kodit 0.1.15__py3-none-any.whl → 0.1.17__py3-none-any.whl

{kodit-0.1.15.dist-info → kodit-0.1.17.dist-info}/RECORD

@@ -1,12 +1,12 @@
 kodit/.gitignore,sha256=ztkjgRwL9Uud1OEi36hGQeDGk3OLK1NfDEO8YqGYy8o,11
 kodit/__init__.py,sha256=aEKHYninUq1yh6jaNfvJBYg-6fenpN132nJt1UU6Jxs,59
-kodit/_version.py,sha256=OX-WIjJlMaFvqRmCfLtOYEOYoiov9NdOA089N36rG-g,513
+kodit/_version.py,sha256=02_IA72k4pYar3Dp1g66WmynC3vl-jdmnf6lQF8QpE4,513
 kodit/app.py,sha256=Mr5BFHOHx5zppwjC4XPWVvHjwgl1yrKbUjTWXKubJQM,891
-kodit/cli.py,sha256=wAaMZQs-h6hyashWB3DBR2GIf496vfHmepcXhpa7-eM,8085
+kodit/cli.py,sha256=i7eEt0FdIQGEfXKFte-8fBcZZGE8BPXBp40aGwJDQGI,11323
 kodit/config.py,sha256=2W2u5J8j-Mbt-C4xzOuK-PeuDCx0S_rnCXPhBwvfLT4,4353
 kodit/database.py,sha256=WB1KpVxUYPgiJGU0gJa2hqytYB8wJEJ5z3WayhWzNMU,2403
 kodit/log.py,sha256=HU1OmuxO4FcVw61k4WW7Y4WM7BrDaeplw1PcBHhuIZY,5434
-kodit/mcp.py,sha256=HA3R7YG0Al1A6MjSCSIi0hEGXG3WP7tix-N5AROasCM,5278
+kodit/mcp.py,sha256=QruyPskWB0_x59pkfj5BBeXuR13GMny5TAZEa2j4U9s,5752
 kodit/middleware.py,sha256=I6FOkqG9-8RH5kR1-0ZoQWfE4qLCB8lZYv8H_OCH29o,2714
 kodit/bm25/__init__.py,sha256=j8zyriNWhbwE5Lbybzg1hQAhANlU9mKHWw4beeUR6og,19
 kodit/bm25/keyword_search_factory.py,sha256=rp-wx3DJsc2KlELK1V337EyeYvmwnMQwUqOo1WVPSmg,631
@@ -14,21 +14,29 @@ kodit/bm25/keyword_search_service.py,sha256=aBbWQKgQmi2re3EIHdXFS00n7Wj3b2D0pZsL
 kodit/bm25/local_bm25.py,sha256=AAbFhbQDqyL3d7jsPL7W4HsLxdoYctaDsREUXOLy6jM,3260
 kodit/bm25/vectorchord_bm25.py,sha256=_nGrkUReYLLV-L8RIuIVLwjuhSYZl9T532n5OVf0kWs,6393
 kodit/embedding/__init__.py,sha256=h9NXzDA1r-K23nvBajBV-RJzHJN0p3UJ7UQsmdnOoRw,24
-kodit/embedding/embedding_factory.py,sha256=qzoxBS3scR-ABd-u9215uGES7c6clYy2DiKcSDQivnA,1603
+kodit/embedding/embedding_factory.py,sha256=UGnFRyyQXazSUOwyW4Hg7Vq2-kfAoDj9lD4CTLu8x04,1630
 kodit/embedding/embedding_models.py,sha256=rN90vSs86dYiqoawcp8E9jtwY31JoJXYfaDlsJK7uqc,656
 kodit/embedding/embedding_repository.py,sha256=-ux3scpBzel8c0pMH9fNOEsSXFIzl-IfgaWrkTb1szo,6907
 kodit/embedding/local_vector_search_service.py,sha256=hkF0qlfzjyGt400qIX9Mr6B7b7i8WvYIYWN2Z2C_pcs,1907
 kodit/embedding/vector_search_service.py,sha256=pQJ129QjGrAWOXzqkywmgtDRpy8_gtzYgkivyqF9Vrs,1009
-kodit/embedding/vectorchord_vector_search_service.py,sha256=OsVeM3gpoT8Ihzh-kEIzBm3xh_a4D-sErPvsQSKCME8,4732
+kodit/embedding/vectorchord_vector_search_service.py,sha256=63Xf7_nAz3xWOwrmZibw8Q-xoRdCrPDDpdSA_WE7mrc,5131
 kodit/embedding/embedding_provider/__init__.py,sha256=h9NXzDA1r-K23nvBajBV-RJzHJN0p3UJ7UQsmdnOoRw,24
-kodit/embedding/embedding_provider/embedding_provider.py,sha256=NKs4nriup47R8xRciP07NE1-eZE9RPHklS7VH910UZ4,1537
+kodit/embedding/embedding_provider/embedding_provider.py,sha256=Tf3bwUsUMzAgoyLFM5qBtOLqPp1qr03TzrwGczkDvy0,1835
 kodit/embedding/embedding_provider/hash_embedding_provider.py,sha256=nAhlhh8j8PqqCCbhVl26Y8ntFBm2vJBCtB4X04g5Wwg,2638
 kodit/embedding/embedding_provider/local_embedding_provider.py,sha256=4ER-UPq506Y0TWU6qcs0nUqw6bSKQkSrdog-DhNQWM8,1906
-kodit/embedding/embedding_provider/openai_embedding_provider.py,sha256=bmUpegDgaF5Qj9uWcj1az4ADA2cKHUjraaMjGGPr83U,2076
+kodit/embedding/embedding_provider/openai_embedding_provider.py,sha256=V_jdUXiaGdslplwxMlfgFc4_hAVS2eaJXMTs2C7RiLI,2666
+kodit/enrichment/__init__.py,sha256=vBEolHpKaHUhfINX0dSGyAPlvgpLNAer9YzFtdvCB24,18
+kodit/enrichment/enrichment_factory.py,sha256=vKjkUTdhj74IW2S4GENDWdWMJx6BwUSZjJGDC0i7DSk,787
+kodit/enrichment/enrichment_service.py,sha256=87Sd3gGbEMJYb_wVrHG8L1yGIZmQNR7foUS4_y94azI,977
+kodit/enrichment/enrichment_provider/__init__.py,sha256=klf8iuLVWX4iRz-DZQauFFNAoJC5CByczh48TBZPW-o,27
+kodit/enrichment/enrichment_provider/enrichment_provider.py,sha256=E0H5rq3OENM0yYbA8K_3nSnj5lUHCpoIOqpWLo-2MVU,413
+kodit/enrichment/enrichment_provider/local_enrichment_provider.py,sha256=bR6HR1gH7wtZdMLOwaKdASjvllRo1FlNW9GyZC11zAM,2164
+kodit/enrichment/enrichment_provider/openai_enrichment_provider.py,sha256=gYuFTAeIVdQNlCUvNSPgRoiRwCvRD0C8419h8ubyABA,2725
 kodit/indexing/__init__.py,sha256=cPyi2Iej3G1JFWlWr7X80_UrsMaTu5W5rBwgif1B3xo,75
+kodit/indexing/fusion.py,sha256=TZb4fPAedXdEUXzwzOofW98QIOymdbclBOP1KOijuEk,1674
 kodit/indexing/indexing_models.py,sha256=6NX9HVcj6Pu9ePwHC7n-PWSyAgukpJq0nCNmUIigtbo,1282
-kodit/indexing/indexing_repository.py,sha256=4RJ3zY8p6QxHrYW7dDjru_w94Eu19v2gQ4mdlTgcXvY,6331
-kodit/indexing/indexing_service.py,sha256=T_dxOzNW_0OCpR4Fha1hHuNkmtLcDMZwL6t5xeu5VXQ,6613
+kodit/indexing/indexing_repository.py,sha256=dqOS0pxKM6bUjMXWqYukAK8XdiD36OnskFASgZRXRQM,6955
+kodit/indexing/indexing_service.py,sha256=_uhoqBic3_zXNJOsKt_w-TgX5ebf7OBwbqMdO9zectM,10779
 kodit/migrations/README,sha256=ISVtAOvqvKk_5ThM5ioJE-lMkvf9IbknFUFVU_vPma4,58
 kodit/migrations/__init__.py,sha256=lP5MuwlyWRMO6UcDWnQcQ3G-GYHcFb6rl9gYPHJ1sjo,40
 kodit/migrations/env.py,sha256=w1M7OZh-ZeR2dPHS0ByXAUxQjfZQ8xIzMseWuzLDTWw,2469
@@ -36,23 +44,22 @@ kodit/migrations/script.py.mako,sha256=zWziKtiwYKEWuwPV_HBNHwa9LCT45_bi01-uSNFaO
 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/__init__.py,sha256=9-lHzptItTzq_fomdIRBegQNm4Znx6pVjwD4MiqRIdo,36
-kodit/search/__init__.py,sha256=4QbdjbrlhNKMovmuKHxJnUeZT7KNjTTFU0GdnuwUHdQ,36
-kodit/search/search_repository.py,sha256=6q0k7JMTM_7hPK2TSA30CykGbc5N16kCL7HTjlbai0w,1563
-kodit/search/search_service.py,sha256=-XlbP_50e1dKFJ5jBvex5FjLnffW43LcwQV_SeYNFB0,3944
+kodit/migrations/versions/c3f5137d30f5_index_all_the_things.py,sha256=rI8LmjF-I2OMxZ2nOIF_NRmqOLXe45hL_iz_nx97DTQ,1680
 kodit/snippets/__init__.py,sha256=-2coNoCRjTixU9KcP6alpmt7zqf37tCRWH3D7FPJ8dg,48
 kodit/snippets/method_snippets.py,sha256=EVHhSNWahAC5nSXv9fWVFJY2yq25goHdCSCuENC07F8,4145
 kodit/snippets/snippets.py,sha256=mwN0bM1Msu8ZeEsUHyQ7tx3Hj3vZsm8G7Wu4eWSkLY8,1539
 kodit/snippets/languages/__init__.py,sha256=Bj5KKZSls2MQ8ZY1S_nHg447MgGZW-2WZM-oq6vjwwA,1187
 kodit/snippets/languages/csharp.scm,sha256=gbBN4RiV1FBuTJF6orSnDFi8H9JwTw-d4piLJYsWUsc,222
+kodit/snippets/languages/go.scm,sha256=SEX9mTOrhP2KiQW7oflDKkd21u5dK56QbJ4LvTDxY8A,533
 kodit/snippets/languages/python.scm,sha256=ee85R9PBzwye3IMTE7-iVoKWd_ViU3EJISTyrFGrVeo,429
 kodit/source/__init__.py,sha256=1NTZyPdjThVQpZO1Mp1ColVsS7sqYanOVLqnoqV9Ipo,83
-kodit/source/source_models.py,sha256=xb42CaNDO1CUB8SIW-xXMrB6Ji8cFw-yeJ550xBEg9Q,2398
+kodit/source/source_models.py,sha256=kcC59XPSDDMth2mOYK3FakqTN0jxKFaTDch0ejyD9Sw,2446
 kodit/source/source_repository.py,sha256=0EksMpoLzdkfe8S4eeCm4Sf7TuxsOzOzaF4BBsMYo-4,3163
 kodit/source/source_service.py,sha256=u_GaH07ewakThQJRfT8O_yZ54A52qLtJuM1bF3xUT2A,9633
 kodit/util/__init__.py,sha256=bPu6CtqDWCRGU7VgW2_aiQrCBi8G89FS6k1PjvDajJ0,37
 kodit/util/spinner.py,sha256=R9bzrHtBiIH6IfLbmsIVHL53s8vg-tqW4lwGGALu4dw,1932
-kodit-0.1.15.dist-info/METADATA,sha256=8E-bw8L-Df5Hdt16R5IWkyw7uUAr13CwYfcEyFExaPw,2380
-kodit-0.1.15.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kodit-0.1.15.dist-info/entry_points.txt,sha256=hoTn-1aKyTItjnY91fnO-rV5uaWQLQ-Vi7V5et2IbHY,40
-kodit-0.1.15.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-kodit-0.1.15.dist-info/RECORD,,
+kodit-0.1.17.dist-info/METADATA,sha256=MvKNOh3LfOOuviJBzZVqPaP0__Z-_DdoUzgfc2lUBFE,5822
+kodit-0.1.17.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+kodit-0.1.17.dist-info/entry_points.txt,sha256=hoTn-1aKyTItjnY91fnO-rV5uaWQLQ-Vi7V5et2IbHY,40
+kodit-0.1.17.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+kodit-0.1.17.dist-info/RECORD,,

kodit/search/__init__.py

@@ -1 +0,0 @@
-"""Search for relevant snippets."""

kodit/search/search_repository.py

@@ -1,57 +0,0 @@
-"""Repository for searching for relevant snippets."""
-
-from typing import TypeVar
-
-from sqlalchemy import (
-    select,
-)
-from sqlalchemy.ext.asyncio import AsyncSession
-
-from kodit.indexing.indexing_models import Snippet
-from kodit.source.source_models import File
-
-T = TypeVar("T")
-
-
-class SearchRepository:
-    """Repository for searching for relevant snippets."""
-
-    def __init__(self, session: AsyncSession) -> None:
-        """Initialize the search repository.
-
-        Args:
-            session: The SQLAlchemy async session to use for database operations.
-
-        """
-        self.session = session
-
-    async def list_snippet_ids(self) -> list[int]:
-        """List all snippet IDs.
-
-        Returns:
-            A list of all snippets.
-
-        """
-        query = select(Snippet.id)
-        rows = await self.session.execute(query)
-        return list(rows.scalars().all())
-
-    async def list_snippets_by_ids(self, ids: list[int]) -> list[tuple[File, Snippet]]:
-        """List snippets by IDs.
-
-        Returns:
-            A list of snippets in the same order as the input IDs.
-
-        """
-        query = (
-            select(Snippet, File)
-            .where(Snippet.id.in_(ids))
-            .join(File, Snippet.file_id == File.id)
-        )
-        rows = await self.session.execute(query)
-
-        # Create a dictionary for O(1) lookup of results by ID
-        id_to_result = {snippet.id: (file, snippet) for snippet, file in rows.all()}
-
-        # Return results in the same order as input IDs
-        return [id_to_result[i] for i in ids]

kodit/search/search_service.py

@@ -1,135 +0,0 @@
-"""Search service."""
-
-import pydantic
-import structlog
-
-from kodit.bm25.keyword_search_service import BM25Result, KeywordSearchProvider
-from kodit.embedding.vector_search_service import VectorSearchService
-from kodit.search.search_repository import SearchRepository
-
-
-class SearchRequest(pydantic.BaseModel):
-    """Request for a search."""
-
-    code_query: str | None = None
-    keywords: list[str] | None = None
-    top_k: int = 10
-
-
-class SearchResult(pydantic.BaseModel):
-    """Data transfer object for search results.
-
-    This model represents a single search result, containing both the file path
-    and the matching snippet content.
-    """
-
-    id: int
-    uri: str
-    content: str
-
-
-class Snippet(pydantic.BaseModel):
-    """Snippet model."""
-
-    content: str
-    file_path: str
-
-
-class SearchService:
-    """Service for searching for relevant data."""
-
-    def __init__(
-        self,
-        repository: SearchRepository,
-        keyword_search_provider: KeywordSearchProvider,
-        embedding_service: VectorSearchService,
-    ) -> None:
-        """Initialize the search service."""
-        self.repository = repository
-        self.log = structlog.get_logger(__name__)
-        self.keyword_search_provider = keyword_search_provider
-        self.code_embedding_service = embedding_service
-
-    async def search(self, request: SearchRequest) -> list[SearchResult]:
-        """Search for relevant data."""
-        fusion_list = []
-        if request.keywords:
-            # Gather results for each keyword
-            result_ids: list[BM25Result] = []
-            for keyword in request.keywords:
-                results = await self.keyword_search_provider.retrieve(
-                    keyword, request.top_k
-                )
-                result_ids.extend(results)
-
-            # Sort results by score
-            result_ids.sort(key=lambda x: x[1], reverse=True)
-
-            self.log.debug("Search results (BM25)", results=result_ids)
-
-            bm25_results = [x[0] for x in result_ids]
-            fusion_list.append(bm25_results)
-
-        # Compute embedding for semantic query
-        semantic_results = []
-        if request.code_query:
-            query_embedding = await self.code_embedding_service.retrieve(
-                request.code_query, top_k=request.top_k
-            )
-            semantic_results = [x.snippet_id for x in query_embedding]
-            fusion_list.append(semantic_results)
-
-        if len(fusion_list) == 0:
-            return []
-
-        # Combine all results together with RFF if required
-        final_results = reciprocal_rank_fusion(fusion_list, k=60)
-
-        # Extract ids from final results
-        final_ids = [x[0] for x in final_results]
-
-        # Get snippets from database (up to top_k)
-        search_results = await self.repository.list_snippets_by_ids(
-            final_ids[: request.top_k]
-        )
-
-        return [
-            SearchResult(
-                id=snippet.id,
-                uri=file.uri,
-                content=snippet.content,
-            )
-            for file, snippet in search_results
-        ]
-
-
-def reciprocal_rank_fusion(
-    rankings: list[list[int]], k: float = 60
-) -> list[tuple[int, float]]:
-    """RRF prioritises results that are present in all results.
-
-    Args:
-        rankings: List of rankers, each containing a list of document ids. Top of the
-        list is considered to be the best result.
-        k: Parameter for RRF.
-
-    Returns:
-        Dictionary of ids and their scores.
-
-    """
-    scores = {}
-    for ranker in rankings:
-        for rank in ranker:
-            scores[rank] = float(0)
-
-    for ranker in rankings:
-        for i, rank in enumerate(ranker):
-            scores[rank] += 1.0 / (k + i)
-
-    # Create a list of tuples of ids and their scores
-    results = [(rank, scores[rank]) for rank in scores]
-
-    # Sort results by score
-    results.sort(key=lambda x: x[1], reverse=True)
-
-    return results

kodit-0.1.15.dist-info/METADATA

@@ -1,89 +0,0 @@
-Metadata-Version: 2.4
-Name: kodit
-Version: 0.1.15
-Summary: Code indexing for better AI code generation
-Project-URL: Homepage, https://docs.helixml.tech/kodit/
-Project-URL: Documentation, https://docs.helixml.tech/kodit/
-Project-URL: Repository, https://github.com/helixml/kodit.git
-Project-URL: Issues, https://github.com/helixml/kodit/issues
-Project-URL: Changelog, https://github.com/helixml/kodit/releases
-Author-email: "Helix.ML" <founders@helix.ml>
-Maintainer-email: "Helix.ML" <founders@helix.ml>
-License-Expression: Apache-2.0
-License-File: LICENSE
-Keywords: ai,indexing,mcp,rag
-Classifier: Development Status :: 2 - Pre-Alpha
-Classifier: Intended Audience :: Developers
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Topic :: Software Development :: Code Generators
-Requires-Python: >=3.12
-Requires-Dist: aiofiles>=24.1.0
-Requires-Dist: aiosqlite>=0.20.0
-Requires-Dist: alembic>=1.15.2
-Requires-Dist: asgi-correlation-id>=4.3.4
-Requires-Dist: asyncpg>=0.30.0
-Requires-Dist: better-exceptions>=0.3.3
-Requires-Dist: bm25s[core]>=0.2.12
-Requires-Dist: click>=8.1.8
-Requires-Dist: colorama>=0.4.6
-Requires-Dist: dotenv>=0.9.9
-Requires-Dist: fastapi[standard]>=0.115.12
-Requires-Dist: fastmcp>=2.3.3
-Requires-Dist: gitpython>=3.1.44
-Requires-Dist: hf-xet>=1.1.2
-Requires-Dist: httpx-retries>=0.3.2
-Requires-Dist: httpx>=0.28.1
-Requires-Dist: openai>=1.82.0
-Requires-Dist: posthog>=4.0.1
-Requires-Dist: pydantic-settings>=2.9.1
-Requires-Dist: pytable-formatter>=0.1.1
-Requires-Dist: sentence-transformers>=4.1.0
-Requires-Dist: sqlalchemy[asyncio]>=2.0.40
-Requires-Dist: structlog>=25.3.0
-Requires-Dist: tdqm>=0.0.1
-Requires-Dist: tiktoken>=0.9.0
-Requires-Dist: tree-sitter-language-pack>=0.7.3
-Requires-Dist: tree-sitter>=0.24.0
-Requires-Dist: uritools>=5.0.0
-Description-Content-Type: text/markdown
-
-# kodit
-
-## Installation
-
-Please choose your preferred installation method. They all ultimately install the kodit
-cli, which contains the kodit MCP server and other tools to manage your data sources.
-
-### Docker
-
-```sh
-docker run -it --rm registry.helix.ml/helix/kodit:latest
-```
-
-Always replace latest with a specific version.
-
-### pipx
-
-```sh
-pipx install kodit
-```
-
-### homebrew
-
-```sh
-brew install helixml/kodit/kodit
-```
-
-### uv
-
-```sh
-uv tool install kodit
-```
-
-### pip
-
-Use this if you want to use kodit as a python library:
-
-```sh
-pip install kodit
-```