refactor(targets): rename storages to targets for remaining code

badmonster0 · badmonster0 · commit e86138c67edd · 2025-06-15T22:55:50.000-07:00
diff --git a/docs/docs/getting_started/quickstart.md b/docs/docs/getting_started/quickstart.md
@@ -214,7 +214,7 @@ from pgvector.psycopg import register_vector
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the text_embedding_flow above.
-    table_name = cocoindex.utils.get_target_storage_default_name(text_embedding_flow, "doc_embeddings")
+    table_name = cocoindex.utils.get_target_default_name(text_embedding_flow, "doc_embeddings")
     # Evaluate the transform flow defined above with the input query, to get the embedding.
     query_vector = text_to_embedding.eval(query)
     # Run the query and get the results.
@@ -237,7 +237,7 @@ There're two CocoIndex-specific logic:
 1.  Get the table name from the export target in the `text_embedding_flow` above.
     Since the table name for the `Postgres` target is not explicitly specified in the `export()` call,
     CocoIndex uses a default name.
-    `cocoindex.utils.get_target_storage_default_name()` is a utility function to get the default table name for this case.
+    `cocoindex.utils.get_target_default_name()` is a utility function to get the default table name for this case.
 
 2.  Evaluate the transform flow defined above with the input query, to get the embedding.
     It's done by the `eval()` method of the transform flow `text_to_embedding`.
diff --git a/docs/docs/query.mdx b/docs/docs/query.mdx
@@ -80,7 +80,7 @@ print(await text_to_embedding.eval_async("Hello, world!"))
 
 In your indexing flow, when you export data to a target, you can specify the target name (e.g. a database table name, a collection name, the node label in property graph databases, etc.) explicitly,
 or for some backends you can also omit it and let CocoIndex generate a default name for you.
-For the latter case, CocoIndex provides a utility function `cocoindex.utils.get_target_storage_default_name()` to get the default name.
+For the latter case, CocoIndex provides a utility function `cocoindex.utils.get_target_default_name()` to get the default name.
 It takes the following arguments:
 
 *   `flow` (type: `cocoindex.Flow`): The flow to get the default name for.
@@ -92,7 +92,7 @@ For example:
 <TabItem value="python" label="Python">
 
 ```python
-table_name = cocoindex.utils.get_target_storage_default_name(text_embedding_flow, "doc_embeddings")
+table_name = cocoindex.utils.get_target_default_name(text_embedding_flow, "doc_embeddings")
 query = f"SELECT filename, text FROM {table_name} ORDER BY embedding <=> %s DESC LIMIT 5"
 ...
 ```
diff --git a/examples/amazon_s3_embedding/main.py b/examples/amazon_s3_embedding/main.py
@@ -74,7 +74,7 @@ def amazon_s3_text_embedding_flow(
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the amazon_s3_text_embedding_flow above.
-    table_name = cocoindex.utils.get_target_storage_default_name(
+    table_name = cocoindex.utils.get_target_default_name(
         amazon_s3_text_embedding_flow, "doc_embeddings"
     )
     # Evaluate the transform flow defined above with the input query, to get the embedding.
diff --git a/examples/code_embedding/main.py b/examples/code_embedding/main.py
@@ -73,7 +73,7 @@ def code_embedding_flow(
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the code_embedding_flow above.
-    table_name = cocoindex.utils.get_target_storage_default_name(
+    table_name = cocoindex.utils.get_target_default_name(
         code_embedding_flow, "code_embeddings"
     )
     # Evaluate the transform flow defined above with the input query, to get the embedding.
diff --git a/examples/fastapi_server_docker/main.py b/examples/fastapi_server_docker/main.py
@@ -67,7 +67,7 @@ def markdown_embedding_flow(
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the text_embedding_flow above.
-    table_name = cocoindex.utils.get_target_storage_default_name(
+    table_name = cocoindex.utils.get_target_default_name(
         markdown_embedding_flow, "doc_embeddings"
     )
     # Evaluate the transform flow defined above with the input query, to get the embedding.
diff --git a/examples/gdrive_text_embedding/main.py b/examples/gdrive_text_embedding/main.py
@@ -73,7 +73,7 @@ def gdrive_text_embedding_flow(
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the gdrive_text_embedding_flow above.
-    table_name = cocoindex.utils.get_target_storage_default_name(
+    table_name = cocoindex.utils.get_target_default_name(
         gdrive_text_embedding_flow, "doc_embeddings"
     )
     # Evaluate the transform flow defined above with the input query, to get the embedding.
diff --git a/examples/pdf_embedding/main.py b/examples/pdf_embedding/main.py
@@ -99,7 +99,7 @@ def pdf_embedding_flow(
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the pdf_embedding_flow above.
-    table_name = cocoindex.utils.get_target_storage_default_name(
+    table_name = cocoindex.utils.get_target_default_name(
         pdf_embedding_flow, "pdf_embeddings"
     )
     # Evaluate the transform flow defined above with the input query, to get the embedding.
diff --git a/examples/text_embedding/Text_Embedding.ipynb b/examples/text_embedding/Text_Embedding.ipynb
@@ -272,7 +272,7 @@
     "\n",
     "def search(pool: ConnectionPool, query: str, top_k: int = 5):\n",
     "    # Get the table name, for the export target in the text_embedding_flow above.\n",
-    "    table_name = cocoindex.utils.get_target_storage_default_name(text_embedding_flow, \"doc_embeddings\")\n",
+    "    table_name = cocoindex.utils.get_target_default_name(text_embedding_flow, \"doc_embeddings\")\n",
     "    # Evaluate the transform flow defined above with the input query, to get the embedding.\n",
     "    query_vector = text_to_embedding.eval(query)\n",
     "    # Run the query and get the results.\n",
diff --git a/examples/text_embedding/main.py b/examples/text_embedding/main.py
@@ -67,7 +67,7 @@ def text_embedding_flow(
 
 def search(pool: ConnectionPool, query: str, top_k: int = 5):
     # Get the table name, for the export target in the text_embedding_flow above.
-    table_name = cocoindex.utils.get_target_storage_default_name(
+    table_name = cocoindex.utils.get_target_default_name(
         text_embedding_flow, "doc_embeddings"
     )
     # Evaluate the transform flow defined above with the input query, to get the embedding.
diff --git a/python/cocoindex/flow.py b/python/cocoindex/flow.py
@@ -327,7 +327,7 @@ def collect(self, **kwargs: Any) -> None:
     def export(
         self,
         name: str,
-        target_spec: op.StorageSpec,
+        target_spec: op.TargetSpec,
         /,
         *,
         primary_key_fields: Sequence[str],
@@ -340,7 +340,7 @@ def export(
 
         `vector_index` is for backward compatibility only. Please use `vector_indexes` instead.
         """
-        if not isinstance(target_spec, op.StorageSpec):
+        if not isinstance(target_spec, op.TargetSpec):
             raise ValueError(
                 "export() can only be called on a CocoIndex target storage"
             )
diff --git a/python/cocoindex/op.py b/python/cocoindex/op.py
@@ -19,7 +19,7 @@ class OpCategory(Enum):
 
     FUNCTION = "function"
     SOURCE = "source"
-    STORAGE = "storage"
+    TARGET = "target"
     DECLARATION = "declaration"
 
 
@@ -52,8 +52,8 @@ class FunctionSpec(metaclass=SpecMeta, category=OpCategory.FUNCTION):  # pylint:
     """A function spec. All its subclass can be instantiated similar to a dataclass, i.e. ClassName(field1=value1, field2=value2, ...)"""
 
 
-class StorageSpec(metaclass=SpecMeta, category=OpCategory.STORAGE):  # pylint: disable=too-few-public-methods
-    """A storage spec. All its subclass can be instantiated similar to a dataclass, i.e. ClassName(field1=value1, field2=value2, ...)"""
+class TargetSpec(metaclass=SpecMeta, category=OpCategory.TARGET):  # pylint: disable=too-few-public-methods
+    """A target spec. All its subclass can be instantiated similar to a dataclass, i.e. ClassName(field1=value1, field2=value2, ...)"""
 
 
 class DeclarationSpec(metaclass=SpecMeta, category=OpCategory.DECLARATION):  # pylint: disable=too-few-public-methods
diff --git a/python/cocoindex/targets.py b/python/cocoindex/targets.py
@@ -9,8 +9,8 @@
 from .setting import DatabaseConnectionSpec
 
 
-class Postgres(op.StorageSpec):
-    """Storage powered by Postgres and pgvector."""
+class Postgres(op.TargetSpec):
+    """Target powered by Postgres and pgvector."""
 
     database: AuthEntryReference[DatabaseConnectionSpec] | None = None
     table_name: str | None = None
@@ -25,8 +25,8 @@ class QdrantConnection:
 
 
 @dataclass
-class Qdrant(op.StorageSpec):
-    """Storage powered by Qdrant - https://qdrant.tech/."""
+class Qdrant(op.TargetSpec):
+    """Target powered by Qdrant - https://qdrant.tech/."""
 
     collection_name: str
     connection: AuthEntryReference[QdrantConnection] | None = None
@@ -52,7 +52,7 @@ class NodeFromFields:
 
 @dataclass
 class ReferencedNode:
-    """Storage spec for a graph node."""
+    """Target spec for a graph node."""
 
     label: str
     primary_key_fields: Sequence[str]
@@ -95,7 +95,7 @@ class Neo4jConnection:
     db: str | None = None
 
 
-class Neo4j(op.StorageSpec):
+class Neo4j(op.TargetSpec):
     """Graph storage powered by Neo4j."""
 
     connection: AuthEntryReference[Neo4jConnection]
@@ -119,7 +119,7 @@ class KuzuConnection:
     api_server_url: str
 
 
-class Kuzu(op.StorageSpec):
+class Kuzu(op.TargetSpec):
     """Graph storage powered by Kuzu."""
 
     connection: AuthEntryReference[KuzuConnection]
diff --git a/python/cocoindex/utils.py b/python/cocoindex/utils.py
@@ -2,16 +2,19 @@
 from .setting import get_app_namespace
 
 
-def get_target_storage_default_name(
-    flow: Flow, target_name: str, delimiter: str = "__"
-) -> str:
+def get_target_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.
+    It's used as the underlying target name (e.g. a table, a collection, etc.) followed by most targets, if not explicitly specified.
     """
     return (
         get_app_namespace(trailing_delimiter=delimiter)
         + flow.name
         + delimiter
         + target_name
     )
+
+
+get_target_storage_default_name = (
+    get_target_default_name  # Deprecated: Use get_target_default_name instead
+)
diff --git a/src/ops/mod.rs b/src/ops/mod.rs
@@ -5,7 +5,7 @@ pub mod registry;
 mod factory_bases;
 mod functions;
 mod sources;
-mod storages;
+mod targets;
 
 mod registration;
 pub(crate) use registration::*;
diff --git a/src/ops/registration.rs b/src/ops/registration.rs
@@ -1,6 +1,6 @@
 use super::{
     factory_bases::*, functions, registry::ExecutorFactoryRegistry, sdk::ExecutorFactory, sources,
-    storages,
+    targets,
 };
 use anyhow::Result;
 use std::sync::{LazyLock, RwLock, RwLockReadGuard};
@@ -16,11 +16,11 @@ fn register_executor_factories(registry: &mut ExecutorFactoryRegistry) -> Result
     functions::split_recursively::register(registry)?;
     functions::extract_by_llm::Factory.register(registry)?;
 
-    storages::postgres::Factory::default().register(registry)?;
-    storages::qdrant::register(registry)?;
-    storages::kuzu::register(registry, reqwest_client)?;
+    targets::postgres::Factory::default().register(registry)?;
+    targets::qdrant::register(registry)?;
+    targets::kuzu::register(registry, reqwest_client)?;
 
-    storages::neo4j::Factory::new().register(registry)?;
+    targets::neo4j::Factory::new().register(registry)?;
 
     Ok(())
 }
diff --git a/src/ops/targets/kuzu.rs b/src/ops/targets/kuzu.rs
diff --git a/src/ops/targets/mod.rs b/src/ops/targets/mod.rs
diff --git a/src/ops/targets/neo4j.rs b/src/ops/targets/neo4j.rs
diff --git a/src/ops/targets/postgres.rs b/src/ops/targets/postgres.rs
diff --git a/src/ops/targets/qdrant.rs b/src/ops/targets/qdrant.rs
diff --git a/src/ops/targets/shared/mod.rs b/src/ops/targets/shared/mod.rs
diff --git a/src/ops/targets/shared/property_graph.rs b/src/ops/targets/shared/property_graph.rs
diff --git a/src/ops/targets/shared/table_columns.rs b/src/ops/targets/shared/table_columns.rs
diff --git a/src/setup/auth_registry.rs b/src/setup/auth_registry.rs
@@ -38,7 +38,7 @@ impl AuthRegistry {
             Some(value) => Ok(serde_json::from_value(value.clone())?),
             None => api_bail!(
                 "Auth entry `{key}` not found.\n\
-                Hint: If you're not referencing `{key}` in your flow, it will likely be caused by a previously persisted storage target using it. \
+                Hint: If you're not referencing `{key}` in your flow, it will likely be caused by a previously persisted target using it. \
                 You need to bring back the definition for the auth entry `{key}`, so that CocoIndex will be able to do a cleanup in the next `setup` run. \
                 See https://cocoindex.io/docs/core/flow_def#auth-registry for more details.",
                 key = entry_ref.key

Original file line number	Diff line number	Diff line change
`@@ -74,7 +74,7 @@ def amazon_s3_text_embedding_flow(`
`74`	`74`
`75`	`75`	`def search(pool: ConnectionPool, query: str, top_k: int = 5):`
`76`	`76`	`# Get the table name, for the export target in the amazon_s3_text_embedding_flow above.`
`77`		`- table_name = cocoindex.utils.get_target_storage_default_name(`
	`77`	`+ table_name = cocoindex.utils.get_target_default_name(`
`78`	`78`	`amazon_s3_text_embedding_flow, "doc_embeddings"`
`79`	`79`	`)`
`80`	`80`	`# Evaluate the transform flow defined above with the input query, to get the embedding.`
Original file line number	Diff line number	Diff line change
`@@ -73,7 +73,7 @@ def code_embedding_flow(`
`73`	`73`
`74`	`74`	`def search(pool: ConnectionPool, query: str, top_k: int = 5):`
`75`	`75`	`# Get the table name, for the export target in the code_embedding_flow above.`
`76`		`- table_name = cocoindex.utils.get_target_storage_default_name(`
	`76`	`+ table_name = cocoindex.utils.get_target_default_name(`
`77`	`77`	`code_embedding_flow, "code_embeddings"`
`78`	`78`	`)`
`79`	`79`	`# Evaluate the transform flow defined above with the input query, to get the embedding.`
Original file line number	Diff line number	Diff line change
`@@ -67,7 +67,7 @@ def markdown_embedding_flow(`
`67`	`67`
`68`	`68`	`def search(pool: ConnectionPool, query: str, top_k: int = 5):`
`69`	`69`	`# Get the table name, for the export target in the text_embedding_flow above.`
`70`		`- table_name = cocoindex.utils.get_target_storage_default_name(`
	`70`	`+ table_name = cocoindex.utils.get_target_default_name(`
`71`	`71`	`markdown_embedding_flow, "doc_embeddings"`
`72`	`72`	`)`
`73`	`73`	`# Evaluate the transform flow defined above with the input query, to get the embedding.`
Original file line number	Diff line number	Diff line change
`@@ -73,7 +73,7 @@ def gdrive_text_embedding_flow(`
`73`	`73`
`74`	`74`	`def search(pool: ConnectionPool, query: str, top_k: int = 5):`
`75`	`75`	`# Get the table name, for the export target in the gdrive_text_embedding_flow above.`
`76`		`- table_name = cocoindex.utils.get_target_storage_default_name(`
	`76`	`+ table_name = cocoindex.utils.get_target_default_name(`
`77`	`77`	`gdrive_text_embedding_flow, "doc_embeddings"`
`78`	`78`	`)`
`79`	`79`	`# Evaluate the transform flow defined above with the input query, to get the embedding.`
Original file line number	Diff line number	Diff line change
`@@ -99,7 +99,7 @@ def pdf_embedding_flow(`
`99`	`99`
`100`	`100`	`def search(pool: ConnectionPool, query: str, top_k: int = 5):`
`101`	`101`	`# Get the table name, for the export target in the pdf_embedding_flow above.`
`102`		`- table_name = cocoindex.utils.get_target_storage_default_name(`
	`102`	`+ table_name = cocoindex.utils.get_target_default_name(`
`103`	`103`	`pdf_embedding_flow, "pdf_embeddings"`
`104`	`104`	`)`
`105`	`105`	`# Evaluate the transform flow defined above with the input query, to get the embedding.`
Original file line number	Diff line number	Diff line change
`@@ -67,7 +67,7 @@ def text_embedding_flow(`
`67`	`67`
`68`	`68`	`def search(pool: ConnectionPool, query: str, top_k: int = 5):`
`69`	`69`	`# Get the table name, for the export target in the text_embedding_flow above.`
`70`		`- table_name = cocoindex.utils.get_target_storage_default_name(`
	`70`	`+ table_name = cocoindex.utils.get_target_default_name(`
`71`	`71`	`text_embedding_flow, "doc_embeddings"`
`72`	`72`	`)`
`73`	`73`	`# Evaluate the transform flow defined above with the input query, to get the embedding.`