cocoindex-code 0.1.13__tar.gz → 0.2.0__tar.gz

{cocoindex_code-0.1.13 → cocoindex_code-0.2.0}/.gitignore

@@ -41,5 +41,8 @@ htmlcov/
 .pytest_cache/
 .mypy_cache/
 
-# CocoIndex
-.cocoindex_code/
+# Generated version file
+src/cocoindex_code/_version.py
+
+# CocoIndex Code (ccc)
+/.cocoindex_code/

{cocoindex_code-0.1.13 → cocoindex_code-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cocoindex-code
-Version: 0.1.13
+Version: 0.2.0
 Summary: MCP server for indexing and querying codebases using CocoIndex
 Project-URL: Homepage, https://github.com/cocoindex-io/cocoindex-code
 Project-URL: Repository, https://github.com/cocoindex-io/cocoindex-code
@@ -17,13 +17,17 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.11
-Requires-Dist: cocoindex[litellm]==1.0.0a28
+Requires-Dist: cocoindex[litellm]==1.0.0a32
 Requires-Dist: einops>=0.8.2
 Requires-Dist: mcp>=1.0.0
+Requires-Dist: msgspec>=0.19.0
 Requires-Dist: numpy>=1.24.0
+Requires-Dist: pathspec>=0.12.1
 Requires-Dist: pydantic>=2.0.0
+Requires-Dist: pyyaml>=6.0
 Requires-Dist: sentence-transformers>=2.2.0
 Requires-Dist: sqlite-vec>=0.1.0
+Requires-Dist: typer>=0.9.0
 Provides-Extra: dev
 Requires-Dist: mypy>=1.0.0; extra == 'dev'
 Requires-Dist: prek>=0.1.0; extra == 'dev'
@@ -163,8 +167,8 @@ Use the cocoindex-code MCP server for semantic code search when:
 |----------|-------------|---------|
 | `COCOINDEX_CODE_ROOT_PATH` | Root path of the codebase | Auto-discovered (see below) |
 | `COCOINDEX_CODE_EMBEDDING_MODEL` | Embedding model (see below) | `sbert/sentence-transformers/all-MiniLM-L6-v2` |
-| `COCOINDEX_CODE_BATCH_SIZE` | Max batch size for local embedding model | `16` |
 | `COCOINDEX_CODE_EXTRA_EXTENSIONS` | Additional file extensions to index (comma-separated, e.g. `"inc:php,yaml,toml"` — use `ext:lang` to override language detection) | _(none)_ |
+| `COCOINDEX_CODE_EXCLUDED_PATTERNS` | Additional glob patterns to exclude from indexing as a JSON array (e.g. `'["**/migration.sql", "{**/*.md,**/*.txt}"]'`) | _(none)_ |
 
 
 ### Root Path Discovery
@@ -297,14 +301,24 @@ claude mcp add cocoindex-code \
 
 Any model supported by LiteLLM works — see the [full list of embedding providers](https://docs.litellm.ai/docs/embedding/supported_embedding).
 
-### GPU-optimised local model
+### Local SentenceTransformers models
 
-If you have a GPU, [`nomic-ai/CodeRankEmbed`](https://huggingface.co/nomic-ai/CodeRankEmbed) delivers significantly better code retrieval than the default model. It is 137M parameters, requires ~1 GB VRAM, and has an 8192-token context window.
+Use the `sbert/` prefix to load any [SentenceTransformers](https://www.sbert.net/) model locally (no API key required).
+
+**Example — general purpose text model:**
+```bash
+claude mcp add cocoindex-code \
+  -e COCOINDEX_CODE_EMBEDDING_MODEL=sbert/nomic-ai/nomic-embed-text-v1 \
+  -- cocoindex-code
+```
+
+**GPU-optimised code retrieval:**
+
+[`nomic-ai/CodeRankEmbed`](https://huggingface.co/nomic-ai/CodeRankEmbed) delivers significantly better code retrieval than the default model. It is 137M parameters, requires ~1 GB VRAM, and has an 8192-token context window.
 
 ```bash
 claude mcp add cocoindex-code \
   -e COCOINDEX_CODE_EMBEDDING_MODEL=sbert/nomic-ai/CodeRankEmbed \
-  -e COCOINDEX_CODE_BATCH_SIZE=16 \
   -- cocoindex-code
 ```
 
@@ -355,6 +369,7 @@ Returns matching code chunks with:
 | javascript | js | `.js` |
 | json | | `.json` |
 | kotlin | | `.kt`, `.kts` |
+| lua | | `.lua` |
 | markdown | md | `.md`, `.mdx` |
 | pascal | pas, dpr, delphi | `.pas`, `.dpr` |
 | php | | `.php` |

{cocoindex_code-0.1.13 → cocoindex_code-0.2.0}/README.md

@@ -128,8 +128,8 @@ Use the cocoindex-code MCP server for semantic code search when:
 |----------|-------------|---------|
 | `COCOINDEX_CODE_ROOT_PATH` | Root path of the codebase | Auto-discovered (see below) |
 | `COCOINDEX_CODE_EMBEDDING_MODEL` | Embedding model (see below) | `sbert/sentence-transformers/all-MiniLM-L6-v2` |
-| `COCOINDEX_CODE_BATCH_SIZE` | Max batch size for local embedding model | `16` |
 | `COCOINDEX_CODE_EXTRA_EXTENSIONS` | Additional file extensions to index (comma-separated, e.g. `"inc:php,yaml,toml"` — use `ext:lang` to override language detection) | _(none)_ |
+| `COCOINDEX_CODE_EXCLUDED_PATTERNS` | Additional glob patterns to exclude from indexing as a JSON array (e.g. `'["**/migration.sql", "{**/*.md,**/*.txt}"]'`) | _(none)_ |
 
 
 ### Root Path Discovery
@@ -262,14 +262,24 @@ claude mcp add cocoindex-code \
 
 Any model supported by LiteLLM works — see the [full list of embedding providers](https://docs.litellm.ai/docs/embedding/supported_embedding).
 
-### GPU-optimised local model
+### Local SentenceTransformers models
 
-If you have a GPU, [`nomic-ai/CodeRankEmbed`](https://huggingface.co/nomic-ai/CodeRankEmbed) delivers significantly better code retrieval than the default model. It is 137M parameters, requires ~1 GB VRAM, and has an 8192-token context window.
+Use the `sbert/` prefix to load any [SentenceTransformers](https://www.sbert.net/) model locally (no API key required).
+
+**Example — general purpose text model:**
+```bash
+claude mcp add cocoindex-code \
+  -e COCOINDEX_CODE_EMBEDDING_MODEL=sbert/nomic-ai/nomic-embed-text-v1 \
+  -- cocoindex-code
+```
+
+**GPU-optimised code retrieval:**
+
+[`nomic-ai/CodeRankEmbed`](https://huggingface.co/nomic-ai/CodeRankEmbed) delivers significantly better code retrieval than the default model. It is 137M parameters, requires ~1 GB VRAM, and has an 8192-token context window.
 
 ```bash
 claude mcp add cocoindex-code \
   -e COCOINDEX_CODE_EMBEDDING_MODEL=sbert/nomic-ai/CodeRankEmbed \
-  -e COCOINDEX_CODE_BATCH_SIZE=16 \
   -- cocoindex-code
 ```
 
@@ -320,6 +330,7 @@ Returns matching code chunks with:
 | javascript | js | `.js` |
 | json | | `.json` |
 | kotlin | | `.kt`, `.kts` |
+| lua | | `.lua` |
 | markdown | md | `.md`, `.mdx` |
 | pascal | pas, dpr, delphi | `.pas`, `.dpr` |
 | php | | `.php` |

{cocoindex_code-0.1.13 → cocoindex_code-0.2.0}/pyproject.toml

@@ -23,12 +23,16 @@ classifiers = [
 
 dependencies = [
     "mcp>=1.0.0",
-    "cocoindex[litellm]==1.0.0a28",
+    "cocoindex[litellm]==1.0.0a32",
     "sentence-transformers>=2.2.0",
     "sqlite-vec>=0.1.0",
     "pydantic>=2.0.0",
     "numpy>=1.24.0",
     "einops>=0.8.2",
+    "typer>=0.9.0",
+    "msgspec>=0.19.0",
+    "pathspec>=0.12.1",
+    "pyyaml>=6.0",
 ]
 
 [project.optional-dependencies]
@@ -43,6 +47,7 @@ dev = [
 
 [project.scripts]
 cocoindex-code = "cocoindex_code:main"
+ccc = "cocoindex_code.cli:app"
 
 [project.urls]
 Homepage = "https://github.com/cocoindex-io/cocoindex-code"
@@ -51,6 +56,10 @@ Issues = "https://github.com/cocoindex-io/cocoindex-code/issues"
 
 [tool.hatch.version]
 source = "vcs"
+fallback-version = "999.0.0"
+
+[tool.hatch.build.hooks.vcs]
+version-file = "src/cocoindex_code/_version.py"
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/cocoindex_code"]
@@ -66,6 +75,7 @@ dev = [
     "ruff>=0.1.0",
     "mypy>=1.0.0",
     "prek>=0.1.0",
+    "types-pyyaml>=6.0.12.20250915",
 ]
 
 [tool.uv]

cocoindex_code-0.2.0/src/cocoindex_code/__init__.py

@@ -0,0 +1,10 @@
+"""CocoIndex Code - MCP server for indexing and querying codebases."""
+
+import logging
+
+logging.basicConfig(level=logging.WARNING)
+
+from ._version import __version__  # noqa: E402
+from .server import main  # noqa: E402
+
+__all__ = ["main", "__version__"]

cocoindex_code-0.2.0/src/cocoindex_code/_version.py

@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '0.2.0'
+__version_tuple__ = version_tuple = (0, 2, 0)
+
+__commit_id__ = commit_id = None