code-graph-rag 0.1.90__tar.gz → 0.2.0__tar.gz

{code_graph_rag-0.1.90/code_graph_rag.egg-info → code_graph_rag-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-graph-rag
-Version: 0.1.90
+Version: 0.2.0
 Summary: The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
 License-Expression: MIT
 Keywords: rag,retrieval-augmented-generation,knowledge-graph,code-analysis,tree-sitter,mcp,mcp-server,llm,graph-database,semantic-search,codebase,memgraph,developer-tools,monorepo
@@ -22,7 +22,6 @@ Requires-Dist: loguru>=0.7.3
 Requires-Dist: mcp<2,>=1.28.1
 Requires-Dist: pydantic-ai-slim[anthropic,google,openai]>=2.0.0
 Requires-Dist: pydantic-settings>=2.12.0
-Requires-Dist: pymgclient>=1.6.0
 Requires-Dist: python-dotenv>=1.2.1
 Requires-Dist: tiktoken>=0.12.0
 Requires-Dist: tomli-w>=1.2.0
@@ -39,6 +38,8 @@ Requires-Dist: defusedxml>=0.7.1
 Requires-Dist: huggingface-hub[hf-xet]>=1.7.2
 Requires-Dist: pathspec>=1.0.4
 Requires-Dist: pygments>=2.20.0
+Requires-Dist: regex>=2024.11.6
+Requires-Dist: cgr-graph-rs<0.2,>=0.1.0; platform_python_implementation == "CPython" and ((sys_platform == "linux" and (platform_machine == "x86_64" or platform_machine == "aarch64")) or sys_platform == "darwin" or (sys_platform == "win32" and platform_machine == "AMD64"))
 Provides-Extra: test
 Requires-Dist: jedi>=0.19; extra == "test"
 Requires-Dist: pytest>=8.4.1; extra == "test"
@@ -50,8 +51,12 @@ Requires-Dist: libclang>=18.1.1; extra == "test"
 Requires-Dist: filelock>=3.12; extra == "test"
 Requires-Dist: ast-grep-py>=0.44.0; extra == "test"
 Requires-Dist: pyyaml>=6.0; extra == "test"
+Requires-Dist: pymgclient>=1.6.0; extra == "test"
+Requires-Dist: sqlite-vec>=0.1.9; extra == "test"
 Provides-Extra: cpp
 Requires-Dist: libclang>=18.1.1; extra == "cpp"
+Provides-Extra: memgraph
+Requires-Dist: pymgclient>=1.6.0; extra == "memgraph"
 Provides-Extra: neo4j
 Requires-Dist: neo4j>=5.28.1; extra == "neo4j"
 Provides-Extra: treesitter-full
@@ -77,6 +82,8 @@ Requires-Dist: torch>=2.6.0; extra == "semantic"
 Requires-Dist: transformers>=5.0.0; extra == "semantic"
 Provides-Extra: milvus
 Requires-Dist: pymilvus[milvus-lite]>=3.0.0; extra == "milvus"
+Provides-Extra: sqlite-vec
+Requires-Dist: sqlite-vec>=0.1.9; extra == "sqlite-vec"
 Provides-Extra: ast-grep
 Requires-Dist: ast-grep-py>=0.44.0; extra == "ast-grep"
 Requires-Dist: pyyaml>=6.0; extra == "ast-grep"
@@ -131,7 +138,9 @@ pip install 'code-graph-rag[semantic]'
 Qdrant is the default vector store for semantic search. To use Milvus Lite,
 install `code-graph-rag[semantic,milvus]`, then set
 `CGR_VECTOR_STORE_BACKEND=milvus` and `MILVUS_URI=./.milvus_code_embeddings.db`
-before indexing.
+before indexing. To keep the vectors in a SQLite file beside the embedded graph
+(`~/.cgr/vectors.sqlite`, no server), install `code-graph-rag[semantic,sqlite-vec]`
+and set `CGR_VECTOR_STORE_BACKEND=sqlite`.
 
 To compute embeddings on an OpenAI-compatible endpoint (OpenAI, Ollama, vLLM)
 instead of locally, set `CGR_EMBEDDING_PROVIDER=openai` with

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/PYPI_README.md

@@ -45,7 +45,9 @@ pip install 'code-graph-rag[semantic]'
 Qdrant is the default vector store for semantic search. To use Milvus Lite,
 install `code-graph-rag[semantic,milvus]`, then set
 `CGR_VECTOR_STORE_BACKEND=milvus` and `MILVUS_URI=./.milvus_code_embeddings.db`
-before indexing.
+before indexing. To keep the vectors in a SQLite file beside the embedded graph
+(`~/.cgr/vectors.sqlite`, no server), install `code-graph-rag[semantic,sqlite-vec]`
+and set `CGR_VECTOR_STORE_BACKEND=sqlite`.
 
 To compute embeddings on an OpenAI-compatible endpoint (OpenAI, Ollama, vLLM)
 instead of locally, set `CGR_EMBEDDING_PROVIDER=openai` with

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/README.md

@@ -137,7 +137,7 @@ uv tool install "code-graph-rag[treesitter-full,ast-grep,semantic] @ git+https:/
 
 To upgrade an existing install, run `uv tool upgrade code-graph-rag` (with pipx, `pipx upgrade code-graph-rag`, or `pipx reinstall code-graph-rag` for a git install). [Upgrade](docs/getting-started/installation.md#upgrade) covers the other install methods.
 
-You also need Python 3.12+, Docker (for Memgraph), `cmake`, and `ripgrep`. Full prerequisites, source installs, and environment setup are in the [Installation](docs/getting-started/installation.md) guide.
+You also need Python 3.12+ and `ripgrep`. The graph lives in an embedded SQLite file by default, so there is no database server to run: no Docker and no `cmake`. Memgraph and Neo4j remain available as opt-in backends ([Graph Backends](docs/architecture/embedded-graph.md)). Full prerequisites, source installs, and environment setup are in the [Installation](docs/getting-started/installation.md) guide.
 
 > [!NOTE]
 > The wheel is pure Python (`py3-none-any`), so it installs on any platform with Python 3.12 or newer. Older system interpreters (Debian Bookworm ships 3.11) need the interpreter pinned explicitly; see [Installation](docs/getting-started/installation.md#older-system-interpreters) for the commands.
@@ -145,14 +145,16 @@ You also need Python 3.12+, Docker (for Memgraph), `cmake`, and `ripgrep`. Full
 ## Quick Start
 
 ```bash
-# Start the packaged Memgraph + Qdrant stack (no compose file needed)
-cgr daemon up
-
 # Parse a repository into the graph, then query it
 cgr start --repo-path /path/to/repo --update-graph
 cgr start --repo-path /path/to/repo
 ```
 
+The graph is written to `~/.cgr/graph.sqlite` (set `SQLITE_GRAPH_PATH` to move it).
+To use Memgraph instead, install the driver with the `memgraph` extra, set
+`GRAPH_BACKEND=memgraph`, and start the packaged Memgraph + Qdrant stack with
+`cgr daemon up`.
+
 Repeat the first command for each repository you want indexed; the graph is
 shared, and syncing one project leaves the others alone. To start over from an
 empty graph, add `--clean` — it deletes **every** project in the shared graph,

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0/code_graph_rag.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: code-graph-rag
-Version: 0.1.90
+Version: 0.2.0
 Summary: The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
 License-Expression: MIT
 Keywords: rag,retrieval-augmented-generation,knowledge-graph,code-analysis,tree-sitter,mcp,mcp-server,llm,graph-database,semantic-search,codebase,memgraph,developer-tools,monorepo
@@ -22,7 +22,6 @@ Requires-Dist: loguru>=0.7.3
 Requires-Dist: mcp<2,>=1.28.1
 Requires-Dist: pydantic-ai-slim[anthropic,google,openai]>=2.0.0
 Requires-Dist: pydantic-settings>=2.12.0
-Requires-Dist: pymgclient>=1.6.0
 Requires-Dist: python-dotenv>=1.2.1
 Requires-Dist: tiktoken>=0.12.0
 Requires-Dist: tomli-w>=1.2.0
@@ -39,6 +38,8 @@ Requires-Dist: defusedxml>=0.7.1
 Requires-Dist: huggingface-hub[hf-xet]>=1.7.2
 Requires-Dist: pathspec>=1.0.4
 Requires-Dist: pygments>=2.20.0
+Requires-Dist: regex>=2024.11.6
+Requires-Dist: cgr-graph-rs<0.2,>=0.1.0; platform_python_implementation == "CPython" and ((sys_platform == "linux" and (platform_machine == "x86_64" or platform_machine == "aarch64")) or sys_platform == "darwin" or (sys_platform == "win32" and platform_machine == "AMD64"))
 Provides-Extra: test
 Requires-Dist: jedi>=0.19; extra == "test"
 Requires-Dist: pytest>=8.4.1; extra == "test"
@@ -50,8 +51,12 @@ Requires-Dist: libclang>=18.1.1; extra == "test"
 Requires-Dist: filelock>=3.12; extra == "test"
 Requires-Dist: ast-grep-py>=0.44.0; extra == "test"
 Requires-Dist: pyyaml>=6.0; extra == "test"
+Requires-Dist: pymgclient>=1.6.0; extra == "test"
+Requires-Dist: sqlite-vec>=0.1.9; extra == "test"
 Provides-Extra: cpp
 Requires-Dist: libclang>=18.1.1; extra == "cpp"
+Provides-Extra: memgraph
+Requires-Dist: pymgclient>=1.6.0; extra == "memgraph"
 Provides-Extra: neo4j
 Requires-Dist: neo4j>=5.28.1; extra == "neo4j"
 Provides-Extra: treesitter-full
@@ -77,6 +82,8 @@ Requires-Dist: torch>=2.6.0; extra == "semantic"
 Requires-Dist: transformers>=5.0.0; extra == "semantic"
 Provides-Extra: milvus
 Requires-Dist: pymilvus[milvus-lite]>=3.0.0; extra == "milvus"
+Provides-Extra: sqlite-vec
+Requires-Dist: sqlite-vec>=0.1.9; extra == "sqlite-vec"
 Provides-Extra: ast-grep
 Requires-Dist: ast-grep-py>=0.44.0; extra == "ast-grep"
 Requires-Dist: pyyaml>=6.0; extra == "ast-grep"
@@ -131,7 +138,9 @@ pip install 'code-graph-rag[semantic]'
 Qdrant is the default vector store for semantic search. To use Milvus Lite,
 install `code-graph-rag[semantic,milvus]`, then set
 `CGR_VECTOR_STORE_BACKEND=milvus` and `MILVUS_URI=./.milvus_code_embeddings.db`
-before indexing.
+before indexing. To keep the vectors in a SQLite file beside the embedded graph
+(`~/.cgr/vectors.sqlite`, no server), install `code-graph-rag[semantic,sqlite-vec]`
+and set `CGR_VECTOR_STORE_BACKEND=sqlite`.
 
 To compute embeddings on an OpenAI-compatible endpoint (OpenAI, Ollama, vLLM)
 instead of locally, set `CGR_EMBEDDING_PROVIDER=openai` with

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/code_graph_rag.egg-info/SOURCES.txt

@@ -46,6 +46,7 @@ codebase_rag/interface_skip.py
 codebase_rag/language_spec.py
 codebase_rag/logs.py
 codebase_rag/main.py
+codebase_rag/mgclient_compat.py
 codebase_rag/mgclient_probe.py
 codebase_rag/models.py
 codebase_rag/parser_fingerprint.py
@@ -58,6 +59,7 @@ codebase_rag/schema_builder.py
 codebase_rag/schema_parse.py
 codebase_rag/schemas.py
 codebase_rag/sql_names.py
+codebase_rag/sqlite_vectors.py
 codebase_rag/structural_check.py
 codebase_rag/structural_delta.py
 codebase_rag/sync_guard.py
@@ -137,6 +139,7 @@ codebase_rag/constants/core.py
 codebase_rag/constants/deadcode_roots.py
 codebase_rag/constants/deps.py
 codebase_rag/constants/duplicates.py
+codebase_rag/constants/embedded_graph.py
 codebase_rag/constants/fqn_specs.py
 codebase_rag/constants/graph.py
 codebase_rag/constants/health.py
@@ -147,6 +150,7 @@ codebase_rag/constants/mcp.py
 codebase_rag/constants/notebook.py
 codebase_rag/constants/providers.py
 codebase_rag/constants/security.py
+codebase_rag/constants/sqlite_vectors.py
 codebase_rag/constants/stdlib_types.py
 codebase_rag/constants/structural.py
 codebase_rag/constants/trace.py
@@ -162,6 +166,22 @@ codebase_rag/editing/signature_contract.py
 codebase_rag/editing/signature_spec.py
 codebase_rag/editing/sites.py
 codebase_rag/editing/transaction.py
+codebase_rag/embedded_graph/__init__.py
+codebase_rag/embedded_graph/compiler.py
+codebase_rag/embedded_graph/connection.py
+codebase_rag/embedded_graph/cypher_ast.py
+codebase_rag/embedded_graph/executor.py
+codebase_rag/embedded_graph/expressions.py
+codebase_rag/embedded_graph/extension.py
+codebase_rag/embedded_graph/functions.py
+codebase_rag/embedded_graph/lexer.py
+codebase_rag/embedded_graph/limits.py
+codebase_rag/embedded_graph/native.py
+codebase_rag/embedded_graph/parser.py
+codebase_rag/embedded_graph/procedures.py
+codebase_rag/embedded_graph/sql.py
+codebase_rag/embedded_graph/store.py
+codebase_rag/embedded_graph/types.py
 codebase_rag/mcp/__init__.py
 codebase_rag/mcp/client.py
 codebase_rag/mcp/server.py

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/code_graph_rag.egg-info/requires.txt

@@ -2,7 +2,6 @@ loguru>=0.7.3
 mcp<2,>=1.28.1
 pydantic-ai-slim[anthropic,google,openai]>=2.0.0
 pydantic-settings>=2.12.0
-pymgclient>=1.6.0
 python-dotenv>=1.2.1
 tiktoken>=0.12.0
 tomli-w>=1.2.0
@@ -19,6 +18,10 @@ defusedxml>=0.7.1
 huggingface-hub[hf-xet]>=1.7.2
 pathspec>=1.0.4
 pygments>=2.20.0
+regex>=2024.11.6
+
+[:platform_python_implementation == "CPython" and ((sys_platform == "linux" and (platform_machine == "x86_64" or platform_machine == "aarch64")) or sys_platform == "darwin" or (sys_platform == "win32" and platform_machine == "AMD64"))]
+cgr-graph-rs<0.2,>=0.1.0
 
 [ast-grep]
 ast-grep-py>=0.44.0
@@ -27,6 +30,9 @@ pyyaml>=6.0
 [cpp]
 libclang>=18.1.1
 
+[memgraph]
+pymgclient>=1.6.0
+
 [milvus]
 pymilvus[milvus-lite]>=3.0.0
 
@@ -41,6 +47,9 @@ qdrant-client>=1.9.0
 torch>=2.6.0
 transformers>=5.0.0
 
+[sqlite-vec]
+sqlite-vec>=0.1.9
+
 [test]
 jedi>=0.19
 pytest>=8.4.1
@@ -52,6 +61,8 @@ libclang>=18.1.1
 filelock>=3.12
 ast-grep-py>=0.44.0
 pyyaml>=6.0
+pymgclient>=1.6.0
+sqlite-vec>=0.1.9
 
 [treesitter-full]
 tree-sitter-python>=0.23.6

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/codebase_rag/cli.py

@@ -57,6 +57,7 @@ from .editor_links import (
     url_template_problem,
 )
 from .graph_cli import cli as graph_cli
+from .graph_dialects import DIALECT_MEMGRAPH
 from .parser_loader import load_parsers
 from .project_selection import ProjectChoice, choose_project, scope_refusal
 from .services.graph_diff import DiffError, diff_indexes, diff_is_empty
@@ -70,7 +71,7 @@ from .services.provenance import (
 )
 from .stack import StackManager
 from .stack.cli import cli as daemon_cli
-from .stack.constants import StackState
+from .stack.constants import SERVICE_QDRANT, StackState
 from .stack.manager import StackError
 from .sync_guard import RUNNING_SYNC_TOKENS as _RUNNING_SYNC_TOKENS
 from .sync_guard import OwnerCheck as _OwnerCheck
@@ -740,7 +741,17 @@ def _resolve_active_projects(projects: str | None, default_project: str) -> list
 
 
 def _maybe_start_stack() -> None:
-    mgr = StackManager()
+    # The Docker stack serves Memgraph, and Qdrant when the vector settings
+    # pick the bundled one. The embedded graph is a file and Neo4j is the
+    # user's own server, so for them the stack runs only for the vectors:
+    # only its Qdrant is started and checked, since every Memgraph check
+    # needs a driver those installs need not have.
+    if settings.GRAPH_BACKEND == DIALECT_MEMGRAPH:
+        mgr = StackManager()
+    else:
+        mgr = StackManager(services=(SERVICE_QDRANT,))
+        if not mgr.serves_vectors():
+            return
     try:
         mgr.locate_published_qdrant()
         if mgr.status().state == StackState.RUNNING:

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/codebase_rag/config.py

@@ -21,7 +21,7 @@ from pydantic_settings import BaseSettings, SettingsConfigDict
 from . import constants as cs
 from . import exceptions as ex
 from . import logs
-from .graph_dialects import DIALECT_MEMGRAPH, available_dialects
+from .graph_dialects import DIALECT_SQLITE, available_dialects
 from .types_defs import CgrignorePatterns, ModelConfigKwargs
 
 # Taken before `.env` is merged into the environment, so a refused value can be
@@ -263,10 +263,15 @@ class AppConfig(BaseSettings):
         enable_decoding=False,
     )
 
-    # Which graph engine the ingestor talks to. Memgraph stays the default,
-    # so an existing install keeps its behaviour without touching config;
-    # see `graph_dialects` for what actually differs between engines.
-    GRAPH_BACKEND: str = DIALECT_MEMGRAPH
+    # Which graph engine the ingestor talks to; see `graph_dialects` for
+    # what actually differs between engines. The embedded SQLite engine is
+    # the default because it needs no server, no Docker and no native
+    # driver: a first run indexes straight into a file (issue #386).
+    # Memgraph and Neo4j stay one setting away.
+    GRAPH_BACKEND: str = DIALECT_SQLITE
+    # The embedded graph's file; unset means `graph.sqlite` under CGR_HOME,
+    # one graph shared by every project, as one Memgraph instance is.
+    SQLITE_GRAPH_PATH: Path | None = None
 
     MEMGRAPH_HOST: str = "localhost"
     MEMGRAPH_PORT: int = 7687
@@ -338,6 +343,25 @@ class AppConfig(BaseSettings):
         True, validation_alias="CGR_CAPTURE_LOCAL_DEFINITIONS"
     )
     CGR_HOME: Path = Field(default_factory=lambda: Path.home() / ".cgr")
+
+    @property
+    def graph_db_file(self) -> Path:
+        if self.SQLITE_GRAPH_PATH is not None:
+            return self.SQLITE_GRAPH_PATH.expanduser()
+        return self.CGR_HOME.expanduser() / cs.EG_DEFAULT_DB_FILENAME
+
+    @property
+    def memgraph_set_without_backend(self) -> bool:
+        """Whether Memgraph is configured but the engine was left to default.
+
+        Memgraph was the default engine before the embedded graph replaced
+        it, so this is how an install upgraded in place looks: its graph
+        lives in Memgraph while cgr now opens an empty file.
+        """
+        return cs.GRAPH_BACKEND_SETTING not in self.model_fields_set and any(
+            name in self.model_fields_set for name in cs.MEMGRAPH_CONNECTION_SETTINGS
+        )
+
     # Editor integration for clickable report locations (OSC 8 hyperlinks)
     # and `cgr duplicates --open`. AUTO sniffs the hosting app (Cursor,
     # Windsurf, Zed, VS Code's terminal) and falls back to VS Code; the
@@ -438,6 +462,19 @@ class AppConfig(BaseSettings):
     MILVUS_VECTOR_DIM: int = 768
     MILVUS_TOP_K: int = 5
     MILVUS_CONSISTENCY_LEVEL: str = "Strong"
+    # The `sqlite` vector store's file; unset means `vectors.sqlite` under
+    # CGR_HOME, beside the embedded graph's, so semantic search needs no
+    # server either.
+    SQLITE_VECTOR_PATH: Path | None = None
+    SQLITE_VECTOR_DIM: int = 768
+    SQLITE_VECTOR_TOP_K: int = 5
+
+    @property
+    def vector_db_file(self) -> Path:
+        if self.SQLITE_VECTOR_PATH is not None:
+            return self.SQLITE_VECTOR_PATH.expanduser()
+        return self.CGR_HOME.expanduser() / cs.SQLITE_VEC_DEFAULT_DB_FILENAME
+
     EMBEDDING_PROVIDER: cs.EmbeddingProvider = Field(
         cs.EmbeddingProvider.UNIXCODER, validation_alias="CGR_EMBEDDING_PROVIDER"
     )

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/codebase_rag/constants/__init__.py

@@ -20,6 +20,7 @@ from .core import *  # noqa: F403
 from .deadcode_roots import *  # noqa: F403
 from .deps import *  # noqa: F403
 from .duplicates import *  # noqa: F403
+from .embedded_graph import *  # noqa: F403
 from .fqn_specs import *  # noqa: F403
 from .graph import *  # noqa: F403
 from .graph import _NODE_LABEL_UNIQUE_KEYS as _NODE_LABEL_UNIQUE_KEYS
@@ -31,6 +32,7 @@ from .mcp import *  # noqa: F403
 from .notebook import *  # noqa: F403
 from .providers import *  # noqa: F403
 from .security import *  # noqa: F403
+from .sqlite_vectors import *  # noqa: F403
 from .stdlib_types import *  # noqa: F403
 from .structural import *  # noqa: F403
 from .trace import *  # noqa: F403

{code_graph_rag-0.1.90 → code_graph_rag-0.2.0}/codebase_rag/constants/build.py

@@ -57,11 +57,9 @@ MGCLIENT_PROBE_CHILD_ARG = "--mgclient-probe-child"
 # `websockets.cli`), which put `libreadline.so.8` inside the MIT-licensed
 # one-file binary. Every importer guards the import, and interactive input
 # goes through prompt_toolkit, so nothing loses behaviour without it.
-# `sqlite3` is excluded because filelock (via huggingface-hub and torch)
-# imports it for its read-write locks, which bundled `libsqlite3` with no
-# licence entry. filelock guards that import, and nothing else in the binary
-# uses sqlite3.
-PYINSTALLER_EXCLUDED_MODULES = ["logfire", "readline", "sqlite3"]
+# `sqlite3` is bundled: the embedded graph, cgr's default backend, is a
+# SQLite file. Its library carries a notice entry (SQLite is public domain).
+PYINSTALLER_EXCLUDED_MODULES = ["logfire", "readline"]
 
 # Archive entries a release binary must never carry, matched against the last
 # path segment of each TOC name. Checked on the built archive, so a new route
@@ -93,4 +91,7 @@ PYINSTALLER_PACKAGES: list["PyInstallerPackage"] = [
     PyInstallerPackage(name="tomli_w", collect_all=True),
     PyInstallerPackage(name="protobuf", collect_all=True),
     PyInstallerPackage(name="genai_prices", collect_all=True),
+    # The embedded graph's Rust half, loaded by name (embedded_graph/
+    # extension.py), so PyInstaller never sees an import of it.
+    PyInstallerPackage(name="cgr_graph_rs", collect_all=True),
 ]