cocoindex 0.1.39__tar.gz → 0.1.40__tar.gz

{cocoindex-0.1.39 → cocoindex-0.1.40}/Cargo.lock

@@ -993,7 +993,7 @@ dependencies = [
 
 [[package]]
 name = "cocoindex"
-version = "0.1.39"
+version = "0.1.40"
 dependencies = [
  "anyhow",
  "async-openai",

{cocoindex-0.1.39 → cocoindex-0.1.40}/Cargo.toml

@@ -2,7 +2,7 @@
 name = "cocoindex"
 # Version used for local development is always higher than others to take precedence.
 # Will be overridden for specific release versions.
-version = "0.1.39"
+version = "0.1.40"
 edition = "2024"
 
 [profile.release]

{cocoindex-0.1.39 → cocoindex-0.1.40}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cocoindex
-Version: 0.1.39
+Version: 0.1.40
 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 → cocoindex-0.1.40}/README.md

@@ -137,7 +137,7 @@ 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 → cocoindex-0.1.40}/examples/amazon_s3_embedding/pyproject.toml

@@ -3,4 +3,7 @@ name = "amazon-s3-text-embedding"
 version = "0.1.0"
 description = "Simple example for cocoindex: build embedding index based on Amazon S3 files."
 requires-python = ">=3.11"
-dependencies = ["cocoindex>=0.1.35", "python-dotenv>=1.0.1"]
+dependencies = ["cocoindex>=0.1.39", "python-dotenv>=1.0.1"]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/code_embedding/pyproject.toml

@@ -3,4 +3,7 @@ name = "code-embedding"
 version = "0.1.0"
 description = "Simple example for cocoindex: build embedding index based on source code."
 requires-python = ">=3.10"
-dependencies = ["cocoindex>=0.1.35", "python-dotenv>=1.0.1"]
+dependencies = ["cocoindex>=0.1.39", "python-dotenv>=1.0.1"]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/docs_to_knowledge_graph/pyproject.toml

@@ -3,4 +3,7 @@ name = "manuals-to-kg"
 version = "0.1.0"
 description = "Simple example for cocoindex: extract triples from files and build knowledge graph."
 requires-python = ">=3.10"
-dependencies = ["cocoindex>=0.1.35", "python-dotenv>=1.0.1"]
+dependencies = ["cocoindex>=0.1.39", "python-dotenv>=1.0.1"]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/gdrive_text_embedding/pyproject.toml

@@ -3,4 +3,7 @@ name = "gdrive-text-embedding"
 version = "0.1.0"
 description = "Simple example for cocoindex: build embedding index based on Google Drive files."
 requires-python = ">=3.11"
-dependencies = ["cocoindex>=0.1.35", "python-dotenv>=1.0.1"]
+dependencies = ["cocoindex>=0.1.39", "python-dotenv>=1.0.1"]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/manuals_llm_extraction/pyproject.toml

@@ -4,7 +4,10 @@ version = "0.1.0"
 description = "Simple example for cocoindex: extract structured information from a Markdown file using LLM."
 requires-python = ">=3.10"
 dependencies = [
-    "cocoindex>=0.1.35",
+    "cocoindex>=0.1.39",
     "python-dotenv>=1.0.1",
     "marker-pdf>=1.5.2",
 ]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/pdf_embedding/pyproject.toml

@@ -4,7 +4,10 @@ version = "0.1.0"
 description = "Simple example for cocoindex: build embedding index based on local PDF files."
 requires-python = ">=3.10"
 dependencies = [
-    "cocoindex>=0.1.35",
+    "cocoindex>=0.1.39",
     "python-dotenv>=1.0.1",
     "marker-pdf>=1.5.2",
 ]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39/examples/product_taxonomy_knowledge_graph → cocoindex-0.1.40/examples/product_recommendation}/README.md

@@ -1,6 +1,8 @@
-# Build Real-Time Product Recommendation based on LLM Taxonomy Extraction and Knowledge Graph
+# Build Real-Time Recommendation Engine with LLM and Graph Database
 
-We will process a list of products and use LLM to extract the taxonomy and complimentary taxonomy for each product.
+We will build a real-time product recommendation engine with LLM and graph database. In particular, we will use LLM to understand the category (taxonomy) of a product. In addition, we will use LLM to enumerate the complementary products - users are likely to buy together with the current product (pencil and notebook). 
+
+We will use Graph to explore the relationships between products that can be further used for product recommendations or labeling.
 
 Please drop [CocoIndex on Github](https://github.com/cocoindex-io/cocoindex) a star to support us and stay tuned for more updates. Thank you so much 🥥🤗. [![GitHub](https://img.shields.io/github/stars/cocoindex-io/cocoindex?color=5B5BD6)](https://github.com/cocoindex-io/cocoindex)
 

{cocoindex-0.1.39/examples/product_taxonomy_knowledge_graph → cocoindex-0.1.40/examples/product_recommendation}/pyproject.toml

@@ -3,4 +3,7 @@ name = "cocoindex-ecommerce-taxonomy"
 version = "0.1.0"
 description = "Simple example for CocoIndex: extract taxonomy from e-commerce products and build knowledge graph."
 requires-python = ">=3.10"
-dependencies = ["cocoindex>=0.1.35", "python-dotenv>=1.0.1", "jinja2>=3.1.6"]
+dependencies = ["cocoindex>=0.1.39", "python-dotenv>=1.0.1", "jinja2>=3.1.6"]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/text_embedding/main.py

@@ -2,6 +2,7 @@ from dotenv import load_dotenv
 
 import cocoindex
 
+@cocoindex.transform_flow()
 def text_to_embedding(text: cocoindex.DataSlice) -> cocoindex.DataSlice:
     """
     Embed the text using a SentenceTransformer model.

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/text_embedding/pyproject.toml

@@ -3,4 +3,7 @@ name = "text-embedding"
 version = "0.1.0"
 description = "Simple example for cocoindex: build embedding index based on local text files."
 requires-python = ">=3.10"
-dependencies = ["cocoindex>=0.1.35", "python-dotenv>=1.0.1"]
+dependencies = ["cocoindex>=0.1.39", "python-dotenv>=1.0.1"]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/examples/text_embedding_qdrant/pyproject.toml

@@ -3,4 +3,7 @@ name = "text-embedding-qdrant"
 version = "0.1.0"
 description = "Simple example for cocoindex: build embedding index based on local text files."
 requires-python = ">=3.10"
-dependencies = ["cocoindex>=0.1.35", "python-dotenv>=1.0.1"]
+dependencies = ["cocoindex>=0.1.39", "python-dotenv>=1.0.1"]
+
+[tool.setuptools]
+packages = []

{cocoindex-0.1.39 → cocoindex-0.1.40}/python/cocoindex/__init__.py

@@ -1,7 +1,7 @@
 """
 Cocoindex is a framework for building and running indexing pipelines.
 """
-from . import functions, query, sources, storages, cli
+from . import functions, query, sources, storages, cli, utils
 from .flow import FlowBuilder, DataScope, DataSlice, Flow, flow_def, transform_flow
 from .flow import EvaluateAndDumpOptions, GeneratedField
 from .flow import update_all_flows_async, FlowLiveUpdater, FlowLiveUpdaterOptions

{cocoindex-0.1.39 → cocoindex-0.1.40}/python/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(

cocoindex-0.1.40/python/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