Metadata-Version: 2.4
Name: pb-dolphin
Version: 0.1.13
Summary: Full-stack AI enablement platform
Project-URL: Homepage, https://plasticbeach.llc/
Project-URL: Documentation, https://github.com/plasticbeachllc/dolphin
Project-URL: Repository, https://github.com/plasticbeachllc/dolphin
Project-URL: Issues, https://github.com/plasticbeachllc/dolphin/issues
Project-URL: Changelog, https://github.com/plasticbeachllc/dolphin/blob/main/CHANGELOG.md
Author-email: "Plastic Beach, LLC" <info@plasticbeach.email>, tdc93 <taylor@plasticbeach.email>
Maintainer-email: "Plastic Beach, LLC" <info@plasticbeach.email>, tdc93 <taylor@plasticbeach.email>
License: MIT
License-File: LICENSE.md
Keywords: ai,knowledge-base,llm,mcp,search
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Requires-Python: >=3.12
Requires-Dist: fastapi
Requires-Dist: lancedb
Requires-Dist: markdown-it-py
Requires-Dist: openai
Requires-Dist: pathspec
Requires-Dist: pydantic
Requires-Dist: python-dotenv
Requires-Dist: pyyaml
Requires-Dist: sqlite-utils
Requires-Dist: sqlmodel
Requires-Dist: tiktoken
Requires-Dist: tomli; python_full_version < '3.11'
Requires-Dist: tree-sitter-javascript>=0.25.0
Requires-Dist: tree-sitter-python>=0.25.0
Requires-Dist: tree-sitter>=0.25.0
Requires-Dist: typer
Requires-Dist: uvicorn
Provides-Extra: dev
Requires-Dist: black>=23.0.0; extra == 'dev'
Requires-Dist: isort>=5.12.0; extra == 'dev'
Requires-Dist: mypy>=1.5.0; extra == 'dev'
Requires-Dist: pre-commit>=3.4.0; extra == 'dev'
Requires-Dist: ruff>=0.1.0; extra == 'dev'
Provides-Extra: reranking
Requires-Dist: sentence-transformers>=2.3.0; extra == 'reranking'
Requires-Dist: torch>=2.2.0; extra == 'reranking'
Provides-Extra: test
Requires-Dist: fakeredis>=2.18.0; extra == 'test'
Requires-Dist: freezegun>=1.2.0; extra == 'test'
Requires-Dist: httpx>=0.25.0; extra == 'test'
Requires-Dist: pytest-asyncio>=0.21.0; extra == 'test'
Requires-Dist: pytest-cov>=4.1.0; extra == 'test'
Requires-Dist: pytest-mock>=3.11.0; extra == 'test'
Requires-Dist: pytest-xdist>=3.3.0; extra == 'test'
Requires-Dist: pytest>=7.4.0; extra == 'test'
Requires-Dist: responses>=0.24.0; extra == 'test'
Description-Content-Type: text/markdown

# 🐬 dolphin

[![PyPi Version](https://img.shields.io/pypi/v/pb-dolphin.svg)](https://pypi.org/project/pb-dolphin/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

**⚠️ EXPERIMENTAL - This is a developmental library under active development. APIs and interfaces are unstable and subject to change without notice.**

A semantic code search and knowledge management system for AI interface. This package includes an indexing program managed by the user and an HTTP retrieval server. The companion MCP server is available at `bunx dolphin-mcp`.

## Quick Start

### Installation

#### Core Installation (~200MB)

```bash
# install with uv (recommended)
uv pip install pb-dolphin

# ensure OPENAI_API_KEY is set as env var
export OPENAI_API_KEY="sk-your-key-here"
```

#### Optional: Cross-Encoder Reranking (~2GB additional)

For advanced search quality improvement (+20-30% MRR):

```bash
uv pip install "pb-dolphin[reranking]"
```

**Trade-off**: Better relevance but 2-3x slower searches. See [Advanced Features](#advanced-features) for configuration.


### Basic Usage

```bash
# Initialize global knowledge store and index a repository
dolphin init
dolphin add-repo my-project /path/to/project
dolphin index my-project

# Search your indexed code
dolphin search "authentication logic"

# Start API server
dolphin serve
```

## Core Commands

- `dolphin init` - Initialize configuration (auto-creates `~/.dolphin/config.toml`)
- `dolphin init --repo` - Create repo-specific config in current directory
- `dolphin add-repo <name> <path>` - Register a repository for indexing
- `dolphin index <name>` - Index a repository with language-aware chunking
- `dolphin search <query>` - Search indexed code semantically
- `dolphin serve` - Start REST API server (port 7777)
- `dolphin config --show` - Display current configuration

## Architecture

### High-Level Overview

```
┌──────────────────────────────────────────┐
│   AI Interfaces (Claude, Continue, etc)  │
└──────────────┬───────────────────────────┘
               │ MCP Protocol
               ▼
┌──────────────────────────────────────────┐
│          Dolphin Knowledge Base          │
│  ┌─────────────┐    ┌────────────────-┐  │
│  │ MCP Bridge  │◄──►│ REST API        │  │
│  │ (TypeScript)│    │ (Python/FastAPI)│  │
│  └─────────────┘    └────────┬────────┘  │
└──────────────────────────────┼───────────┘
                               │
               ┌───────────────┴────────────┐
               ▼                            ▼
          ┌─────────┐                ┌──────────┐
          │LanceDB  │                │ SQLite   │
          │(Vectors)│                │(Metadata)│
          └─────────┘                └──────────┘
```

### Key Features

- **Language-Aware Chunking** - Code parsing for Python, TypeScript, JavaScript, Markdown
- **Semantic Search**
  * OpenAI embeddings with LanceDB vector storage
  * Hybrid approximate nn vector + BM25 keyword search with RRF scoring
  * Re-ranking with cross-encoder
  * MMR relevancy enhancement
- **Interfaces**
  * `dolphin` CLI app
  * FastAPI server with search, retrieval, and metadata endpoints
  * MCP server implementation available at `bunx dolphin-mcp`
- **Configuration** - Per-repo chunking and ignore configuration



## Configuration

Dolphin uses a multi-level configuration system:

1. **Repo-specific** (`./.dolphin/config.toml`) - Optional per-repository chunking settings
2. **User-global** (`~/.dolphin/config.toml`) - Auto-created on first use

### Configuration TOMLs

You can use `dolphin init` to initialize your global config and edit from there.

```toml
# ~/.dolphin/config.toml
default_embed_model = "large"  # or "small"

[embedding]
provider = "openai"
batch_size = 100

[retrieval]
top_k = 8
score_cutoff = 0.0
```

To generate a repo-specific config, use `dolphin init --repo` at the repository root. 

### Environment Variables

```bash
# Required when using OpenAI embeddings (recommended for production)
export OPENAI_API_KEY="sk-your-openai-api-key-here"
```

### Post-Commit Hook (recommended)

Add this line to the repo's `.git/postcommit` file, inserting the actual repo name.

```
uv run dolphin index {repo-name}
```

Since the indexer walks the git diff, your repository index will always remain fresh.

## MCP Configuration

The small companion MCP interface can be run via `bun` without install. Add to your favorite AI application's config:

```json
{
  "mcpServers": {
    "dolphin": {
      "command": "bunx",
      "args": ["dolphin-mcp"]
    }
  }
}
```

Make sure you are running the HTTP retrieval server: `uv run dolphin serve`

Available MCP tools: `search_knowledge`, `fetch_chunk`, `fetch_lines`, `get_vector_store_info`

## REST API

```bash
# Start server
dolphin serve

# Health check
curl http://127.0.0.1:7777/health

# List repositories
curl http://127.0.0.1:7777/repos

# Search "authentication"
curl -X POST http://127.0.0.1:7777/search \
  -H "Content-Type: application/json" \
  -d '{"query": "authentication", "top_k": 5}'
```

## Advanced Features

### Cross-Encoder Reranking

Cross-encoder reranking improves search result relevance by re-scoring each result pairwise against the query using an ML model, leading to 20-30% improvements in search result ranking quality ([Nogueira & Cho, 2019](https://arxiv.org/abs/1901.04085)).

**Performance Impact:**
- ⚠️ **2-3x slower searches** - cross-encoder is compute-intensive
- ⚠️ **~2GB install size** - requires torch and sentence-transformers

#### Installation

```bash
uv pip install "pb-dolphin[reranking]"
```

#### Configuration

Enable in your `~/.dolphin/config.toml`:

```toml
[retrieval.reranking]
enabled = true  # Enable cross-encoder reranking
model = "cross-encoder/ms-marco-MiniLM-L-6-v2"  # HuggingFace model
device = ""  # Auto-detect (CPU or CUDA if available)
batch_size = 32  # Higher = faster but more memory
candidate_multiplier = 4  # Rerank top_k × multiplier candidates
score_threshold = 0.3  # Minimum relevance score (0-1)
```

Restart the API server to apply changes:

```bash
uv run dolphin serve
```

## Development Status

**Current**: Beta (0.1.x)

- ✅ Core indexing and search pipeline
- ✅ Language-aware chunking (Python, TS, JS, Markdown)
- ✅ REST API with MCP bridge available at `bunx dolphin-mcp`
- ⚠️ Developmental stage

**Upcoming**:
- Performance optimization
- Production hardening
- Evaluation framework
- Expanded language support

## Requirements

- Python ≥3.12
- OpenAI API key (for embeddings)
- Bun (for MCP bridge)
- Git (for repository scanning)

## Testing

```bash
# Run all tests
uv run pytest

# Run specific test suite
uv run pytest tests/unit/
uv run pytest tests/integration/
```

## License

MIT License

## Acknowledgments

Built with [LanceDB](https://lancedb.com/), [OpenAI](https://openai.com/), [FastAPI](https://fastapi.tiangolo.com/), [Bun](https://bun.sh/), and lots of other tech.

---

**⚠️ Remember**: This is experimental software under active development. Use at your own risk.
