pgvector-template 0.5__tar.gz → 0.5.1__tar.gz

{pgvector_template-0.5 → pgvector_template-0.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pgvector-template
-Version: 0.5
+Version: 0.5.1
 Summary: Template library for flexible PGVector RAG implementations
 Author-email: DL <v49t9zpqd@mozmail.com>
 License: MIT
@@ -44,10 +44,12 @@ from pgvector_template.core.document import BaseDocument
 from sqlalchemy import create_engine
 from uuid import uuid4
 
+
 # 1. Define your document model
 class MyDocument(BaseDocument):
     __tablename__ = "my_documents"
 
+
 # 2. Set up database connection
 engine = create_engine("postgresql://user:pass@localhost/mydb")
 db_manager = DatabaseManager(engine)
@@ -151,6 +153,7 @@ db_manager = DatabaseManager(engine)
 
 # Option 2: From environment variable
 import os
+
 engine = create_engine(os.getenv("DATABASE_URL"))
 db_manager = DatabaseManager(engine)
 ```
@@ -185,10 +188,12 @@ DATABASE_URL=postgresql://user:password@localhost:5432/dev_db
 from pgvector_template.core.document import BaseDocument, BaseDocumentMetadata
 from pydantic import Field
 
+
 class MyDocumentMetadata(BaseDocumentMetadata):
     source_type: str = Field(..., description="Type of source document")
     author: str = Field(default="unknown", description="Document author")
 
+
 class MyDocument(BaseDocument):
     __tablename__ = "my_documents"
 ```
@@ -205,7 +210,7 @@ optional_props = BaseDocumentOptionalProps(
     title="Chapter 1: Introduction",
     collection="textbooks",
     language="en",
-    tags=["education", "intro"]
+    tags=["education", "intro"],
 )
 
 doc = MyDocument.from_props(
@@ -214,7 +219,7 @@ doc = MyDocument.from_props(
     content="This is the document content...",
     embedding=your_embedding_vector,  # list[float] with 1024 dimensions
     metadata=metadata.to_dict(),
-    optional_props=optional_props
+    optional_props=optional_props,
 )
 
 with db_manager.get_session() as session:
@@ -227,10 +232,7 @@ with db_manager.get_session() as session:
 # Basic similarity search
 with db_manager.get_session() as session:
     results = doc_manager.search_similar(
-        session=session,
-        document_cls=MyDocument,
-        query_embedding=query_vector,
-        limit=10
+        session=session, document_cls=MyDocument, query_embedding=query_vector, limit=10
     )
 
 # Search with filters
@@ -238,7 +240,7 @@ from pgvector_template.models.search import MetadataFilter
 
 filters = [
     MetadataFilter(key="source_type", value="pdf"),
-    MetadataFilter(key="author", value="John Doe")
+    MetadataFilter(key="author", value="John Doe"),
 ]
 
 results = doc_manager.search_similar(
@@ -247,7 +249,7 @@ results = doc_manager.search_similar(
     query_embedding=query_vector,
     limit=10,
     metadata_filters=filters,
-    collection="textbooks"
+    collection="textbooks",
 )
 ```
 
@@ -256,14 +258,10 @@ results = doc_manager.search_similar(
 ```python
 # Get all documents in a collection
 with db_manager.get_session() as session:
-    docs = doc_manager.get_documents_by_collection(
-        session, MyDocument, "textbooks"
-    )
+    docs = doc_manager.get_documents_by_collection(session, MyDocument, "textbooks")
 
-# Get all chunks from a corpus
-    corpus_docs = doc_manager.get_documents_by_corpus_id(
-        session, MyDocument, corpus_id
-    )
+    # Get all chunks from a corpus
+    corpus_docs = doc_manager.get_documents_by_corpus_id(session, MyDocument, corpus_id)
 ```
 
 ## Concept Reference

{pgvector_template-0.5 → pgvector_template-0.5.1}/README.md

@@ -14,10 +14,12 @@ from pgvector_template.core.document import BaseDocument
 from sqlalchemy import create_engine
 from uuid import uuid4
 
+
 # 1. Define your document model
 class MyDocument(BaseDocument):
     __tablename__ = "my_documents"
 
+
 # 2. Set up database connection
 engine = create_engine("postgresql://user:pass@localhost/mydb")
 db_manager = DatabaseManager(engine)
@@ -121,6 +123,7 @@ db_manager = DatabaseManager(engine)
 
 # Option 2: From environment variable
 import os
+
 engine = create_engine(os.getenv("DATABASE_URL"))
 db_manager = DatabaseManager(engine)
 ```
@@ -155,10 +158,12 @@ DATABASE_URL=postgresql://user:password@localhost:5432/dev_db
 from pgvector_template.core.document import BaseDocument, BaseDocumentMetadata
 from pydantic import Field
 
+
 class MyDocumentMetadata(BaseDocumentMetadata):
     source_type: str = Field(..., description="Type of source document")
     author: str = Field(default="unknown", description="Document author")
 
+
 class MyDocument(BaseDocument):
     __tablename__ = "my_documents"
 ```
@@ -175,7 +180,7 @@ optional_props = BaseDocumentOptionalProps(
     title="Chapter 1: Introduction",
     collection="textbooks",
     language="en",
-    tags=["education", "intro"]
+    tags=["education", "intro"],
 )
 
 doc = MyDocument.from_props(
@@ -184,7 +189,7 @@ doc = MyDocument.from_props(
     content="This is the document content...",
     embedding=your_embedding_vector,  # list[float] with 1024 dimensions
     metadata=metadata.to_dict(),
-    optional_props=optional_props
+    optional_props=optional_props,
 )
 
 with db_manager.get_session() as session:
@@ -197,10 +202,7 @@ with db_manager.get_session() as session:
 # Basic similarity search
 with db_manager.get_session() as session:
     results = doc_manager.search_similar(
-        session=session,
-        document_cls=MyDocument,
-        query_embedding=query_vector,
-        limit=10
+        session=session, document_cls=MyDocument, query_embedding=query_vector, limit=10
     )
 
 # Search with filters
@@ -208,7 +210,7 @@ from pgvector_template.models.search import MetadataFilter
 
 filters = [
     MetadataFilter(key="source_type", value="pdf"),
-    MetadataFilter(key="author", value="John Doe")
+    MetadataFilter(key="author", value="John Doe"),
 ]
 
 results = doc_manager.search_similar(
@@ -217,7 +219,7 @@ results = doc_manager.search_similar(
     query_embedding=query_vector,
     limit=10,
     metadata_filters=filters,
-    collection="textbooks"
+    collection="textbooks",
 )
 ```
 
@@ -226,14 +228,10 @@ results = doc_manager.search_similar(
 ```python
 # Get all documents in a collection
 with db_manager.get_session() as session:
-    docs = doc_manager.get_documents_by_collection(
-        session, MyDocument, "textbooks"
-    )
+    docs = doc_manager.get_documents_by_collection(session, MyDocument, "textbooks")
 
-# Get all chunks from a corpus
-    corpus_docs = doc_manager.get_documents_by_corpus_id(
-        session, MyDocument, corpus_id
-    )
+    # Get all chunks from a corpus
+    corpus_docs = doc_manager.get_documents_by_corpus_id(session, MyDocument, corpus_id)
 ```
 
 ## Concept Reference

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/core/__init__.py

@@ -5,21 +5,16 @@ from pgvector_template.core.document import (
 )
 from pgvector_template.core.embedder import BaseEmbeddingProvider
 from pgvector_template.core.manager import BaseCorpusManager, BaseCorpusManagerConfig, Corpus
-from pgvector_template.core.search import BaseSearchClientConfig, BaseSearchClient
-
+from pgvector_template.core.search import BaseSearchClient, BaseSearchClientConfig
 
 __all__ = [
-    ### document
-    "BaseDocumentOptionalProps",
+    "BaseCorpusManager",
+    "BaseCorpusManagerConfig",
     "BaseDocument",
     "BaseDocumentMetadata",
-    "Corpus",
-    ### embedder
+    "BaseDocumentOptionalProps",
     "BaseEmbeddingProvider",
-    ### manager
-    "BaseCorpusManager",
-    "BaseCorpusManagerConfig",
-    ### search
-    "BaseSearchClientConfig",
     "BaseSearchClient",
+    "BaseSearchClientConfig",
+    "Corpus",
 ]

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/core/document.py

@@ -1,21 +1,22 @@
-from datetime import datetime, timezone
-from typing import Any, Type, TypeVar
-from uuid import uuid4, UUID as UuidLiteral
+from datetime import UTC, datetime
+from typing import Any, Self
+from uuid import UUID as UuidLiteral
+from uuid import uuid4
 
+from pgvector.sqlalchemy import Vector
 from pydantic import BaseModel, Field
 from sqlalchemy import (
+    Boolean,
     Column,
-    String,
-    Text,
     DateTime,
-    Boolean,
-    Integer,
     Index,
+    Integer,
+    String,
+    Text,
     UniqueConstraint,
 )
+from sqlalchemy.dialects.postgresql import JSONB, UUID
 from sqlalchemy.orm import declarative_base
-from sqlalchemy.dialects.postgresql import UUID, JSONB
-from pgvector.sqlalchemy import Vector
 
 Base = declarative_base()
 
@@ -33,9 +34,6 @@ class BaseDocumentOptionalProps(BaseModel):
     """Language of the content (ISO 639-1 code), e.g., 'en', 'es', 'zh'"""
 
 
-T = TypeVar("T", bound="BaseDocument")
-
-
 class BaseDocument(Base):
     """
     Template table for Documents, that works for all collection types.
@@ -89,11 +87,11 @@ class BaseDocument(Base):
     """
 
     # Audit fields
-    created_at = Column(DateTime(timezone=True), default=lambda: datetime.now(timezone.utc))
+    created_at = Column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
     updated_at = Column(
         DateTime(timezone=True),
-        default=lambda: datetime.now(timezone.utc),
-        onupdate=lambda: datetime.now(timezone.utc),
+        default=lambda: datetime.now(UTC),
+        onupdate=lambda: datetime.now(UTC),
     )
     is_deleted = Column(Boolean, default=False, index=True)
     """Entries can be logically marked for deletion before they are permanently deleted."""
@@ -131,7 +129,7 @@ class BaseDocument(Base):
 
     @classmethod
     def from_props(
-        cls: Type[T],
+        cls,
         corpus_id: UuidLiteral | str,
         chunk_index: int,
         content: str,
@@ -139,7 +137,7 @@ class BaseDocument(Base):
         embedding_config: dict[str, Any] | None = None,
         metadata: dict[str, Any] | None = None,
         optional_props: BaseDocumentOptionalProps | None = None,
-    ) -> T:
+    ) -> Self:
         """
         Create a BaseDocument instance from mandatory and optional properties.
 

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/core/manager.py

@@ -1,7 +1,7 @@
 from abc import ABC
 from dataclasses import dataclass
 from logging import getLogger
-from typing import Any, Type
+from typing import Any
 from uuid import UUID, uuid4
 
 from pydantic import BaseModel, Field
@@ -14,18 +14,17 @@ from pgvector_template.core.document import (
 )
 from pgvector_template.core.embedder import BaseEmbeddingProvider
 
-
 logger = getLogger(__name__)
 
 
 class BaseCorpusManagerConfig(BaseModel):
     """Base configuration for `Corpus` & `Document` management operations"""
 
-    document_cls: Type[BaseDocument] = Field(...)
+    document_cls: type[BaseDocument] = Field(...)
     """Document class **type** (not an instance). Must be subclass of `BaseDocument`."""
     embedding_provider: BaseEmbeddingProvider | None = Field(default=None)
     """Instance of `BaseEmbeddingProvider` child class. Acts as embedding provider for insert operations."""
-    document_metadata_cls: Type[BaseDocumentMetadata] = Field(default=BaseDocumentMetadata)
+    document_metadata_cls: type[BaseDocumentMetadata] = Field(default=BaseDocumentMetadata)
     """Document metadata class **type** (not an instance). Must be subclass of BaseDocumentMetadata."""
 
     model_config = {"arbitrary_types_allowed": True}
@@ -59,7 +58,7 @@ class BaseCorpusManager(ABC):
         return self._cfg
 
     @property
-    def document_metadata_class(self) -> Type[BaseDocumentMetadata]:
+    def document_metadata_class(self) -> type[BaseDocumentMetadata]:
         """Returns the document metadata class, raising an error if it's not set."""
         return self.config.document_metadata_cls
 
@@ -88,7 +87,7 @@ class BaseCorpusManager(ABC):
             self.session.query(self.config.document_cls)
             .filter(
                 self.config.document_cls.corpus_id == corpus_id,
-                self.config.document_cls.is_deleted == False,  # noqa: E712
+                self.config.document_cls.is_deleted == False,
             )
             .order_by(self.config.document_cls.chunk_index)
             .all()

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/core/search.py

@@ -1,31 +1,31 @@
+from collections.abc import Sequence
 from logging import getLogger
-from typing import Any, Type, Sequence
+from typing import Any
 
 from pydantic import BaseModel, Field
-from sqlalchemy import select, or_, Integer, Float
+from sqlalchemy import Float, Integer, or_, select
 from sqlalchemy.orm import Session
-from sqlalchemy.sql import Select, ColumnElement
+from sqlalchemy.sql import ColumnElement, Select
 
 from pgvector_template.core import (
-    BaseEmbeddingProvider,
     BaseDocument,
     BaseDocumentMetadata,
+    BaseEmbeddingProvider,
 )
-from pgvector_template.models.search import SearchQuery, MetadataFilter, RetrievalResult
+from pgvector_template.models.search import MetadataFilter, RetrievalResult, SearchQuery
 from pgvector_template.utils.metadata_filter import validate_metadata_filters
 
-
 logger = getLogger(__name__)
 
 
 class BaseSearchClientConfig(BaseModel):
     """Config obj for `BaseSearchClient`."""
 
-    document_cls: Type[BaseDocument] = Field(default=BaseDocument)
+    document_cls: type[BaseDocument] = Field(default=BaseDocument)
     """Document class **type** (not an instance). Must be subclass of `BaseDocument`."""
     embedding_provider: BaseEmbeddingProvider | None = Field(default=None)
     """Instance of `BaseEmbeddingProvider` child class. Acts as embedding provider for semantic search."""
-    document_metadata_cls: Type[BaseDocumentMetadata] = Field(default=BaseDocumentMetadata)
+    document_metadata_cls: type[BaseDocumentMetadata] = Field(default=BaseDocumentMetadata)
     """Document metadata class type. Used for metadata search operations."""
 
     model_config = {"arbitrary_types_allowed": True}
@@ -39,7 +39,7 @@ class BaseSearchClient:
         return self._cfg
 
     @property
-    def document_metadata_class(self) -> Type[BaseDocumentMetadata]:
+    def document_metadata_class(self) -> type[BaseDocumentMetadata]:
         """Returns the document metadata class, raising an error if it's not set."""
         return self.config.document_metadata_cls
 

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/db/connection.py

@@ -1,10 +1,10 @@
+from collections.abc import Generator
 from contextlib import contextmanager
 from logging import getLogger
-from typing import Generator, Type
 
 from sqlalchemy import Engine, create_engine, text
-from sqlalchemy.orm import sessionmaker, Session
 from sqlalchemy.ext.declarative import DeclarativeMeta
+from sqlalchemy.orm import Session, sessionmaker
 
 
 class DatabaseManager:
@@ -40,7 +40,7 @@ class DatabaseManager:
 
         self.logger.info(f"Created schema: {schema_name}")
 
-    def create_tables(self, base_class: Type[DeclarativeMeta], schema_name: str) -> None:
+    def create_tables(self, base_class: type[DeclarativeMeta], schema_name: str) -> None:
         """Create tables for a specific schema"""
         # Ensure all tables in this base class use the specified schema
         for table in base_class.metadata.tables.values():

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/db/document_db.py

@@ -1,5 +1,3 @@
-from typing import List, Type
-
 from sqlalchemy import text
 
 from pgvector_template.core.document import BaseDocument
@@ -24,7 +22,7 @@ class DocumentDatabaseManager(DatabaseManager):
     SCHEMA_PREFIX = "knowledge_base_"
 
     def __init__(
-        self, database_url: str, schema_suffix: str, document_classes: List[Type[BaseDocument]]
+        self, database_url: str, schema_suffix: str, document_classes: list[type[BaseDocument]]
     ):
         """
         Initialize a document-oriented database manager

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/models/__init__.py

@@ -1,5 +1,9 @@
 from pgvector_template.models.search import (
     MetadataFilter as MetadataFilter,
+)
+from pgvector_template.models.search import (
     RetrievalResult as RetrievalResult,
+)
+from pgvector_template.models.search import (
     SearchQuery as SearchQuery,
 )

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/models/search.py

@@ -1,4 +1,4 @@
-from dataclasses import dataclass, asdict
+from dataclasses import asdict, dataclass
 from typing import Any, Literal
 
 from pydantic import BaseModel, ConfigDict, Field, model_validator

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/service/document_service.py

@@ -3,7 +3,7 @@ Document service layer combining corpus management and search capabilities.
 """
 
 from logging import getLogger
-from typing import Generic, Type, TypeVar
+from typing import Generic, TypeVar
 
 from pydantic import BaseModel, Field
 from sqlalchemy.orm import Session
@@ -23,17 +23,17 @@ class DocumentServiceConfig(BaseModel):
     """Configuration for DocumentService"""
 
     # Required fields
-    document_cls: Type[BaseDocument] = Field(...)
+    document_cls: type[BaseDocument] = Field(...)
     """Document class **type** (not an instance). Must be subclass of `BaseDocument`."""
-    corpus_manager_cls: Type[BaseCorpusManager] = Field(default=BaseCorpusManager)
+    corpus_manager_cls: type[BaseCorpusManager] = Field(default=BaseCorpusManager)
     """CorpusManager class **type** (not an instance). Must be child of `BaseCorpusManager`."""
-    search_client_cls: Type[BaseSearchClient] = Field(default=BaseSearchClient)
+    search_client_cls: type[BaseSearchClient] = Field(default=BaseSearchClient)
     """SearchClient class **type** (not an instance). Must be child of `BaseSearchClient`."""
 
     # Optional fields with defaults
     embedding_provider: BaseEmbeddingProvider | None = Field(default=None)
     """Embedding provider for insert & vector-search operations."""
-    document_metadata_cls: Type[BaseDocumentMetadata] = Field(default=BaseDocumentMetadata)
+    document_metadata_cls: type[BaseDocumentMetadata] = Field(default=BaseDocumentMetadata)
     """Document metadata schema. Must be child of `BaseDocumentMetadata`."""
     corpus_manager_cfg: BaseCorpusManagerConfig = Field(
         default=BaseCorpusManagerConfig(document_cls=BaseDocument)

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template/utils/metadata_filter.py

@@ -1,11 +1,9 @@
-from typing import Type
-
 from pgvector_template.core.document import BaseDocumentMetadata
 from pgvector_template.models.search import MetadataFilter
 
 
 def validate_metadata_filters(
-    filter_obj_list: list[MetadataFilter], metadata_cls: Type[BaseDocumentMetadata]
+    filter_obj_list: list[MetadataFilter], metadata_cls: type[BaseDocumentMetadata]
 ) -> None:
     """Validate a `list[MetadataFilter]` against schema and condition compatibility.
 
@@ -18,7 +16,7 @@ def validate_metadata_filters(
 
 
 def validate_metadata_filter(
-    filter_obj: MetadataFilter, metadata_cls: Type[BaseDocumentMetadata]
+    filter_obj: MetadataFilter, metadata_cls: type[BaseDocumentMetadata]
 ) -> None:
     """Validate metadata filter against schema and condition compatibility.
 
@@ -57,7 +55,7 @@ def validate_metadata_filter(
     validate_condition_compatibility(field_type, filter_obj.condition)
 
 
-def validate_condition_compatibility(field_type: Type, condition: str) -> None:
+def validate_condition_compatibility(field_type: type, condition: str) -> None:
     """Validate that condition is compatible with field type."""
     # Extract base type from Optional/Union types
     origin = getattr(field_type, "__origin__", None)
@@ -66,7 +64,7 @@ def validate_condition_compatibility(field_type: Type, condition: str) -> None:
         if origin is list:
             field_type = list
         elif len(args) > 0:
-            field_type = args[0]  # ty: ignore[index-out-of-bounds]
+            field_type = args[0]
 
     valid_conditions: dict[type, set[str]] = {
         str: {"eq", "gt", "gte", "lt", "lte", "in", "exists"},

{pgvector_template-0.5 → pgvector_template-0.5.1}/pgvector_template.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pgvector-template
-Version: 0.5
+Version: 0.5.1
 Summary: Template library for flexible PGVector RAG implementations
 Author-email: DL <v49t9zpqd@mozmail.com>
 License: MIT
@@ -44,10 +44,12 @@ from pgvector_template.core.document import BaseDocument
 from sqlalchemy import create_engine
 from uuid import uuid4
 
+
 # 1. Define your document model
 class MyDocument(BaseDocument):
     __tablename__ = "my_documents"
 
+
 # 2. Set up database connection
 engine = create_engine("postgresql://user:pass@localhost/mydb")
 db_manager = DatabaseManager(engine)
@@ -151,6 +153,7 @@ db_manager = DatabaseManager(engine)
 
 # Option 2: From environment variable
 import os
+
 engine = create_engine(os.getenv("DATABASE_URL"))
 db_manager = DatabaseManager(engine)
 ```
@@ -185,10 +188,12 @@ DATABASE_URL=postgresql://user:password@localhost:5432/dev_db
 from pgvector_template.core.document import BaseDocument, BaseDocumentMetadata
 from pydantic import Field
 
+
 class MyDocumentMetadata(BaseDocumentMetadata):
     source_type: str = Field(..., description="Type of source document")
     author: str = Field(default="unknown", description="Document author")
 
+
 class MyDocument(BaseDocument):
     __tablename__ = "my_documents"
 ```
@@ -205,7 +210,7 @@ optional_props = BaseDocumentOptionalProps(
     title="Chapter 1: Introduction",
     collection="textbooks",
     language="en",
-    tags=["education", "intro"]
+    tags=["education", "intro"],
 )
 
 doc = MyDocument.from_props(
@@ -214,7 +219,7 @@ doc = MyDocument.from_props(
     content="This is the document content...",
     embedding=your_embedding_vector,  # list[float] with 1024 dimensions
     metadata=metadata.to_dict(),
-    optional_props=optional_props
+    optional_props=optional_props,
 )
 
 with db_manager.get_session() as session:
@@ -227,10 +232,7 @@ with db_manager.get_session() as session:
 # Basic similarity search
 with db_manager.get_session() as session:
     results = doc_manager.search_similar(
-        session=session,
-        document_cls=MyDocument,
-        query_embedding=query_vector,
-        limit=10
+        session=session, document_cls=MyDocument, query_embedding=query_vector, limit=10
     )
 
 # Search with filters
@@ -238,7 +240,7 @@ from pgvector_template.models.search import MetadataFilter
 
 filters = [
     MetadataFilter(key="source_type", value="pdf"),
-    MetadataFilter(key="author", value="John Doe")
+    MetadataFilter(key="author", value="John Doe"),
 ]
 
 results = doc_manager.search_similar(
@@ -247,7 +249,7 @@ results = doc_manager.search_similar(
     query_embedding=query_vector,
     limit=10,
     metadata_filters=filters,
-    collection="textbooks"
+    collection="textbooks",
 )
 ```
 
@@ -256,14 +258,10 @@ results = doc_manager.search_similar(
 ```python
 # Get all documents in a collection
 with db_manager.get_session() as session:
-    docs = doc_manager.get_documents_by_collection(
-        session, MyDocument, "textbooks"
-    )
+    docs = doc_manager.get_documents_by_collection(session, MyDocument, "textbooks")
 
-# Get all chunks from a corpus
-    corpus_docs = doc_manager.get_documents_by_corpus_id(
-        session, MyDocument, corpus_id
-    )
+    # Get all chunks from a corpus
+    corpus_docs = doc_manager.get_documents_by_corpus_id(session, MyDocument, corpus_id)
 ```
 
 ## Concept Reference

{pgvector_template-0.5 → pgvector_template-0.5.1}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pgvector-template"
-version = "0.5"
+version = "0.5.1"
 description = "Template library for flexible PGVector RAG implementations"
 authors = [{ name="DL", email="v49t9zpqd@mozmail.com" }]
 license = { text = "MIT" }