# abhasbali/samsung-hackathon architecture

> Architecture diagram of the GitHub repository abhasbali/samsung-hackathon, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/abhasbali/samsung-hackathon
- Repository: https://github.com/abhasbali/samsung-hackathon

## Overview

CodeFusion indexes repositories into semantic code snippets and answers natural-language questions with ranked, provenance-bearing results rather than generated prose. The main workflow is repository indexing (parse and chunk, construct representations and retrieval indexes), followed by intent-aware search, graph-aware retrieval and ranking. It also tracks incremental Git updates and snippet lineage across versions; the API and frontend expose search, index/version status, call chains and experiment results. Edges are limited to README statements and source-index references or excerpts; several implementation details are unsampled, so uncertain connections are omitted.

Main entry points: [`src/codefusion/retrieval/pipeline.py`](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/pipeline.py) (Retrieval engine), [`src/codefusion/versions/incremental.py`](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/versions/incremental.py) (Incremental indexing), [`frontend/src/App.tsx`](https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/App.tsx) (Web interface), [`src/codefusion/parsing/chunker.py`](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/chunker.py) (Parse and chunk)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_ingest["Code indexing"]
  node_parse["Parse and chunk<br/>[chunker.py]"]
  node_parser["Tree-sitter parser"]
  node_fallback["Parser fallback<br/>[fallback.py]"]
  node_identifiers["Identifier tokens<br/>[identifiers.py]"]
  node_representations["Code representations"]
end

subgraph group_search["Query and retrieval"]
  node_engine["Retrieval engine<br/>[pipeline.py]"]
  node_embeddings["Embedding providers<br/>[embeddings.py]"]
  node_dense["Dense retrieval<br/>[dense.py]"]
  node_lexical["BM25 retrieval<br/>[bm25.py]"]
  node_symbols["Symbol retrieval<br/>[symbols.py]"]
  node_graph["Call graph<br/>[builder.py]"]
  node_graphscore["Graph scoring<br/>[scoring.py]"]
  node_fusion["Rank fusion<br/>[fusion.py]"]
  node_reranker["Reranking<br/>[reranker.py]"]
  node_diversity["Dedup and diversity<br/>[diversity.py]"]
  node_snippetstore[("Snippet store<br/>[pipeline.py]")]
end

subgraph group_versions["Version history"]
  node_incremental["Incremental indexing<br/>[incremental.py]"]
  node_git["Git tracking<br/>[git_tracker.py]"]
  node_lineage["Snippet lineage<br/>[lineage.py]"]
end

subgraph group_service["API and UI"]
  node_api["HTTP API<br/>[main.py]"]
  node_frontend["Web interface<br/>[App.tsx]"]
  node_api_client["API client<br/>[api.ts]"]
  node_searchview["Search view<br/>[SearchView.tsx]"]
  node_resultview["Result details<br/>[ResultCard.tsx]"]
  node_indexview["Index and versions<br/>[IndexView.tsx]"]
  node_experimentsview["Experiments view"]
end

subgraph group_evaluation["Evaluation"]
  node_evaluation["Evaluation harness<br/>[official.py]"]
  node_encoder["MTEB encoder<br/>[mteb_encoder.py]"]
  node_metrics["Evaluation metrics<br/>[metrics.py]"]
  node_tracking["Run tracking<br/>[tracking.py]"]
  node_experiments[("Experiment artifacts<br/>[artifacts.py]")]
end

node_user(("Engineer"))
node_repo["Code repository"]
node_results["Ranked snippets"]

node_user -->|"uses"| node_frontend
node_frontend -->|"delegates"| node_api_client
node_api_client -.->|"HTTP requests"| node_api
node_frontend -->|"renders"| node_searchview
node_frontend -->|"renders"| node_indexview
node_frontend -->|"renders"| node_experimentsview
node_searchview -->|"requests search"| node_api_client
node_searchview -->|"renders results"| node_resultview
node_indexview -->|"requests indexing"| node_api_client
node_experimentsview -->|"loads experiments"| node_api_client
node_repo -->|"indexes versions"| node_incremental
node_incremental -->|"reads history"| node_git
node_incremental -->|"chunks changes"| node_parse
node_incremental -->|"adds snippets"| node_engine
node_incremental -->|"matches lineage"| node_lineage
node_parse -->|"uses parser"| node_parser
node_parse -->|"falls back"| node_fallback
node_parse -.->|"tokenizes names"| node_identifiers
node_repo -->|"parses code"| node_parse
node_engine -->|"builds views"| node_representations
node_engine -->|"embeds snippets"| node_embeddings
node_engine -->|"retrieves dense"| node_dense
node_engine -->|"retrieves BM25"| node_lexical
node_engine -->|"retrieves symbols"| node_symbols
node_engine -->|"expands candidates"| node_graph
node_engine -->|"scores structure"| node_graphscore
node_engine -->|"fuses rankings"| node_fusion
node_engine -->|"reranks candidates"| node_reranker
node_engine -->|"deduplicates results"| node_diversity
node_engine -->|"stores snippets"| node_snippetstore
node_api -->|"searches"| node_engine
node_api -->|"indexes repository"| node_incremental
node_engine -->|"returns ranked snippets"| node_results
node_api -->|"serves search output"| node_results
node_evaluation -->|"uses encoder"| node_encoder
node_evaluation -->|"computes metrics"| node_metrics
node_evaluation -->|"tracks runs"| node_tracking
node_evaluation -.->|"writes artifacts"| node_experiments
node_experimentsview -.->|"displays results"| node_experiments

click node_parse "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/chunker.py"
click node_parser "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/tree_sitter_parser.py"
click node_fallback "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/fallback.py"
click node_identifiers "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/identifiers.py"
click node_representations "https://github.com/abhasbali/samsung-hackathon/tree/main/src/codefusion/representations"
click node_engine "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/pipeline.py"
click node_embeddings "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/embeddings.py"
click node_dense "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/dense.py"
click node_lexical "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/bm25.py"
click node_symbols "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/symbols.py"
click node_graph "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/graph/builder.py"
click node_graphscore "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/graph/scoring.py"
click node_fusion "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/fusion.py"
click node_reranker "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/reranker.py"
click node_diversity "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/diversity.py"
click node_snippetstore "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/pipeline.py"
click node_incremental "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/versions/incremental.py"
click node_git "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/versions/git_tracker.py"
click node_lineage "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/versions/lineage.py"
click node_api "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/api/main.py"
click node_frontend "https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/App.tsx"
click node_api_client "https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/api.ts"
click node_searchview "https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/SearchView.tsx"
click node_resultview "https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/ResultCard.tsx"
click node_indexview "https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/IndexView.tsx"
click node_experimentsview "https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/ExperimentsView.tsx"
click node_evaluation "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/official.py"
click node_encoder "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/mteb_encoder.py"
click node_metrics "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/metrics.py"
click node_tracking "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/tracking.py"
click node_experiments "https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/storage/artifacts.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_parse,node_parser,node_fallback,node_identifiers,node_representations toneBlue
class node_engine,node_embeddings,node_dense,node_lexical,node_symbols,node_graph,node_graphscore,node_fusion,node_reranker,node_diversity,node_snippetstore toneAmber
class node_incremental,node_git,node_lineage toneMint
class node_api,node_frontend,node_api_client,node_searchview,node_resultview,node_indexview,node_experimentsview toneRose
class node_evaluation,node_encoder,node_metrics,node_tracking,node_experiments,node_user,node_repo,node_results toneIndigo
```

## Components

### Code indexing

- [Parse and chunk](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/chunker.py): `src/codefusion/parsing/chunker.py`
- [Tree-sitter parser](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/tree_sitter_parser.py): `src/codefusion/parsing/tree_sitter_parser.py`
- [Parser fallback](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/fallback.py): `src/codefusion/parsing/fallback.py`
- [Identifier tokens](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/parsing/identifiers.py): `src/codefusion/parsing/identifiers.py`
- [Code representations](https://github.com/abhasbali/samsung-hackathon/tree/main/src/codefusion/representations): `src/codefusion/representations`

### Query and retrieval

- [Retrieval engine](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/pipeline.py): `src/codefusion/retrieval/pipeline.py`
- [Embedding providers](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/embeddings.py): `src/codefusion/retrieval/embeddings.py`
- [Dense retrieval](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/dense.py): `src/codefusion/retrieval/dense.py`
- [BM25 retrieval](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/bm25.py): `src/codefusion/retrieval/bm25.py`
- [Symbol retrieval](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/symbols.py): `src/codefusion/retrieval/symbols.py`
- [Call graph](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/graph/builder.py): `src/codefusion/graph/builder.py`
- [Graph scoring](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/graph/scoring.py): `src/codefusion/graph/scoring.py`
- [Rank fusion](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/fusion.py): `src/codefusion/retrieval/fusion.py`
- [Reranking](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/reranker.py): `src/codefusion/retrieval/reranker.py`
- [Dedup and diversity](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/diversity.py): `src/codefusion/retrieval/diversity.py`
- [Snippet store](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/retrieval/pipeline.py): `src/codefusion/retrieval/pipeline.py`

### Version history

- [Incremental indexing](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/versions/incremental.py): `src/codefusion/versions/incremental.py`
- [Git tracking](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/versions/git_tracker.py): `src/codefusion/versions/git_tracker.py`
- [Snippet lineage](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/versions/lineage.py): `src/codefusion/versions/lineage.py`

### API and UI

- [HTTP API](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/api/main.py): `src/codefusion/api/main.py`
- [Web interface](https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/App.tsx): `frontend/src/App.tsx`
- [API client](https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/api.ts): `frontend/src/api.ts`
- [Search view](https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/SearchView.tsx): `frontend/src/components/SearchView.tsx`
- [Result details](https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/ResultCard.tsx): `frontend/src/components/ResultCard.tsx`
- [Index and versions](https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/IndexView.tsx): `frontend/src/components/IndexView.tsx`
- [Experiments view](https://github.com/abhasbali/samsung-hackathon/blob/main/frontend/src/components/ExperimentsView.tsx): `frontend/src/components/ExperimentsView.tsx`

### Evaluation

- [Evaluation harness](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/official.py): `src/codefusion/evaluation/official.py`
- [MTEB encoder](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/mteb_encoder.py): `src/codefusion/evaluation/mteb_encoder.py`
- [Evaluation metrics](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/metrics.py): `src/codefusion/evaluation/metrics.py`
- [Run tracking](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/evaluation/tracking.py): `src/codefusion/evaluation/tracking.py`
- [Experiment artifacts](https://github.com/abhasbali/samsung-hackathon/blob/main/src/codefusion/storage/artifacts.py): `src/codefusion/storage/artifacts.py`

### Other components

- **Engineer**
- **Code repository**
- **Ranked snippets**

## Connections

- Engineer → Web interface: uses
- Web interface → API client: delegates (evidence: `frontend/src/App.tsx`)
- API client → HTTP API: HTTP requests
- Web interface → Search view: renders (evidence: `frontend/src/App.tsx`)
- Web interface → Index and versions: renders (evidence: `frontend/src/App.tsx`)
- Web interface → Experiments view: renders (evidence: `frontend/src/App.tsx`)
- Search view → API client: requests search (evidence: `frontend/src/components/SearchView.tsx`)
- Search view → Result details: renders results (evidence: `frontend/src/components/SearchView.tsx`)
- Index and versions → API client: requests indexing (evidence: `frontend/src/components/IndexView.tsx`)
- Experiments view → API client: loads experiments (evidence: `frontend/src/components/ExperimentsView.tsx`)
- Code repository → Incremental indexing: indexes versions
- Incremental indexing → Git tracking: reads history (evidence: `src/codefusion/versions/incremental.py`)
- Incremental indexing → Parse and chunk: chunks changes (evidence: `src/codefusion/versions/incremental.py`)
- Incremental indexing → Retrieval engine: adds snippets (evidence: `src/codefusion/versions/incremental.py`)
- Incremental indexing → Snippet lineage: matches lineage (evidence: `src/codefusion/versions/incremental.py`)
- Parse and chunk → Tree-sitter parser: uses parser (evidence: `src/codefusion/parsing/chunker.py`)
- Parse and chunk → Parser fallback: falls back (evidence: `src/codefusion/parsing/chunker.py`)
- Parse and chunk → Identifier tokens: tokenizes names
- Code repository → Parse and chunk: parses code
- Retrieval engine → Code representations: builds views (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Embedding providers: embeds snippets (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Dense retrieval: retrieves dense (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → BM25 retrieval: retrieves BM25 (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Symbol retrieval: retrieves symbols (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Call graph: expands candidates (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Graph scoring: scores structure (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Rank fusion: fuses rankings (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Reranking: reranks candidates (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Dedup and diversity: deduplicates results (evidence: `src/codefusion/retrieval/pipeline.py`)
- Retrieval engine → Snippet store: stores snippets (evidence: `src/codefusion/retrieval/pipeline.py`)
- HTTP API → Retrieval engine: searches (evidence: `src/codefusion/api/main.py`)
- HTTP API → Incremental indexing: indexes repository (evidence: `src/codefusion/api/main.py`)
- Retrieval engine → Ranked snippets: returns ranked snippets
- HTTP API → Ranked snippets: serves search output (evidence: `src/codefusion/api/main.py`)
- Evaluation harness → MTEB encoder: uses encoder (evidence: `src/codefusion/evaluation/official.py`)
- Evaluation harness → Evaluation metrics: computes metrics (evidence: `src/codefusion/evaluation/official.py`)
- Evaluation harness → Run tracking: tracks runs (evidence: `src/codefusion/evaluation/official.py`)
- Evaluation harness → Experiment artifacts: writes artifacts
- Experiments view → Experiment artifacts: displays results
