groundx 2.2.9__tar.gz → 2.3.3__tar.gz

{groundx-2.2.9 → groundx-2.3.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: groundx
-Version: 2.2.9
+Version: 2.3.3
 Summary: 
 License: MIT
 Requires-Python: >=3.8,<4.0

{groundx-2.2.9 → groundx-2.3.3}/pyproject.toml

@@ -3,7 +3,7 @@ name = "groundx"
 
 [tool.poetry]
 name = "groundx"
-version = "2.2.9"
+version = "2.3.3"
 description = ""
 readme = "README.md"
 authors = []

{groundx-2.2.9 → groundx-2.3.3}/src/groundx/__init__.py

@@ -27,17 +27,16 @@ from .types import (
     IngestLocalDocumentMetadata,
     IngestRemoteDocument,
     IngestResponse,
-    IngestResponseIngest,
+    IngestStatus,
+    IngestStatusLight,
+    IngestStatusProgress,
+    IngestStatusProgressCancelled,
+    IngestStatusProgressComplete,
+    IngestStatusProgressErrors,
+    IngestStatusProgressProcessing,
     MessageResponse,
     MeterDetail,
     ProcessLevel,
-    ProcessStatusResponse,
-    ProcessStatusResponseIngest,
-    ProcessStatusResponseIngestProgress,
-    ProcessStatusResponseIngestProgressCancelled,
-    ProcessStatusResponseIngestProgressComplete,
-    ProcessStatusResponseIngestProgressErrors,
-    ProcessStatusResponseIngestProgressProcessing,
     ProcessesStatusResponse,
     ProcessingStatus,
     SearchResponse,
@@ -87,17 +86,16 @@ __all__ = [
     "IngestLocalDocumentMetadata",
     "IngestRemoteDocument",
     "IngestResponse",
-    "IngestResponseIngest",
+    "IngestStatus",
+    "IngestStatusLight",
+    "IngestStatusProgress",
+    "IngestStatusProgressCancelled",
+    "IngestStatusProgressComplete",
+    "IngestStatusProgressErrors",
+    "IngestStatusProgressProcessing",
     "MessageResponse",
     "MeterDetail",
     "ProcessLevel",
-    "ProcessStatusResponse",
-    "ProcessStatusResponseIngest",
-    "ProcessStatusResponseIngestProgress",
-    "ProcessStatusResponseIngestProgressCancelled",
-    "ProcessStatusResponseIngestProgressComplete",
-    "ProcessStatusResponseIngestProgressErrors",
-    "ProcessStatusResponseIngestProgressProcessing",
     "ProcessesStatusResponse",
     "ProcessingStatus",
     "SearchContentRequestId",

{groundx-2.2.9 → groundx-2.3.3}/src/groundx/core/client_wrapper.py

@@ -16,7 +16,7 @@ class BaseClientWrapper:
         headers: typing.Dict[str, str] = {
             "X-Fern-Language": "Python",
             "X-Fern-SDK-Name": "groundx",
-            "X-Fern-SDK-Version": "2.2.9",
+            "X-Fern-SDK-Version": "2.3.3",
         }
         headers["X-API-Key"] = self.api_key
         return headers

{groundx-2.2.9 → groundx-2.3.3}/src/groundx/documents/client.py

@@ -17,7 +17,6 @@ from ..types.sort import Sort
 from ..types.sort_order import SortOrder
 from ..types.processing_status import ProcessingStatus
 from ..types.document_list_response import DocumentListResponse
-from ..types.process_status_response import ProcessStatusResponse
 from ..core.jsonable_encoder import jsonable_encoder
 from ..types.document_lookup_response import DocumentLookupResponse
 from ..types.document_response import DocumentResponse
@@ -41,6 +40,8 @@ class DocumentsClient:
         """
         Ingest documents hosted on public URLs into a GroundX bucket.
 
+        [Supported Document Types and Ingest Capacities](https://docs.eyelevel.ai/documentation/fundamentals/document-types-and-ingest-capacities)
+
         Parameters
         ----------
         documents : typing.Sequence[IngestRemoteDocument]
@@ -125,6 +126,8 @@ class DocumentsClient:
         """
         Upload documents hosted on a local file system into a GroundX bucket.
 
+        [Supported Document Types and Ingest Capacities](https://docs.eyelevel.ai/documentation/fundamentals/document-types-and-ingest-capacities)
+
         Parameters
         ----------
         request : DocumentLocalIngestRequest
@@ -205,9 +208,12 @@ class DocumentsClient:
     ) -> IngestResponse:
         """
         Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
+
         Note1: This endpoint is currently not supported for on-prem deployments.
         Note2: The `source_url` must include the protocol, http:// or https://.
 
+        [Supported Document Types and Ingest Capacities](https://docs.eyelevel.ai/documentation/fundamentals/document-types-and-ingest-capacities)
+
         Parameters
         ----------
         websites : typing.Sequence[WebsiteSource]
@@ -442,7 +448,7 @@ class DocumentsClient:
 
     def get_processing_status_by_id(
         self, process_id: str, *, request_options: typing.Optional[RequestOptions] = None
-    ) -> ProcessStatusResponse:
+    ) -> IngestResponse:
         """
         Get the current status of an ingest, initiated with documents.ingest_remote, documents.ingest_local, or documents.crawl_website, by specifying the processId (the processId is included in the response of the documents.ingest functions).
 
@@ -456,7 +462,7 @@ class DocumentsClient:
 
         Returns
         -------
-        ProcessStatusResponse
+        IngestResponse
             Look up success
 
         Examples
@@ -478,9 +484,9 @@ class DocumentsClient:
         try:
             if 200 <= _response.status_code < 300:
                 return typing.cast(
-                    ProcessStatusResponse,
+                    IngestResponse,
                     parse_obj_as(
-                        type_=ProcessStatusResponse,  # type: ignore
+                        type_=IngestResponse,  # type: ignore
                         object_=_response.json(),
                     ),
                 )
@@ -522,12 +528,12 @@ class DocumentsClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> DocumentLookupResponse:
         """
-        lookup the document(s) associated with a processId, bucketId, groupId, or projectId.
+        lookup the document(s) associated with a processId, bucketId, or groupId.
 
         Parameters
         ----------
         id : int
-            a processId, bucketId, groupId, or projectId
+            a processId, bucketId, or groupId
 
         n : typing.Optional[int]
             The maximum number of returned documents. Accepts 1-100 with a default of 20.
@@ -821,6 +827,8 @@ class AsyncDocumentsClient:
         """
         Ingest documents hosted on public URLs into a GroundX bucket.
 
+        [Supported Document Types and Ingest Capacities](https://docs.eyelevel.ai/documentation/fundamentals/document-types-and-ingest-capacities)
+
         Parameters
         ----------
         documents : typing.Sequence[IngestRemoteDocument]
@@ -913,6 +921,8 @@ class AsyncDocumentsClient:
         """
         Upload documents hosted on a local file system into a GroundX bucket.
 
+        [Supported Document Types and Ingest Capacities](https://docs.eyelevel.ai/documentation/fundamentals/document-types-and-ingest-capacities)
+
         Parameters
         ----------
         request : DocumentLocalIngestRequest
@@ -1005,9 +1015,12 @@ class AsyncDocumentsClient:
     ) -> IngestResponse:
         """
         Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
+
         Note1: This endpoint is currently not supported for on-prem deployments.
         Note2: The `source_url` must include the protocol, http:// or https://.
 
+        [Supported Document Types and Ingest Capacities](https://docs.eyelevel.ai/documentation/fundamentals/document-types-and-ingest-capacities)
+
         Parameters
         ----------
         websites : typing.Sequence[WebsiteSource]
@@ -1266,7 +1279,7 @@ class AsyncDocumentsClient:
 
     async def get_processing_status_by_id(
         self, process_id: str, *, request_options: typing.Optional[RequestOptions] = None
-    ) -> ProcessStatusResponse:
+    ) -> IngestResponse:
         """
         Get the current status of an ingest, initiated with documents.ingest_remote, documents.ingest_local, or documents.crawl_website, by specifying the processId (the processId is included in the response of the documents.ingest functions).
 
@@ -1280,7 +1293,7 @@ class AsyncDocumentsClient:
 
         Returns
         -------
-        ProcessStatusResponse
+        IngestResponse
             Look up success
 
         Examples
@@ -1310,9 +1323,9 @@ class AsyncDocumentsClient:
         try:
             if 200 <= _response.status_code < 300:
                 return typing.cast(
-                    ProcessStatusResponse,
+                    IngestResponse,
                     parse_obj_as(
-                        type_=ProcessStatusResponse,  # type: ignore
+                        type_=IngestResponse,  # type: ignore
                         object_=_response.json(),
                     ),
                 )
@@ -1354,12 +1367,12 @@ class AsyncDocumentsClient:
         request_options: typing.Optional[RequestOptions] = None,
     ) -> DocumentLookupResponse:
         """
-        lookup the document(s) associated with a processId, bucketId, groupId, or projectId.
+        lookup the document(s) associated with a processId, bucketId, or groupId.
 
         Parameters
         ----------
         id : int
-            a processId, bucketId, groupId, or projectId
+            a processId, bucketId, or groupId
 
         n : typing.Optional[int]
             The maximum number of returned documents. Accepts 1-100 with a default of 20.

{groundx-2.2.9 → groundx-2.3.3}/src/groundx/ingest.py

@@ -9,6 +9,7 @@ from .csv_splitter import CSVSplitter
 from .types.document import Document
 from .types.ingest_remote_document import IngestRemoteDocument
 from .types.ingest_response import IngestResponse
+from .types.ingest_status import IngestStatus
 
 # this is used as the default value for optional parameters
 OMIT = typing.cast(typing.Any, ...)
@@ -140,6 +141,8 @@ class GroundX(GroundXBase):
         self,
         *,
         documents: typing.Sequence[Document],
+        batch_size: typing.Optional[int] = 10,
+        wait_for_complete: typing.Optional[bool] = False,
         upload_api: typing.Optional[str] = "https://api.eyelevel.ai/upload/file",
         request_options: typing.Optional[RequestOptions] = None,
     ) -> IngestResponse:
@@ -150,6 +153,13 @@ class GroundX(GroundXBase):
         ----------
         documents : typing.Sequence[Document]
 
+        # defines how many files to send per batch
+        # ignored unless wait_for_complete is True
+        batch_size : typing.Optional[int]
+
+        # will turn on progress bar and wait for ingestion to complete
+        wait_for_complete : typing.Optional[bool]
+
         # an endpoint that accepts 'name' and 'type' query params
         # and returns a presigned URL in a JSON dictionary with key 'URL'
         upload_api : typing.Optional[str]
@@ -183,36 +193,84 @@ class GroundX(GroundXBase):
         """
         remote_documents, local_documents = prep_documents(documents)
 
-        if len(remote_documents) + len(local_documents) > MAX_BATCH_SIZE:
-            raise ValueError("You have sent too many documents in this request")
-
         if len(remote_documents) + len(local_documents) == 0:
             raise ValueError("No valid documents were provided")
 
-        for d in local_documents:
-            splits = split_doc(Path(os.path.expanduser(d.file_path)))
+        if wait_for_complete:
+            with tqdm(total=len(remote_documents) + len(local_documents), desc="Ingesting Files", unit="file") as pbar:
+                n = max(MIN_BATCH_SIZE, min(batch_size or MIN_BATCH_SIZE, MAX_BATCH_SIZE))
 
-            for sd in splits:
-                url = self._upload_file(upload_api, sd)
+                remote_batch: typing.List[IngestRemoteDocument] = []
+                ingest = IngestResponse(ingest=IngestStatus(process_id="",status="queued"))
 
-                ft = d.file_type
-                if sd.suffix.lower() in SUFFIX_ALIASES:
-                    ft = SUFFIX_ALIASES[sd.suffix.lower()]
+                progress = float(len(remote_documents))
+                for rd in remote_documents:
+                    if len(remote_batch) >= n:
+                        ingest = self.documents.ingest_remote(
+                            documents=remote_batch,
+                            request_options=request_options,
+                        )
+                        ingest, progress = self._monitor_batch(ingest, progress, pbar)
 
-                fn = sd.name
-                if len(splits) == 1 and d.file_name:
-                    fn = d.file_name
+                        remote_batch = []
 
-                remote_documents.append(
-                    IngestRemoteDocument(
-                        bucket_id=d.bucket_id,
-                        file_name=fn,
-                        file_type=ft,
-                        process_level=d.process_level,
-                        search_data=d.search_data,
-                        source_url=url,
+                    remote_batch.append(rd)
+                    pbar.update(0.25)
+                    progress -= 0.25
+
+                if remote_batch:
+                    ingest = self.documents.ingest_remote(
+                        documents=remote_batch,
+                        request_options=request_options,
                     )
-                )
+                    ingest, progress = self._monitor_batch(ingest, progress, pbar)
+
+
+                if progress > 0:
+                    pbar.update(progress)
+
+                current_batch_size = 0
+                local_batch: typing.List[Document] = []
+
+                progress = float(len(local_documents))
+                for ld in local_documents:
+                    fp = Path(os.path.expanduser(ld.file_path))
+                    file_size = fp.stat().st_size
+
+                    if (current_batch_size + file_size > MAX_BATCH_SIZE_BYTES) or (len(local_batch) >= n):
+                        up_docs, progress = self._process_local(local_batch, upload_api, progress, pbar)
+
+                        ingest = self.documents.ingest_remote(
+                            documents=up_docs,
+                            request_options=request_options,
+                        )
+                        ingest, progress = self._monitor_batch(ingest, progress, pbar)
+
+                        local_batch = []
+                        current_batch_size = 0
+
+                    local_batch.append(ld)
+                    current_batch_size += file_size
+
+                if local_batch:
+                    up_docs, progress = self._process_local(local_batch, upload_api, progress, pbar)
+
+                    ingest = self.documents.ingest_remote(
+                        documents=up_docs,
+                        request_options=request_options,
+                    )
+                    ingest, progress = self._monitor_batch(ingest, progress, pbar)
+
+                if progress > 0:
+                    pbar.update(progress)
+
+                return ingest
+        elif len(remote_documents) + len(local_documents) > MAX_BATCH_SIZE:
+            raise ValueError("You have sent too many documents in this request")
+
+
+        up_docs, _ = self._process_local(local_documents, upload_api)
+        remote_documents.extend(up_docs)
 
         return self.documents.ingest_remote(
             documents=remote_documents,
@@ -346,6 +404,92 @@ class GroundX(GroundXBase):
 
         return strip_query_params(upload_url)
 
+    def _process_local(
+        self,
+        local_docs,
+        upload_api,
+        progress = None,
+        pbar = None,
+    ):
+        remote_docs = []
+        for d in local_docs:
+            splits = split_doc(Path(os.path.expanduser(d.file_path)))
+
+            for sd in splits:
+                url = self._upload_file(upload_api, sd)
+
+                ft = d.file_type
+                if sd.suffix.lower() in SUFFIX_ALIASES:
+                    ft = SUFFIX_ALIASES[sd.suffix.lower()]
+
+                fn = sd.name
+                if len(splits) == 1 and d.file_name:
+                    fn = d.file_name
+
+                remote_docs.append(
+                    IngestRemoteDocument(
+                        bucket_id=d.bucket_id,
+                        file_name=fn,
+                        file_type=ft,
+                        process_level=d.process_level,
+                        search_data=d.search_data,
+                        source_url=url,
+                    )
+                )
+
+                if progress is not None and pbar is not None and pbar.update is not None:
+                    pbar.update(0.25)
+                    progress -= 0.25
+
+        return remote_docs, progress
+
+    def _monitor_batch(
+        self,
+        ingest,
+        progress,
+        pbar,
+    ):
+        completed_files = set()
+
+        while (
+            ingest is not None
+            and ingest.ingest.status not in ["complete", "error", "cancelled"]
+        ):
+            time.sleep(3)
+            ingest = self.documents.get_processing_status_by_id(ingest.ingest.process_id)
+
+            if ingest.ingest.progress:
+                if ingest.ingest.progress.processing and ingest.ingest.progress.processing.documents:
+                    for doc in ingest.ingest.progress.processing.documents:
+                        if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
+                            pbar.update(0.75)
+                            progress -= 0.75
+                            completed_files.add(doc.document_id)
+                if ingest.ingest.progress.complete and ingest.ingest.progress.complete.documents:
+                    for doc in ingest.ingest.progress.complete.documents:
+                        if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
+                            pbar.update(0.75)
+                            progress -= 0.75
+                            completed_files.add(doc.document_id)
+                if ingest.ingest.progress.cancelled and ingest.ingest.progress.cancelled.documents:
+                    for doc in ingest.ingest.progress.cancelled.documents:
+                        if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
+                            pbar.update(0.75)
+                            progress -= 0.75
+                            completed_files.add(doc.document_id)
+                if ingest.ingest.progress.errors and ingest.ingest.progress.errors.documents:
+                    for doc in ingest.ingest.progress.errors.documents:
+                        if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
+                            pbar.update(0.75)
+                            progress -= 0.75
+                            completed_files.add(doc.document_id)
+
+
+        if ingest.ingest.status in ["error", "cancelled"]:
+            raise ValueError(f"Ingest failed with status: {ingest.ingest.status}")
+
+        return ingest, progress
+
     def _upload_file_batch(
         self,
         bucket_id,
@@ -356,7 +500,7 @@ class GroundX(GroundXBase):
     ):
         docs = []
 
-        progress = len(batch)
+        progress =  float(len(batch))
         for file in batch:
             url = self._upload_file(upload_api, file)
             if file.suffix.lower() in SUFFIX_ALIASES:
@@ -381,44 +525,10 @@ class GroundX(GroundXBase):
 
         if docs:
             ingest = self.ingest(documents=docs, request_options=request_options)
+            ingest, progress = self._monitor_batch(ingest, progress, pbar)
 
-            completed_files = set()
-
-            while (
-                ingest is not None
-                and ingest.ingest.status not in ["complete", "error", "cancelled"]
-            ):
-                time.sleep(3)
-                ingest = self.documents.get_processing_status_by_id(ingest.ingest.process_id)
-
-                if ingest.ingest.progress:
-                    if ingest.ingest.progress.processing and ingest.ingest.progress.processing.documents:
-                        for doc in ingest.ingest.progress.processing.documents:
-                            if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
-                                pbar.update(0.75)
-                                progress -= 0.75
-                    if ingest.ingest.progress.complete and ingest.ingest.progress.complete.documents:
-                        for doc in ingest.ingest.progress.complete.documents:
-                            if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
-                                pbar.update(0.75)
-                                progress -= 0.75
-                    if ingest.ingest.progress.cancelled and ingest.ingest.progress.cancelled.documents:
-                        for doc in ingest.ingest.progress.cancelled.documents:
-                            if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
-                                pbar.update(0.75)
-                                progress -= 0.75
-                    if ingest.ingest.progress.errors and ingest.ingest.progress.errors.documents:
-                        for doc in ingest.ingest.progress.errors.documents:
-                            if doc.status in ["complete", "error", "cancelled"] and doc.document_id not in completed_files:
-                                pbar.update(0.75)
-                                progress -= 0.75
-
-
-            if ingest.ingest.status in ["error", "cancelled"]:
-                raise ValueError(f"Ingest failed with status: {ingest.ingest.status}")
-
-            if progress > 0:
-                pbar.update(progress)
+        if progress > 0:
+            pbar.update(progress)
 
 
 

{groundx-2.2.9 → groundx-2.3.3}/src/groundx/search/client.py

@@ -29,6 +29,7 @@ class SearchClient:
         n: typing.Optional[int] = None,
         next_token: typing.Optional[str] = None,
         verbosity: typing.Optional[int] = None,
+        filter: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         relevance: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SearchResponse:
@@ -39,7 +40,7 @@ class SearchClient:
         Parameters
         ----------
         id : SearchContentRequestId
-            The bucketId, groupId, projectId, or documentId to be searched. The document or documents within the specified container will be compared to the query, and relevant information will be extracted.
+            The bucketId, groupId, or documentId to be searched. The document or documents within the specified container will be compared to the query, and relevant information will be extracted.
 
         query : str
             The search query to be used to find relevant documentation.
@@ -53,6 +54,9 @@ class SearchClient:
         verbosity : typing.Optional[int]
             The amount of data returned with each search result. 0 == no search results, only the recommended context. 1 == search results but no searchData. 2 == search results and searchData.
 
+        filter : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            A dictionary of key-value pairs that can be used to pre-filter documents prior to a search.
+
         relevance : typing.Optional[float]
             The minimum search relevance score required to include the result. By default, this is 10.0.
 
@@ -87,6 +91,7 @@ class SearchClient:
             },
             json={
                 "query": query,
+                "filter": filter,
                 "relevance": relevance,
             },
             headers={
@@ -137,6 +142,7 @@ class SearchClient:
         n: typing.Optional[int] = None,
         next_token: typing.Optional[str] = None,
         verbosity: typing.Optional[int] = None,
+        filter: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         relevance: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SearchResponse:
@@ -161,6 +167,9 @@ class SearchClient:
         verbosity : typing.Optional[int]
             The amount of data returned with each search result. 0 == no search results, only the recommended context. 1 == search results but no searchData. 2 == search results and searchData.
 
+        filter : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            A dictionary of key-value pairs that can be used to pre-filter documents prior to a search.
+
         relevance : typing.Optional[float]
             The minimum search relevance score required to include the result. By default, this is 10.0.
 
@@ -196,6 +205,7 @@ class SearchClient:
             json={
                 "query": query,
                 "documentIds": document_ids,
+                "filter": filter,
                 "relevance": relevance,
             },
             headers={
@@ -251,6 +261,7 @@ class AsyncSearchClient:
         n: typing.Optional[int] = None,
         next_token: typing.Optional[str] = None,
         verbosity: typing.Optional[int] = None,
+        filter: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         relevance: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SearchResponse:
@@ -261,7 +272,7 @@ class AsyncSearchClient:
         Parameters
         ----------
         id : SearchContentRequestId
-            The bucketId, groupId, projectId, or documentId to be searched. The document or documents within the specified container will be compared to the query, and relevant information will be extracted.
+            The bucketId, groupId, or documentId to be searched. The document or documents within the specified container will be compared to the query, and relevant information will be extracted.
 
         query : str
             The search query to be used to find relevant documentation.
@@ -275,6 +286,9 @@ class AsyncSearchClient:
         verbosity : typing.Optional[int]
             The amount of data returned with each search result. 0 == no search results, only the recommended context. 1 == search results but no searchData. 2 == search results and searchData.
 
+        filter : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            A dictionary of key-value pairs that can be used to pre-filter documents prior to a search.
+
         relevance : typing.Optional[float]
             The minimum search relevance score required to include the result. By default, this is 10.0.
 
@@ -317,6 +331,7 @@ class AsyncSearchClient:
             },
             json={
                 "query": query,
+                "filter": filter,
                 "relevance": relevance,
             },
             headers={
@@ -367,6 +382,7 @@ class AsyncSearchClient:
         n: typing.Optional[int] = None,
         next_token: typing.Optional[str] = None,
         verbosity: typing.Optional[int] = None,
+        filter: typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]] = OMIT,
         relevance: typing.Optional[float] = OMIT,
         request_options: typing.Optional[RequestOptions] = None,
     ) -> SearchResponse:
@@ -391,6 +407,9 @@ class AsyncSearchClient:
         verbosity : typing.Optional[int]
             The amount of data returned with each search result. 0 == no search results, only the recommended context. 1 == search results but no searchData. 2 == search results and searchData.
 
+        filter : typing.Optional[typing.Dict[str, typing.Optional[typing.Any]]]
+            A dictionary of key-value pairs that can be used to pre-filter documents prior to a search.
+
         relevance : typing.Optional[float]
             The minimum search relevance score required to include the result. By default, this is 10.0.
 
@@ -434,6 +453,7 @@ class AsyncSearchClient:
             json={
                 "query": query,
                 "documentIds": document_ids,
+                "filter": filter,
                 "relevance": relevance,
             },
             headers={