llama-stack 0.0.42__py3-none-any.whl → 0.3.4__py3-none-any.whl

llama_stack/providers/remote/files/s3/files.py

@@ -0,0 +1,313 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import uuid
+from datetime import UTC, datetime
+from typing import Annotated, Any
+
+import boto3
+from botocore.exceptions import BotoCoreError, ClientError, NoCredentialsError
+from fastapi import Depends, File, Form, Response, UploadFile
+
+from llama_stack.apis.common.errors import ResourceNotFoundError
+from llama_stack.apis.common.responses import Order
+from llama_stack.apis.files import (
+    ExpiresAfter,
+    Files,
+    ListOpenAIFileResponse,
+    OpenAIFileDeleteResponse,
+    OpenAIFileObject,
+    OpenAIFilePurpose,
+)
+from llama_stack.core.datatypes import AccessRule
+from llama_stack.core.id_generation import generate_object_id
+from llama_stack.providers.utils.files.form_data import parse_expires_after
+from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
+from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
+from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
+
+from .config import S3FilesImplConfig
+
+# TODO: provider data for S3 credentials
+
+
+def _create_s3_client(config: S3FilesImplConfig) -> boto3.client:
+    try:
+        s3_config = {
+            "region_name": config.region,
+        }
+
+        # endpoint URL if specified (for MinIO, LocalStack, etc.)
+        if config.endpoint_url:
+            s3_config["endpoint_url"] = config.endpoint_url
+
+        if config.aws_access_key_id and config.aws_secret_access_key:
+            s3_config.update(
+                {
+                    "aws_access_key_id": config.aws_access_key_id,
+                    "aws_secret_access_key": config.aws_secret_access_key,
+                }
+            )
+
+        return boto3.client("s3", **s3_config)
+
+    except (BotoCoreError, NoCredentialsError) as e:
+        raise RuntimeError(f"Failed to initialize S3 client: {e}") from e
+
+
+async def _create_bucket_if_not_exists(client: boto3.client, config: S3FilesImplConfig) -> None:
+    try:
+        client.head_bucket(Bucket=config.bucket_name)
+    except ClientError as e:
+        error_code = e.response["Error"]["Code"]
+        if error_code == "404":
+            if not config.auto_create_bucket:
+                raise RuntimeError(
+                    f"S3 bucket '{config.bucket_name}' does not exist. "
+                    f"Either create the bucket manually or set 'auto_create_bucket: true' in your configuration."
+                ) from e
+            try:
+                # For us-east-1, we can't specify LocationConstraint
+                if config.region == "us-east-1":
+                    client.create_bucket(Bucket=config.bucket_name)
+                else:
+                    client.create_bucket(
+                        Bucket=config.bucket_name,
+                        CreateBucketConfiguration={"LocationConstraint": config.region},
+                    )
+            except ClientError as create_error:
+                raise RuntimeError(
+                    f"Failed to create S3 bucket '{config.bucket_name}': {create_error}"
+                ) from create_error
+        elif error_code == "403":
+            raise RuntimeError(f"Access denied to S3 bucket '{config.bucket_name}'") from e
+        else:
+            raise RuntimeError(f"Failed to access S3 bucket '{config.bucket_name}': {e}") from e
+
+
+def _make_file_object(
+    *,
+    id: str,
+    filename: str,
+    purpose: str,
+    bytes: int,
+    created_at: int,
+    expires_at: int,
+    **kwargs: Any,  # here to ignore any additional fields, e.g. extra fields from AuthorizedSqlStore
+) -> OpenAIFileObject:
+    """
+    Construct an OpenAIFileObject and normalize expires_at.
+
+    If expires_at is greater than the max we treat it as no-expiration and
+    return None for expires_at.
+
+    The OpenAI spec says expires_at type is Integer, but the implementation
+    will return None for no expiration.
+    """
+    obj = OpenAIFileObject(
+        id=id,
+        filename=filename,
+        purpose=OpenAIFilePurpose(purpose),
+        bytes=bytes,
+        created_at=created_at,
+        expires_at=expires_at,
+    )
+
+    if obj.expires_at is not None and obj.expires_at > (obj.created_at + ExpiresAfter.MAX):
+        obj.expires_at = None  # type: ignore
+
+    return obj
+
+
+class S3FilesImpl(Files):
+    """S3-based implementation of the Files API."""
+
+    def __init__(self, config: S3FilesImplConfig, policy: list[AccessRule]) -> None:
+        self._config = config
+        self.policy = policy
+        self._client: boto3.client | None = None
+        self._sql_store: AuthorizedSqlStore | None = None
+
+    def _now(self) -> int:
+        """Return current UTC timestamp as int seconds."""
+        return int(datetime.now(UTC).timestamp())
+
+    async def _get_file(self, file_id: str, return_expired: bool = False) -> dict[str, Any]:
+        where: dict[str, str | dict] = {"id": file_id}
+        if not return_expired:
+            where["expires_at"] = {">": self._now()}
+        if not (row := await self.sql_store.fetch_one("openai_files", where=where)):
+            raise ResourceNotFoundError(file_id, "File", "files.list()")
+        return row
+
+    async def _delete_file(self, file_id: str) -> None:
+        """Delete a file from S3 and the database."""
+        try:
+            self.client.delete_object(
+                Bucket=self._config.bucket_name,
+                Key=file_id,
+            )
+        except ClientError as e:
+            if e.response["Error"]["Code"] != "NoSuchKey":
+                raise RuntimeError(f"Failed to delete file from S3: {e}") from e
+
+        await self.sql_store.delete("openai_files", where={"id": file_id})
+
+    async def _delete_if_expired(self, file_id: str) -> None:
+        """If the file exists and is expired, delete it."""
+        if row := await self._get_file(file_id, return_expired=True):
+            if (expires_at := row.get("expires_at")) and expires_at <= self._now():
+                await self._delete_file(file_id)
+
+    async def initialize(self) -> None:
+        self._client = _create_s3_client(self._config)
+        await _create_bucket_if_not_exists(self._client, self._config)
+
+        self._sql_store = AuthorizedSqlStore(sqlstore_impl(self._config.metadata_store), self.policy)
+        await self._sql_store.create_table(
+            "openai_files",
+            {
+                "id": ColumnDefinition(type=ColumnType.STRING, primary_key=True),
+                "filename": ColumnType.STRING,
+                "purpose": ColumnType.STRING,
+                "bytes": ColumnType.INTEGER,
+                "created_at": ColumnType.INTEGER,
+                "expires_at": ColumnType.INTEGER,
+                # TODO: add s3_etag field for integrity checking
+            },
+        )
+
+    async def shutdown(self) -> None:
+        pass
+
+    @property
+    def client(self) -> boto3.client:
+        assert self._client is not None, "Provider not initialized"
+        return self._client
+
+    @property
+    def sql_store(self) -> AuthorizedSqlStore:
+        assert self._sql_store is not None, "Provider not initialized"
+        return self._sql_store
+
+    async def openai_upload_file(
+        self,
+        file: Annotated[UploadFile, File()],
+        purpose: Annotated[OpenAIFilePurpose, Form()],
+        expires_after: Annotated[ExpiresAfter | None, Depends(parse_expires_after)] = None,
+    ) -> OpenAIFileObject:
+        file_id = generate_object_id("file", lambda: f"file-{uuid.uuid4().hex}")
+
+        filename = getattr(file, "filename", None) or "uploaded_file"
+
+        created_at = self._now()
+
+        # the default is no expiration.
+        # to implement no expiration we set an expiration beyond the max.
+        # we'll hide this fact from users when returning the file object.
+        expires_at = created_at + ExpiresAfter.MAX * 42
+        # the default for BATCH files is 30 days, which happens to be the expiration max.
+        if purpose == OpenAIFilePurpose.BATCH:
+            expires_at = created_at + ExpiresAfter.MAX
+
+        if expires_after is not None:
+            expires_at = created_at + expires_after.seconds
+
+        content = await file.read()
+        file_size = len(content)
+
+        entry: dict[str, Any] = {
+            "id": file_id,
+            "filename": filename,
+            "purpose": purpose.value,
+            "bytes": file_size,
+            "created_at": created_at,
+            "expires_at": expires_at,
+        }
+
+        await self.sql_store.insert("openai_files", entry)
+
+        try:
+            self.client.put_object(
+                Bucket=self._config.bucket_name,
+                Key=file_id,
+                Body=content,
+                # TODO: enable server-side encryption
+            )
+        except ClientError as e:
+            await self.sql_store.delete("openai_files", where={"id": file_id})
+
+            raise RuntimeError(f"Failed to upload file to S3: {e}") from e
+
+        return _make_file_object(**entry)
+
+    async def openai_list_files(
+        self,
+        after: str | None = None,
+        limit: int | None = 10000,
+        order: Order | None = Order.desc,
+        purpose: OpenAIFilePurpose | None = None,
+    ) -> ListOpenAIFileResponse:
+        # this purely defensive. it should not happen because the router also default to Order.desc.
+        if not order:
+            order = Order.desc
+
+        where_conditions: dict[str, Any] = {"expires_at": {">": self._now()}}
+        if purpose:
+            where_conditions["purpose"] = purpose.value
+
+        paginated_result = await self.sql_store.fetch_all(
+            table="openai_files",
+            where=where_conditions,
+            order_by=[("created_at", order.value)],
+            cursor=("id", after) if after else None,
+            limit=limit,
+        )
+
+        files = [_make_file_object(**row) for row in paginated_result.data]
+
+        return ListOpenAIFileResponse(
+            data=files,
+            has_more=paginated_result.has_more,
+            # empty string or None? spec says str, ref impl returns str | None, we go with spec
+            first_id=files[0].id if files else "",
+            last_id=files[-1].id if files else "",
+        )
+
+    async def openai_retrieve_file(self, file_id: str) -> OpenAIFileObject:
+        await self._delete_if_expired(file_id)
+        row = await self._get_file(file_id)
+        return _make_file_object(**row)
+
+    async def openai_delete_file(self, file_id: str) -> OpenAIFileDeleteResponse:
+        await self._delete_if_expired(file_id)
+        _ = await self._get_file(file_id)  # raises if not found
+        await self._delete_file(file_id)
+        return OpenAIFileDeleteResponse(id=file_id, deleted=True)
+
+    async def openai_retrieve_file_content(self, file_id: str) -> Response:
+        await self._delete_if_expired(file_id)
+
+        row = await self._get_file(file_id)
+
+        try:
+            response = self.client.get_object(
+                Bucket=self._config.bucket_name,
+                Key=row["id"],
+            )
+            # TODO: can we stream this instead of loading it into memory
+            content = response["Body"].read()
+        except ClientError as e:
+            if e.response["Error"]["Code"] == "NoSuchKey":
+                await self._delete_file(file_id)
+                raise ResourceNotFoundError(file_id, "File", "files.list()") from e
+            raise RuntimeError(f"Failed to download file from S3: {e}") from e
+
+        return Response(
+            content=content,
+            media_type="application/octet-stream",
+            headers={"Content-Disposition": f'attachment; filename="{row["filename"]}"'},
+        )

llama_stack/providers/remote/inference/__init__.py

@@ -0,0 +1,5 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.

llama_stack/providers/{adapters/safety/sample → remote/inference/anthropic}/__init__.py

@@ -4,14 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from typing import Any
+from .config import AnthropicConfig
 
-from .config import SampleConfig
 
+async def get_adapter_impl(config: AnthropicConfig, _deps):
+    from .anthropic import AnthropicInferenceAdapter
 
-async def get_adapter_impl(config: SampleConfig, _deps) -> Any:
-    from .sample import SampleSafetyImpl
-
-    impl = SampleSafetyImpl(config)
+    impl = AnthropicInferenceAdapter(config=config)
     await impl.initialize()
     return impl

llama_stack/providers/remote/inference/anthropic/anthropic.py

@@ -0,0 +1,36 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from collections.abc import Iterable
+
+from anthropic import AsyncAnthropic
+
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+
+from .config import AnthropicConfig
+
+
+class AnthropicInferenceAdapter(OpenAIMixin):
+    config: AnthropicConfig
+
+    provider_data_api_key_field: str = "anthropic_api_key"
+    # source: https://docs.claude.com/en/docs/build-with-claude/embeddings
+    # TODO: add support for voyageai, which is where these models are hosted
+    # embedding_model_metadata = {
+    #     "voyage-3-large": {"embedding_dimension": 1024, "context_length": 32000},  # supports dimensions 256, 512, 1024, 2048
+    #     "voyage-3.5": {"embedding_dimension": 1024, "context_length": 32000},  # supports dimensions 256, 512, 1024, 2048
+    #     "voyage-3.5-lite": {"embedding_dimension": 1024, "context_length": 32000},  # supports dimensions 256, 512, 1024, 2048
+    #     "voyage-code-3": {"embedding_dimension": 1024, "context_length": 32000},  # supports dimensions 256, 512, 1024, 2048
+    #     "voyage-finance-2": {"embedding_dimension": 1024, "context_length": 32000},
+    #     "voyage-law-2": {"embedding_dimension": 1024, "context_length": 16000},
+    #     "voyage-multimodal-3": {"embedding_dimension": 1024, "context_length": 32000},
+    # }
+
+    def get_base_url(self):
+        return "https://api.anthropic.com/v1"
+
+    async def list_provider_model_ids(self) -> Iterable[str]:
+        return [m.id async for m in AsyncAnthropic(api_key=self.get_api_key()).models.list()]

llama_stack/providers/remote/inference/anthropic/config.py

@@ -0,0 +1,28 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Any
+
+from pydantic import BaseModel, Field
+
+from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack.schema_utils import json_schema_type
+
+
+class AnthropicProviderDataValidator(BaseModel):
+    anthropic_api_key: str | None = Field(
+        default=None,
+        description="API key for Anthropic models",
+    )
+
+
+@json_schema_type
+class AnthropicConfig(RemoteInferenceProviderConfig):
+    @classmethod
+    def sample_run_config(cls, api_key: str = "${env.ANTHROPIC_API_KEY:=}", **kwargs) -> dict[str, Any]:
+        return {
+            "api_key": api_key,
+        }

llama_stack/providers/{impls/meta_reference/telemetry → remote/inference/azure}/__init__.py

@@ -4,12 +4,12 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .config import ConsoleConfig
+from .config import AzureConfig
 
 
-async def get_provider_impl(config: ConsoleConfig, _deps):
-    from .console import ConsoleTelemetryImpl
+async def get_adapter_impl(config: AzureConfig, _deps):
+    from .azure import AzureInferenceAdapter
 
-    impl = ConsoleTelemetryImpl(config)
+    impl = AzureInferenceAdapter(config=config)
     await impl.initialize()
     return impl

llama_stack/providers/remote/inference/azure/azure.py

@@ -0,0 +1,25 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from urllib.parse import urljoin
+
+from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
+
+from .config import AzureConfig
+
+
+class AzureInferenceAdapter(OpenAIMixin):
+    config: AzureConfig
+
+    provider_data_api_key_field: str = "azure_api_key"
+
+    def get_base_url(self) -> str:
+        """
+        Get the Azure API base URL.
+
+        Returns the Azure API base URL from the configuration.
+        """
+        return urljoin(str(self.config.api_base), "/openai/v1")

llama_stack/providers/remote/inference/azure/config.py

@@ -0,0 +1,61 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import os
+from typing import Any
+
+from pydantic import BaseModel, Field, HttpUrl, SecretStr
+
+from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig
+from llama_stack.schema_utils import json_schema_type
+
+
+class AzureProviderDataValidator(BaseModel):
+    azure_api_key: SecretStr = Field(
+        description="Azure API key for Azure",
+    )
+    azure_api_base: HttpUrl = Field(
+        description="Azure API base for Azure (e.g., https://your-resource-name.openai.azure.com)",
+    )
+    azure_api_version: str | None = Field(
+        default=None,
+        description="Azure API version for Azure (e.g., 2024-06-01)",
+    )
+    azure_api_type: str | None = Field(
+        default="azure",
+        description="Azure API type for Azure (e.g., azure)",
+    )
+
+
+@json_schema_type
+class AzureConfig(RemoteInferenceProviderConfig):
+    api_base: HttpUrl = Field(
+        description="Azure API base for Azure (e.g., https://your-resource-name.openai.azure.com)",
+    )
+    api_version: str | None = Field(
+        default_factory=lambda: os.getenv("AZURE_API_VERSION"),
+        description="Azure API version for Azure (e.g., 2024-12-01-preview)",
+    )
+    api_type: str | None = Field(
+        default_factory=lambda: os.getenv("AZURE_API_TYPE", "azure"),
+        description="Azure API type for Azure (e.g., azure)",
+    )
+
+    @classmethod
+    def sample_run_config(
+        cls,
+        api_key: str = "${env.AZURE_API_KEY:=}",
+        api_base: str = "${env.AZURE_API_BASE:=}",
+        api_version: str = "${env.AZURE_API_VERSION:=}",
+        api_type: str = "${env.AZURE_API_TYPE:=}",
+        **kwargs,
+    ) -> dict[str, Any]:
+        return {
+            "api_key": api_key,
+            "api_base": api_base,
+            "api_version": api_version,
+            "api_type": api_type,
+        }

llama_stack/providers/{adapters → remote}/inference/bedrock/__init__.py

@@ -1,17 +1,18 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-from .bedrock import BedrockInferenceAdapter
-from .config import BedrockConfig
-
-
-async def get_adapter_impl(config: BedrockConfig, _deps):
-    assert isinstance(config, BedrockConfig), f"Unexpected config type: {type(config)}"
-
-    impl = BedrockInferenceAdapter(config)
-
-    await impl.initialize()
-
-    return impl
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+from .config import BedrockConfig
+
+
+async def get_adapter_impl(config: BedrockConfig, _deps):
+    from .bedrock import BedrockInferenceAdapter
+
+    assert isinstance(config, BedrockConfig), f"Unexpected config type: {type(config)}"
+
+    impl = BedrockInferenceAdapter(config)
+
+    await impl.initialize()
+
+    return impl

llama_stack/providers/remote/inference/bedrock/bedrock.py

@@ -0,0 +1,142 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import json
+from collections.abc import AsyncIterator
+
+from botocore.client import BaseClient
+
+from llama_stack.apis.inference import (
+    ChatCompletionRequest,
+    Inference,
+    OpenAIChatCompletionRequestWithExtraBody,
+    OpenAICompletionRequestWithExtraBody,
+    OpenAIEmbeddingsRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+)
+from llama_stack.apis.inference.inference import (
+    OpenAIChatCompletion,
+    OpenAIChatCompletionChunk,
+    OpenAICompletion,
+)
+from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
+from llama_stack.providers.utils.bedrock.client import create_bedrock_client
+from llama_stack.providers.utils.inference.model_registry import (
+    ModelRegistryHelper,
+)
+from llama_stack.providers.utils.inference.openai_compat import (
+    get_sampling_strategy_options,
+)
+from llama_stack.providers.utils.inference.prompt_adapter import (
+    chat_completion_request_to_prompt,
+)
+
+from .models import MODEL_ENTRIES
+
+REGION_PREFIX_MAP = {
+    "us": "us.",
+    "eu": "eu.",
+    "ap": "ap.",
+}
+
+
+def _get_region_prefix(region: str | None) -> str:
+    # AWS requires region prefixes for inference profiles
+    if region is None:
+        return "us."  # default to US when we don't know
+
+    # Handle case insensitive region matching
+    region_lower = region.lower()
+    for prefix in REGION_PREFIX_MAP:
+        if region_lower.startswith(f"{prefix}-"):
+            return REGION_PREFIX_MAP[prefix]
+
+    # Fallback to US for anything we don't recognize
+    return "us."
+
+
+def _to_inference_profile_id(model_id: str, region: str = None) -> str:
+    # Return ARNs unchanged
+    if model_id.startswith("arn:"):
+        return model_id
+
+    # Return inference profile IDs that already have regional prefixes
+    if any(model_id.startswith(p) for p in REGION_PREFIX_MAP.values()):
+        return model_id
+
+    # Default to US East when no region is provided
+    if region is None:
+        region = "us-east-1"
+
+    return _get_region_prefix(region) + model_id
+
+
+class BedrockInferenceAdapter(
+    ModelRegistryHelper,
+    Inference,
+):
+    def __init__(self, config: BedrockConfig) -> None:
+        ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES)
+        self._config = config
+        self._client = None
+
+    @property
+    def client(self) -> BaseClient:
+        if self._client is None:
+            self._client = create_bedrock_client(self._config)
+        return self._client
+
+    async def initialize(self) -> None:
+        pass
+
+    async def shutdown(self) -> None:
+        if self._client is not None:
+            self._client.close()
+
+    async def _get_params_for_chat_completion(self, request: ChatCompletionRequest) -> dict:
+        bedrock_model = request.model
+
+        sampling_params = request.sampling_params
+        options = get_sampling_strategy_options(sampling_params)
+
+        if sampling_params.max_tokens:
+            options["max_gen_len"] = sampling_params.max_tokens
+        if sampling_params.repetition_penalty > 0:
+            options["repetition_penalty"] = sampling_params.repetition_penalty
+
+        prompt = await chat_completion_request_to_prompt(request, self.get_llama_model(request.model))
+
+        # Convert foundation model ID to inference profile ID
+        region_name = self.client.meta.region_name
+        inference_profile_id = _to_inference_profile_id(bedrock_model, region_name)
+
+        return {
+            "modelId": inference_profile_id,
+            "body": json.dumps(
+                {
+                    "prompt": prompt,
+                    **options,
+                }
+            ),
+        }
+
+    async def openai_embeddings(
+        self,
+        params: OpenAIEmbeddingsRequestWithExtraBody,
+    ) -> OpenAIEmbeddingsResponse:
+        raise NotImplementedError()
+
+    async def openai_completion(
+        self,
+        params: OpenAICompletionRequestWithExtraBody,
+    ) -> OpenAICompletion:
+        raise NotImplementedError("OpenAI completion not supported by the Bedrock provider")
+
+    async def openai_chat_completion(
+        self,
+        params: OpenAIChatCompletionRequestWithExtraBody,
+    ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
+        raise NotImplementedError("OpenAI chat completion not supported by the Bedrock provider")