agent-coderag 1.1.0__tar.gz

agent_coderag-1.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Igor Boloban
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

agent_coderag-1.1.0/NOTICE

@@ -0,0 +1,17 @@
+CodeRAG
+Copyright 2026 Igor Boloban
+
+This product includes software developed by the following third-party projects:
+
+- DuckDB (MIT License) - https://duckdb.org/
+- NumPy (BSD License) - https://numpy.org/
+- LiteLLM (MIT License) - https://litellm.ai/
+- ONNX Runtime (MIT License) - https://onnxruntime.ai/
+- Tokenizers (Apache License 2.0) - https://github.com/huggingface/tokenizers
+- Pydantic (MIT License) - https://github.com/pydantic/pydantic
+- HTTPX (BSD License) - https://github.com/encode/httpx
+- Aiofiles (Apache License 2.0) - https://github.com/Tinche/aiofiles
+- Sentence Transformers (Apache License 2.0) - https://www.sbert.net/
+
+This product also uses various other open-source libraries as listed in THIRD_PARTY_LICENSES.md.
+All trademarks are the property of their respective owners.

agent_coderag-1.1.0/PKG-INFO

@@ -0,0 +1,188 @@
+Metadata-Version: 2.4
+Name: agent-coderag
+Version: 1.1.0
+Summary: Lightweight semantic code search and distillation utility for AI coding agents. It solves the API knowledge gap via real-time local signature extraction and intent analysis without PyTorch. Optimized for token efficiency, it compresses codebase context into compact semantic summaries stored in a local DuckDB vector similarity index.
+Author-email: Igor Boloban <naranor@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/naranor/agent-coderag
+Project-URL: Repository, https://github.com/naranor/agent-coderag
+Project-URL: Issues, https://github.com/naranor/agent-coderag/issues
+Project-URL: Changelog, https://github.com/naranor/agent-coderag/blob/main/CHANGELOG.md
+Keywords: rag,ai-agents,semantic-search,code-analysis,context-compression,onnx,local-embeddings
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Indexing
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: duckdb
+Requires-Dist: numpy
+Requires-Dist: litellm
+Requires-Dist: onnxruntime
+Requires-Dist: tokenizers
+Requires-Dist: pydantic
+Requires-Dist: httpx
+Requires-Dist: aiofiles
+Dynamic: license-file
+
+# Agent-CodeRAG: Semantic Intelligence for AI Coding Agents
+
+> **Fast. Local. Agent-First. Token-Efficient.**
+
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![No PyTorch](https://img.shields.io/badge/Footprint-No_PyTorch-green.svg)](#-key-technologies)
+[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
+
+---
+
+## 📖 Table of Contents
+- [🧠 The Problem: The API Knowledge Gap](#-the-problem-the-api-knowledge-gap)
+- [🚀 The Solution: Real-Time Contextual Truth](#-the-solution-real-time-contextual-truth)
+- [🛠 How it Works](#-how-it-works)
+- [📡 API Discovery](#-api-discovery)
+- [🏃 Quick Start](#-quick-start)
+- [🤖 For AI Agents](#-for-ai-agents)
+- [🔧 Development](#-development)
+- [📄 License](#-license)
+
+---
+
+## 🧠 The Problem: The API Knowledge Gap
+
+AI coding agents often hallucinate when calling library APIs because their training data is static. This leads to a **"Fail-Fix-Fail" cycle**:
+
+1.  **Broken Code**: Agents use deprecated parameters or non-existent methods from outdated versions.
+2.  **Token Waste**: You provide the error, the agent tries to fix it using more outdated data, consuming thousands of tokens in a loop.
+3.  **Environment Mismatch**: The agent knows the API for version 1.0, but your environment has 2.0.
+
+### Real-world Example (The Pydantic Gap)
+*   **Agent's Knowledge**: Knows Pydantic v1 (`model.dict()`).
+*   **Your Environment**: Uses Pydantic v2 (`model.model_dump()`).
+*   **The Result**: The agent writes `dict()`, the code fails, and it wastes **5000+ tokens** trying to "fix" a problem it doesn't understand.
+
+## 🚀 The Solution: Real-Time Contextual Truth
+
+Agent-CodeRAG acts as a lightweight semantic bridge between your local environment and the LLM. 
+
+*   **API Discovery**: Extracts *actual* signatures from your installed libraries.
+*   **Semantic Retrieval**: Provides the LLM with the exact **Intent** of your code units, indexed locally via ONNX.
+*   **Token Efficiency**: Instead of sending whole files, Agent-CodeRAG distills code into compact semantic summaries, **saving up to 80% of context window tokens**.
+
+---
+
+## 🛠 How it Works
+
+```mermaid
+graph TD
+    A[Local Python Code] --> B[AST Parser]
+    B --> C{Delta-Sync}
+    C -- Changed/New --> D[LLM Distiller]
+    C -- Unchanged --> E[Local Cache]
+    D --> F[Semantic Summary]
+    E --> F
+    F --> G[ONNX Embedder]
+    G --> H[(DuckDB VSS)]
+    H --> I[Semantic Search / JSON API]
+```
+
+### ✨ Key Features
+*   **⚡ No PyTorch**: Uses `onnxruntime` and `tokenizers` (Rust) for a tiny footprint and instant startup.
+*   **💾 DuckDB VSS**: High-performance vector similarity search stored in a single local file.
+*   **🔄 Delta-Sync**: Uses SHA-256 hashing to only re-distill changed code, saving your API budget.
+*   **🔌 Hybrid Intelligence**: Works offline using name-based embeddings; adds AI-distilled reasoning when an LLM is connected.
+
+---
+
+## 📡 API Discovery
+To help your agent understand a specific library version installed in your environment:
+```bash
+agent-coderag api pydantic
+```
+Returns the *live* public API, methods, and signatures.
+
+---
+
+## 🏃 Quick Start
+
+### 1. Install
+```bash
+pip install agent-coderag
+```
+
+### 2. Setup AI Models
+Download the lightweight `paraphrase-multilingual-MiniLM` ONNX model to your global cache:
+```bash
+agent-coderag setup
+```
+
+### 3. Configure your LLM (For Distillation)
+
+**Option A: Cloud (OpenAI)**
+```bash
+agent-coderag config --url "https://api.openai.com/v1" --model "gpt-4o-mini" --key "sk-..."
+```
+
+**Option B: Local (Ollama) - Recommended**
+```bash
+agent-coderag config --url "http://localhost:11434" --provider "ollama" --model "qwen2.5-coder:7b"
+```
+*We recommend using `qwen2.5-coder` or `llama3.2` for fast and private local distillation.*
+
+
+### 4. Index your Project
+```bash
+agent-coderag sync --all
+```
+
+### 5. Search
+*   **Human Mode (Compact)**: `agent-coderag search "how to handle errors"`
+*   **Agent Mode (JSON)**: `agent-coderag --json search "data storage" --limit 1`
+
+### 🐳 Docker (Alternative)
+```bash
+docker build -t agent-coderag .
+docker run -v ~/.cache/agent-coderag:/root/.cache/agent-coderag agent-coderag setup
+```
+
+---
+
+## 🤖 For AI Agents
+
+Agent-CodeRAG is built specifically for programmatic consumption.
+
+### Agent Strategy
+1.  **Search First**: Use `agent-coderag --json search "topic"` to find relevant code units before reading files.
+2.  **Use Intent**: The `summary` field provides technical intent, allowing you to skip reading complex implementation details.
+
+---
+
+## 🔧 Development
+
+### Running Tests
+```bash
+pytest tests/
+pytest e2e_tests/
+```
+
+### Pre-commit Hooks
+We use `pre-commit` to maintain high code standards:
+```bash
+pip install pre-commit
+pre-commit install
+```
+
+---
+
+## 📄 License
+MIT © 2026 Igor Boloban
+
+## 🙏 Acknowledgments
+This project stands on the shoulders of giants. See [THIRD_PARTY_LICENSES.md](THIRD_PARTY_LICENSES.md) for a full list of open-source libraries used in Agent-CodeRAG.

agent_coderag-1.1.0/README.md

@@ -0,0 +1,154 @@
+# Agent-CodeRAG: Semantic Intelligence for AI Coding Agents
+
+> **Fast. Local. Agent-First. Token-Efficient.**
+
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![No PyTorch](https://img.shields.io/badge/Footprint-No_PyTorch-green.svg)](#-key-technologies)
+[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
+
+---
+
+## 📖 Table of Contents
+- [🧠 The Problem: The API Knowledge Gap](#-the-problem-the-api-knowledge-gap)
+- [🚀 The Solution: Real-Time Contextual Truth](#-the-solution-real-time-contextual-truth)
+- [🛠 How it Works](#-how-it-works)
+- [📡 API Discovery](#-api-discovery)
+- [🏃 Quick Start](#-quick-start)
+- [🤖 For AI Agents](#-for-ai-agents)
+- [🔧 Development](#-development)
+- [📄 License](#-license)
+
+---
+
+## 🧠 The Problem: The API Knowledge Gap
+
+AI coding agents often hallucinate when calling library APIs because their training data is static. This leads to a **"Fail-Fix-Fail" cycle**:
+
+1.  **Broken Code**: Agents use deprecated parameters or non-existent methods from outdated versions.
+2.  **Token Waste**: You provide the error, the agent tries to fix it using more outdated data, consuming thousands of tokens in a loop.
+3.  **Environment Mismatch**: The agent knows the API for version 1.0, but your environment has 2.0.
+
+### Real-world Example (The Pydantic Gap)
+*   **Agent's Knowledge**: Knows Pydantic v1 (`model.dict()`).
+*   **Your Environment**: Uses Pydantic v2 (`model.model_dump()`).
+*   **The Result**: The agent writes `dict()`, the code fails, and it wastes **5000+ tokens** trying to "fix" a problem it doesn't understand.
+
+## 🚀 The Solution: Real-Time Contextual Truth
+
+Agent-CodeRAG acts as a lightweight semantic bridge between your local environment and the LLM. 
+
+*   **API Discovery**: Extracts *actual* signatures from your installed libraries.
+*   **Semantic Retrieval**: Provides the LLM with the exact **Intent** of your code units, indexed locally via ONNX.
+*   **Token Efficiency**: Instead of sending whole files, Agent-CodeRAG distills code into compact semantic summaries, **saving up to 80% of context window tokens**.
+
+---
+
+## 🛠 How it Works
+
+```mermaid
+graph TD
+    A[Local Python Code] --> B[AST Parser]
+    B --> C{Delta-Sync}
+    C -- Changed/New --> D[LLM Distiller]
+    C -- Unchanged --> E[Local Cache]
+    D --> F[Semantic Summary]
+    E --> F
+    F --> G[ONNX Embedder]
+    G --> H[(DuckDB VSS)]
+    H --> I[Semantic Search / JSON API]
+```
+
+### ✨ Key Features
+*   **⚡ No PyTorch**: Uses `onnxruntime` and `tokenizers` (Rust) for a tiny footprint and instant startup.
+*   **💾 DuckDB VSS**: High-performance vector similarity search stored in a single local file.
+*   **🔄 Delta-Sync**: Uses SHA-256 hashing to only re-distill changed code, saving your API budget.
+*   **🔌 Hybrid Intelligence**: Works offline using name-based embeddings; adds AI-distilled reasoning when an LLM is connected.
+
+---
+
+## 📡 API Discovery
+To help your agent understand a specific library version installed in your environment:
+```bash
+agent-coderag api pydantic
+```
+Returns the *live* public API, methods, and signatures.
+
+---
+
+## 🏃 Quick Start
+
+### 1. Install
+```bash
+pip install agent-coderag
+```
+
+### 2. Setup AI Models
+Download the lightweight `paraphrase-multilingual-MiniLM` ONNX model to your global cache:
+```bash
+agent-coderag setup
+```
+
+### 3. Configure your LLM (For Distillation)
+
+**Option A: Cloud (OpenAI)**
+```bash
+agent-coderag config --url "https://api.openai.com/v1" --model "gpt-4o-mini" --key "sk-..."
+```
+
+**Option B: Local (Ollama) - Recommended**
+```bash
+agent-coderag config --url "http://localhost:11434" --provider "ollama" --model "qwen2.5-coder:7b"
+```
+*We recommend using `qwen2.5-coder` or `llama3.2` for fast and private local distillation.*
+
+
+### 4. Index your Project
+```bash
+agent-coderag sync --all
+```
+
+### 5. Search
+*   **Human Mode (Compact)**: `agent-coderag search "how to handle errors"`
+*   **Agent Mode (JSON)**: `agent-coderag --json search "data storage" --limit 1`
+
+### 🐳 Docker (Alternative)
+```bash
+docker build -t agent-coderag .
+docker run -v ~/.cache/agent-coderag:/root/.cache/agent-coderag agent-coderag setup
+```
+
+---
+
+## 🤖 For AI Agents
+
+Agent-CodeRAG is built specifically for programmatic consumption.
+
+### Agent Strategy
+1.  **Search First**: Use `agent-coderag --json search "topic"` to find relevant code units before reading files.
+2.  **Use Intent**: The `summary` field provides technical intent, allowing you to skip reading complex implementation details.
+
+---
+
+## 🔧 Development
+
+### Running Tests
+```bash
+pytest tests/
+pytest e2e_tests/
+```
+
+### Pre-commit Hooks
+We use `pre-commit` to maintain high code standards:
+```bash
+pip install pre-commit
+pre-commit install
+```
+
+---
+
+## 📄 License
+MIT © 2026 Igor Boloban
+
+## 🙏 Acknowledgments
+This project stands on the shoulders of giants. See [THIRD_PARTY_LICENSES.md](THIRD_PARTY_LICENSES.md) for a full list of open-source libraries used in Agent-CodeRAG.

agent_coderag-1.1.0/agent_coderag.egg-info/PKG-INFO

@@ -0,0 +1,188 @@
+Metadata-Version: 2.4
+Name: agent-coderag
+Version: 1.1.0
+Summary: Lightweight semantic code search and distillation utility for AI coding agents. It solves the API knowledge gap via real-time local signature extraction and intent analysis without PyTorch. Optimized for token efficiency, it compresses codebase context into compact semantic summaries stored in a local DuckDB vector similarity index.
+Author-email: Igor Boloban <naranor@gmail.com>
+License: MIT
+Project-URL: Homepage, https://github.com/naranor/agent-coderag
+Project-URL: Repository, https://github.com/naranor/agent-coderag
+Project-URL: Issues, https://github.com/naranor/agent-coderag/issues
+Project-URL: Changelog, https://github.com/naranor/agent-coderag/blob/main/CHANGELOG.md
+Keywords: rag,ai-agents,semantic-search,code-analysis,context-compression,onnx,local-embeddings
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Text Processing :: Indexing
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: duckdb
+Requires-Dist: numpy
+Requires-Dist: litellm
+Requires-Dist: onnxruntime
+Requires-Dist: tokenizers
+Requires-Dist: pydantic
+Requires-Dist: httpx
+Requires-Dist: aiofiles
+Dynamic: license-file
+
+# Agent-CodeRAG: Semantic Intelligence for AI Coding Agents
+
+> **Fast. Local. Agent-First. Token-Efficient.**
+
+[![Python 3.10+](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![No PyTorch](https://img.shields.io/badge/Footprint-No_PyTorch-green.svg)](#-key-technologies)
+[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)
+
+---
+
+## 📖 Table of Contents
+- [🧠 The Problem: The API Knowledge Gap](#-the-problem-the-api-knowledge-gap)
+- [🚀 The Solution: Real-Time Contextual Truth](#-the-solution-real-time-contextual-truth)
+- [🛠 How it Works](#-how-it-works)
+- [📡 API Discovery](#-api-discovery)
+- [🏃 Quick Start](#-quick-start)
+- [🤖 For AI Agents](#-for-ai-agents)
+- [🔧 Development](#-development)
+- [📄 License](#-license)
+
+---
+
+## 🧠 The Problem: The API Knowledge Gap
+
+AI coding agents often hallucinate when calling library APIs because their training data is static. This leads to a **"Fail-Fix-Fail" cycle**:
+
+1.  **Broken Code**: Agents use deprecated parameters or non-existent methods from outdated versions.
+2.  **Token Waste**: You provide the error, the agent tries to fix it using more outdated data, consuming thousands of tokens in a loop.
+3.  **Environment Mismatch**: The agent knows the API for version 1.0, but your environment has 2.0.
+
+### Real-world Example (The Pydantic Gap)
+*   **Agent's Knowledge**: Knows Pydantic v1 (`model.dict()`).
+*   **Your Environment**: Uses Pydantic v2 (`model.model_dump()`).
+*   **The Result**: The agent writes `dict()`, the code fails, and it wastes **5000+ tokens** trying to "fix" a problem it doesn't understand.
+
+## 🚀 The Solution: Real-Time Contextual Truth
+
+Agent-CodeRAG acts as a lightweight semantic bridge between your local environment and the LLM. 
+
+*   **API Discovery**: Extracts *actual* signatures from your installed libraries.
+*   **Semantic Retrieval**: Provides the LLM with the exact **Intent** of your code units, indexed locally via ONNX.
+*   **Token Efficiency**: Instead of sending whole files, Agent-CodeRAG distills code into compact semantic summaries, **saving up to 80% of context window tokens**.
+
+---
+
+## 🛠 How it Works
+
+```mermaid
+graph TD
+    A[Local Python Code] --> B[AST Parser]
+    B --> C{Delta-Sync}
+    C -- Changed/New --> D[LLM Distiller]
+    C -- Unchanged --> E[Local Cache]
+    D --> F[Semantic Summary]
+    E --> F
+    F --> G[ONNX Embedder]
+    G --> H[(DuckDB VSS)]
+    H --> I[Semantic Search / JSON API]
+```
+
+### ✨ Key Features
+*   **⚡ No PyTorch**: Uses `onnxruntime` and `tokenizers` (Rust) for a tiny footprint and instant startup.
+*   **💾 DuckDB VSS**: High-performance vector similarity search stored in a single local file.
+*   **🔄 Delta-Sync**: Uses SHA-256 hashing to only re-distill changed code, saving your API budget.
+*   **🔌 Hybrid Intelligence**: Works offline using name-based embeddings; adds AI-distilled reasoning when an LLM is connected.
+
+---
+
+## 📡 API Discovery
+To help your agent understand a specific library version installed in your environment:
+```bash
+agent-coderag api pydantic
+```
+Returns the *live* public API, methods, and signatures.
+
+---
+
+## 🏃 Quick Start
+
+### 1. Install
+```bash
+pip install agent-coderag
+```
+
+### 2. Setup AI Models
+Download the lightweight `paraphrase-multilingual-MiniLM` ONNX model to your global cache:
+```bash
+agent-coderag setup
+```
+
+### 3. Configure your LLM (For Distillation)
+
+**Option A: Cloud (OpenAI)**
+```bash
+agent-coderag config --url "https://api.openai.com/v1" --model "gpt-4o-mini" --key "sk-..."
+```
+
+**Option B: Local (Ollama) - Recommended**
+```bash
+agent-coderag config --url "http://localhost:11434" --provider "ollama" --model "qwen2.5-coder:7b"
+```
+*We recommend using `qwen2.5-coder` or `llama3.2` for fast and private local distillation.*
+
+
+### 4. Index your Project
+```bash
+agent-coderag sync --all
+```
+
+### 5. Search
+*   **Human Mode (Compact)**: `agent-coderag search "how to handle errors"`
+*   **Agent Mode (JSON)**: `agent-coderag --json search "data storage" --limit 1`
+
+### 🐳 Docker (Alternative)
+```bash
+docker build -t agent-coderag .
+docker run -v ~/.cache/agent-coderag:/root/.cache/agent-coderag agent-coderag setup
+```
+
+---
+
+## 🤖 For AI Agents
+
+Agent-CodeRAG is built specifically for programmatic consumption.
+
+### Agent Strategy
+1.  **Search First**: Use `agent-coderag --json search "topic"` to find relevant code units before reading files.
+2.  **Use Intent**: The `summary` field provides technical intent, allowing you to skip reading complex implementation details.
+
+---
+
+## 🔧 Development
+
+### Running Tests
+```bash
+pytest tests/
+pytest e2e_tests/
+```
+
+### Pre-commit Hooks
+We use `pre-commit` to maintain high code standards:
+```bash
+pip install pre-commit
+pre-commit install
+```
+
+---
+
+## 📄 License
+MIT © 2026 Igor Boloban
+
+## 🙏 Acknowledgments
+This project stands on the shoulders of giants. See [THIRD_PARTY_LICENSES.md](THIRD_PARTY_LICENSES.md) for a full list of open-source libraries used in Agent-CodeRAG.

agent_coderag-1.1.0/agent_coderag.egg-info/SOURCES.txt

@@ -0,0 +1,29 @@
+LICENSE
+NOTICE
+README.md
+pyproject.toml
+agent_coderag.egg-info/PKG-INFO
+agent_coderag.egg-info/SOURCES.txt
+agent_coderag.egg-info/dependency_links.txt
+agent_coderag.egg-info/entry_points.txt
+agent_coderag.egg-info/requires.txt
+agent_coderag.egg-info/top_level.txt
+code_rag/__init__.py
+code_rag/core/__init__.py
+code_rag/core/interfaces.py
+code_rag/core/manager.py
+code_rag/core/models.py
+code_rag/discovery/__init__.py
+code_rag/discovery/dependency.py
+code_rag/entry/__init__.py
+code_rag/entry/cli.py
+code_rag/intelligence/__init__.py
+code_rag/intelligence/distiller.py
+code_rag/intelligence/embedder.py
+code_rag/parsers/__init__.py
+code_rag/parsers/ast_index.py
+code_rag/storage/__init__.py
+code_rag/storage/duckdb_impl.py
+tests/test_ast_parser.py
+tests/test_code_rag_simple.py
+tests/test_dependency_discovery.py

agent_coderag-1.1.0/agent_coderag.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

agent_coderag-1.1.0/agent_coderag.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+agent-coderag = code_rag.entry.cli:main

agent_coderag-1.1.0/agent_coderag.egg-info/requires.txt

@@ -0,0 +1,8 @@
+duckdb
+numpy
+litellm
+onnxruntime
+tokenizers
+pydantic
+httpx
+aiofiles

agent_coderag-1.1.0/agent_coderag.egg-info/top_level.txt

@@ -0,0 +1 @@
+code_rag

agent_coderag-1.1.0/code_rag/core/interfaces.py

@@ -0,0 +1,29 @@
+from abc import ABC, abstractmethod
+from typing import List, Optional
+from .models import KnowledgeUnit
+
+class IParser(ABC):
+    """Interface for extracting structure from code."""
+    @abstractmethod
+    async def distill_file(self, file_path: str) -> List[KnowledgeUnit]:
+        pass
+
+class IStorage(ABC):
+    """Interface for storing the index."""
+    @abstractmethod
+    async def upsert_unit(self, unit: KnowledgeUnit):
+        pass
+    
+    @abstractmethod
+    async def get_unit(self, unit_id: str) -> Optional[KnowledgeUnit]:
+        pass
+    
+    @abstractmethod
+    async def search_units(self, query: str, limit: int = 5) -> List[KnowledgeUnit]:
+        pass
+
+class IIntelligence(ABC):
+    """Interface for LLM-based analysis (distillation, embeddings)."""
+    @abstractmethod
+    async def summarize(self, code: str, unit_name: str) -> str:
+        pass