codegraph-cli 2.1.0__tar.gz → 2.1.1__tar.gz

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codegraph-cli
-Version: 2.1.0
+Version: 2.1.1
 Summary: AI-powered code intelligence CLI with multi-agent analysis, impact graphs, and conversational coding.
 Author-email: Ali Nasir <muhammadalinasir00786@gmail.com>
 License: MIT
@@ -59,7 +59,7 @@ Dynamic: license-file
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
 [![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://www.python.org)
-[![Version](https://img.shields.io/badge/version-2.0.0-blue.svg)](https://github.com/al1-nasir/codegraph-cli)
+[![Version](https://img.shields.io/badge/version-2.1.0-blue.svg)](https://github.com/al1-nasir/codegraph-cli)
 
 ---
 
@@ -84,12 +84,24 @@ Core capabilities:
 pip install codegraph-cli
 ```
 
+With neural embedding models (semantic code search):
+
+```bash
+pip install codegraph-cli[embeddings]
+```
+
 With CrewAI multi-agent support:
 
 ```bash
 pip install codegraph-cli[crew]
 ```
 
+Everything:
+
+```bash
+pip install codegraph-cli[all]
+```
+
 For development:
 
 ```bash
@@ -156,6 +168,34 @@ cg unset-llm       # reset to defaults
 
 ---
 
+## Embedding Models
+
+CodeGraph supports configurable embedding models for semantic code search. Choose based on your hardware and quality needs:
+
+| Model | Download | Dim | Quality | Command |
+|-------|----------|-----|---------|---------|
+| hash | 0 bytes | 256 | Keyword-only | `cg set-embedding hash` |
+| minilm | ~80 MB | 384 | Decent | `cg set-embedding minilm` |
+| bge-base | ~440 MB | 768 | Good | `cg set-embedding bge-base` |
+| jina-code | ~550 MB | 768 | Code-aware | `cg set-embedding jina-code` |
+| qodo-1.5b | ~6.2 GB | 1536 | Best | `cg set-embedding qodo-1.5b` |
+
+The default is `hash` (zero-dependency, no download). Neural models require the `[embeddings]` extra and are downloaded on first use from HuggingFace.
+
+```bash
+cg set-embedding jina-code    # switch to a neural model
+cg show-embedding             # view current model and all options
+cg unset-embedding            # reset to hash default
+```
+
+After changing the embedding model, re-index your project:
+
+```bash
+cg index /path/to/project
+```
+
+---
+
 ## Commands
 
 ### Project Management
@@ -252,8 +292,9 @@ CLI Layer (Typer)
     |       |                           |
     |       +-- Parser (tree-sitter)    +-- VectorStore (LanceDB)
     |       +-- RAGRetriever            |
-    |       +-- LLM Adapter             +-- Embeddings
-    |
+    |       +-- LLM Adapter             +-- Embeddings (configurable)
+    |                                       hash | minilm | bge-base
+    |                                       jina-code | qodo-1.5b
     +-- ChatAgent (standard mode)
     |
     +-- CrewChatAgent (--crew mode)
@@ -264,6 +305,8 @@ CLI Layer (Typer)
             +-- Code Analysis Agent ---> 3 search/analysis tools
 ```
 
+**Embeddings**: Five models available via `cg set-embedding`. Hash (default, zero-dependency) through Qodo-Embed-1-1.5B (best quality, 6 GB). Neural models use raw `transformers` + `torch` — no sentence-transformers overhead. Models are cached in `~/.codegraph/models/`.
+
 **Parser**: tree-sitter grammars for Python, JavaScript, and TypeScript. Extracts modules, classes, functions, imports, and call relationships into a directed graph.
 
 **Storage**: SQLite for the code graph (nodes + edges), LanceDB for vector embeddings. All data stored under `~/.codegraph/`.
@@ -278,14 +321,14 @@ CLI Layer (Typer)
 codegraph_cli/
     cli.py               # main Typer application, all top-level commands
     cli_chat.py           # interactive chat REPL with styled output
-    cli_setup.py          # setup wizard, set-llm, unset-llm, show-llm
+    cli_setup.py          # setup wizard, set-llm, unset-llm, set-embedding
     cli_v2.py             # v2 code generation commands
     config.py             # loads config from TOML
-    config_manager.py     # TOML read/write, provider validation
+    config_manager.py     # TOML read/write, provider and embedding config
     llm.py                # multi-provider LLM adapter
     parser.py             # tree-sitter AST parsing
     storage.py            # SQLite graph store
-    embeddings.py         # hash-based embedding model
+    embeddings.py         # configurable embedding engine (5 models)
     rag.py                # RAG retriever
     vector_store.py       # LanceDB vector store
     orchestrator.py       # coordinates parsing, search, impact
@@ -310,7 +353,7 @@ codegraph_cli/
 git clone https://github.com/al1-nasir/codegraph-cli.git
 cd codegraph-cli
 python -m venv .venv && source .venv/bin/activate
-pip install -e ".[dev,crew]"
+pip install -e ".[dev,crew,embeddings]"
 pytest
 ```
 

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/README.md

@@ -4,7 +4,7 @@
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
 [![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://www.python.org)
-[![Version](https://img.shields.io/badge/version-2.0.0-blue.svg)](https://github.com/al1-nasir/codegraph-cli)
+[![Version](https://img.shields.io/badge/version-2.1.0-blue.svg)](https://github.com/al1-nasir/codegraph-cli)
 
 ---
 
@@ -29,12 +29,24 @@ Core capabilities:
 pip install codegraph-cli
 ```
 
+With neural embedding models (semantic code search):
+
+```bash
+pip install codegraph-cli[embeddings]
+```
+
 With CrewAI multi-agent support:
 
 ```bash
 pip install codegraph-cli[crew]
 ```
 
+Everything:
+
+```bash
+pip install codegraph-cli[all]
+```
+
 For development:
 
 ```bash
@@ -101,6 +113,34 @@ cg unset-llm       # reset to defaults
 
 ---
 
+## Embedding Models
+
+CodeGraph supports configurable embedding models for semantic code search. Choose based on your hardware and quality needs:
+
+| Model | Download | Dim | Quality | Command |
+|-------|----------|-----|---------|---------|
+| hash | 0 bytes | 256 | Keyword-only | `cg set-embedding hash` |
+| minilm | ~80 MB | 384 | Decent | `cg set-embedding minilm` |
+| bge-base | ~440 MB | 768 | Good | `cg set-embedding bge-base` |
+| jina-code | ~550 MB | 768 | Code-aware | `cg set-embedding jina-code` |
+| qodo-1.5b | ~6.2 GB | 1536 | Best | `cg set-embedding qodo-1.5b` |
+
+The default is `hash` (zero-dependency, no download). Neural models require the `[embeddings]` extra and are downloaded on first use from HuggingFace.
+
+```bash
+cg set-embedding jina-code    # switch to a neural model
+cg show-embedding             # view current model and all options
+cg unset-embedding            # reset to hash default
+```
+
+After changing the embedding model, re-index your project:
+
+```bash
+cg index /path/to/project
+```
+
+---
+
 ## Commands
 
 ### Project Management
@@ -197,8 +237,9 @@ CLI Layer (Typer)
     |       |                           |
     |       +-- Parser (tree-sitter)    +-- VectorStore (LanceDB)
     |       +-- RAGRetriever            |
-    |       +-- LLM Adapter             +-- Embeddings
-    |
+    |       +-- LLM Adapter             +-- Embeddings (configurable)
+    |                                       hash | minilm | bge-base
+    |                                       jina-code | qodo-1.5b
     +-- ChatAgent (standard mode)
     |
     +-- CrewChatAgent (--crew mode)
@@ -209,6 +250,8 @@ CLI Layer (Typer)
             +-- Code Analysis Agent ---> 3 search/analysis tools
 ```
 
+**Embeddings**: Five models available via `cg set-embedding`. Hash (default, zero-dependency) through Qodo-Embed-1-1.5B (best quality, 6 GB). Neural models use raw `transformers` + `torch` — no sentence-transformers overhead. Models are cached in `~/.codegraph/models/`.
+
 **Parser**: tree-sitter grammars for Python, JavaScript, and TypeScript. Extracts modules, classes, functions, imports, and call relationships into a directed graph.
 
 **Storage**: SQLite for the code graph (nodes + edges), LanceDB for vector embeddings. All data stored under `~/.codegraph/`.
@@ -223,14 +266,14 @@ CLI Layer (Typer)
 codegraph_cli/
     cli.py               # main Typer application, all top-level commands
     cli_chat.py           # interactive chat REPL with styled output
-    cli_setup.py          # setup wizard, set-llm, unset-llm, show-llm
+    cli_setup.py          # setup wizard, set-llm, unset-llm, set-embedding
     cli_v2.py             # v2 code generation commands
     config.py             # loads config from TOML
-    config_manager.py     # TOML read/write, provider validation
+    config_manager.py     # TOML read/write, provider and embedding config
     llm.py                # multi-provider LLM adapter
     parser.py             # tree-sitter AST parsing
     storage.py            # SQLite graph store
-    embeddings.py         # hash-based embedding model
+    embeddings.py         # configurable embedding engine (5 models)
     rag.py                # RAG retriever
     vector_store.py       # LanceDB vector store
     orchestrator.py       # coordinates parsing, search, impact
@@ -255,7 +298,7 @@ codegraph_cli/
 git clone https://github.com/al1-nasir/codegraph-cli.git
 cd codegraph-cli
 python -m venv .venv && source .venv/bin/activate
-pip install -e ".[dev,crew]"
+pip install -e ".[dev,crew,embeddings]"
 pytest
 ```
 

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/codegraph_cli/cli_chat.py

@@ -13,7 +13,6 @@ import typer
 from . import config
 from .chat_agent import ChatAgent
 from .chat_session import SessionManager
-from .crew_chat import CrewChatAgent
 from .llm import LocalLLM
 from .orchestrator import MCPOrchestrator
 from .rag import RAGRetriever
@@ -299,7 +298,13 @@ def start_chat(
     rag_retriever = RAGRetriever(context.store, embedding_model)
     
     if use_crew:
-        print(f"\n  {C_MAGENTA}🤖 Initializing CrewAI multi-agent system...{C_RESET}")
+        try:
+            from .crew_chat import CrewChatAgent
+        except ImportError:
+            print(f"\n  {C_RED}CrewAI is not installed.{C_RESET}")
+            print(f"  {C_DIM}Install with: pip install codegraph-cli[crew]{C_RESET}\n")
+            raise typer.Exit(1)
+        print(f"\n  {C_MAGENTA}Initializing CrewAI multi-agent system...{C_RESET}")
         agent = CrewChatAgent(context, llm, rag_retriever)
     else:
         orchestrator = MCPOrchestrator(

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/codegraph_cli/crew_agents.py

@@ -4,7 +4,12 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, List
 
-from crewai import Agent
+try:
+    from crewai import Agent
+    CREWAI_AVAILABLE = True
+except ImportError:
+    Agent = None  # type: ignore
+    CREWAI_AVAILABLE = False
 
 if TYPE_CHECKING:
     from .crew_tools import create_tools

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/codegraph_cli/crew_chat.py

@@ -8,7 +8,11 @@ from typing import TYPE_CHECKING, Dict, List
 
 from datetime import datetime
 
-from crewai import Agent, Crew, Task
+try:
+    from crewai import Agent, Crew, Task
+    CREWAI_AVAILABLE = True
+except ImportError:
+    CREWAI_AVAILABLE = False
 
 from .crew_agents import (
     create_code_analysis_agent,

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/codegraph_cli/crew_tools.py

@@ -9,7 +9,15 @@ from datetime import datetime
 from pathlib import Path
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Type
 
-from crewai.tools import BaseTool
+try:
+    from crewai.tools import BaseTool
+    CREWAI_AVAILABLE = True
+except ImportError:
+    # Provide a dummy base class so the module can still be imported
+    class BaseTool:  # type: ignore
+        def __init_subclass__(cls, **kwargs): pass
+        def __init__(self, **kwargs): pass
+    CREWAI_AVAILABLE = False
 from pydantic import BaseModel, Field, PrivateAttr
 
 if TYPE_CHECKING:

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/codegraph_cli.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: codegraph-cli
-Version: 2.1.0
+Version: 2.1.1
 Summary: AI-powered code intelligence CLI with multi-agent analysis, impact graphs, and conversational coding.
 Author-email: Ali Nasir <muhammadalinasir00786@gmail.com>
 License: MIT
@@ -59,7 +59,7 @@ Dynamic: license-file
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)
 [![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-blue.svg)](https://www.python.org)
-[![Version](https://img.shields.io/badge/version-2.0.0-blue.svg)](https://github.com/al1-nasir/codegraph-cli)
+[![Version](https://img.shields.io/badge/version-2.1.0-blue.svg)](https://github.com/al1-nasir/codegraph-cli)
 
 ---
 
@@ -84,12 +84,24 @@ Core capabilities:
 pip install codegraph-cli
 ```
 
+With neural embedding models (semantic code search):
+
+```bash
+pip install codegraph-cli[embeddings]
+```
+
 With CrewAI multi-agent support:
 
 ```bash
 pip install codegraph-cli[crew]
 ```
 
+Everything:
+
+```bash
+pip install codegraph-cli[all]
+```
+
 For development:
 
 ```bash
@@ -156,6 +168,34 @@ cg unset-llm       # reset to defaults
 
 ---
 
+## Embedding Models
+
+CodeGraph supports configurable embedding models for semantic code search. Choose based on your hardware and quality needs:
+
+| Model | Download | Dim | Quality | Command |
+|-------|----------|-----|---------|---------|
+| hash | 0 bytes | 256 | Keyword-only | `cg set-embedding hash` |
+| minilm | ~80 MB | 384 | Decent | `cg set-embedding minilm` |
+| bge-base | ~440 MB | 768 | Good | `cg set-embedding bge-base` |
+| jina-code | ~550 MB | 768 | Code-aware | `cg set-embedding jina-code` |
+| qodo-1.5b | ~6.2 GB | 1536 | Best | `cg set-embedding qodo-1.5b` |
+
+The default is `hash` (zero-dependency, no download). Neural models require the `[embeddings]` extra and are downloaded on first use from HuggingFace.
+
+```bash
+cg set-embedding jina-code    # switch to a neural model
+cg show-embedding             # view current model and all options
+cg unset-embedding            # reset to hash default
+```
+
+After changing the embedding model, re-index your project:
+
+```bash
+cg index /path/to/project
+```
+
+---
+
 ## Commands
 
 ### Project Management
@@ -252,8 +292,9 @@ CLI Layer (Typer)
     |       |                           |
     |       +-- Parser (tree-sitter)    +-- VectorStore (LanceDB)
     |       +-- RAGRetriever            |
-    |       +-- LLM Adapter             +-- Embeddings
-    |
+    |       +-- LLM Adapter             +-- Embeddings (configurable)
+    |                                       hash | minilm | bge-base
+    |                                       jina-code | qodo-1.5b
     +-- ChatAgent (standard mode)
     |
     +-- CrewChatAgent (--crew mode)
@@ -264,6 +305,8 @@ CLI Layer (Typer)
             +-- Code Analysis Agent ---> 3 search/analysis tools
 ```
 
+**Embeddings**: Five models available via `cg set-embedding`. Hash (default, zero-dependency) through Qodo-Embed-1-1.5B (best quality, 6 GB). Neural models use raw `transformers` + `torch` — no sentence-transformers overhead. Models are cached in `~/.codegraph/models/`.
+
 **Parser**: tree-sitter grammars for Python, JavaScript, and TypeScript. Extracts modules, classes, functions, imports, and call relationships into a directed graph.
 
 **Storage**: SQLite for the code graph (nodes + edges), LanceDB for vector embeddings. All data stored under `~/.codegraph/`.
@@ -278,14 +321,14 @@ CLI Layer (Typer)
 codegraph_cli/
     cli.py               # main Typer application, all top-level commands
     cli_chat.py           # interactive chat REPL with styled output
-    cli_setup.py          # setup wizard, set-llm, unset-llm, show-llm
+    cli_setup.py          # setup wizard, set-llm, unset-llm, set-embedding
     cli_v2.py             # v2 code generation commands
     config.py             # loads config from TOML
-    config_manager.py     # TOML read/write, provider validation
+    config_manager.py     # TOML read/write, provider and embedding config
     llm.py                # multi-provider LLM adapter
     parser.py             # tree-sitter AST parsing
     storage.py            # SQLite graph store
-    embeddings.py         # hash-based embedding model
+    embeddings.py         # configurable embedding engine (5 models)
     rag.py                # RAG retriever
     vector_store.py       # LanceDB vector store
     orchestrator.py       # coordinates parsing, search, impact
@@ -310,7 +353,7 @@ codegraph_cli/
 git clone https://github.com/al1-nasir/codegraph-cli.git
 cd codegraph-cli
 python -m venv .venv && source .venv/bin/activate
-pip install -e ".[dev,crew]"
+pip install -e ".[dev,crew,embeddings]"
 pytest
 ```
 

{codegraph_cli-2.1.0 → codegraph_cli-2.1.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "codegraph-cli"
-version = "2.1.0"
+version = "2.1.1"
 description = "AI-powered code intelligence CLI with multi-agent analysis, impact graphs, and conversational coding."
 readme = "README.md"
 license = {text = "MIT"}