kodit 0.1.10__py3-none-any.whl → 0.1.12__py3-none-any.whl

kodit/retreival/repository.py

@@ -1,183 +0,0 @@
-"""Repository for retrieving code snippets and search results.
-
-This module provides the RetrievalRepository class which handles all database operations
-related to searching and retrieving code snippets, including string-based searches
-and their associated file information.
-"""
-
-import math
-from typing import Any, TypeVar
-
-import pydantic
-from sqlalchemy import (
-    ColumnElement,
-    Float,
-    cast,
-    desc,
-    func,
-    literal,
-    select,
-)
-from sqlalchemy.ext.asyncio import AsyncSession
-from sqlalchemy.orm import Mapped
-
-from kodit.embedding.models import Embedding, EmbeddingType
-from kodit.indexing.models import Snippet
-from kodit.sources.models import File
-
-T = TypeVar("T")
-
-
-class RetrievalResult(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
-    score: float
-
-
-class RetrievalRepository:
-    """Repository for retrieving code snippets and search results.
-
-    This class provides methods for searching and retrieving code snippets from
-    the database, including string-based searches and their associated file information.
-    """
-
-    def __init__(self, session: AsyncSession) -> None:
-        """Initialize the retrieval repository.
-
-        Args:
-            session: The SQLAlchemy async session to use for database operations.
-
-        """
-        self.session = session
-
-    async def string_search(self, query: str) -> list[RetrievalResult]:
-        """Search for snippets containing the given query string.
-
-        This method performs a case-insensitive search for the query string within
-        snippet contents, returning up to 10 most recent matches.
-
-        Args:
-            query: The string to search for within snippet contents.
-
-        Returns:
-            A list of RetrievalResult objects containing the matching snippets
-            and their associated file paths.
-
-        """
-        search_query = (
-            select(Snippet, File)
-            .join(File, Snippet.file_id == File.id)
-            .where(Snippet.content.ilike(f"%{query}%"))
-            .limit(10)
-        )
-        rows = await self.session.execute(search_query)
-        results = list(rows.all())
-
-        return [
-            RetrievalResult(
-                id=snippet.id,
-                uri=file.uri,
-                content=snippet.content,
-                score=1.0,
-            )
-            for snippet, file in results
-        ]
-
-    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[RetrievalResult]:
-        """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: RetrievalResult(
-                id=snippet.id,
-                uri=file.uri,
-                content=snippet.content,
-                score=1.0,
-            )
-            for snippet, file in rows.all()
-        }
-
-        # Return results in the same order as input IDs
-        return [id_to_result[i] for i in ids]
-
-    async def list_semantic_results(
-        self, embedding_type: EmbeddingType, embedding: list[float], top_k: int = 10
-    ) -> list[tuple[int, float]]:
-        """List semantic results."""
-        cosine_similarity = cosine_similarity_json(Embedding.embedding, embedding)
-
-        query = (
-            select(Embedding, cosine_similarity)
-            .where(Embedding.type == embedding_type)
-            .order_by(desc(cosine_similarity))
-            .limit(top_k)
-        )
-        rows = await self.session.execute(query)
-        return [(embedding.snippet_id, distance) for embedding, distance in rows.all()]
-
-
-def cosine_similarity_json(
-    col: Mapped[Any], query_vec: list[float]
-) -> ColumnElement[Any]:
-    """Calculate the cosine similarity using pure sqlalchemy.
-
-    Works for a *fixed-length* vector stored as a JSON array in SQLite.
-    The calculation is done entirely in SQL using SQLite's JSON functions.
-
-    Args:
-        col: The column containing the JSON array of floats
-        query_vec: The query vector to compare against
-
-    Returns:
-        A SQLAlchemy expression that computes the cosine similarity
-
-    """
-    # Pre-compute query norm
-    q_norm = math.sqrt(sum(x * x for x in query_vec))
-
-    # Calculate dot product using JSON array functions
-    dot = sum(
-        cast(func.json_extract(col, f"$[{i}]"), Float) * literal(float(q))
-        for i, q in enumerate(query_vec)
-    )
-
-    # Calculate row norm on the fly
-    row_norm = func.sqrt(
-        sum(
-            cast(func.json_extract(col, f"$[{i}]"), Float)
-            * cast(func.json_extract(col, f"$[{i}]"), Float)
-            for i in range(len(query_vec))
-        )
-    )
-
-    # Calculate cosine similarity
-    return (dot / (row_norm * literal(q_norm))).label("cosine_similarity")

kodit-0.1.10.dist-info/RECORD

@@ -1,44 +0,0 @@
-kodit/.gitignore,sha256=ztkjgRwL9Uud1OEi36hGQeDGk3OLK1NfDEO8YqGYy8o,11
-kodit/__init__.py,sha256=aEKHYninUq1yh6jaNfvJBYg-6fenpN132nJt1UU6Jxs,59
-kodit/_version.py,sha256=HsFzfK6RsoG-sFr1kLh3t-q2dq2wNylFvX6VW_rx5vM,513
-kodit/app.py,sha256=Mr5BFHOHx5zppwjC4XPWVvHjwgl1yrKbUjTWXKubJQM,891
-kodit/cli.py,sha256=qEQy_Sd64cEV5KzYsKlGLyMxFQ4fFi-as4QO8CRrKYo,8978
-kodit/config.py,sha256=hQshTMW_8jpk94zP-1JaxowgmW_LrT534ipHFaRUGMw,3006
-kodit/database.py,sha256=kekSdyEATdb47jxzQemkSOXMNOwnUwmVVTpn9hYaDK8,2356
-kodit/log.py,sha256=PhyzQktEyyHaNr78W0wmL-RSRuq311DQ-d0l-EKTGmQ,5417
-kodit/mcp.py,sha256=qp16vRb0TY46-xQy179iWgYebr6Ju_Z91ZSzZnWPHuk,4771
-kodit/middleware.py,sha256=I6FOkqG9-8RH5kR1-0ZoQWfE4qLCB8lZYv8H_OCH29o,2714
-kodit/bm25/__init__.py,sha256=j8zyriNWhbwE5Lbybzg1hQAhANlU9mKHWw4beeUR6og,19
-kodit/bm25/bm25.py,sha256=NtlcLrgqJja11qDGKz_U6tuYWaS9sfbyS-TcA__rBKs,2284
-kodit/embedding/__init__.py,sha256=h9NXzDA1r-K23nvBajBV-RJzHJN0p3UJ7UQsmdnOoRw,24
-kodit/embedding/embedding.py,sha256=X2Fa-eXhQwp__QFj9yxIhvlCAiYVQSaZ2y18ZtG5_1Y,1810
-kodit/embedding/models.py,sha256=rN90vSs86dYiqoawcp8E9jtwY31JoJXYfaDlsJK7uqc,656
-kodit/indexing/__init__.py,sha256=cPyi2Iej3G1JFWlWr7X80_UrsMaTu5W5rBwgif1B3xo,75
-kodit/indexing/models.py,sha256=sZIhGwvL4Dw0QTWFxrjfWctSLkAoDT6fv5DlGz8-Fr8,1258
-kodit/indexing/repository.py,sha256=eIaIbqNs9Z3XTVymZ5Zl5uPWveqiEXNo0JTa-y-Tl24,5430
-kodit/indexing/service.py,sha256=hhQ_6vI7J7LnNgOLbsO4B07TOJvEePqqFviiqr3TL_M,6579
-kodit/migrations/README,sha256=ISVtAOvqvKk_5ThM5ioJE-lMkvf9IbknFUFVU_vPma4,58
-kodit/migrations/__init__.py,sha256=lP5MuwlyWRMO6UcDWnQcQ3G-GYHcFb6rl9gYPHJ1sjo,40
-kodit/migrations/env.py,sha256=bzB6vod_tO-X2F_G671FwYSAn0pyhNw8M1kG4MgidO8,2444
-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/__init__.py,sha256=9-lHzptItTzq_fomdIRBegQNm4Znx6pVjwD4MiqRIdo,36
-kodit/retreival/__init__.py,sha256=33PhJU-3gtsqYq6A1UkaLNKbev_Zee9Lq6dYC59-CsA,69
-kodit/retreival/repository.py,sha256=ZXHUYJrsmHCII9PUgYzLfN0EhiyWw7eJ3_rKCvMrSpY,5465
-kodit/retreival/service.py,sha256=gGp74jnqhyCDF5vKOrN2dJKDnhlfR4HZaxADSrjTb4s,3778
-kodit/snippets/__init__.py,sha256=-2coNoCRjTixU9KcP6alpmt7zqf37tCRWH3D7FPJ8dg,48
-kodit/snippets/method_snippets.py,sha256=EVHhSNWahAC5nSXv9fWVFJY2yq25goHdCSCuENC07F8,4145
-kodit/snippets/snippets.py,sha256=QumvhltWoxXw41SyKb-RbSvAr3m6V3lUy9n0AI8jcto,1409
-kodit/snippets/languages/__init__.py,sha256=Bj5KKZSls2MQ8ZY1S_nHg447MgGZW-2WZM-oq6vjwwA,1187
-kodit/snippets/languages/csharp.scm,sha256=gbBN4RiV1FBuTJF6orSnDFi8H9JwTw-d4piLJYsWUsc,222
-kodit/snippets/languages/python.scm,sha256=ee85R9PBzwye3IMTE7-iVoKWd_ViU3EJISTyrFGrVeo,429
-kodit/sources/__init__.py,sha256=1NTZyPdjThVQpZO1Mp1ColVsS7sqYanOVLqnoqV9Ipo,83
-kodit/sources/models.py,sha256=xb42CaNDO1CUB8SIW-xXMrB6Ji8cFw-yeJ550xBEg9Q,2398
-kodit/sources/repository.py,sha256=mGJrHWH6Uo8YABdoojHFbzaf_jW-2ywJpAHIa1gnc3U,3401
-kodit/sources/service.py,sha256=aV_qiqkU2kMBNPvye5_v4NnZiK-lJ64rQdmFtBtsQaY,9243
-kodit-0.1.10.dist-info/METADATA,sha256=wi-_Yl0ZPw898Mc1QjtvNQRl5-4xkdfBUlf6isC7Wr0,2288
-kodit-0.1.10.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-kodit-0.1.10.dist-info/entry_points.txt,sha256=hoTn-1aKyTItjnY91fnO-rV5uaWQLQ-Vi7V5et2IbHY,40
-kodit-0.1.10.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-kodit-0.1.10.dist-info/RECORD,,