag_chain.py`
- [Categorized PDFs](https://github.com/ferozewaris/multi-agent-intelligent-assistant/tree/main/src2/data): `src2/data`

### Structured Data

- [Agent Router](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/agent_router.py): `src2/agent_router.py`
- [DuckDB Agent](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/duckdb_agent.py): `src2/duckdb_agent.py`
- [DuckDB](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/duckdb_agent.py): `src2/duckdb_agent.py`

### Shared Services

- [Runtime Configuration](https://github.com/ferozewaris/multi-agent-intelligent-assistant/blob/main/src2/config.py): `src2/config.py`
- **MLflow Tracking**

### Other components

- **User**
- **Groq Chat Model**
- **Embedding Services**

## Connections

- User → Streamlit Chat: asks query (evidence: `README.md`)
- User → REST API: sends request (evidence: `README.md`)
- Streamlit Chat → Agent Router: selects agent (evidence: `src2/streamlit_app.py`)
- Streamlit Chat → RAG Chain: queries (evidence: `src2/streamlit_app.py`)
- Streamlit Chat → DuckDB Agent: handles data query (evidence: `src2/streamlit_app.py`)
- REST API → RAG Chain: queries (evidence: `src2/api.py`)
- Document Indexer → PDF Processing: loads and splits (evidence: `src2/embed_documents.py`)
- Categorized PDFs → PDF Processing: provides PDFs (evidence: `src2/document_processor.py`)
- Document Indexer → Embedding Provider: initializes (evidence: `src2/embed_documents.py`)
- Document Indexer → Category Vector Store: adds chunks (evidence: `src2/embed_documents.py`)
- RAG Chain → Category Vector Store: searches categories (evidence: `src2/rag_chain.py`)
- RAG Chain → Embedding Provider: uses embeddings (evidence: `src2/rag_chain.py`)
- Agent Router → Groq Chat Model: classifies query (evidence: `src2/agent_router.py`)
- DuckDB Agent → DuckDB: executes SQL (evidence: `src2/duckdb_agent.py`)
- DuckDB Agent → Groq Chat Model: generates SQL (evidence: `src2/duckdb_agent.py`)
- DuckDB Agent → Groq Chat Model: summarizes results (evidence: `src2/duckdb_agent.py`)
- RAG Chain → Groq Chat Model: generates answer (evidence: `src2/rag_chain.py`)
- Embedding Provider → Embedding Services: creates vectors (evidence: `src2/embeddings.py`)
- Agent Router → MLflow Tracking: logs routing (evidence: `src2/agent_router.py`)
- DuckDB Agent → MLflow Tracking: tracks queries (evidence: `src2/duckdb_agent.py`)
- Document Indexer → MLflow Tracking: tracks indexing (evidence: `src2/embed_documents.py`)
- RAG Chain → MLflow Tracking: tracks retrieval
- Runtime Configuration → Agent Router: configures (evidence: `src2/agent_router.py`)
- Runtime Configuration → Embedding Provider: configures (evidence: `src2/embeddings.py`)
- Runtime Configuration → Category Vector Store: configures (evidence: `src2/vector_store.py`)
