# dharun11/ai architecture

> Architecture diagram of the GitHub repository dharun11/ai, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-02). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/dharun11/ai
- Repository: https://github.com/dharun11/ai

## Overview

This tree is a portfolio of AI applications rather than one unified runtime: resume review, student mentoring, document ingestion for retrieval, web research, and a SQL-oriented agent. The clearest user-to-result flows are resume text through parallel HR/engineering reviews and a merge, student chat through an agent orchestrator, uploaded documents through ingestion stages, and research sources through claim analysis to a brief. The README is only a heading; relationships below rely on the shown excerpts and SOURCE INDEX references. Some listed modules were not sampled, so uncertain wiring is omitted.

Main entry points: [`Agentic Rag/src/ingestion/pipeline.py`](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/pipeline.py) (Ingestion pipeline), [`MentorAgent/orchestrator.py`](https://github.com/dharun11/ai/blob/main/MentorAgent/orchestrator.py) (Agent orchestrator), [`Research Agent/src/research_agent/pipeline/graph.py`](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/graph.py) (Research workflow), [`Agentic Rag/src/api/routes/ingest.py`](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/api/routes/ingest.py) (Upload endpoint)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_resume["Resume Roaster"]
  node_resume_app["Resume app<br/>[app.py]"]
  node_resume_orch["Review orchestrator<br/>[main.py]"]
  node_engineer["Engineering review<br/>[tools.py]"]
  node_hr["HR review<br/>[tools.py]"]
end

subgraph group_rag["Document Ingestion"]
  node_rag_route["Upload endpoint<br/>[ingest.py]"]
  node_rag_config["Pipeline composition<br/>[dependencies.py]"]
  node_rag_pipeline["Ingestion pipeline<br/>[pipeline.py]"]
  node_parser["Document parsing<br/>[docling_parser.py]"]
  node_chunking["Chunk coordination<br/>[coordinator.py]"]
  node_hashing[("Content deduplication<br/>[mysql_store.py]")]
  node_embedding["Embedding providers"]
  node_vector_store[("Vector stores")]
  node_rag_models["Ingestion records<br/>[models.py]"]
  node_rag_observe["Run observability<br/>[observability.py]"]
end

subgraph group_mentor["Student Mentor"]
  node_mentor_api["Chat API<br/>[main.py]"]
  node_mentor_orch["Agent orchestrator<br/>[orchestrator.py]"]
  node_mentor_agent["Academic mentor<br/>[mentor_agent.py]"]
  node_placement_agent["Placement advisor<br/>[placement_agent.py]"]
  node_emotional_agent["Emotional support<br/>[emotional_agent.py]"]
  node_mentor_data[("Student data store<br/>[db.py]")]
  node_llm_factory["LLM provider factory<br/>[factory.py]"]
end

subgraph group_research["Research Agent"]
  node_research_api["Research API<br/>[api.py]"]
  node_research_graph["Research workflow<br/>[graph.py]"]
  node_fetcher["Source fetching<br/>[fetcher.py]"]
  node_extract["Claim extraction<br/>[extract.py]"]
  node_gaps["Facet gap analysis<br/>[gaps.py]"]
  node_synthesize["Consensus synthesis<br/>[synthesize.py]"]
  node_verify["Claim verification<br/>[verify.py]"]
end

subgraph group_sql["SQL Agent"]
end

node_resume_user(("Resume submitter"))
node_engineer_service{{"Engineer A2A service"}}
node_hr_service{{"HR A2A service"}}
node_rag_user(("Ingest client"))
node_mentor_user(("Student"))
node_research_user(("Research requester"))

node_resume_user -.->|"submits resume"| node_resume_app
node_resume_app -->|"invokes orchestrator"| node_resume_orch
node_resume_orch -->|"sends A2A review"| node_engineer_service
node_resume_orch -->|"sends A2A review"| node_hr_service
node_engineer_service -.->|"runs review"| node_engineer
node_hr_service -.->|"runs review"| node_hr
node_rag_user -.->|"uploads documents"| node_rag_route
node_rag_route -->|"builds pipeline"| node_rag_config
node_rag_route -->|"processes uploads"| node_rag_pipeline
node_rag_pipeline -->|"parses documents"| node_parser
node_rag_pipeline -->|"chunks content"| node_chunking
node_rag_pipeline -->|"filters duplicates"| node_hashing
node_rag_pipeline -->|"embeds chunks"| node_embedding
node_rag_pipeline -->|"upserts vectors"| node_vector_store
node_rag_route -->|"formats results"| node_rag_models
node_rag_route -->|"counts outcomes"| node_rag_observe
node_mentor_user -.->|"asks question"| node_mentor_api
node_mentor_api -->|"routes chat"| node_mentor_orch
node_mentor_orch -->|"invokes agent"| node_mentor_agent
node_mentor_orch -->|"invokes agent"| node_placement_agent
node_mentor_orch -->|"invokes agent"| node_emotional_agent
node_mentor_orch -->|"uses student data"| node_mentor_data
node_mentor_orch -->|"creates model"| node_llm_factory
node_mentor_agent -->|"reads student records"| node_mentor_data
node_placement_agent -->|"reads placement data"| node_mentor_data
node_emotional_agent -->|"creates model"| node_llm_factory
node_research_user -.->|"requests research"| node_research_api
node_research_api -.->|"starts workflow"| node_research_graph
node_research_graph -->|"fetches sources"| node_fetcher
node_research_graph -->|"extracts claims"| node_extract
node_research_graph -->|"checks coverage"| node_gaps
node_research_graph -->|"groups claims"| node_synthesize
node_research_graph -->|"verifies claims"| node_verify

click node_resume_app "https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/app.py"
click node_resume_orch "https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/agents/orchestrator/main.py"
click node_engineer "https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/agents/engineer_agent/tools.py"
click node_hr "https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/agents/hr_agent/tools.py"
click node_rag_route "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/api/routes/ingest.py"
click node_rag_config "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/api/dependencies.py"
click node_rag_pipeline "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/pipeline.py"
click node_parser "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/parsers/docling_parser.py"
click node_chunking "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/chunkers/coordinator.py"
click node_hashing "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/hashing/mysql_store.py"
click node_embedding "https://github.com/dharun11/ai/tree/main/Agentic%20Rag/src/ingestion/embedders"
click node_vector_store "https://github.com/dharun11/ai/tree/main/Agentic%20Rag/src/ingestion/store"
click node_rag_models "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/models.py"
click node_rag_observe "https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/observability.py"
click node_mentor_api "https://github.com/dharun11/ai/blob/main/MentorAgent/main.py"
click node_mentor_orch "https://github.com/dharun11/ai/blob/main/MentorAgent/orchestrator.py"
click node_mentor_agent "https://github.com/dharun11/ai/blob/main/MentorAgent/agents/mentor_agent.py"
click node_placement_agent "https://github.com/dharun11/ai/blob/main/MentorAgent/agents/placement_agent.py"
click node_emotional_agent "https://github.com/dharun11/ai/blob/main/MentorAgent/agents/emotional_agent.py"
click node_mentor_data "https://github.com/dharun11/ai/blob/main/MentorAgent/db.py"
click node_llm_factory "https://github.com/dharun11/ai/blob/main/MentorAgent/factory.py"
click node_research_api "https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/api.py"
click node_research_graph "https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/graph.py"
click node_fetcher "https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/fetch/fetcher.py"
click node_extract "https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/extract.py"
click node_gaps "https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/gaps.py"
click node_synthesize "https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/synthesize.py"
click node_verify "https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/verify.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_resume_app,node_resume_orch,node_engineer,node_hr,node_rag_user toneBlue
class node_rag_route,node_rag_config,node_rag_pipeline,node_parser,node_chunking,node_hashing,node_embedding,node_vector_store,node_rag_models,node_rag_observe toneAmber
class node_mentor_api,node_mentor_orch,node_mentor_agent,node_placement_agent,node_emotional_agent,node_mentor_data,node_llm_factory,node_research_user toneMint
class node_research_api,node_research_graph,node_fetcher,node_extract,node_gaps,node_synthesize,node_verify toneRose
class node_resume_user,node_engineer_service,node_hr_service,node_mentor_user toneIndigo
```

## Components

### Resume Roaster

- [Resume app](https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/app.py): `A2A/resume-roaster/app.py`
- [Review orchestrator](https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/agents/orchestrator/main.py): `A2A/resume-roaster/agents/orchestrator/main.py`
- [Engineering review](https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/agents/engineer_agent/tools.py): `A2A/resume-roaster/agents/engineer_agent/tools.py`
- [HR review](https://github.com/dharun11/ai/blob/main/A2A/resume-roaster/agents/hr_agent/tools.py): `A2A/resume-roaster/agents/hr_agent/tools.py`

### Document Ingestion

- [Upload endpoint](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/api/routes/ingest.py): `Agentic Rag/src/api/routes/ingest.py`
- [Pipeline composition](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/api/dependencies.py): `Agentic Rag/src/api/dependencies.py`
- [Ingestion pipeline](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/pipeline.py): `Agentic Rag/src/ingestion/pipeline.py`
- [Document parsing](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/parsers/docling_parser.py): `Agentic Rag/src/ingestion/parsers/docling_parser.py`
- [Chunk coordination](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/chunkers/coordinator.py): `Agentic Rag/src/ingestion/chunkers/coordinator.py`
- [Content deduplication](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/hashing/mysql_store.py): `Agentic Rag/src/ingestion/hashing/mysql_store.py`
- [Embedding providers](https://github.com/dharun11/ai/tree/main/Agentic%20Rag/src/ingestion/embedders): `Agentic Rag/src/ingestion/embedders`
- [Vector stores](https://github.com/dharun11/ai/tree/main/Agentic%20Rag/src/ingestion/store): `Agentic Rag/src/ingestion/store`
- [Ingestion records](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/models.py): `Agentic Rag/src/ingestion/models.py`
- [Run observability](https://github.com/dharun11/ai/blob/main/Agentic%20Rag/src/ingestion/observability.py): `Agentic Rag/src/ingestion/observability.py`

### Student Mentor

- [Chat API](https://github.com/dharun11/ai/blob/main/MentorAgent/main.py): `MentorAgent/main.py`
- [Agent orchestrator](https://github.com/dharun11/ai/blob/main/MentorAgent/orchestrator.py): `MentorAgent/orchestrator.py`
- [Academic mentor](https://github.com/dharun11/ai/blob/main/MentorAgent/agents/mentor_agent.py): `MentorAgent/agents/mentor_agent.py`
- [Placement advisor](https://github.com/dharun11/ai/blob/main/MentorAgent/agents/placement_agent.py): `MentorAgent/agents/placement_agent.py`
- [Emotional support](https://github.com/dharun11/ai/blob/main/MentorAgent/agents/emotional_agent.py): `MentorAgent/agents/emotional_agent.py`
- [Student data store](https://github.com/dharun11/ai/blob/main/MentorAgent/db.py): `MentorAgent/db.py`
- [LLM provider factory](https://github.com/dharun11/ai/blob/main/MentorAgent/factory.py): `MentorAgent/factory.py`

### Research Agent

- [Research API](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/api.py): `Research Agent/src/research_agent/api.py`
- [Research workflow](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/graph.py): `Research Agent/src/research_agent/pipeline/graph.py`
- [Source fetching](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/fetch/fetcher.py): `Research Agent/src/research_agent/fetch/fetcher.py`
- [Claim extraction](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/extract.py): `Research Agent/src/research_agent/pipeline/extract.py`
- [Facet gap analysis](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/gaps.py): `Research Agent/src/research_agent/pipeline/gaps.py`
- [Consensus synthesis](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/synthesize.py): `Research Agent/src/research_agent/pipeline/synthesize.py`
- [Claim verification](https://github.com/dharun11/ai/blob/main/Research%20Agent/src/research_agent/pipeline/verify.py): `Research Agent/src/research_agent/pipeline/verify.py`

### Other components

- **Resume submitter**
- **Engineer A2A service**
- **HR A2A service**
- **Ingest client**
- **Student**
- **Research requester**

## Connections

- Resume submitter → Resume app: submits resume
- Resume app → Review orchestrator: invokes orchestrator (evidence: `A2A/resume-roaster/app.py`)
- Review orchestrator → Engineer A2A service: sends A2A review (evidence: `A2A/resume-roaster/agents/orchestrator/main.py`)
- Review orchestrator → HR A2A service: sends A2A review (evidence: `A2A/resume-roaster/agents/orchestrator/main.py`)
- Engineer A2A service → Engineering review: runs review
- HR A2A service → HR review: runs review
- Ingest client → Upload endpoint: uploads documents
- Upload endpoint → Pipeline composition: builds pipeline (evidence: `Agentic Rag/src/api/routes/ingest.py`)
- Upload endpoint → Ingestion pipeline: processes uploads (evidence: `Agentic Rag/src/api/routes/ingest.py`)
- Ingestion pipeline → Document parsing: parses documents (evidence: `Agentic Rag/src/ingestion/pipeline.py`)
- Ingestion pipeline → Chunk coordination: chunks content (evidence: `Agentic Rag/src/ingestion/pipeline.py`)
- Ingestion pipeline → Content deduplication: filters duplicates (evidence: `Agentic Rag/src/ingestion/pipeline.py`)
- Ingestion pipeline → Embedding providers: embeds chunks (evidence: `Agentic Rag/src/ingestion/pipeline.py`)
- Ingestion pipeline → Vector stores: upserts vectors (evidence: `Agentic Rag/src/ingestion/pipeline.py`)
- Upload endpoint → Ingestion records: formats results (evidence: `Agentic Rag/src/api/routes/ingest.py`)
- Upload endpoint → Run observability: counts outcomes (evidence: `Agentic Rag/src/api/routes/ingest.py`)
- Student → Chat API: asks question
- Chat API → Agent orchestrator: routes chat (evidence: `MentorAgent/main.py`)
- Agent orchestrator → Academic mentor: invokes agent (evidence: `MentorAgent/orchestrator.py`)
- Agent orchestrator → Placement advisor: invokes agent (evidence: `MentorAgent/orchestrator.py`)
- Agent orchestrator → Emotional support: invokes agent (evidence: `MentorAgent/orchestrator.py`)
- Agent orchestrator → Student data store: uses student data (evidence: `MentorAgent/orchestrator.py`)
- Agent orchestrator → LLM provider factory: creates model (evidence: `MentorAgent/orchestrator.py`)
- Academic mentor → Student data store: reads student records (evidence: `MentorAgent/agents/mentor_agent.py`)
- Placement advisor → Student data store: reads placement data (evidence: `MentorAgent/agents/placement_agent.py`)
- Emotional support → LLM provider factory: creates model (evidence: `MentorAgent/agents/emotional_agent.py`)
- Research requester → Research API: requests research
- Research API → Research workflow: starts workflow
- Research workflow → Source fetching: fetches sources (evidence: `Research Agent/src/research_agent/pipeline/graph.py`)
- Research workflow → Claim extraction: extracts claims (evidence: `Research Agent/src/research_agent/pipeline/graph.py`)
- Research workflow → Facet gap analysis: checks coverage (evidence: `Research Agent/src/research_agent/pipeline/graph.py`)
- Research workflow → Consensus synthesis: groups claims (evidence: `Research Agent/src/research_agent/pipeline/graph.py`)
- Research workflow → Claim verification: verifies claims (evidence: `Research Agent/src/research_agent/pipeline/graph.py`)
