修改为东南天坐标系

backend_service/venv/lib/python3.13/site-packages/chromadb/api/__init__.py

@@ -62,6 +62,7 @@ from chromadb.api.types import (
     IncludeMetadataDocuments,
     Loadable,
     Metadatas,
+    ReadLevel,
     Schema,
     URIs,
     Where,
@@ -697,6 +698,15 @@ class ServerAPI(BaseAPI, AdminAPI, Component):
     ) -> CollectionModel:
         pass
 
+    @abstractmethod
+    def _get_indexing_status(
+        self,
+        collection_id: UUID,
+        tenant: str = DEFAULT_TENANT,
+        database: str = DEFAULT_DATABASE,
+    ) -> "IndexingStatus":
+        pass
+
     @abstractmethod
     def _search(
         self,
@@ -704,6 +714,7 @@ class ServerAPI(BaseAPI, AdminAPI, Component):
         searches: List[Search],
         tenant: str = DEFAULT_TENANT,
         database: str = DEFAULT_DATABASE,
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         pass
 

backend_service/venv/lib/python3.13/site-packages/chromadb/api/async_api.py

@@ -19,8 +19,10 @@ from chromadb.api.types import (
     Embeddings,
     IDs,
     Include,
+    IndexingStatus,
     Loadable,
     Metadatas,
+    ReadLevel,
     Schema,
     URIs,
     Where,
@@ -648,6 +650,15 @@ class AsyncServerAPI(AsyncBaseAPI, AsyncAdminAPI, Component):
     ) -> CollectionModel:
         pass
 
+    @abstractmethod
+    async def _get_indexing_status(
+        self,
+        collection_id: UUID,
+        tenant: str = DEFAULT_TENANT,
+        database: str = DEFAULT_DATABASE,
+    ) -> "IndexingStatus":
+        pass
+
     @abstractmethod
     async def _search(
         self,
@@ -655,6 +666,7 @@ class AsyncServerAPI(AsyncBaseAPI, AsyncAdminAPI, Component):
         searches: List[Search],
         tenant: str = DEFAULT_TENANT,
         database: str = DEFAULT_DATABASE,
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         pass
 

backend_service/venv/lib/python3.13/site-packages/chromadb/api/async_fastapi.py

@@ -32,8 +32,10 @@ from chromadb.api.types import (
     Embeddings,
     IDs,
     Include,
+    IndexingStatus,
     Schema,
     Metadatas,
+    ReadLevel,
     URIs,
     Where,
     WhereDocument,
@@ -414,6 +416,27 @@ class AsyncFastAPI(BaseHTTPClient, AsyncServerAPI):
         model = CollectionModel.from_json(resp_json)
         return model
 
+    @trace_method(
+        "AsyncFastAPI._get_indexing_status", OpenTelemetryGranularity.OPERATION
+    )
+    @override
+    async def _get_indexing_status(
+        self,
+        collection_id: UUID,
+        tenant: str = DEFAULT_TENANT,
+        database: str = DEFAULT_DATABASE,
+    ) -> IndexingStatus:
+        resp_json = await self._make_request(
+            "get",
+            f"/tenants/{tenant}/databases/{database}/collections/{collection_id}/indexing_status",
+        )
+        return IndexingStatus(
+            num_indexed_ops=resp_json["num_indexed_ops"],
+            num_unindexed_ops=resp_json["num_unindexed_ops"],
+            total_ops=resp_json["total_ops"],
+            op_indexing_progress=resp_json["op_indexing_progress"],
+        )
+
     @trace_method("AsyncFastAPI._search", OpenTelemetryGranularity.OPERATION)
     @override
     async def _search(
@@ -422,9 +445,13 @@ class AsyncFastAPI(BaseHTTPClient, AsyncServerAPI):
         searches: List[Search],
         tenant: str = DEFAULT_TENANT,
         database: str = DEFAULT_DATABASE,
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         """Performs hybrid search on a collection"""
-        payload = {"searches": [s.to_dict() for s in searches]}
+        payload = {
+            "searches": [s.to_dict() for s in searches],
+            "read_level": read_level,
+        }
 
         resp_json = await self._make_request(
             "post",

backend_service/venv/lib/python3.13/site-packages/chromadb/api/fastapi.py

@@ -26,8 +26,10 @@ from chromadb.api.types import (
     Embeddings,
     IDs,
     Include,
+    IndexingStatus,
     Schema,
     Metadatas,
+    ReadLevel,
     URIs,
     Where,
     WhereDocument,
@@ -379,6 +381,25 @@ class FastAPI(BaseHTTPClient, ServerAPI):
         model = CollectionModel.from_json(resp_json)
         return model
 
+    @trace_method("FastAPI._get_indexing_status", OpenTelemetryGranularity.OPERATION)
+    @override
+    def _get_indexing_status(
+        self,
+        collection_id: UUID,
+        tenant: str = DEFAULT_TENANT,
+        database: str = DEFAULT_DATABASE,
+    ) -> IndexingStatus:
+        resp_json = self._make_request(
+            "get",
+            f"/tenants/{tenant}/databases/{database}/collections/{collection_id}/indexing_status",
+        )
+        return IndexingStatus(
+            num_indexed_ops=resp_json["num_indexed_ops"],
+            num_unindexed_ops=resp_json["num_unindexed_ops"],
+            total_ops=resp_json["total_ops"],
+            op_indexing_progress=resp_json["op_indexing_progress"],
+        )
+
     @trace_method("FastAPI._search", OpenTelemetryGranularity.OPERATION)
     @override
     def _search(
@@ -387,10 +408,14 @@ class FastAPI(BaseHTTPClient, ServerAPI):
         searches: List[Search],
         tenant: str = DEFAULT_TENANT,
         database: str = DEFAULT_DATABASE,
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         """Performs hybrid search on a collection"""
         # Convert Search objects to dictionaries
-        payload = {"searches": [s.to_dict() for s in searches]}
+        payload = {
+            "searches": [s.to_dict() for s in searches],
+            "read_level": read_level,
+        }
 
         resp_json = self._make_request(
             "post",

backend_service/venv/lib/python3.13/site-packages/chromadb/api/functions.py

@@ -0,0 +1,33 @@
+"""Attachable function definitions for ChromaDB collections.
+
+This module provides function constants that can be attached to collections
+to perform automatic computations on collection data.
+
+Example:
+    >>> from chromadb.api.functions import STATISTICS_FUNCTION
+    >>> attached_fn = collection.attach_function(
+    ...     function=STATISTICS_FUNCTION,
+    ...     name="my_stats",
+    ...     output_collection="my_stats_output"
+    ... )
+"""
+
+from enum import Enum
+
+
+class Function(str, Enum):
+    """Available functions that can be attached to collections."""
+
+    STATISTICS = "statistics"
+    """Computes metadata value frequencies for a collection."""
+
+    RECORD_COUNTER = "record_counter"
+    """Counts records in a collection."""
+
+    # Used only for failure testing - not a real function
+    _NONEXISTENT_TEST_ONLY = "nonexistent_function"
+
+
+# Convenience aliases for cleaner imports
+STATISTICS_FUNCTION = Function.STATISTICS
+RECORD_COUNTER_FUNCTION = Function.RECORD_COUNTER

backend_service/venv/lib/python3.13/site-packages/chromadb/api/models/AsyncCollection.py

@@ -6,6 +6,7 @@ from chromadb.api.types import (
     Embedding,
     PyEmbedding,
     Include,
+    IndexingStatus,
     Metadata,
     Document,
     Image,
@@ -15,6 +16,7 @@ from chromadb.api.types import (
     QueryResult,
     ID,
     OneOrMany,
+    ReadLevel,
     WhereDocument,
     SearchResult,
     maybe_cast_one_to_many,
@@ -96,6 +98,22 @@ class AsyncCollection(CollectionCommon["AsyncServerAPI"]):
             database=self.database,
         )
 
+    async def get_indexing_status(self) -> IndexingStatus:
+        """Get the indexing status of this collection.
+
+        Returns:
+            IndexingStatus: An object containing:
+                - num_indexed_ops: Number of user operations that have been indexed
+                - num_unindexed_ops: Number of user operations pending indexing
+                - total_ops: Total number of user operations in collection
+                - op_indexing_progress: Proportion of user operations that have been indexed as a float between 0 and 1
+        """
+        return await self._client._get_indexing_status(
+            collection_id=self.id,
+            tenant=self.tenant,
+            database=self.database,
+        )
+
     async def get(
         self,
         ids: Optional[OneOrMany[ID]] = None,
@@ -294,6 +312,7 @@ class AsyncCollection(CollectionCommon["AsyncServerAPI"]):
     async def search(
         self,
         searches: OneOrMany[Search],
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         """Perform hybrid search on the collection.
         This is an experimental API that only works for Hosted Chroma for now.
@@ -304,6 +323,11 @@ class AsyncCollection(CollectionCommon["AsyncServerAPI"]):
                 - rank: Ranking expression for hybrid search (defaults to Val(0.0))
                 - limit: Limit configuration for pagination (defaults to no limit)
                 - select: Select configuration for keys to return (defaults to empty)
+            read_level: Controls whether to read from the write-ahead log (WAL):
+                - ReadLevel.INDEX_AND_WAL: Read from both the compacted index and WAL (default).
+                  All committed writes will be visible.
+                - ReadLevel.INDEX_ONLY: Read only from the compacted index, skipping the WAL.
+                  Faster, but recent writes that haven't been compacted may not be visible.
 
         Returns:
             SearchResult: Column-major format response with:
@@ -351,6 +375,10 @@ class AsyncCollection(CollectionCommon["AsyncServerAPI"]):
                 Search().where(K("type") == "paper").rank(Knn(query=[0.3, 0.4]))
             ]
             results = await collection.search(searches)
+
+            # Skip WAL for faster queries (may miss recent uncommitted writes)
+            from chromadb.api.types import ReadLevel
+            result = await collection.search(search, read_level=ReadLevel.INDEX_ONLY)
         """
         # Convert single search to list for consistent handling
         searches_list = maybe_cast_one_to_many(searches)
@@ -367,6 +395,7 @@ class AsyncCollection(CollectionCommon["AsyncServerAPI"]):
             searches=cast(List[Search], embedded_searches),
             tenant=self.tenant,
             database=self.database,
+            read_level=read_level,
         )
 
     async def update(

backend_service/venv/lib/python3.13/site-packages/chromadb/api/models/Collection.py

@@ -7,6 +7,7 @@ from chromadb.api.types import (
     Embedding,
     PyEmbedding,
     Include,
+    IndexingStatus,
     Metadata,
     Document,
     Image,
@@ -16,6 +17,7 @@ from chromadb.api.types import (
     QueryResult,
     ID,
     OneOrMany,
+    ReadLevel,
     WhereDocument,
     SearchResult,
     maybe_cast_one_to_many,
@@ -50,6 +52,22 @@ class Collection(CollectionCommon["ServerAPI"]):
             database=self.database,
         )
 
+    def get_indexing_status(self) -> IndexingStatus:
+        """Get the indexing status of this collection.
+
+        Returns:
+            IndexingStatus: An object containing:
+                - num_indexed_ops: Number of user operations that have been indexed
+                - num_unindexed_ops: Number of user operations pending indexing
+                - total_ops: Total number of user operations in collection
+                - op_indexing_progress: Proportion of user operations that have been indexed as a float between 0 and 1
+        """
+        return self._client._get_indexing_status(
+            collection_id=self.id,
+            tenant=self.tenant,
+            database=self.database,
+        )
+
     def add(
         self,
         ids: OneOrMany[ID],
@@ -303,6 +321,7 @@ class Collection(CollectionCommon["ServerAPI"]):
     def search(
         self,
         searches: OneOrMany[Search],
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         """Perform hybrid search on the collection.
         This is an experimental API that only works for Hosted Chroma for now.
@@ -313,6 +332,11 @@ class Collection(CollectionCommon["ServerAPI"]):
                 - rank: Ranking expression for hybrid search (defaults to Val(0.0))
                 - limit: Limit configuration for pagination (defaults to no limit)
                 - select: Select configuration for keys to return (defaults to empty)
+            read_level: Controls whether to read from the write-ahead log (WAL):
+                - ReadLevel.INDEX_AND_WAL: Read from both the compacted index and WAL (default).
+                  All committed writes will be visible.
+                - ReadLevel.INDEX_ONLY: Read only from the compacted index, skipping the WAL.
+                  Faster, but recent writes that haven't been compacted may not be visible.
 
         Returns:
             SearchResult: Column-major format response with:
@@ -360,6 +384,10 @@ class Collection(CollectionCommon["ServerAPI"]):
                 Search().where(K("type") == "paper").rank(Knn(query=[0.3, 0.4]))
             ]
             results = collection.search(searches)
+
+            # Skip WAL for faster queries (may miss recent uncommitted writes)
+            from chromadb.api.types import ReadLevel
+            result = collection.search(search, read_level=ReadLevel.INDEX_ONLY)
         """
         # Convert single search to list for consistent handling
         searches_list = maybe_cast_one_to_many(searches)
@@ -376,6 +404,7 @@ class Collection(CollectionCommon["ServerAPI"]):
             searches=cast(List[Search], embedded_searches),
             tenant=self.tenant,
             database=self.database,
+            read_level=read_level,
         )
 
     def update(

backend_service/venv/lib/python3.13/site-packages/chromadb/api/rust.py

@@ -39,6 +39,7 @@ from chromadb.api.types import (
     IncludeMetadataDocuments,
     IncludeMetadataDocumentsDistances,
     IncludeMetadataDocumentsEmbeddings,
+    ReadLevel,
     Schema,
     SearchResult,
 )
@@ -334,6 +335,15 @@ class RustBindingsAPI(ServerAPI):
             "Collection forking is not implemented for Local Chroma"
         )
 
+    @override
+    def _get_indexing_status(
+        self,
+        collection_id: UUID,
+        tenant: str = DEFAULT_TENANT,
+        database: str = DEFAULT_DATABASE,
+    ) -> "IndexingStatus":
+        raise NotImplementedError("Indexing status is not implemented for Local Chroma")
+
     @override
     def _search(
         self,
@@ -341,6 +351,7 @@ class RustBindingsAPI(ServerAPI):
         searches: List[Search],
         tenant: str = DEFAULT_TENANT,
         database: str = DEFAULT_DATABASE,
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         raise NotImplementedError("Search is not implemented for Local Chroma")
 

backend_service/venv/lib/python3.13/site-packages/chromadb/api/segment.py

@@ -40,6 +40,7 @@ from chromadb.api.types import (
     Embeddings,
     Metadatas,
     Documents,
+    ReadLevel,
     Schema,
     URIs,
     Where,
@@ -432,6 +433,15 @@ class SegmentAPI(ServerAPI):
             "Collection forking is not implemented for SegmentAPI"
         )
 
+    @override
+    def _get_indexing_status(
+        self,
+        collection_id: UUID,
+        tenant: str = DEFAULT_TENANT,
+        database: str = DEFAULT_DATABASE,
+    ) -> "IndexingStatus":
+        raise NotImplementedError("Indexing status is not implemented for SegmentAPI")
+
     @override
     def _search(
         self,
@@ -439,6 +449,7 @@ class SegmentAPI(ServerAPI):
         searches: List[Search],
         tenant: str = DEFAULT_TENANT,
         database: str = DEFAULT_DATABASE,
+        read_level: ReadLevel = ReadLevel.INDEX_AND_WAL,
     ) -> SearchResult:
         raise NotImplementedError("Search is not implemented for SegmentAPI")
 

backend_service/venv/lib/python3.13/site-packages/chromadb/api/types.py

@@ -66,6 +66,7 @@ __all__ = [
     "UpdateMetadata",
     "SearchResult",
     "SearchResultRow",
+    "IndexingStatus",
     "SparseVector",
     # Index Configuration Types
     "FtsIndexConfig",
@@ -619,6 +620,14 @@ class QueryResult(TypedDict):
     included: Include
 
 
+@dataclass
+class IndexingStatus:
+    num_indexed_ops: int
+    num_unindexed_ops: int
+    total_ops: int
+    op_indexing_progress: float
+
+
 class SearchResultRow(TypedDict, total=False):
     """A single row from search results.
 
@@ -751,6 +760,20 @@ class IndexMetadata(TypedDict):
 Space = Literal["cosine", "l2", "ip"]
 
 
+class ReadLevel(str, Enum):
+    """Controls whether search queries read from the write-ahead log (WAL).
+
+    Attributes:
+        INDEX_AND_WAL: Read from both the compacted index and the WAL (default).
+            All committed writes will be visible.
+        INDEX_ONLY: Read only from the compacted index, skipping the WAL.
+            Faster, but recent writes that haven't been compacted may not be visible.
+    """
+
+    INDEX_AND_WAL = "index_and_wal"
+    INDEX_ONLY = "index_only"
+
+
 # TODO: make warnings prettier and add link to migration docs
 @runtime_checkable
 class EmbeddingFunction(Protocol[D]):
@@ -767,7 +790,8 @@ class EmbeddingFunction(Protocol[D]):
     """
 
     @abstractmethod
-    def __call__(self, input: D) -> Embeddings: ...
+    def __call__(self, input: D) -> Embeddings:
+        ...
 
     def embed_query(self, input: D) -> Embeddings:
         """
@@ -951,7 +975,8 @@ def validate_embedding_function(
 
 
 class DataLoader(Protocol[L]):
-    def __call__(self, uris: URIs) -> L: ...
+    def __call__(self, uris: URIs) -> L:
+        ...
 
 
 def validate_ids(ids: IDs) -> IDs:
@@ -1408,7 +1433,8 @@ class SparseEmbeddingFunction(Protocol[D]):
     """
 
     @abstractmethod
-    def __call__(self, input: D) -> SparseVectors: ...
+    def __call__(self, input: D) -> SparseVectors:
+        ...
 
     def embed_query(self, input: D) -> SparseVectors:
         """
@@ -1602,9 +1628,9 @@ class VectorIndexConfig(BaseModel):
 
     space: Optional[Space] = None
     embedding_function: Optional[Any] = DefaultEmbeddingFunction()
-    source_key: Optional[str] = (
-        None  # key to source the vector from (accepts str or Key)
-    )
+    source_key: Optional[
+        str
+    ] = None  # key to source the vector from (accepts str or Key)
     hnsw: Optional[HnswIndexConfig] = None
     spann: Optional[SpannIndexConfig] = None
 
@@ -1653,9 +1679,9 @@ class SparseVectorIndexConfig(BaseModel):
 
     # TODO(Sanket): Change this to the appropriate sparse ef and use a default here.
     embedding_function: Optional[Any] = None
-    source_key: Optional[str] = (
-        None  # key to source the sparse vector from (accepts str or Key)
-    )
+    source_key: Optional[
+        str
+    ] = None  # key to source the sparse vector from (accepts str or Key)
     bm25: Optional[bool] = None
 
     @field_validator("source_key", mode="before")