cocoindex 0.1.39__cp312-cp312-macosx_11_0_arm64.whl → 0.1.41__cp312-cp312-macosx_11_0_arm64.whl

cocoindex/__init__.py

@@ -1,15 +1,16 @@
 """
 Cocoindex is a framework for building and running indexing pipelines.
 """
-from . import functions, query, sources, storages, cli
-from .flow import FlowBuilder, DataScope, DataSlice, Flow, flow_def, transform_flow
+from . import functions, query, sources, storages, cli, utils
+
+from .auth_registry import AuthEntryReference, add_auth_entry, ref_auth_entry
+from .flow import FlowBuilder, DataScope, DataSlice, Flow, transform_flow
+from .flow import flow_def, flow_def as flow
 from .flow import EvaluateAndDumpOptions, GeneratedField
 from .flow import update_all_flows_async, FlowLiveUpdater, FlowLiveUpdaterOptions
+from .lib import init, start_server, stop, main_fn
 from .llm import LlmSpec, LlmApiType
 from .index import VectorSimilarityMetric, VectorIndexDef, IndexOptions
-from .auth_registry import AuthEntryReference, add_auth_entry, ref_auth_entry
-from .lib import *
 from .setting import DatabaseConnectionSpec, Settings, ServerSettings
 from .setting import get_app_namespace
-from ._engine import OpArgSchema
 from .typing import Float32, Float64, LocalDateTime, OffsetDateTime, Range, Vector, Json

cocoindex/flow.py

@@ -310,9 +310,8 @@ class _FlowBuilderState:
     engine_flow_builder: _engine.FlowBuilder
     field_name_builder: _NameBuilder
 
-    def __init__(self, /, name: str | None = None):
-        flow_name = _flow_name_builder.build_name(name, prefix="_flow_")
-        self.engine_flow_builder = _engine.FlowBuilder(get_full_flow_name(flow_name))
+    def __init__(self, full_name: str):
+        self.engine_flow_builder = _engine.FlowBuilder(full_name)
         self.field_name_builder = _NameBuilder()
 
     def get_data_slice(self, v: Any) -> _engine.DataSlice:
@@ -464,9 +463,13 @@ class Flow:
     """
     A flow describes an indexing pipeline.
     """
+    _name: str
+    _full_name: str
     _lazy_engine_flow: Callable[[], _engine.Flow]
 
-    def __init__(self, engine_flow_creator: Callable[[], _engine.Flow]):
+    def __init__(self, name: str, full_name: str, engine_flow_creator: Callable[[], _engine.Flow]):
+        self._name = name
+        self._full_name = full_name
         engine_flow = None
         lock = Lock()
         def _lazy_engine_flow() -> _engine.Flow:
@@ -497,7 +500,7 @@ class Flow:
             tree.children.append(section_node)
         return tree
 
-    def _get_spec(self, verbose: bool = False) -> list[tuple[str, str, int]]:
+    def _get_spec(self, verbose: bool = False) -> _engine.RenderedSpec:
         return self._lazy_engine_flow().get_spec(output_mode="verbose" if verbose else "concise")
     
     def _get_schema(self) -> list[tuple[str, str, str]]:
@@ -509,12 +512,19 @@ class Flow:
     def __repr__(self):
         return repr(self._lazy_engine_flow())
 
+    @property
+    def name(self) -> str:
+        """
+        Get the name of the flow.
+        """
+        return self._name
+
     @property
     def full_name(self) -> str:
         """
         Get the full name of the flow.
         """
-        return self._lazy_engine_flow().name()
+        return self._full_name
 
     def update(self) -> _engine.IndexUpdateInfo:
         """
@@ -555,14 +565,16 @@ def _create_lazy_flow(name: str | None, fl_def: Callable[[FlowBuilder, DataScope
     Create a flow without really building it yet.
     The flow will be built the first time when it's really needed.
     """
+    flow_name = _flow_name_builder.build_name(name, prefix="_flow_")
+    flow_full_name = get_full_flow_name(flow_name)
     def _create_engine_flow() -> _engine.Flow:
-        flow_builder_state = _FlowBuilderState(name=name)
+        flow_builder_state = _FlowBuilderState(flow_full_name)
         root_scope = DataScope(
             flow_builder_state, flow_builder_state.engine_flow_builder.root_scope())
         fl_def(FlowBuilder(flow_builder_state), root_scope)
         return flow_builder_state.engine_flow_builder.build_flow(execution_context.event_loop)
 
-    return Flow(_create_engine_flow)
+    return Flow(flow_name, flow_full_name, _create_engine_flow)
 
 
 _flows_lock = Lock()
@@ -695,7 +707,7 @@ class TransformFlow(Generic[T]):
             return self._lazy_flow_info
 
     async def _build_flow_info_async(self) -> TransformFlowInfo:
-        flow_builder_state = _FlowBuilderState(name=self._flow_name)
+        flow_builder_state = _FlowBuilderState(self._flow_name)
         sig = inspect.signature(self._flow_fn)
         if len(sig.parameters) != len(self._flow_arg_types):
             raise ValueError(
@@ -706,9 +718,11 @@ class TransformFlow(Generic[T]):
         for (param_name, param), param_type in zip(sig.parameters.items(), self._flow_arg_types):
             if param.kind not in (inspect.Parameter.POSITIONAL_OR_KEYWORD,
                                   inspect.Parameter.KEYWORD_ONLY):
-                raise ValueError(f"Parameter {param_name} is not a parameter can be passed by name")
-            engine_ds = flow_builder_state.engine_flow_builder.add_direct_input(
-                param_name, encode_enriched_type(param_type))
+                raise ValueError(f"Parameter `{param_name}` is not a parameter can be passed by name")
+            encoded_type = encode_enriched_type(param_type)
+            if encoded_type is None:
+                raise ValueError(f"Parameter `{param_name}` has no type annotation")
+            engine_ds = flow_builder_state.engine_flow_builder.add_direct_input(param_name, encoded_type)
             kwargs[param_name] = DataSlice(_DataSliceState(flow_builder_state, engine_ds))
 
         output = self._flow_fn(**kwargs)
@@ -768,8 +782,13 @@ def transform_flow() -> Callable[[Callable[..., DataSlice[T]]], TransformFlow[T]
         for (param_name, param) in sig.parameters.items():
             if param.kind not in (inspect.Parameter.POSITIONAL_OR_KEYWORD,
                                   inspect.Parameter.KEYWORD_ONLY):
-                raise ValueError(f"Parameter {param_name} is not a parameter can be passed by name")
-            arg_types.append(_get_data_slice_annotation_type(param.annotation))
+                raise ValueError(f"Parameter `{param_name}` is not a parameter can be passed by name")
+            value_type_annotation = _get_data_slice_annotation_type(param.annotation)
+            if value_type_annotation is None:
+                raise ValueError(
+                    f"Parameter `{param_name}` for {fn} has no value type annotation. "
+                    "Please use `cocoindex.DataSlice[T]` where T is the type of the value.")
+            arg_types.append(value_type_annotation)
 
         _transform_flow = TransformFlow(fn, arg_types)
         functools.update_wrapper(_transform_flow, fn)

cocoindex/utils.py

@@ -0,0 +1,9 @@
+from .flow import Flow
+from .setting import get_app_namespace
+
+def get_target_storage_default_name(flow: Flow, target_name: str, delimiter: str = "__") -> str:
+    """
+    Get the default name for a target.
+    It's used as the underlying storage name (e.g. a table, a collection, etc.) followed by most storage backends, if not explicitly specified.
+    """
+    return get_app_namespace(trailing_delimiter=delimiter) + flow.name + delimiter + target_name

{cocoindex-0.1.39.dist-info → cocoindex-0.1.41.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cocoindex
-Version: 0.1.39
+Version: 0.1.41
 Requires-Dist: sentence-transformers>=3.3.1
 Requires-Dist: click>=8.1.8
 Requires-Dist: rich>=14.0.0
@@ -153,7 +153,7 @@ It defines an index flow like this:
 | [Docs to Knowledge Graph](examples/docs_to_knowledge_graph) | Extract relationships from Markdown documents and build a knowledge graph |
 | [Embeddings to Qdrant](examples/text_embedding_qdrant) | Index documents in a Qdrant collection for semantic search |
 | [FastAPI Server with Docker](examples/fastapi_server_docker) | Run the semantic search server in a Dockerized FastAPI setup | 
-| [Product_Taxonomy_Knowledge_Graph](examples/product_taxonomy_knowledge_graph) | Build knowledge graph for product recommendations | 
+| [Product Recommendation](examples/product_recommendation) | Build real-time product recommendations with LLM and graph database| 
 | [Image Search with Vision API](examples/image_search_example) | Generates detailed captions for images using a vision model, embeds them, enables live-updating semantic search via FastAPI and served on a React frontend|
 
 More coming and stay tuned 👀!

{cocoindex-0.1.39.dist-info → cocoindex-0.1.41.dist-info}/RECORD

@@ -1,12 +1,12 @@
-cocoindex-0.1.39.dist-info/METADATA,sha256=eTJ6EcBVU9sRefo_tDR3TGMBWlsVlMOmlL5UxVuzLgY,9793
-cocoindex-0.1.39.dist-info/WHEEL,sha256=ryp1uXCltaq3TPfjxhSWoam4EHMC40-Yabw-yvEW9gU,104
-cocoindex-0.1.39.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-cocoindex/__init__.py,sha256=OP1mmYR7pcJpAtCeHuEjNh2zyJnOe4OsAs9B7qqWCC8,792
-cocoindex/_engine.cpython-312-darwin.so,sha256=INjqvC4TDjTSUfaIOSZygs5nFddN7B9qgvBhgd9Bqn0,56853152
+cocoindex-0.1.41.dist-info/METADATA,sha256=_wnwGo7A-7PLOp6HuG18kFtC-ld4QEP4RtKwVEWdpQ4,9790
+cocoindex-0.1.41.dist-info/WHEEL,sha256=ryp1uXCltaq3TPfjxhSWoam4EHMC40-Yabw-yvEW9gU,104
+cocoindex-0.1.41.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+cocoindex/__init__.py,sha256=0iO3lM8w35zhVDPsvCGBAXwUQZsCWRRqjt2wFdtJhME,834
+cocoindex/_engine.cpython-312-darwin.so,sha256=TgrpClutvTXWvlJ4Mr3VU0ifRutOlh6yOrsSjZrPlj4,56853136
 cocoindex/auth_registry.py,sha256=NsALZ3SKsDG9cPdrlTlalIqUvgbgFOaFGAbWJNedtJE,692
 cocoindex/cli.py,sha256=Ac3ybnQW-HGVGJeUwIOHd1qhjs0KC5wCsemWuyouEfU,8999
 cocoindex/convert.py,sha256=75HSBie7DokM0RJyUBqeveZRl5y_Fl8lzByoRF0yb2M,6915
-cocoindex/flow.py,sha256=bKd5kK59ist0MpjwJkAEF3B3AGlylsagQl1JgnE2lkI,27618
+cocoindex/flow.py,sha256=FJGuw71q8EPd37DUbveiMV-LTpqRG2ckQ7jM5bVMJcw,28356
 cocoindex/functions.py,sha256=F79dNmGE127LaU67kF5Oqtf_tIzebFQH7MkyceMX4-s,1830
 cocoindex/index.py,sha256=LssEOuZi6AqhwKtZM3QFeQpa9T-0ELi8G5DsrYKECvc,534
 cocoindex/lib.py,sha256=OqTMuOHicdyX9PRA7fmTzznK8HZMrzxpUDbqxAEF--Q,2383
@@ -22,4 +22,5 @@ cocoindex/storages.py,sha256=MFMsfyOCYMggTWeWrOi82miqOXQmiUuqq828x5htBr0,2207
 cocoindex/tests/__init__.py,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 cocoindex/tests/test_convert.py,sha256=7jc--I3frrg7DB5MPr4JFzE7DSCznJuWyHdlDLQJ_fM,15516
 cocoindex/typing.py,sha256=369ABRtnpbaVSQVIBc2ZDutXW8jUmncvNJd9CHEWT3Q,8962
-cocoindex-0.1.39.dist-info/RECORD,,
+cocoindex/utils.py,sha256=eClhMdjBjcXaDkah-rPUmE7Y5Ncd7S1goUe2qTETR08,456
+cocoindex-0.1.41.dist-info/RECORD,,