antfly-sdk 0.0.2.dev2__py3-none-any.whl

antfly/client_generated/api/default/generate_embeddings.py

@@ -0,0 +1,204 @@
+from http import HTTPStatus
+from typing import Any
+
+import httpx
+
+from ... import errors
+from ...client import AuthenticatedClient, Client
+from ...models.inference_embed_request import InferenceEmbedRequest
+from ...models.inference_embed_response import InferenceEmbedResponse
+from ...models.inference_error import InferenceError
+from ...types import Response
+
+
+def _get_kwargs(
+    *,
+    body: InferenceEmbedRequest,
+) -> dict[str, Any]:
+    headers: dict[str, Any] = {}
+
+    _kwargs: dict[str, Any] = {
+        "method": "post",
+        "url": "/ai/v1/embed",
+    }
+
+    _kwargs["json"] = body.to_dict()
+
+    headers["Content-Type"] = "application/json"
+
+    _kwargs["headers"] = headers
+    return _kwargs
+
+
+def _parse_response(
+    *, client: AuthenticatedClient | Client, response: httpx.Response
+) -> InferenceEmbedResponse | InferenceError | None:
+    if response.status_code == 200:
+        response_200 = InferenceEmbedResponse.from_dict(response.json())
+
+        return response_200
+
+    if response.status_code == 400:
+        response_400 = InferenceError.from_dict(response.json())
+
+        return response_400
+
+    if response.status_code == 404:
+        response_404 = InferenceError.from_dict(response.json())
+
+        return response_404
+
+    if response.status_code == 500:
+        response_500 = InferenceError.from_dict(response.json())
+
+        return response_500
+
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(
+    *, client: AuthenticatedClient | Client, response: httpx.Response
+) -> Response[InferenceEmbedResponse | InferenceError]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+    body: InferenceEmbedRequest,
+) -> Response[InferenceEmbedResponse | InferenceError]:
+    """Create embeddings (alias of `/embeddings`)
+
+     Alias of `/ai/v1/embeddings`.
+
+    Accepts the OpenAI embeddings request shape and returns the same OpenAI-compatible
+    response envelope. For sparse-capable models, `data[i].embedding` is a sparse
+    vector object instead of a dense float array.
+
+    Args:
+        body (InferenceEmbedRequest): OpenAI-compatible embedding request with inference
+            multimodal content-part extension
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[InferenceEmbedResponse | InferenceError]
+    """
+
+    kwargs = _get_kwargs(
+        body=body,
+    )
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+
+def sync(
+    *,
+    client: AuthenticatedClient | Client,
+    body: InferenceEmbedRequest,
+) -> InferenceEmbedResponse | InferenceError | None:
+    """Create embeddings (alias of `/embeddings`)
+
+     Alias of `/ai/v1/embeddings`.
+
+    Accepts the OpenAI embeddings request shape and returns the same OpenAI-compatible
+    response envelope. For sparse-capable models, `data[i].embedding` is a sparse
+    vector object instead of a dense float array.
+
+    Args:
+        body (InferenceEmbedRequest): OpenAI-compatible embedding request with inference
+            multimodal content-part extension
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        InferenceEmbedResponse | InferenceError
+    """
+
+    return sync_detailed(
+        client=client,
+        body=body,
+    ).parsed
+
+
+async def asyncio_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+    body: InferenceEmbedRequest,
+) -> Response[InferenceEmbedResponse | InferenceError]:
+    """Create embeddings (alias of `/embeddings`)
+
+     Alias of `/ai/v1/embeddings`.
+
+    Accepts the OpenAI embeddings request shape and returns the same OpenAI-compatible
+    response envelope. For sparse-capable models, `data[i].embedding` is a sparse
+    vector object instead of a dense float array.
+
+    Args:
+        body (InferenceEmbedRequest): OpenAI-compatible embedding request with inference
+            multimodal content-part extension
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[InferenceEmbedResponse | InferenceError]
+    """
+
+    kwargs = _get_kwargs(
+        body=body,
+    )
+
+    response = await client.get_async_httpx_client().request(**kwargs)
+
+    return _build_response(client=client, response=response)
+
+
+async def asyncio(
+    *,
+    client: AuthenticatedClient | Client,
+    body: InferenceEmbedRequest,
+) -> InferenceEmbedResponse | InferenceError | None:
+    """Create embeddings (alias of `/embeddings`)
+
+     Alias of `/ai/v1/embeddings`.
+
+    Accepts the OpenAI embeddings request shape and returns the same OpenAI-compatible
+    response envelope. For sparse-capable models, `data[i].embedding` is a sparse
+    vector object instead of a dense float array.
+
+    Args:
+        body (InferenceEmbedRequest): OpenAI-compatible embedding request with inference
+            multimodal content-part extension
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        InferenceEmbedResponse | InferenceError
+    """
+
+    return (
+        await asyncio_detailed(
+            client=client,
+            body=body,
+        )
+    ).parsed

antfly/client_generated/api/default/list_models.py

@@ -0,0 +1,327 @@
+from http import HTTPStatus
+from typing import Any
+
+import httpx
+
+from ... import errors
+from ...client import AuthenticatedClient, Client
+from ...models.inference_error import InferenceError
+from ...models.inference_models_response import InferenceModelsResponse
+from ...types import Response
+
+
+def _get_kwargs() -> dict[str, Any]:
+
+    _kwargs: dict[str, Any] = {
+        "method": "get",
+        "url": "/ai/v1/models",
+    }
+
+    return _kwargs
+
+
+def _parse_response(
+    *, client: AuthenticatedClient | Client, response: httpx.Response
+) -> InferenceError | InferenceModelsResponse | None:
+    if response.status_code == 200:
+        response_200 = InferenceModelsResponse.from_dict(response.json())
+
+        return response_200
+
+    if response.status_code == 400:
+        response_400 = InferenceError.from_dict(response.json())
+
+        return response_400
+
+    if response.status_code == 500:
+        response_500 = InferenceError.from_dict(response.json())
+
+        return response_500
+
+    if client.raise_on_unexpected_status:
+        raise errors.UnexpectedStatus(response.status_code, response.content)
+    else:
+        return None
+
+
+def _build_response(
+    *, client: AuthenticatedClient | Client, response: httpx.Response
+) -> Response[InferenceError | InferenceModelsResponse]:
+    return Response(
+        status_code=HTTPStatus(response.status_code),
+        content=response.content,
+        headers=response.headers,
+        parsed=_parse_response(client=client, response=response),
+    )
+
+
+def sync_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+) -> Response[InferenceError | InferenceModelsResponse]:
+    r"""List available models
+
+     Returns lists of available embedding, chunking, reranking, generator, NER, rewriter, reader, and
+    transcriber models.
+
+    ## Embedders
+
+    - ONNX models from `models_dir/embedders/`
+    - Quantized variants have `-i8` suffix
+
+    ## Chunkers
+
+    - Always includes \"fixed\" (built-in)
+    - Plus any ONNX models from `models_dir/chunkers/`
+
+    ## Rerankers
+
+    - Native or ONNX rerankers from `models_dir/rerankers/`
+    - `model_manifest.json` capabilities can mark late-interaction text rerankers (`late_interaction`,
+    `colbert`)
+    - Empty if no models configured
+
+    ## Generators
+
+    - LLM models from `models_dir/generators/`
+    - Empty if no models configured
+
+    ## Recognizers
+
+    - ONNX models from `models_dir/recognizers/`
+    - Includes GLiNER models for zero-shot recognition
+
+    ## Rewriters
+
+    - Seq2Seq models from `models_dir/rewriters/`
+    - T5, FLAN-T5, BART, and LMQG question generation models
+
+    ## Readers
+
+    - Vision2Seq models from `models_dir/readers/`
+    - TrOCR, Donut, Florence-2 for OCR and document understanding
+
+    ## Transcribers
+
+    - Speech2Seq models from `models_dir/transcribers/`
+    - Whisper, Wav2Vec2, HuBERT for speech-to-text
+
+    Models are discovered at service startup and cached.
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[InferenceError | InferenceModelsResponse]
+    """
+
+    kwargs = _get_kwargs()
+
+    response = client.get_httpx_client().request(
+        **kwargs,
+    )
+
+    return _build_response(client=client, response=response)
+
+
+def sync(
+    *,
+    client: AuthenticatedClient | Client,
+) -> InferenceError | InferenceModelsResponse | None:
+    r"""List available models
+
+     Returns lists of available embedding, chunking, reranking, generator, NER, rewriter, reader, and
+    transcriber models.
+
+    ## Embedders
+
+    - ONNX models from `models_dir/embedders/`
+    - Quantized variants have `-i8` suffix
+
+    ## Chunkers
+
+    - Always includes \"fixed\" (built-in)
+    - Plus any ONNX models from `models_dir/chunkers/`
+
+    ## Rerankers
+
+    - Native or ONNX rerankers from `models_dir/rerankers/`
+    - `model_manifest.json` capabilities can mark late-interaction text rerankers (`late_interaction`,
+    `colbert`)
+    - Empty if no models configured
+
+    ## Generators
+
+    - LLM models from `models_dir/generators/`
+    - Empty if no models configured
+
+    ## Recognizers
+
+    - ONNX models from `models_dir/recognizers/`
+    - Includes GLiNER models for zero-shot recognition
+
+    ## Rewriters
+
+    - Seq2Seq models from `models_dir/rewriters/`
+    - T5, FLAN-T5, BART, and LMQG question generation models
+
+    ## Readers
+
+    - Vision2Seq models from `models_dir/readers/`
+    - TrOCR, Donut, Florence-2 for OCR and document understanding
+
+    ## Transcribers
+
+    - Speech2Seq models from `models_dir/transcribers/`
+    - Whisper, Wav2Vec2, HuBERT for speech-to-text
+
+    Models are discovered at service startup and cached.
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        InferenceError | InferenceModelsResponse
+    """
+
+    return sync_detailed(
+        client=client,
+    ).parsed
+
+
+async def asyncio_detailed(
+    *,
+    client: AuthenticatedClient | Client,
+) -> Response[InferenceError | InferenceModelsResponse]:
+    r"""List available models
+
+     Returns lists of available embedding, chunking, reranking, generator, NER, rewriter, reader, and
+    transcriber models.
+
+    ## Embedders
+
+    - ONNX models from `models_dir/embedders/`
+    - Quantized variants have `-i8` suffix
+
+    ## Chunkers
+
+    - Always includes \"fixed\" (built-in)
+    - Plus any ONNX models from `models_dir/chunkers/`
+
+    ## Rerankers
+
+    - Native or ONNX rerankers from `models_dir/rerankers/`
+    - `model_manifest.json` capabilities can mark late-interaction text rerankers (`late_interaction`,
+    `colbert`)
+    - Empty if no models configured
+
+    ## Generators
+
+    - LLM models from `models_dir/generators/`
+    - Empty if no models configured
+
+    ## Recognizers
+
+    - ONNX models from `models_dir/recognizers/`
+    - Includes GLiNER models for zero-shot recognition
+
+    ## Rewriters
+
+    - Seq2Seq models from `models_dir/rewriters/`
+    - T5, FLAN-T5, BART, and LMQG question generation models
+
+    ## Readers
+
+    - Vision2Seq models from `models_dir/readers/`
+    - TrOCR, Donut, Florence-2 for OCR and document understanding
+
+    ## Transcribers
+
+    - Speech2Seq models from `models_dir/transcribers/`
+    - Whisper, Wav2Vec2, HuBERT for speech-to-text
+
+    Models are discovered at service startup and cached.
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[InferenceError | InferenceModelsResponse]
+    """
+
+    kwargs = _get_kwargs()
+
+    response = await client.get_async_httpx_client().request(**kwargs)
+
+    return _build_response(client=client, response=response)
+
+
+async def asyncio(
+    *,
+    client: AuthenticatedClient | Client,
+) -> InferenceError | InferenceModelsResponse | None:
+    r"""List available models
+
+     Returns lists of available embedding, chunking, reranking, generator, NER, rewriter, reader, and
+    transcriber models.
+
+    ## Embedders
+
+    - ONNX models from `models_dir/embedders/`
+    - Quantized variants have `-i8` suffix
+
+    ## Chunkers
+
+    - Always includes \"fixed\" (built-in)
+    - Plus any ONNX models from `models_dir/chunkers/`
+
+    ## Rerankers
+
+    - Native or ONNX rerankers from `models_dir/rerankers/`
+    - `model_manifest.json` capabilities can mark late-interaction text rerankers (`late_interaction`,
+    `colbert`)
+    - Empty if no models configured
+
+    ## Generators
+
+    - LLM models from `models_dir/generators/`
+    - Empty if no models configured
+
+    ## Recognizers
+
+    - ONNX models from `models_dir/recognizers/`
+    - Includes GLiNER models for zero-shot recognition
+
+    ## Rewriters
+
+    - Seq2Seq models from `models_dir/rewriters/`
+    - T5, FLAN-T5, BART, and LMQG question generation models
+
+    ## Readers
+
+    - Vision2Seq models from `models_dir/readers/`
+    - TrOCR, Donut, Florence-2 for OCR and document understanding
+
+    ## Transcribers
+
+    - Speech2Seq models from `models_dir/transcribers/`
+    - Whisper, Wav2Vec2, HuBERT for speech-to-text
+
+    Models are discovered at service startup and cached.
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        InferenceError | InferenceModelsResponse
+    """
+
+    return (
+        await asyncio_detailed(
+            client=client,
+        )
+    ).parsed