vellum-ai 0.5.2__py3-none-any.whl → 0.6.0__py3-none-any.whl

vellum/types/basic_vectorizer_sentence_transformers_multi_qa_mpnet_base_cos_v_1_request.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class BasicVectorizerSentenceTransformersMultiQaMpnetBaseCosV1Request(pydantic_v1.BaseModel):
+    """
+    Basic vectorizer for sentence-transformers/multi-qa-mpnet-base-cos-v1.
+    """
+
+    config: typing.Optional[typing.Dict[str, typing.Any]] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/basic_vectorizer_sentence_transformers_multi_qa_mpnet_base_dot_v_1.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1(pydantic_v1.BaseModel):
+    """
+    Basic vectorizer for sentence-transformers/multi-qa-mpnet-base-dot-v1.
+    """
+
+    config: typing.Optional[typing.Dict[str, typing.Any]] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/basic_vectorizer_sentence_transformers_multi_qa_mpnet_base_dot_v_1_request.py

@@ -0,0 +1,29 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+
+
+class BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1Request(pydantic_v1.BaseModel):
+    """
+    Basic vectorizer for sentence-transformers/multi-qa-mpnet-base-dot-v1.
+    """
+
+    config: typing.Optional[typing.Dict[str, typing.Any]] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/document_index_chunking.py

@@ -0,0 +1,46 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+from .reducto_chunking import ReductoChunking
+from .sentence_chunking import SentenceChunking
+from .token_overlapping_window_chunking import TokenOverlappingWindowChunking
+
+
+class DocumentIndexChunking_ReductoChunker(ReductoChunking):
+    chunker_name: typing.Literal["reducto-chunker"] = "reducto-chunker"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class DocumentIndexChunking_SentenceChunker(SentenceChunking):
+    chunker_name: typing.Literal["sentence-chunker"] = "sentence-chunker"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class DocumentIndexChunking_TokenOverlappingWindowChunker(TokenOverlappingWindowChunking):
+    chunker_name: typing.Literal["token-overlapping-window-chunker"] = "token-overlapping-window-chunker"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+DocumentIndexChunking = typing.Union[
+    DocumentIndexChunking_ReductoChunker,
+    DocumentIndexChunking_SentenceChunker,
+    DocumentIndexChunking_TokenOverlappingWindowChunker,
+]

vellum/types/document_index_chunking_request.py

@@ -0,0 +1,46 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+from .reducto_chunking_request import ReductoChunkingRequest
+from .sentence_chunking_request import SentenceChunkingRequest
+from .token_overlapping_window_chunking_request import TokenOverlappingWindowChunkingRequest
+
+
+class DocumentIndexChunkingRequest_ReductoChunker(ReductoChunkingRequest):
+    chunker_name: typing.Literal["reducto-chunker"] = "reducto-chunker"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class DocumentIndexChunkingRequest_SentenceChunker(SentenceChunkingRequest):
+    chunker_name: typing.Literal["sentence-chunker"] = "sentence-chunker"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class DocumentIndexChunkingRequest_TokenOverlappingWindowChunker(TokenOverlappingWindowChunkingRequest):
+    chunker_name: typing.Literal["token-overlapping-window-chunker"] = "token-overlapping-window-chunker"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+DocumentIndexChunkingRequest = typing.Union[
+    DocumentIndexChunkingRequest_ReductoChunker,
+    DocumentIndexChunkingRequest_SentenceChunker,
+    DocumentIndexChunkingRequest_TokenOverlappingWindowChunker,
+]

vellum/types/document_index_indexing_config.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .document_index_chunking import DocumentIndexChunking
+from .indexing_config_vectorizer import IndexingConfigVectorizer
+
+
+class DocumentIndexIndexingConfig(pydantic_v1.BaseModel):
+    vectorizer: IndexingConfigVectorizer
+    chunking: typing.Optional[DocumentIndexChunking] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/document_index_indexing_config_request.py

@@ -0,0 +1,28 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .document_index_chunking_request import DocumentIndexChunkingRequest
+from .indexing_config_vectorizer_request import IndexingConfigVectorizerRequest
+
+
+class DocumentIndexIndexingConfigRequest(pydantic_v1.BaseModel):
+    vectorizer: IndexingConfigVectorizerRequest
+    chunking: typing.Optional[DocumentIndexChunkingRequest] = None
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/document_index_read.py

@@ -5,6 +5,7 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from ..core.pydantic_utilities import pydantic_v1
+from .document_index_indexing_config import DocumentIndexIndexingConfig
 from .entity_status import EntityStatus
 from .environment_enum import EnvironmentEnum
 
@@ -39,10 +40,7 @@ class DocumentIndexRead(pydantic_v1.BaseModel):
     - `PRODUCTION` - Production
     """
 
-    indexing_config: typing.Dict[str, typing.Any] = pydantic_v1.Field()
-    """
-    Configuration representing how documents should be indexed
-    """
+    indexing_config: DocumentIndexIndexingConfig
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/function_call.py

@@ -1,31 +1,33 @@
 # This file was auto-generated by Fern from our API Definition.
 
-from __future__ import annotations
-
+import datetime as dt
 import typing
 
-from .fulfilled_function_call import FulfilledFunctionCall
-from .rejected_function_call import RejectedFunctionCall
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .fulfilled_enum import FulfilledEnum
 
 
-class FunctionCall_Fulfilled(FulfilledFunctionCall):
-    state: typing.Literal["FULFILLED"] = "FULFILLED"
+class FunctionCall(pydantic_v1.BaseModel):
+    """
+    The final resolved function call value.
+    """
 
-    class Config:
-        frozen = True
-        smart_union = True
-        allow_population_by_field_name = True
-        populate_by_name = True
+    arguments: typing.Dict[str, typing.Any]
+    id: typing.Optional[str] = None
+    name: str
+    state: typing.Optional[FulfilledEnum] = None
 
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
 
-class FunctionCall_Rejected(RejectedFunctionCall):
-    state: typing.Literal["REJECTED"] = "REJECTED"
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
 
     class Config:
         frozen = True
         smart_union = True
-        allow_population_by_field_name = True
-        populate_by_name = True
-
-
-FunctionCall = typing.Union[FunctionCall_Fulfilled, FunctionCall_Rejected]
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/{fulfilled_function_call_request.py → function_call_request.py}

@@ -8,15 +8,15 @@ from ..core.pydantic_utilities import pydantic_v1
 from .fulfilled_enum import FulfilledEnum
 
 
-class FulfilledFunctionCallRequest(pydantic_v1.BaseModel):
+class FunctionCallRequest(pydantic_v1.BaseModel):
     """
     The final resolved function call value.
     """
 
-    state: FulfilledEnum
     arguments: typing.Dict[str, typing.Any]
     id: typing.Optional[str] = None
     name: str
+    state: typing.Optional[FulfilledEnum] = None
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/function_call_vellum_value.py

@@ -13,7 +13,7 @@ class FunctionCallVellumValue(pydantic_v1.BaseModel):
     A value representing a Function Call.
     """
 
-    value: FunctionCall
+    value: typing.Optional[FunctionCall] = None
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/hkunlp_instructor_xl_enum.py

@@ -0,0 +1,5 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import typing
+
+HkunlpInstructorXlEnum = typing.Literal["hkunlp/instructor-xl"]

vellum/types/hkunlp_instructor_xl_vectorizer.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .instructor_vectorizer_config import InstructorVectorizerConfig
+
+
+class HkunlpInstructorXlVectorizer(pydantic_v1.BaseModel):
+    """
+    Vectorizer for hkunlp/instructor-xl.
+    """
+
+    config: InstructorVectorizerConfig
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/hkunlp_instructor_xl_vectorizer_request.py

@@ -0,0 +1,30 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import datetime as dt
+import typing
+
+from ..core.datetime_utils import serialize_datetime
+from ..core.pydantic_utilities import pydantic_v1
+from .instructor_vectorizer_config_request import InstructorVectorizerConfigRequest
+
+
+class HkunlpInstructorXlVectorizerRequest(pydantic_v1.BaseModel):
+    """
+    Vectorizer for hkunlp/instructor-xl.
+    """
+
+    config: InstructorVectorizerConfigRequest
+
+    def json(self, **kwargs: typing.Any) -> str:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().json(**kwargs_with_defaults)
+
+    def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
+        kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
+        return super().dict(**kwargs_with_defaults)
+
+    class Config:
+        frozen = True
+        smart_union = True
+        extra = pydantic_v1.Extra.allow
+        json_encoders = {dt.datetime: serialize_datetime}

vellum/types/{fulfilled_function_call.py → image_vellum_value.py}

@@ -5,16 +5,15 @@ import typing
 
 from ..core.datetime_utils import serialize_datetime
 from ..core.pydantic_utilities import pydantic_v1
+from .vellum_image import VellumImage
 
 
-class FulfilledFunctionCall(pydantic_v1.BaseModel):
+class ImageVellumValue(pydantic_v1.BaseModel):
     """
-    The final resolved function call value.
+    A base Vellum primitive value representing an image.
     """
 
-    arguments: typing.Dict[str, typing.Any]
-    id: typing.Optional[str] = None
-    name: str
+    value: typing.Optional[VellumImage] = None
 
     def json(self, **kwargs: typing.Any) -> str:
         kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}

vellum/types/indexing_config_vectorizer.py

@@ -0,0 +1,106 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+from .basic_vectorizer_intfloat_multilingual_e_5_large import BasicVectorizerIntfloatMultilingualE5Large
+from .basic_vectorizer_sentence_transformers_multi_qa_mpnet_base_cos_v_1 import (
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseCosV1,
+)
+from .basic_vectorizer_sentence_transformers_multi_qa_mpnet_base_dot_v_1 import (
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1,
+)
+from .hkunlp_instructor_xl_vectorizer import HkunlpInstructorXlVectorizer
+from .open_ai_vectorizer_text_embedding_3_large import OpenAiVectorizerTextEmbedding3Large
+from .open_ai_vectorizer_text_embedding_3_small import OpenAiVectorizerTextEmbedding3Small
+from .open_ai_vectorizer_text_embedding_ada_002 import OpenAiVectorizerTextEmbeddingAda002
+
+
+class IndexingConfigVectorizer_TextEmbedding3Small(OpenAiVectorizerTextEmbedding3Small):
+    model_name: typing.Literal["text-embedding-3-small"] = "text-embedding-3-small"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizer_TextEmbedding3Large(OpenAiVectorizerTextEmbedding3Large):
+    model_name: typing.Literal["text-embedding-3-large"] = "text-embedding-3-large"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizer_TextEmbeddingAda002(OpenAiVectorizerTextEmbeddingAda002):
+    model_name: typing.Literal["text-embedding-ada-002"] = "text-embedding-ada-002"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizer_IntfloatMultilingualE5Large(BasicVectorizerIntfloatMultilingualE5Large):
+    model_name: typing.Literal["intfloat/multilingual-e5-large"] = "intfloat/multilingual-e5-large"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizer_SentenceTransformersMultiQaMpnetBaseCosV1(
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseCosV1
+):
+    model_name: typing.Literal[
+        "sentence-transformers/multi-qa-mpnet-base-cos-v1"
+    ] = "sentence-transformers/multi-qa-mpnet-base-cos-v1"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizer_SentenceTransformersMultiQaMpnetBaseDotV1(
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1
+):
+    model_name: typing.Literal[
+        "sentence-transformers/multi-qa-mpnet-base-dot-v1"
+    ] = "sentence-transformers/multi-qa-mpnet-base-dot-v1"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizer_HkunlpInstructorXl(HkunlpInstructorXlVectorizer):
+    model_name: typing.Literal["hkunlp/instructor-xl"] = "hkunlp/instructor-xl"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+IndexingConfigVectorizer = typing.Union[
+    IndexingConfigVectorizer_TextEmbedding3Small,
+    IndexingConfigVectorizer_TextEmbedding3Large,
+    IndexingConfigVectorizer_TextEmbeddingAda002,
+    IndexingConfigVectorizer_IntfloatMultilingualE5Large,
+    IndexingConfigVectorizer_SentenceTransformersMultiQaMpnetBaseCosV1,
+    IndexingConfigVectorizer_SentenceTransformersMultiQaMpnetBaseDotV1,
+    IndexingConfigVectorizer_HkunlpInstructorXl,
+]

vellum/types/indexing_config_vectorizer_request.py

@@ -0,0 +1,106 @@
+# This file was auto-generated by Fern from our API Definition.
+
+from __future__ import annotations
+
+import typing
+
+from .basic_vectorizer_intfloat_multilingual_e_5_large_request import BasicVectorizerIntfloatMultilingualE5LargeRequest
+from .basic_vectorizer_sentence_transformers_multi_qa_mpnet_base_cos_v_1_request import (
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseCosV1Request,
+)
+from .basic_vectorizer_sentence_transformers_multi_qa_mpnet_base_dot_v_1_request import (
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1Request,
+)
+from .hkunlp_instructor_xl_vectorizer_request import HkunlpInstructorXlVectorizerRequest
+from .open_ai_vectorizer_text_embedding_3_large_request import OpenAiVectorizerTextEmbedding3LargeRequest
+from .open_ai_vectorizer_text_embedding_3_small_request import OpenAiVectorizerTextEmbedding3SmallRequest
+from .open_ai_vectorizer_text_embedding_ada_002_request import OpenAiVectorizerTextEmbeddingAda002Request
+
+
+class IndexingConfigVectorizerRequest_TextEmbedding3Small(OpenAiVectorizerTextEmbedding3SmallRequest):
+    model_name: typing.Literal["text-embedding-3-small"] = "text-embedding-3-small"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizerRequest_TextEmbedding3Large(OpenAiVectorizerTextEmbedding3LargeRequest):
+    model_name: typing.Literal["text-embedding-3-large"] = "text-embedding-3-large"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizerRequest_TextEmbeddingAda002(OpenAiVectorizerTextEmbeddingAda002Request):
+    model_name: typing.Literal["text-embedding-ada-002"] = "text-embedding-ada-002"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizerRequest_IntfloatMultilingualE5Large(BasicVectorizerIntfloatMultilingualE5LargeRequest):
+    model_name: typing.Literal["intfloat/multilingual-e5-large"] = "intfloat/multilingual-e5-large"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizerRequest_SentenceTransformersMultiQaMpnetBaseCosV1(
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseCosV1Request
+):
+    model_name: typing.Literal[
+        "sentence-transformers/multi-qa-mpnet-base-cos-v1"
+    ] = "sentence-transformers/multi-qa-mpnet-base-cos-v1"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizerRequest_SentenceTransformersMultiQaMpnetBaseDotV1(
+    BasicVectorizerSentenceTransformersMultiQaMpnetBaseDotV1Request
+):
+    model_name: typing.Literal[
+        "sentence-transformers/multi-qa-mpnet-base-dot-v1"
+    ] = "sentence-transformers/multi-qa-mpnet-base-dot-v1"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+class IndexingConfigVectorizerRequest_HkunlpInstructorXl(HkunlpInstructorXlVectorizerRequest):
+    model_name: typing.Literal["hkunlp/instructor-xl"] = "hkunlp/instructor-xl"
+
+    class Config:
+        frozen = True
+        smart_union = True
+        allow_population_by_field_name = True
+        populate_by_name = True
+
+
+IndexingConfigVectorizerRequest = typing.Union[
+    IndexingConfigVectorizerRequest_TextEmbedding3Small,
+    IndexingConfigVectorizerRequest_TextEmbedding3Large,
+    IndexingConfigVectorizerRequest_TextEmbeddingAda002,
+    IndexingConfigVectorizerRequest_IntfloatMultilingualE5Large,
+    IndexingConfigVectorizerRequest_SentenceTransformersMultiQaMpnetBaseCosV1,
+    IndexingConfigVectorizerRequest_SentenceTransformersMultiQaMpnetBaseDotV1,
+    IndexingConfigVectorizerRequest_HkunlpInstructorXl,
+]