sf-vector-sdk 0.2.0__tar.gz → 0.2.3__tar.gz

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sf-vector-sdk
-Version: 0.2.0
+Version: 0.2.3
 Summary: Python SDK for the Vector Gateway service (embeddings and vector search)
 Requires-Python: >=3.11
 Requires-Dist: redis>=5.0.0
@@ -220,25 +220,42 @@ Type-safe embedding for known tool types (FlashCard, TestQuestion, etc.) with au
 |--------|-------------|
 | `embed_flashcard(data, metadata)` | Embed a flashcard, return request ID |
 | `embed_flashcard_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_flashcard_batch(items)` | Embed batch of flashcards, return request ID |
+| `embed_flashcard_batch_and_wait(items, timeout)` | Embed batch and wait for result |
 | `embed_test_question(data, metadata)` | Embed a test question, return request ID |
 | `embed_test_question_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_test_question_batch(items)` | Embed batch of test questions, return request ID |
+| `embed_test_question_batch_and_wait(items, timeout)` | Embed batch and wait for result |
 | `embed_spaced_test_question(data, metadata)` | Embed a spaced test question, return request ID |
 | `embed_spaced_test_question_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_spaced_test_question_batch(items)` | Embed batch of spaced test questions, return request ID |
+| `embed_spaced_test_question_batch_and_wait(items, timeout)` | Embed batch and wait for result |
 | `embed_audio_recap(data, metadata)` | Embed an audio recap section, return request ID |
 | `embed_audio_recap_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_audio_recap_batch(items)` | Embed batch of audio recaps, return request ID |
+| `embed_audio_recap_batch_and_wait(items, timeout)` | Embed batch and wait for result |
+| `embed_topic(data, metadata)` | Embed a topic (uses `TopicMetadata`), return request ID |
+| `embed_topic_and_wait(data, metadata, timeout)` | Embed and wait for result (uses `TopicMetadata`) |
+| `embed_topic_batch(items)` | Embed batch of topics (uses `TopicMetadata`), return request ID |
+| `embed_topic_batch_and_wait(items, timeout)` | Embed batch and wait for result (uses `TopicMetadata`) |
+
+**Metadata Types:**
+
+- `ToolMetadata` - For tools (FlashCard, TestQuestion, etc.) - requires `tool_id`
+- `TopicMetadata` - For topics only - all fields optional (`user_id`, `topic_id`)
 
 ```python
-from vector_sdk import VectorClient, ToolMetadata, TestQuestionInput
+from vector_sdk import VectorClient, ToolMetadata, TopicMetadata, TestQuestionInput
 
 client = VectorClient(redis_url="redis://localhost:6379")
 
-# Embed a flashcard - SDK handles text extraction, hashing, and routing
+# Embed a flashcard - uses ToolMetadata (tool_id required)
 result = client.structured_embeddings.embed_flashcard_and_wait(
     data={"type": "BASIC", "term": "Mitochondria", "definition": "The powerhouse of the cell"},
     metadata=ToolMetadata(tool_id="tool123", user_id="user456", topic_id="topic789"),
 )
 
-# Embed a test question
+# Embed a test question - uses ToolMetadata (tool_id required)
 result = client.structured_embeddings.embed_test_question_and_wait(
     data=TestQuestionInput(
         question="What is the capital?",
@@ -247,6 +264,23 @@ result = client.structured_embeddings.embed_test_question_and_wait(
     ),
     metadata=ToolMetadata(tool_id="tool456"),
 )
+
+# Embed a topic - uses TopicMetadata (all fields optional)
+result = client.structured_embeddings.embed_topic_and_wait(
+    data={"topic": "Photosynthesis", "description": "The process by which plants convert sunlight to energy"},
+    metadata=TopicMetadata(user_id="user123", topic_id="topic456"),  # No tool_id needed
+)
+
+# Batch embedding - embed multiple topics in a single request
+from vector_sdk import TopicBatchItem
+
+batch_result = client.structured_embeddings.embed_topic_batch_and_wait(
+    items=[
+        TopicBatchItem(data={"topic": "Topic 1", "description": "Description 1"}, metadata=TopicMetadata(user_id="user1")),
+        TopicBatchItem(data={"topic": "Topic 2", "description": "Description 2"}, metadata=TopicMetadata(topic_id="topic2")),
+        TopicBatchItem(data={"topic": "Topic 3", "description": "Description 3"}, metadata=TopicMetadata()),  # All optional
+    ],
+)
 ```
 
 **Database Routing:**

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/README.md

@@ -208,25 +208,42 @@ Type-safe embedding for known tool types (FlashCard, TestQuestion, etc.) with au
 |--------|-------------|
 | `embed_flashcard(data, metadata)` | Embed a flashcard, return request ID |
 | `embed_flashcard_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_flashcard_batch(items)` | Embed batch of flashcards, return request ID |
+| `embed_flashcard_batch_and_wait(items, timeout)` | Embed batch and wait for result |
 | `embed_test_question(data, metadata)` | Embed a test question, return request ID |
 | `embed_test_question_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_test_question_batch(items)` | Embed batch of test questions, return request ID |
+| `embed_test_question_batch_and_wait(items, timeout)` | Embed batch and wait for result |
 | `embed_spaced_test_question(data, metadata)` | Embed a spaced test question, return request ID |
 | `embed_spaced_test_question_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_spaced_test_question_batch(items)` | Embed batch of spaced test questions, return request ID |
+| `embed_spaced_test_question_batch_and_wait(items, timeout)` | Embed batch and wait for result |
 | `embed_audio_recap(data, metadata)` | Embed an audio recap section, return request ID |
 | `embed_audio_recap_and_wait(data, metadata, timeout)` | Embed and wait for result |
+| `embed_audio_recap_batch(items)` | Embed batch of audio recaps, return request ID |
+| `embed_audio_recap_batch_and_wait(items, timeout)` | Embed batch and wait for result |
+| `embed_topic(data, metadata)` | Embed a topic (uses `TopicMetadata`), return request ID |
+| `embed_topic_and_wait(data, metadata, timeout)` | Embed and wait for result (uses `TopicMetadata`) |
+| `embed_topic_batch(items)` | Embed batch of topics (uses `TopicMetadata`), return request ID |
+| `embed_topic_batch_and_wait(items, timeout)` | Embed batch and wait for result (uses `TopicMetadata`) |
+
+**Metadata Types:**
+
+- `ToolMetadata` - For tools (FlashCard, TestQuestion, etc.) - requires `tool_id`
+- `TopicMetadata` - For topics only - all fields optional (`user_id`, `topic_id`)
 
 ```python
-from vector_sdk import VectorClient, ToolMetadata, TestQuestionInput
+from vector_sdk import VectorClient, ToolMetadata, TopicMetadata, TestQuestionInput
 
 client = VectorClient(redis_url="redis://localhost:6379")
 
-# Embed a flashcard - SDK handles text extraction, hashing, and routing
+# Embed a flashcard - uses ToolMetadata (tool_id required)
 result = client.structured_embeddings.embed_flashcard_and_wait(
     data={"type": "BASIC", "term": "Mitochondria", "definition": "The powerhouse of the cell"},
     metadata=ToolMetadata(tool_id="tool123", user_id="user456", topic_id="topic789"),
 )
 
-# Embed a test question
+# Embed a test question - uses ToolMetadata (tool_id required)
 result = client.structured_embeddings.embed_test_question_and_wait(
     data=TestQuestionInput(
         question="What is the capital?",
@@ -235,6 +252,23 @@ result = client.structured_embeddings.embed_test_question_and_wait(
     ),
     metadata=ToolMetadata(tool_id="tool456"),
 )
+
+# Embed a topic - uses TopicMetadata (all fields optional)
+result = client.structured_embeddings.embed_topic_and_wait(
+    data={"topic": "Photosynthesis", "description": "The process by which plants convert sunlight to energy"},
+    metadata=TopicMetadata(user_id="user123", topic_id="topic456"),  # No tool_id needed
+)
+
+# Batch embedding - embed multiple topics in a single request
+from vector_sdk import TopicBatchItem
+
+batch_result = client.structured_embeddings.embed_topic_batch_and_wait(
+    items=[
+        TopicBatchItem(data={"topic": "Topic 1", "description": "Description 1"}, metadata=TopicMetadata(user_id="user1")),
+        TopicBatchItem(data={"topic": "Topic 2", "description": "Description 2"}, metadata=TopicMetadata(topic_id="topic2")),
+        TopicBatchItem(data={"topic": "Topic 3", "description": "Description 3"}, metadata=TopicMetadata()),  # All optional
+    ],
+)
 ```
 
 **Database Routing:**

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/__init__.py

@@ -70,6 +70,7 @@ from vector_sdk.hash import (
     MultipleChoiceOption,
     QuestionData,
     ToolCollection,
+    TopicData,
     compute_content_hash,
     extract_tool_text,
 )
@@ -89,15 +90,21 @@ from vector_sdk.namespaces import (
 # ============================================================================
 from vector_sdk.structured import (
     TOOL_CONFIGS,
+    AudioRecapBatchItem,
+    BatchItem,
     DatabaseRoutingError,
     DatabaseRoutingMode,
+    FlashCardBatchItem,
     PineconeToolConfig,
     QuestionType,
     StructuredEmbeddingsNamespace,
+    TestQuestionBatchItem,
     TestQuestionInput,
     ToolConfig,
     ToolDatabaseConfig,
     ToolMetadata,
+    TopicBatchItem,
+    TopicMetadata,
     TurboPufferToolConfig,
     build_storage_config,
     get_content_type,
@@ -159,7 +166,7 @@ from vector_sdk.types import (
     validate_model,
 )
 
-__version__ = "0.2.0"
+__version__ = "0.2.3"
 
 __all__ = [
     # Clients (New API)
@@ -236,12 +243,21 @@ __all__ = [
     "FlashCardData",
     "QuestionData",
     "AudioRecapSectionData",
+    "TopicData",
     "MultipleChoiceOption",
     "AnswerObject",
     # Structured Embeddings
     "StructuredEmbeddingsNamespace",
     "ToolMetadata",
+    "TopicMetadata",
     "TestQuestionInput",
+    # Batch types
+    "BatchItem",
+    "FlashCardBatchItem",
+    "TestQuestionBatchItem",
+    "AudioRecapBatchItem",
+    "TopicBatchItem",
+    # Tool configuration
     "ToolConfig",
     "ToolDatabaseConfig",
     "TurboPufferToolConfig",

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/generated/embedding_pipeline/content_types/v1/content_types_pb2.py

@@ -2,7 +2,7 @@
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # NO CHECKED-IN PROTOBUF GENCODE
 # source: embedding_pipeline/content_types/v1/content_types.proto
-# Protobuf Python Version: 6.33.4
+# Protobuf Python Version: 6.33.5
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -13,7 +13,7 @@ _runtime_version.ValidateProtobufRuntimeVersion(
     _runtime_version.Domain.PUBLIC,
     6,
     33,
-    4,
+    5,
     '',
     'embedding_pipeline/content_types/v1/content_types.proto'
 )

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/generated/embedding_pipeline/db/vectors/v1/vectors_pb2.py

@@ -2,7 +2,7 @@
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # NO CHECKED-IN PROTOBUF GENCODE
 # source: embedding_pipeline/db/vectors/v1/vectors.proto
-# Protobuf Python Version: 6.33.4
+# Protobuf Python Version: 6.33.5
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -13,7 +13,7 @@ _runtime_version.ValidateProtobufRuntimeVersion(
     _runtime_version.Domain.PUBLIC,
     6,
     33,
-    4,
+    5,
     '',
     'embedding_pipeline/db/vectors/v1/vectors.proto'
 )

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/generated/embedding_pipeline/query/v1/query_pb2.py

@@ -2,7 +2,7 @@
 # Generated by the protocol buffer compiler.  DO NOT EDIT!
 # NO CHECKED-IN PROTOBUF GENCODE
 # source: embedding_pipeline/query/v1/query.proto
-# Protobuf Python Version: 6.33.4
+# Protobuf Python Version: 6.33.5
 """Generated protocol buffer code."""
 from google.protobuf import descriptor as _descriptor
 from google.protobuf import descriptor_pool as _descriptor_pool
@@ -13,7 +13,7 @@ _runtime_version.ValidateProtobufRuntimeVersion(
     _runtime_version.Domain.PUBLIC,
     6,
     33,
-    4,
+    5,
     '',
     'embedding_pipeline/query/v1/query.proto'
 )

sf_vector_sdk-0.2.3/vector_sdk/generated/embedding_pipeline/tools/v1/tools_pb2.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+# Generated by the protocol buffer compiler.  DO NOT EDIT!
+# NO CHECKED-IN PROTOBUF GENCODE
+# source: embedding_pipeline/tools/v1/tools.proto
+# Protobuf Python Version: 6.33.5
+"""Generated protocol buffer code."""
+from google.protobuf import descriptor as _descriptor
+from google.protobuf import descriptor_pool as _descriptor_pool
+from google.protobuf import runtime_version as _runtime_version
+from google.protobuf import symbol_database as _symbol_database
+from google.protobuf.internal import builder as _builder
+_runtime_version.ValidateProtobufRuntimeVersion(
+    _runtime_version.Domain.PUBLIC,
+    6,
+    33,
+    5,
+    '',
+    'embedding_pipeline/tools/v1/tools.proto'
+)
+# @@protoc_insertion_point(imports)
+
+_sym_db = _symbol_database.Default()
+
+
+
+
+DESCRIPTOR = _descriptor_pool.Default().AddSerializedFile(b'\n\'embedding_pipeline/tools/v1/tools.proto\x12\x1b\x65mbedding_pipeline.tools.v1\"\xed\x01\n\rTopicMetadata\x12\x1c\n\x07user_id\x18\x01 \x01(\tH\x00R\x06userId\x88\x01\x01\x12\x1e\n\x08topic_id\x18\x02 \x01(\tH\x01R\x07topicId\x88\x01\x01\x12K\n\x05\x65xtra\x18\x03 \x03(\x0b\x32\x35.embedding_pipeline.tools.v1.TopicMetadata.ExtraEntryR\x05\x65xtra\x1a\x38\n\nExtraEntry\x12\x10\n\x03key\x18\x01 \x01(\tR\x03key\x12\x14\n\x05value\x18\x02 \x01(\tR\x05value:\x02\x38\x01\x42\n\n\x08_user_idB\x0b\n\t_topic_id*\xe4\x01\n\x0eToolCollection\x12\x1f\n\x1bTOOL_COLLECTION_UNSPECIFIED\x10\x00\x12\x1d\n\x19TOOL_COLLECTION_FLASHCARD\x10\x01\x12!\n\x1dTOOL_COLLECTION_TEST_QUESTION\x10\x02\x12(\n$TOOL_COLLECTION_SPACED_TEST_QUESTION\x10\x03\x12*\n&TOOL_COLLECTION_AUDIO_RECAP_V2_SECTION\x10\x04\x12\x19\n\x15TOOL_COLLECTION_TOPIC\x10\x05*\xb2\x01\n\rFlashCardType\x12\x1f\n\x1b\x46LASH_CARD_TYPE_UNSPECIFIED\x10\x00\x12\x19\n\x15\x46LASH_CARD_TYPE_BASIC\x10\x01\x12\x19\n\x15\x46LASH_CARD_TYPE_CLOZE\x10\x02\x12%\n!FLASH_CARD_TYPE_FILL_IN_THE_BLANK\x10\x03\x12#\n\x1f\x46LASH_CARD_TYPE_MULTIPLE_CHOICE\x10\x04\x42gZegithub.com/GoStudyFetchGo/vector-management-monorepo/packages/go/proto-go/embedding_pipeline/tools/v1b\x06proto3')
+
+_globals = globals()
+_builder.BuildMessageAndEnumDescriptors(DESCRIPTOR, _globals)
+_builder.BuildTopDescriptorsAndMessages(DESCRIPTOR, 'embedding_pipeline.tools.v1.tools_pb2', _globals)
+if not _descriptor._USE_C_DESCRIPTORS:
+  _globals['DESCRIPTOR']._loaded_options = None
+  _globals['DESCRIPTOR']._serialized_options = b'Zegithub.com/GoStudyFetchGo/vector-management-monorepo/packages/go/proto-go/embedding_pipeline/tools/v1'
+  _globals['_TOPICMETADATA_EXTRAENTRY']._loaded_options = None
+  _globals['_TOPICMETADATA_EXTRAENTRY']._serialized_options = b'8\001'
+  _globals['_TOOLCOLLECTION']._serialized_start=313
+  _globals['_TOOLCOLLECTION']._serialized_end=541
+  _globals['_FLASHCARDTYPE']._serialized_start=544
+  _globals['_FLASHCARDTYPE']._serialized_end=722
+  _globals['_TOPICMETADATA']._serialized_start=73
+  _globals['_TOPICMETADATA']._serialized_end=310
+  _globals['_TOPICMETADATA_EXTRAENTRY']._serialized_start=229
+  _globals['_TOPICMETADATA_EXTRAENTRY']._serialized_end=285
+# @@protoc_insertion_point(module_scope)

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/generated/embedding_pipeline/tools/v1/tools_pb2.pyi

@@ -1,6 +1,9 @@
+from google.protobuf.internal import containers as _containers
 from google.protobuf.internal import enum_type_wrapper as _enum_type_wrapper
 from google.protobuf import descriptor as _descriptor
-from typing import ClassVar as _ClassVar
+from google.protobuf import message as _message
+from collections.abc import Mapping as _Mapping
+from typing import ClassVar as _ClassVar, Optional as _Optional
 
 DESCRIPTOR: _descriptor.FileDescriptor
 
@@ -11,6 +14,7 @@ class ToolCollection(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
     TOOL_COLLECTION_TEST_QUESTION: _ClassVar[ToolCollection]
     TOOL_COLLECTION_SPACED_TEST_QUESTION: _ClassVar[ToolCollection]
     TOOL_COLLECTION_AUDIO_RECAP_V2_SECTION: _ClassVar[ToolCollection]
+    TOOL_COLLECTION_TOPIC: _ClassVar[ToolCollection]
 
 class FlashCardType(int, metaclass=_enum_type_wrapper.EnumTypeWrapper):
     __slots__ = ()
@@ -24,8 +28,26 @@ TOOL_COLLECTION_FLASHCARD: ToolCollection
 TOOL_COLLECTION_TEST_QUESTION: ToolCollection
 TOOL_COLLECTION_SPACED_TEST_QUESTION: ToolCollection
 TOOL_COLLECTION_AUDIO_RECAP_V2_SECTION: ToolCollection
+TOOL_COLLECTION_TOPIC: ToolCollection
 FLASH_CARD_TYPE_UNSPECIFIED: FlashCardType
 FLASH_CARD_TYPE_BASIC: FlashCardType
 FLASH_CARD_TYPE_CLOZE: FlashCardType
 FLASH_CARD_TYPE_FILL_IN_THE_BLANK: FlashCardType
 FLASH_CARD_TYPE_MULTIPLE_CHOICE: FlashCardType
+
+class TopicMetadata(_message.Message):
+    __slots__ = ("user_id", "topic_id", "extra")
+    class ExtraEntry(_message.Message):
+        __slots__ = ("key", "value")
+        KEY_FIELD_NUMBER: _ClassVar[int]
+        VALUE_FIELD_NUMBER: _ClassVar[int]
+        key: str
+        value: str
+        def __init__(self, key: _Optional[str] = ..., value: _Optional[str] = ...) -> None: ...
+    USER_ID_FIELD_NUMBER: _ClassVar[int]
+    TOPIC_ID_FIELD_NUMBER: _ClassVar[int]
+    EXTRA_FIELD_NUMBER: _ClassVar[int]
+    user_id: str
+    topic_id: str
+    extra: _containers.ScalarMap[str, str]
+    def __init__(self, user_id: _Optional[str] = ..., topic_id: _Optional[str] = ..., extra: _Optional[_Mapping[str, str]] = ...) -> None: ...

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/hash/__init__.py

@@ -16,6 +16,7 @@ from .types import (
     MultipleChoiceOption,
     QuestionData,
     ToolCollection,
+    TopicData,
 )
 
 __all__ = [
@@ -26,6 +27,7 @@ __all__ = [
     "FlashCardData",
     "QuestionData",
     "AudioRecapSectionData",
+    "TopicData",
     "MultipleChoiceOption",
     "AnswerObject",
 ]

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/hash/hasher.py

@@ -15,6 +15,7 @@ from .types import (
     MultipleChoiceOption,
     QuestionData,
     ToolCollection,
+    TopicData,
 )
 
 # Hash length in hex characters (128 bits = 32 hex chars)
@@ -23,7 +24,7 @@ HASH_LENGTH = 32
 
 def compute_content_hash(
     tool_collection: ToolCollection,
-    data: Union[FlashCardData, QuestionData, AudioRecapSectionData, dict],
+    data: Union[FlashCardData, QuestionData, AudioRecapSectionData, TopicData, dict],
 ) -> str:
     """
     Compute a deterministic content hash for a learning tool.
@@ -52,7 +53,7 @@ def compute_content_hash(
 
 def extract_tool_text(
     tool_collection: ToolCollection,
-    data: Union[FlashCardData, QuestionData, AudioRecapSectionData, dict],
+    data: Union[FlashCardData, QuestionData, AudioRecapSectionData, TopicData, dict],
 ) -> str:
     """
     Extract the text content from a learning tool for embedding.
@@ -94,6 +95,8 @@ def extract_tool_text(
         return _extract_question_text(data_dict)
     elif tool_collection == "AudioRecapV2Section":
         return _extract_audio_recap_text(data_dict)
+    elif tool_collection == "Topic":
+        return _extract_topic_text(data_dict)
     else:
         return ""
 
@@ -183,6 +186,29 @@ def _extract_audio_recap_text(data: dict) -> str:
     return ""
 
 
+def _extract_topic_text(data: dict) -> str:
+    """
+    Extract text from Topic.
+
+    Format: "Topic: {topic}. Description: {description}."
+    """
+    parts: list[str] = []
+
+    topic = data.get("topic")
+    if topic:
+        trimmed = topic.strip()
+        if trimmed:
+            parts.append(f"Topic: {trimmed}.")
+
+    description = data.get("description")
+    if description:
+        trimmed = description.strip()
+        if trimmed:
+            parts.append(f"Description: {trimmed}.")
+
+    return " ".join(parts)
+
+
 def _strip_flashcard_syntax(text: str) -> str:
     """
     Strip {{...}} markers from cloze/fill-in-blank text.

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/hash/types.py

@@ -9,7 +9,7 @@ from typing import Literal, Optional, Union
 from pydantic import BaseModel, ConfigDict, Field
 
 # Tool collection types
-ToolCollection = Literal["FlashCard", "TestQuestion", "SpacedTestQuestion", "AudioRecapV2Section"]
+ToolCollection = Literal["FlashCard", "TestQuestion", "SpacedTestQuestion", "AudioRecapV2Section", "Topic"]
 
 # FlashCard type variants
 FlashCardType = Literal["BASIC", "CLOZE", "FILL_IN_THE_BLANK", "MULTIPLE_CHOICE"]
@@ -65,3 +65,12 @@ class AudioRecapSectionData(BaseModel):
     model_config = ConfigDict(extra="allow")
 
     script: Optional[str] = None
+
+
+class TopicData(BaseModel):
+    """Topic data for content hashing."""
+
+    model_config = ConfigDict(extra="allow")
+
+    topic: Optional[str] = None
+    description: Optional[str] = None

{sf_vector_sdk-0.2.0 → sf_vector_sdk-0.2.3}/vector_sdk/namespaces/embeddings.py

@@ -154,26 +154,21 @@ class EmbeddingsNamespace(BaseNamespace):
         Raises:
             TimeoutError: If no result is received within the timeout
         """
-        channel = f"embedding:result:{request_id}"
-        pubsub = self._redis.pubsub()
-        pubsub.subscribe(channel)
-
-        try:
-            start_time = datetime.utcnow()
-            while True:
-                message = pubsub.get_message(timeout=1.0)
-                if message and message["type"] == "message":
-                    data = json.loads(message["data"])
-                    return EmbeddingResult.from_dict(data)
-
-                elapsed = (datetime.utcnow() - start_time).total_seconds()
-                if elapsed >= timeout:
-                    raise TimeoutError(
-                        f"No result received for {request_id} within {timeout}s"
-                    )
-        finally:
-            pubsub.unsubscribe(channel)
-            pubsub.close()
+        list_key = f"embedding:response:{request_id}"
+
+        # BRPOP blocks until result is available or timeout
+        result = self._redis.brpop(list_key, timeout=timeout)
+
+        if result is None:
+            raise TimeoutError(
+                f"No result received for {request_id} within {timeout}s"
+            )
+
+        # result = (key, value)
+        data = json.loads(result[1])
+        # Cleanup the response list
+        self._redis.delete(list_key)
+        return EmbeddingResult.from_dict(data)
 
     def create_and_wait(
         self,
@@ -189,8 +184,8 @@ class EmbeddingsNamespace(BaseNamespace):
         """
         Create embeddings and wait for the result.
 
-        This method subscribes to the result channel BEFORE submitting the request,
-        ensuring no race condition where the result is published before we're listening.
+        Uses BRPOP for efficient blocking wait - no race condition since the result
+        is pushed to a list that persists until consumed.
 
         Args:
             texts: List of text inputs
@@ -205,43 +200,22 @@ class EmbeddingsNamespace(BaseNamespace):
         Returns:
             The embedding result
         """
-        # Generate request ID upfront so we can subscribe before submitting
         request_id = str(uuid.uuid4())
-        channel = f"embedding:result:{request_id}"
-
-        # Subscribe BEFORE submitting to avoid race condition
-        pubsub = self._redis.pubsub()
-        pubsub.subscribe(channel)
-
-        try:
-            # Now submit the request (subscription is already active)
-            self.create(
-                texts=texts,
-                content_type=content_type,
-                priority=priority,
-                storage=storage,
-                metadata=metadata,
-                request_id=request_id,
-                embedding_model=embedding_model,
-                embedding_dimensions=embedding_dimensions,
-            )
 
-            # Wait for message with timeout
-            start_time = datetime.utcnow()
-            while True:
-                message = pubsub.get_message(timeout=1.0)
-                if message and message["type"] == "message":
-                    data = json.loads(message["data"])
-                    return EmbeddingResult.from_dict(data)
-
-                elapsed = (datetime.utcnow() - start_time).total_seconds()
-                if elapsed >= timeout:
-                    raise TimeoutError(
-                        f"No result received for {request_id} within {timeout}s"
-                    )
-        finally:
-            pubsub.unsubscribe(channel)
-            pubsub.close()
+        # Submit the request first
+        self.create(
+            texts=texts,
+            content_type=content_type,
+            priority=priority,
+            storage=storage,
+            metadata=metadata,
+            request_id=request_id,
+            embedding_model=embedding_model,
+            embedding_dimensions=embedding_dimensions,
+        )
+
+        # Wait for result via BRPOP
+        return self.wait_for(request_id, timeout)
 
     def get_queue_depth(self) -> dict[str, int]:
         """