kodit 0.2.4__py3-none-any.whl → 0.2.5__py3-none-any.whl

kodit/infrastructure/ui/progress.py

@@ -0,0 +1,127 @@
+"""Progress UI implementations."""
+
+from collections.abc import Callable
+
+from tqdm import tqdm
+
+from kodit.domain.interfaces import ProgressCallback
+from kodit.domain.value_objects import ProgressEvent
+
+
+class TQDMProgressCallback(ProgressCallback):
+    """TQDM-based progress callback implementation."""
+
+    def __init__(self, pbar: "tqdm") -> None:
+        """Initialize with a TQDM progress bar."""
+        self.pbar = pbar
+
+    async def on_progress(self, event: ProgressEvent) -> None:
+        """Update the TQDM progress bar."""
+        # Update total if it changes
+        if event.total != self.pbar.total:
+            self.pbar.total = event.total
+
+        # Update the progress bar
+        self.pbar.n = event.current
+        self.pbar.refresh()
+
+        # Update description if message is provided
+        if event.message:
+            # Fix the event message to a specific size so it's not jumping around
+            # If it's too small, add spaces
+            # If it's too large, truncate
+            if len(event.message) < 30:
+                self.pbar.set_description(
+                    event.message + " " * (30 - len(event.message))
+                )
+            else:
+                self.pbar.set_description(event.message[-30:])
+
+    async def on_complete(self, operation: str) -> None:
+        """Complete the progress bar."""
+        # TQDM will handle cleanup with leave=False
+
+
+class LazyProgressCallback(ProgressCallback):
+    """Progress callback that only shows progress when there's actual work to do."""
+
+    def __init__(self, create_pbar_func: Callable[[], tqdm]) -> None:
+        """Initialize with a function that creates a progress bar."""
+        self.create_pbar_func = create_pbar_func
+        self._callback: ProgressCallback | None = None
+        self._has_work = False
+
+    async def on_progress(self, event: ProgressEvent) -> None:
+        """Update progress, creating the actual callback if needed."""
+        if not self._has_work:
+            self._has_work = True
+            # Only create the progress bar when we actually have work to do
+            pbar = self.create_pbar_func()
+            self._callback = TQDMProgressCallback(pbar)
+
+        if self._callback:
+            await self._callback.on_progress(event)
+
+    async def on_complete(self, operation: str) -> None:
+        """Complete the progress operation."""
+        if self._callback:
+            await self._callback.on_complete(operation)
+
+
+class MultiStageProgressCallback(ProgressCallback):
+    """Progress callback that handles multiple stages with separate progress bars."""
+
+    def __init__(self, create_pbar_func: Callable[[str], tqdm]) -> None:
+        """Initialize with a function that creates progress bars."""
+        self.create_pbar_func = create_pbar_func
+        self._current_callback: ProgressCallback | None = None
+        self._current_operation: str | None = None
+
+    async def on_progress(self, event: ProgressEvent) -> None:
+        """Update progress for the current operation."""
+        # If this is a new operation, create a new progress bar
+        if self._current_operation != event.operation:
+            # Create a new progress bar for this operation
+            pbar = self.create_pbar_func(event.operation)
+            self._current_callback = TQDMProgressCallback(pbar)
+            self._current_operation = event.operation
+
+        # Update the current progress bar
+        if self._current_callback:
+            await self._current_callback.on_progress(event)
+
+    async def on_complete(self, operation: str) -> None:
+        """Complete the current operation."""
+        if self._current_callback and self._current_operation == operation:
+            await self._current_callback.on_complete(operation)
+            self._current_callback = None
+            self._current_operation = None
+
+
+def create_progress_bar(desc: str = "Processing", unit: str = "items") -> "tqdm":
+    """Create a progress bar with the given description and unit."""
+    from tqdm import tqdm
+
+    return tqdm(
+        desc=desc,
+        unit=unit,
+        leave=False,
+        dynamic_ncols=True,
+        total=None,  # Will be set dynamically
+        position=0,  # Position at top
+        mininterval=0.1,  # Update at most every 0.1 seconds
+    )
+
+
+def create_lazy_progress_callback() -> LazyProgressCallback:
+    """Create a lazy progress callback that only shows progress when needed."""
+    return LazyProgressCallback(
+        lambda: create_progress_bar("Processing files", "files")
+    )
+
+
+def create_multi_stage_progress_callback() -> MultiStageProgressCallback:
+    """Create a multi-stage progress callback for indexing operations."""
+    return MultiStageProgressCallback(
+        lambda operation: create_progress_bar(operation, "items")
+    )

kodit/{util → infrastructure/ui}/spinner.py

@@ -1,4 +1,4 @@
-"""Spinner for long-running tasks."""
+"""Spinner for long-running tasks in the UI layer."""
 
 import itertools
 import sys
@@ -7,10 +7,20 @@ import time
 
 
 class Spinner:
-    """Spinner for long-running tasks."""
+    """Spinner for long-running tasks.
+
+    This class provides visual feedback for long-running operations by displaying
+    a spinning animation in the terminal. It's designed to be used as a context
+    manager for operations that may take some time to complete.
+    """
 
     def __init__(self, delay: float = 0.1) -> None:
-        """Initialize the spinner."""
+        """Initialize the spinner.
+
+        Args:
+            delay: The delay between spinner updates in seconds.
+
+        """
         self.spinner = itertools.cycle(["-", "/", "|", "\\"])
         self.delay = delay
         self.busy = False
@@ -25,7 +35,12 @@ class Spinner:
                 sys.stdout.flush()
 
     def remove_spinner(self, cleanup: bool = False) -> None:  # noqa: FBT001, FBT002
-        """Remove the spinner."""
+        """Remove the spinner.
+
+        Args:
+            cleanup: Whether to clean up the spinner display.
+
+        """
         with self._screen_lock:
             if self.spinner_visible:
                 sys.stdout.write("\b")

kodit/mcp.py

@@ -12,15 +12,20 @@ from pydantic import Field
 from sqlalchemy.ext.asyncio import AsyncSession
 
 from kodit._version import version
-from kodit.bm25.keyword_search_factory import keyword_search_factory
+from kodit.application.services.snippet_application_service import (
+    SnippetApplicationService,
+)
 from kodit.config import AppContext
 from kodit.database import Database
-from kodit.embedding.embedding_factory import embedding_factory
-from kodit.enrichment.enrichment_factory import enrichment_factory
-from kodit.indexing.indexing_repository import IndexRepository
-from kodit.indexing.indexing_service import IndexService, SearchRequest, SearchResult
-from kodit.source.source_repository import SourceRepository
-from kodit.source.source_service import SourceService
+from kodit.domain.services.source_service import SourceService
+from kodit.domain.value_objects import MultiSearchRequest, MultiSearchResult
+from kodit.infrastructure.indexing.indexing_factory import (
+    create_indexing_application_service,
+)
+from kodit.infrastructure.snippet_extraction.snippet_extraction_factory import (
+    create_snippet_extraction_domain_service,
+    create_snippet_repositories,
+)
 
 
 @dataclass
@@ -69,6 +74,32 @@ mcp = FastMCP(
 )
 
 
+def create_snippet_application_service(
+    session: AsyncSession,
+) -> SnippetApplicationService:
+    """Create a snippet application service with all dependencies.
+
+    Args:
+        session: SQLAlchemy session
+
+    Returns:
+        Configured snippet application service
+
+    """
+    # Create domain service
+    snippet_extraction_service = create_snippet_extraction_domain_service()
+
+    # Create repositories
+    snippet_repository, file_repository = create_snippet_repositories(session)
+
+    # Create application service
+    return SnippetApplicationService(
+        snippet_extraction_service=snippet_extraction_service,
+        snippet_repository=snippet_repository,
+        file_repository=file_repository,
+    )
+
+
 @mcp.tool()
 async def search(
     ctx: Context,
@@ -126,31 +157,22 @@ async def search(
 
     mcp_context: MCPContext = ctx.request_context.lifespan_context
 
-    source_repository = SourceRepository(mcp_context.session)
     source_service = SourceService(
-        mcp_context.app_context.get_clone_dir(), source_repository
+        clone_dir=mcp_context.app_context.get_clone_dir(),
+        session_factory=lambda: mcp_context.session,
     )
-    repository = IndexRepository(mcp_context.session)
-    service = IndexService(
-        repository=repository,
+    # Create snippet application service
+    snippet_application_service = create_snippet_application_service(
+        mcp_context.session
+    )
+    service = create_indexing_application_service(
+        app_context=mcp_context.app_context,
+        session=mcp_context.session,
         source_service=source_service,
-        keyword_search_provider=keyword_search_factory(
-            mcp_context.app_context, mcp_context.session
-        ),
-        code_search_service=embedding_factory(
-            task_name="code",
-            app_context=mcp_context.app_context,
-            session=mcp_context.session,
-        ),
-        text_search_service=embedding_factory(
-            task_name="text",
-            app_context=mcp_context.app_context,
-            session=mcp_context.session,
-        ),
-        enrichment_service=enrichment_factory(mcp_context.app_context),
+        snippet_application_service=snippet_application_service,
     )
 
-    search_request = SearchRequest(
+    search_request = MultiSearchRequest(
         keywords=keywords,
         code_query="\n".join(related_file_contents),
         text_query=user_intent,
@@ -166,7 +188,7 @@ async def search(
     return output
 
 
-def output_fusion(snippets: list[SearchResult]) -> str:
+def output_fusion(snippets: list[MultiSearchResult]) -> str:
     """Fuse the snippets into a single output."""
     return "\n\n".join(f"{snippet.uri}\n{snippet.content}" for snippet in snippets)
 

kodit/migrations/env.py

@@ -8,10 +8,7 @@ from sqlalchemy import pool
 from sqlalchemy.engine import Connection
 from sqlalchemy.ext.asyncio import async_engine_from_config
 
-import kodit.embedding.embedding_models
-import kodit.indexing.indexing_models
-import kodit.source.source_models
-from kodit.database import Base
+from kodit.domain.entities import Base
 
 # this is the Alembic Config object, which provides
 # access to the values within the .ini file in use.

kodit/reporting.py

@@ -0,0 +1,78 @@
+"""Unified logging and progress-reporting helper.
+
+This utility consolidates the repeated pattern where services:
+1. Log a message (usually via structlog) and
+2. Emit a ProgressEvent via a ProgressCallback.
+
+Using Reporter removes boiler-plate and guarantees consistent telemetry.
+"""
+
+import structlog
+
+from kodit.domain.interfaces import NullProgressCallback, ProgressCallback
+from kodit.domain.value_objects import ProgressEvent
+
+
+class Reporter:
+    """Emit log and progress updates with a single call."""
+
+    def __init__(
+        self,
+        logger: structlog.BoundLogger | None = None,
+        progress: ProgressCallback | None = None,
+    ) -> None:
+        """Initialize the reporter."""
+        self.log: structlog.BoundLogger = logger or structlog.get_logger(__name__)
+        self.progress: ProgressCallback = progress or NullProgressCallback()
+
+    # ---------------------------------------------------------------------
+    # Life-cycle helpers
+    # ---------------------------------------------------------------------
+    async def start(
+        self, operation: str, total: int, message: str | None = None
+    ) -> None:
+        """Log *operation.start* and emit initial ProgressEvent."""
+        self.log.debug(
+            "operation.start", operation=operation, total=total, message=message
+        )
+        await self.progress.on_progress(
+            ProgressEvent(operation=operation, current=0, total=total, message=message)
+        )
+
+    async def step(
+        self,
+        operation: str,
+        current: int,
+        total: int,
+        message: str | None = None,
+    ) -> None:
+        """Emit an intermediate progress step (no log by default)."""
+        await self.progress.on_progress(
+            ProgressEvent(
+                operation=operation, current=current, total=total, message=message
+            )
+        )
+
+    async def done(self, operation: str, message: str | None = None) -> None:
+        """Log *operation.done* and emit completion event."""
+        self.log.debug("operation.done", operation=operation, message=message)
+        await self.progress.on_complete(operation)
+
+    async def advance(
+        self,
+        operation: str,
+        current: int,
+        total: int,
+        message: str | None = None,
+        log_every: int | None = None,
+    ) -> None:
+        """Emit step; optionally log when *current % log_every == 0*."""
+        if log_every and current % log_every == 0:
+            self.log.debug(
+                "operation.progress",
+                operation=operation,
+                current=current,
+                total=total,
+                message=message,
+            )
+        await self.step(operation, current, total, message)

{kodit-0.2.4.dist-info → kodit-0.2.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: kodit
-Version: 0.2.4
+Version: 0.2.5
 Summary: Code indexing for better AI code generation
 Project-URL: Homepage, https://docs.helixml.tech/kodit/
 Project-URL: Documentation, https://docs.helixml.tech/kodit/

kodit-0.2.5.dist-info/RECORD

@@ -0,0 +1,99 @@
+kodit/.gitignore,sha256=ztkjgRwL9Uud1OEi36hGQeDGk3OLK1NfDEO8YqGYy8o,11
+kodit/__init__.py,sha256=aEKHYninUq1yh6jaNfvJBYg-6fenpN132nJt1UU6Jxs,59
+kodit/_version.py,sha256=N3oBwJUFmS-AwCjqOcSlRW4GvSq-uJJMaBvoGfv1-hM,511
+kodit/app.py,sha256=qKBWJ0VNSY_M6G3VFfAQ0133q5bnS99cUFD0p396taw,1032
+kodit/cli.py,sha256=SUoo9R-Jut0OlZLajD-nSPdhvHPOZ2SpN35SDyON8tc,11500
+kodit/config.py,sha256=3yh7hfLSILjZK_qJMhcExwRcrWJ0b5Eb1JjjOvMPJZo,4146
+kodit/database.py,sha256=kI9yBm4uunsgV4-QeVoCBL0wLzU4kYmYv5qZilGnbPE,1740
+kodit/log.py,sha256=sHPHYetlMcKTor2VaFLMyao1_fZ_xhuzqXCAt5F5UMU,8575
+kodit/mcp.py,sha256=kiWyZ2Ptluh0jLDQNxKjxNmD18bEG1-zAFVOoZAPsWI,6192
+kodit/middleware.py,sha256=I6FOkqG9-8RH5kR1-0ZoQWfE4qLCB8lZYv8H_OCH29o,2714
+kodit/reporting.py,sha256=icce1ZyiADsA_Qz-mSjgn2H4SSqKuGfLKnw-yrl9nsg,2722
+kodit/application/__init__.py,sha256=mH50wTpgP9dhbKztFsL8Dda9Hi18TSnMVxXtpp4aGOA,35
+kodit/application/commands/__init__.py,sha256=AOVs25fwboBnMCWdgDB7fPbAYTljurAPVMkATIGRKuk,38
+kodit/application/commands/snippet_commands.py,sha256=WzRrnJOnLpIK8-wvN7c-ecGs_4LosQ_jR30dQkFqFBY,600
+kodit/application/services/__init__.py,sha256=p5UQNw-H5sxQvs5Etfte93B3cJ1kKW6DNxK34uFvU1E,38
+kodit/application/services/indexing_application_service.py,sha256=n7ViSfAPshUqe_gebgduRKwIPkB3Cl72CDw2U_qUJXY,13558
+kodit/application/services/snippet_application_service.py,sha256=NJxR3X78lTK0zXpYPdiCCw8NAJdLwyMyynfGnBfvONM,4759
+kodit/domain/__init__.py,sha256=TCpg4Xx-oF4mKV91lo4iXqMEfBT1OoRSYnbG-zVWolA,66
+kodit/domain/entities.py,sha256=6XVuwDIQjkBw5Bm51io5ZUxB6_O4A774CDke2bfKWTY,5584
+kodit/domain/enums.py,sha256=Ik_h3D3eZ0FsSlPsU0ikm-Yv3Rmvzicffi9yBn19UIE,191
+kodit/domain/interfaces.py,sha256=Jkd0Ob4qSvhZHI9jRPFQ1n5Cv0SvU-y3Z-HCw2ikc4I,742
+kodit/domain/repositories.py,sha256=bdKxSKGI6XzrpzeKcv-NDV2JBirbEMRK-Y4UCZmDtoY,2706
+kodit/domain/value_objects.py,sha256=4Vs7Uk1wQgTjnCkZlOlw7E1Q8NiyAmBpFv38Lhs3WZ0,3869
+kodit/domain/services/__init__.py,sha256=Q1GhCK_PqKHYwYE4tkwDz5BIyXkJngLBBOHhzvX8nzo,42
+kodit/domain/services/bm25_service.py,sha256=N3kAcsRjxn22bbYNRhGu-VY6fnLsE-M2WyzEIk7Im3s,3809
+kodit/domain/services/embedding_service.py,sha256=ZgC4n7vuqwW_NOCTRiNxezmCs73OB-G1dTDRGYorGGo,4588
+kodit/domain/services/enrichment_service.py,sha256=XsXg3nV-KN4rqtC7Zro_ZiZ6RSq-1eA1MG6IDzFGyBA,1316
+kodit/domain/services/ignore_service.py,sha256=boEN-IRLmUtwO9ZnuACaVFZbIKrtUG8YwnsXKEDIG28,1136
+kodit/domain/services/indexing_service.py,sha256=FEizu2GkvZA32xHOYXXch0LuHoWg6Z-BbJMPjZslzjc,5853
+kodit/domain/services/snippet_extraction_service.py,sha256=QW_99bXWpr8g6ZI-hp4Aj57VCSrUf71dLwQca5T6pyg,3065
+kodit/domain/services/source_service.py,sha256=CM9TKTvn-9xfsk3AoKvIoPQ5_MridXng2jY8skn6_5Q,2987
+kodit/infrastructure/__init__.py,sha256=HzEYIjoXnkz_i_MHO2e0sIVYweUcRnl2RpyBiTbMObU,28
+kodit/infrastructure/bm25/__init__.py,sha256=DmGbrEO34FOJy4e685BbyxLA7gPW1eqs2gAxsp6JOuM,34
+kodit/infrastructure/bm25/bm25_factory.py,sha256=I4eo7qRslnyXIRkBf-StZ5ga2Evrr5J5YFocTChFD3g,884
+kodit/infrastructure/bm25/local_bm25_repository.py,sha256=HjhzY24FU5R81qfzXfzJl14E3JafLO0l0ug6psutErQ,4276
+kodit/infrastructure/bm25/vectorchord_bm25_repository.py,sha256=0Db9XWFjiS4TFrsNazBMo6FxhX9SxLGNVQB0rDHqnL4,6875
+kodit/infrastructure/cloning/__init__.py,sha256=IzIvX-yeRRFZ-lfvPVSEe_qXszO6DGQdjKwwDigexyQ,30
+kodit/infrastructure/cloning/metadata.py,sha256=C5LLmsUzi29RhSbzVDNqiShbekg7qdp1ihGUyFXy5yM,4277
+kodit/infrastructure/cloning/folder/__init__.py,sha256=w6ykrVtbYJlUDEXAjqgf6w2rMsUMCrrpIbl3QMjubgY,37
+kodit/infrastructure/cloning/folder/factory.py,sha256=qpFXxZuwYbdO17FKurWtm84ahwerDpcaLubClEZrbtk,3955
+kodit/infrastructure/cloning/folder/working_copy.py,sha256=FPhwzuPj40yGoYvwcm9VG8mv8MbJxwfby_N5JS-_daA,1154
+kodit/infrastructure/cloning/git/__init__.py,sha256=20ePcp0qE6BuLsjsv4KYB1DzKhMIMsPXwEqIEZtjTJs,34
+kodit/infrastructure/cloning/git/factory.py,sha256=pjIvl3NIhXNNbRcI86wedz8CP-jV_Z3OVpGl4BUGCmo,4585
+kodit/infrastructure/cloning/git/working_copy.py,sha256=DMW_p7WWGoSeyDI9g55ItwsRomZSotXWRrlopqwszaQ,1115
+kodit/infrastructure/embedding/__init__.py,sha256=F-8nLlWAerYJ0MOIA4tbXHLan8bW5rRR84vzxx6tRKI,39
+kodit/infrastructure/embedding/embedding_factory.py,sha256=1AypjhWJGxvLnZt1SEH_FHPk9P0Vkt9fXdSGzFPp2ow,3432
+kodit/infrastructure/embedding/local_vector_search_repository.py,sha256=UO8A3Eb_djFVrWKKSukAo4u7k8djDD1SlOPHk2pP9ps,3921
+kodit/infrastructure/embedding/vectorchord_vector_search_repository.py,sha256=7P5Uz8heQOi-x0k5wrNSE2biiy8FaC4VTfX0vPdfy6Y,7638
+kodit/infrastructure/embedding/embedding_providers/__init__.py,sha256=qeZ-oAIAxMl5QqebGtO1lq-tHjl_ucAwOXePklcwwGk,34
+kodit/infrastructure/embedding/embedding_providers/batching.py,sha256=a8CL9PX2VLmbeg616fc_lQzfC4BWTVn32m4SEhXpHxc,3279
+kodit/infrastructure/embedding/embedding_providers/hash_embedding_provider.py,sha256=HfilGGJ-hiw3mHOj6Zf7jlouSIIDaDFqwPe-4vKPREE,2611
+kodit/infrastructure/embedding/embedding_providers/local_embedding_provider.py,sha256=U5fc8jUP8wF-nq1zo-CfSbJbLQyE-3muKmRCaYGtytk,4387
+kodit/infrastructure/embedding/embedding_providers/openai_embedding_provider.py,sha256=LIK9Iir7geraZoqiaNbeHv3hXrghZRDpYGJDEjZaqzQ,4086
+kodit/infrastructure/enrichment/__init__.py,sha256=8acZKNzql8Fs0lceFu9U3KoUrOptRBtVIxr_Iw6lz3Y,40
+kodit/infrastructure/enrichment/enrichment_factory.py,sha256=4saTSHJY9o1LC4wkkL0I_fCsLPh0-Wb7GdZt9-1lXVA,1827
+kodit/infrastructure/enrichment/legacy_enrichment_models.py,sha256=YS-sNEH-b4hoy2ThcqhfkiefsftUsFgIjZjbvfU7j6w,1035
+kodit/infrastructure/enrichment/local_enrichment_provider.py,sha256=8CATNtgMHgBRt24GrYEwaZKrroNCxMJS-39xQJoG3N0,3818
+kodit/infrastructure/enrichment/null_enrichment_provider.py,sha256=5Ksyxl3qDLxUjmOeIdHZ0UAIULy7RcbLXJoT7_CNXoQ,775
+kodit/infrastructure/enrichment/openai_enrichment_provider.py,sha256=fenq4HiJ2UkrzsE2D0A0qpmro38z9mKaIzKKU5v7hnY,3189
+kodit/infrastructure/git/__init__.py,sha256=0iMosFzudj4_xNIMe2SRbV6l5bWqkjnUsZoFsoZFuM8,33
+kodit/infrastructure/git/git_utils.py,sha256=lOujEx41UuWfYSnFWbY4HC2tK5utytyzNkW1e5IPCr0,543
+kodit/infrastructure/ignore/__init__.py,sha256=VzFv8XOzHmsu0MEGnWVSF6KsgqLBmvHlRqAkT1Xb1MY,36
+kodit/infrastructure/ignore/ignore_pattern_provider.py,sha256=9m2XCsgW87UBTfzHr6Z0Ns6WpzwkLir3zyBY3PwsgXk,2225
+kodit/infrastructure/indexing/__init__.py,sha256=7UPRa2jwCAsa0Orsp6PqXSF8iIXJVzXHMFmrKkI9yH8,38
+kodit/infrastructure/indexing/fusion_service.py,sha256=mXUUcx3-8e75mWkxXMfl30HIoFXrTNHzB1w90MmEbak,1806
+kodit/infrastructure/indexing/index_repository.py,sha256=iHK9wcC8893Q6vY8OhW9UrN0gj1_GVzjTVlbewyZdxI,9094
+kodit/infrastructure/indexing/indexing_factory.py,sha256=BbavU9DJZapAe0V9H6Zsk7J6oPY48SJhGP3nrCPvzoQ,3914
+kodit/infrastructure/snippet_extraction/__init__.py,sha256=v6KqrRDjSj0nt87m7UwRGx2GN_fz_14VWq9Q0uABR_s,54
+kodit/infrastructure/snippet_extraction/language_detection_service.py,sha256=Lo9xPLVia-70yP9gzyH4cQcBQzsp7WXjGOa5NBggScg,1158
+kodit/infrastructure/snippet_extraction/snippet_extraction_factory.py,sha256=LGbm614KCPNsM9K8r1z-E763NyAMIZA9ETJ_C61EknA,2759
+kodit/infrastructure/snippet_extraction/snippet_query_provider.py,sha256=pLjFExJx5bX4s6a_mMA4-AfjtfBaC2wjTV3GjYD2HVE,1284
+kodit/infrastructure/snippet_extraction/tree_sitter_snippet_extractor.py,sha256=8B14jy_QS9SBA5jNpLtSSOayKP1WgMeCQEsZPuyAs8o,6190
+kodit/infrastructure/snippet_extraction/languages/csharp.scm,sha256=gbBN4RiV1FBuTJF6orSnDFi8H9JwTw-d4piLJYsWUsc,222
+kodit/infrastructure/snippet_extraction/languages/go.scm,sha256=SEX9mTOrhP2KiQW7oflDKkd21u5dK56QbJ4LvTDxY8A,533
+kodit/infrastructure/snippet_extraction/languages/javascript.scm,sha256=Ini5TsVNmcBKQ8aL46a5Id9ut0g9UdmvmVqdMqRJtFk,446
+kodit/infrastructure/snippet_extraction/languages/python.scm,sha256=ee85R9PBzwye3IMTE7-iVoKWd_ViU3EJISTyrFGrVeo,429
+kodit/infrastructure/snippet_extraction/languages/typescript.scm,sha256=U-ujbbv4tylbUBj9wuhL-e5cW6hmgPCNs4xrIX3r_hE,448
+kodit/infrastructure/sqlalchemy/__init__.py,sha256=UXPMSF_hgWaqr86cawRVqM8XdVNumQyyK5B8B97GnlA,33
+kodit/infrastructure/sqlalchemy/embedding_repository.py,sha256=vdjn3E5dFriFkceK8E8QMZzZk83etSf3NQOyS_LCeGY,7548
+kodit/infrastructure/sqlalchemy/file_repository.py,sha256=9O6ysCG_ldZFzDtpcxaTJQ8xya1A2q3CU2NafQo7GS0,2027
+kodit/infrastructure/sqlalchemy/repository.py,sha256=xWVAO9Bx9NKh3fSM-D1KGehT-6MNIYW2YQQcUcTE2xk,4369
+kodit/infrastructure/sqlalchemy/snippet_repository.py,sha256=zMqc5KxD0rP6r2BG2qLVAf3rh3IONkhZkI_pXg-r3a8,2137
+kodit/infrastructure/ui/__init__.py,sha256=CzbLOBwIZ6B6iAHEd1L8cIBydCj-n_kobxJAhz2I9_Y,32
+kodit/infrastructure/ui/progress.py,sha256=BaAeMEgXlSSb0c_t_NPxnThIktkzzCS9kegb5ExULJs,4791
+kodit/infrastructure/ui/spinner.py,sha256=GcP115qtR0VEnGfMEtsGoAUpRzVGUSfiUXfoJJERngA,2357
+kodit/migrations/README,sha256=ISVtAOvqvKk_5ThM5ioJE-lMkvf9IbknFUFVU_vPma4,58
+kodit/migrations/__init__.py,sha256=lP5MuwlyWRMO6UcDWnQcQ3G-GYHcFb6rl9gYPHJ1sjo,40
+kodit/migrations/env.py,sha256=j89vEWdSgfnreTAz5ZvFAPlsMGI8SfKti0MlWhm7Jbc,2364
+kodit/migrations/script.py.mako,sha256=zWziKtiwYKEWuwPV_HBNHwa9LCT45_bi01-uSNFaOOE,703
+kodit/migrations/versions/7c3bbc2ab32b_add_embeddings_table.py,sha256=-61qol9PfQKILCDQRA5jEaats9aGZs9Wdtp-j-38SF4,1644
+kodit/migrations/versions/85155663351e_initial.py,sha256=Cg7zlF871o9ShV5rQMQ1v7hRV7fI59veDY9cjtTrs-8,3306
+kodit/migrations/versions/9e53ea8bb3b0_add_authors.py,sha256=a32Zm8KUQyiiLkjKNPYdaJDgjW6VsV-GhaLnPnK_fpI,3884
+kodit/migrations/versions/__init__.py,sha256=9-lHzptItTzq_fomdIRBegQNm4Znx6pVjwD4MiqRIdo,36
+kodit/migrations/versions/c3f5137d30f5_index_all_the_things.py,sha256=rI8LmjF-I2OMxZ2nOIF_NRmqOLXe45hL_iz_nx97DTQ,1680
+kodit-0.2.5.dist-info/METADATA,sha256=UuPIpWyvjccCITCITmMcJhUwIxRd211UvDmVXi8MbY4,5867
+kodit-0.2.5.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kodit-0.2.5.dist-info/entry_points.txt,sha256=hoTn-1aKyTItjnY91fnO-rV5uaWQLQ-Vi7V5et2IbHY,40
+kodit-0.2.5.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+kodit-0.2.5.dist-info/RECORD,,

kodit/bm25/__init__.py

@@ -1 +0,0 @@
-"""BM25 module."""

kodit/bm25/keyword_search_factory.py

@@ -1,17 +0,0 @@
-"""Factory for creating keyword search providers."""
-
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from kodit.bm25.keyword_search_service import KeywordSearchProvider
-from kodit.bm25.local_bm25 import BM25Service
-from kodit.bm25.vectorchord_bm25 import VectorChordBM25
-from kodit.config import AppContext
-
-
-def keyword_search_factory(
-    app_context: AppContext, session: AsyncSession
-) -> KeywordSearchProvider:
-    """Create a keyword search provider."""
-    if app_context.default_search.provider == "vectorchord":
-        return VectorChordBM25(session=session)
-    return BM25Service(data_dir=app_context.get_data_dir())

kodit/bm25/keyword_search_service.py

@@ -1,34 +0,0 @@
-"""Keyword search service."""
-
-from abc import ABC, abstractmethod
-from typing import NamedTuple
-
-
-class BM25Document(NamedTuple):
-    """BM25 document."""
-
-    snippet_id: int
-    text: str
-
-
-class BM25Result(NamedTuple):
-    """BM25 result."""
-
-    snippet_id: int
-    score: float
-
-
-class KeywordSearchProvider(ABC):
-    """Interface for keyword search providers."""
-
-    @abstractmethod
-    async def index(self, corpus: list[BM25Document]) -> None:
-        """Index a new corpus."""
-
-    @abstractmethod
-    async def retrieve(self, query: str, top_k: int = 2) -> list[BM25Result]:
-        """Retrieve from the index."""
-
-    @abstractmethod
-    async def delete(self, snippet_ids: list[int]) -> None:
-        """Delete documents from the index."""

kodit/embedding/__init__.py

@@ -1 +0,0 @@
-"""Embedding module."""

kodit/embedding/embedding_factory.py

@@ -1,69 +0,0 @@
-"""Embedding service."""
-
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from kodit.config import AppContext, Endpoint
-from kodit.embedding.embedding_models import EmbeddingType
-from kodit.embedding.embedding_provider.local_embedding_provider import (
-    CODE,
-    LocalEmbeddingProvider,
-)
-from kodit.embedding.embedding_provider.openai_embedding_provider import (
-    OpenAIEmbeddingProvider,
-)
-from kodit.embedding.embedding_repository import EmbeddingRepository
-from kodit.embedding.local_vector_search_service import LocalVectorSearchService
-from kodit.embedding.vector_search_service import (
-    VectorSearchService,
-)
-from kodit.embedding.vectorchord_vector_search_service import (
-    TaskName,
-    VectorChordVectorSearchService,
-)
-from kodit.log import log_event
-
-
-def _get_endpoint_configuration(app_context: AppContext) -> Endpoint | None:
-    """Get the endpoint configuration for the embedding service."""
-    return app_context.embedding_endpoint or app_context.default_endpoint or None
-
-
-def embedding_factory(
-    task_name: TaskName, app_context: AppContext, session: AsyncSession
-) -> VectorSearchService:
-    """Create an embedding service."""
-    embedding_repository = EmbeddingRepository(session=session)
-    endpoint = _get_endpoint_configuration(app_context)
-
-    if endpoint and endpoint.type == "openai":
-        log_event("kodit.embedding", {"provider": "openai"})
-        from openai import AsyncOpenAI
-
-        embedding_provider = OpenAIEmbeddingProvider(
-            openai_client=AsyncOpenAI(
-                api_key=endpoint.api_key or "default",
-                base_url=endpoint.base_url or "https://api.openai.com/v1",
-            ),
-            model_name=endpoint.model or "text-embedding-3-small",
-        )
-    else:
-        log_event("kodit.embedding", {"provider": "local"})
-        embedding_provider = LocalEmbeddingProvider(CODE)
-
-    if app_context.default_search.provider == "vectorchord":
-        log_event("kodit.database", {"provider": "vectorchord"})
-        return VectorChordVectorSearchService(task_name, session, embedding_provider)
-    if app_context.default_search.provider == "sqlite":
-        log_event("kodit.database", {"provider": "sqlite"})
-        if task_name == "code":
-            embedding_type = EmbeddingType.CODE
-        elif task_name == "text":
-            embedding_type = EmbeddingType.TEXT
-        return LocalVectorSearchService(
-            embedding_repository=embedding_repository,
-            embedding_provider=embedding_provider,
-            embedding_type=embedding_type,
-        )
-
-    msg = f"Invalid semantic search provider: {app_context.default_search.provider}"
-    raise ValueError(msg)

kodit/embedding/embedding_models.py

@@ -1,28 +0,0 @@
-"""Embedding models."""
-
-from enum import Enum
-
-from sqlalchemy import JSON, ForeignKey
-from sqlalchemy import Enum as SQLAlchemyEnum
-from sqlalchemy.orm import Mapped, mapped_column
-
-from kodit.database import Base, CommonMixin
-
-
-class EmbeddingType(Enum):
-    """Embedding type."""
-
-    CODE = 1
-    TEXT = 2
-
-
-class Embedding(Base, CommonMixin):
-    """Embedding model."""
-
-    __tablename__ = "embeddings"
-
-    snippet_id: Mapped[int] = mapped_column(ForeignKey("snippets.id"), index=True)
-    type: Mapped[EmbeddingType] = mapped_column(
-        SQLAlchemyEnum(EmbeddingType), index=True
-    )
-    embedding: Mapped[list[float]] = mapped_column(JSON)

kodit/embedding/embedding_provider/__init__.py

@@ -1 +0,0 @@
-"""Embedding module."""