mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-27 03:34:10 +00:00
Add Google AI Studio /v1/files upload API support (#9645)
* test: fix import for test
* fix: fix bad error string
* docs: cleanup files docs
* fix(files/main.py): cleanup error string
* style: initial commit with a provider/config pattern for files api
google ai studio files api onboarding
* fix: test
* feat(gemini/files/transformation.py): support gemini files api response transformation
* fix(gemini/files/transformation.py): return file id as gemini uri
allows id to be passed in to chat completion request, just like openai
* feat(llm_http_handler.py): support async route for files api on llm_http_handler
* fix: fix linting errors
* fix: fix model info check
* fix: fix ruff errors
* fix: fix linting errors
* Revert "fix: fix linting errors"
This reverts commit 926a5a527f.
* fix: fix linting errors
* test: fix test
* test: fix tests
This commit is contained in:
Krish Dholakia
GitHub
parent
d1abb9b68b
commit
0519c0c507
40 changed files with 1006 additions and 245 deletions
|
|
@ -15,7 +15,9 @@ import httpx
|
|||
|
||||
import litellm
|
||||
from litellm import get_secret_str
|
||||
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
||||
from litellm.llms.azure.files.handler import AzureOpenAIFilesAPI
|
||||
from litellm.llms.custom_httpx.llm_http_handler import BaseLLMHTTPHandler
|
||||
from litellm.llms.openai.openai import FileDeleted, FileObject, OpenAIFilesAPI
|
||||
from litellm.llms.vertex_ai.files.handler import VertexAIFilesHandler
|
||||
from litellm.types.llms.openai import (
|
||||
|
|
@ -23,9 +25,18 @@ from litellm.types.llms.openai import (
|
|||
FileContentRequest,
|
||||
FileTypes,
|
||||
HttpxBinaryResponseContent,
|
||||
OpenAIFileObject,
|
||||
)
|
||||
from litellm.types.router import *
|
||||
from litellm.utils import get_litellm_params, supports_httpx_timeout
|
||||
from litellm.types.utils import LlmProviders
|
||||
from litellm.utils import (
|
||||
ProviderConfigManager,
|
||||
client,
|
||||
get_litellm_params,
|
||||
supports_httpx_timeout,
|
||||
)
|
||||
|
||||
base_llm_http_handler = BaseLLMHTTPHandler()
|
||||
|
||||
####### ENVIRONMENT VARIABLES ###################
|
||||
openai_files_instance = OpenAIFilesAPI()
|
||||
|
|
@ -34,6 +45,224 @@ vertex_ai_files_instance = VertexAIFilesHandler()
|
|||
#################################################
|
||||
|
||||
|
||||
@client
|
||||
async def acreate_file(
|
||||
file: FileTypes,
|
||||
purpose: Literal["assistants", "batch", "fine-tune"],
|
||||
custom_llm_provider: Literal["openai", "azure", "vertex_ai"] = "openai",
|
||||
extra_headers: Optional[Dict[str, str]] = None,
|
||||
extra_body: Optional[Dict[str, str]] = None,
|
||||
**kwargs,
|
||||
) -> OpenAIFileObject:
|
||||
"""
|
||||
Async: Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API.
|
||||
|
||||
LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files
|
||||
"""
|
||||
try:
|
||||
loop = asyncio.get_event_loop()
|
||||
kwargs["acreate_file"] = True
|
||||
|
||||
# Use a partial function to pass your keyword arguments
|
||||
func = partial(
|
||||
create_file,
|
||||
file,
|
||||
purpose,
|
||||
custom_llm_provider,
|
||||
extra_headers,
|
||||
extra_body,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
# Add the context to the function
|
||||
ctx = contextvars.copy_context()
|
||||
func_with_context = partial(ctx.run, func)
|
||||
init_response = await loop.run_in_executor(None, func_with_context)
|
||||
if asyncio.iscoroutine(init_response):
|
||||
response = await init_response
|
||||
else:
|
||||
response = init_response # type: ignore
|
||||
|
||||
return response
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
||||
|
||||
@client
|
||||
def create_file(
|
||||
file: FileTypes,
|
||||
purpose: Literal["assistants", "batch", "fine-tune"],
|
||||
custom_llm_provider: Literal["openai", "azure", "vertex_ai"] = "openai",
|
||||
extra_headers: Optional[Dict[str, str]] = None,
|
||||
extra_body: Optional[Dict[str, str]] = None,
|
||||
**kwargs,
|
||||
) -> Union[OpenAIFileObject, Coroutine[Any, Any, OpenAIFileObject]]:
|
||||
"""
|
||||
Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API.
|
||||
|
||||
LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files
|
||||
"""
|
||||
try:
|
||||
_is_async = kwargs.pop("acreate_file", False) is True
|
||||
optional_params = GenericLiteLLMParams(**kwargs)
|
||||
litellm_params_dict = get_litellm_params(**kwargs)
|
||||
logging_obj = cast(
|
||||
Optional[LiteLLMLoggingObj], kwargs.get("litellm_logging_obj")
|
||||
)
|
||||
if logging_obj is None:
|
||||
raise ValueError("logging_obj is required")
|
||||
client = kwargs.get("client")
|
||||
|
||||
### TIMEOUT LOGIC ###
|
||||
timeout = optional_params.timeout or kwargs.get("request_timeout", 600) or 600
|
||||
# set timeout for 10 minutes by default
|
||||
|
||||
if (
|
||||
timeout is not None
|
||||
and isinstance(timeout, httpx.Timeout)
|
||||
and supports_httpx_timeout(custom_llm_provider) is False
|
||||
):
|
||||
read_timeout = timeout.read or 600
|
||||
timeout = read_timeout # default 10 min timeout
|
||||
elif timeout is not None and not isinstance(timeout, httpx.Timeout):
|
||||
timeout = float(timeout) # type: ignore
|
||||
elif timeout is None:
|
||||
timeout = 600.0
|
||||
|
||||
_create_file_request = CreateFileRequest(
|
||||
file=file,
|
||||
purpose=purpose,
|
||||
extra_headers=extra_headers,
|
||||
extra_body=extra_body,
|
||||
)
|
||||
|
||||
provider_config = ProviderConfigManager.get_provider_files_config(
|
||||
model="",
|
||||
provider=LlmProviders(custom_llm_provider),
|
||||
)
|
||||
if provider_config is not None:
|
||||
response = base_llm_http_handler.create_file(
|
||||
provider_config=provider_config,
|
||||
litellm_params=litellm_params_dict,
|
||||
create_file_data=_create_file_request,
|
||||
headers=extra_headers or {},
|
||||
api_base=optional_params.api_base,
|
||||
api_key=optional_params.api_key,
|
||||
logging_obj=logging_obj,
|
||||
_is_async=_is_async,
|
||||
client=client
|
||||
if client is not None
|
||||
and isinstance(client, (HTTPHandler, AsyncHTTPHandler))
|
||||
else None,
|
||||
timeout=timeout,
|
||||
)
|
||||
elif custom_llm_provider == "openai":
|
||||
# for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
|
||||
api_base = (
|
||||
optional_params.api_base
|
||||
or litellm.api_base
|
||||
or os.getenv("OPENAI_API_BASE")
|
||||
or "https://api.openai.com/v1"
|
||||
)
|
||||
organization = (
|
||||
optional_params.organization
|
||||
or litellm.organization
|
||||
or os.getenv("OPENAI_ORGANIZATION", None)
|
||||
or None # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105
|
||||
)
|
||||
# set API KEY
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there
|
||||
or litellm.openai_key
|
||||
or os.getenv("OPENAI_API_KEY")
|
||||
)
|
||||
|
||||
response = openai_files_instance.create_file(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
organization=organization,
|
||||
create_file_data=_create_file_request,
|
||||
)
|
||||
elif custom_llm_provider == "azure":
|
||||
api_base = optional_params.api_base or litellm.api_base or get_secret_str("AZURE_API_BASE") # type: ignore
|
||||
api_version = (
|
||||
optional_params.api_version
|
||||
or litellm.api_version
|
||||
or get_secret_str("AZURE_API_VERSION")
|
||||
) # type: ignore
|
||||
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key
|
||||
or litellm.azure_key
|
||||
or get_secret_str("AZURE_OPENAI_API_KEY")
|
||||
or get_secret_str("AZURE_API_KEY")
|
||||
) # type: ignore
|
||||
|
||||
extra_body = optional_params.get("extra_body", {})
|
||||
if extra_body is not None:
|
||||
extra_body.pop("azure_ad_token", None)
|
||||
else:
|
||||
get_secret_str("AZURE_AD_TOKEN") # type: ignore
|
||||
|
||||
response = azure_files_instance.create_file(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
api_version=api_version,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
create_file_data=_create_file_request,
|
||||
litellm_params=litellm_params_dict,
|
||||
)
|
||||
elif custom_llm_provider == "vertex_ai":
|
||||
api_base = optional_params.api_base or ""
|
||||
vertex_ai_project = (
|
||||
optional_params.vertex_project
|
||||
or litellm.vertex_project
|
||||
or get_secret_str("VERTEXAI_PROJECT")
|
||||
)
|
||||
vertex_ai_location = (
|
||||
optional_params.vertex_location
|
||||
or litellm.vertex_location
|
||||
or get_secret_str("VERTEXAI_LOCATION")
|
||||
)
|
||||
vertex_credentials = optional_params.vertex_credentials or get_secret_str(
|
||||
"VERTEXAI_CREDENTIALS"
|
||||
)
|
||||
|
||||
response = vertex_ai_files_instance.create_file(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
vertex_project=vertex_ai_project,
|
||||
vertex_location=vertex_ai_location,
|
||||
vertex_credentials=vertex_credentials,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
create_file_data=_create_file_request,
|
||||
)
|
||||
else:
|
||||
raise litellm.exceptions.BadRequestError(
|
||||
message="LiteLLM doesn't support {} for 'create_file'. Only ['openai', 'azure', 'vertex_ai'] are supported.".format(
|
||||
custom_llm_provider
|
||||
),
|
||||
model="n/a",
|
||||
llm_provider=custom_llm_provider,
|
||||
response=httpx.Response(
|
||||
status_code=400,
|
||||
content="Unsupported provider",
|
||||
request=httpx.Request(method="create_file", url="https://github.com/BerriAI/litellm"), # type: ignore
|
||||
),
|
||||
)
|
||||
return response
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
||||
|
||||
async def afile_retrieve(
|
||||
file_id: str,
|
||||
custom_llm_provider: Literal["openai", "azure"] = "openai",
|
||||
|
|
@ -488,195 +717,6 @@ def file_list(
|
|||
raise e
|
||||
|
||||
|
||||
async def acreate_file(
|
||||
file: FileTypes,
|
||||
purpose: Literal["assistants", "batch", "fine-tune"],
|
||||
custom_llm_provider: Literal["openai", "azure", "vertex_ai"] = "openai",
|
||||
extra_headers: Optional[Dict[str, str]] = None,
|
||||
extra_body: Optional[Dict[str, str]] = None,
|
||||
**kwargs,
|
||||
) -> FileObject:
|
||||
"""
|
||||
Async: Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API.
|
||||
|
||||
LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files
|
||||
"""
|
||||
try:
|
||||
loop = asyncio.get_event_loop()
|
||||
kwargs["acreate_file"] = True
|
||||
|
||||
# Use a partial function to pass your keyword arguments
|
||||
func = partial(
|
||||
create_file,
|
||||
file,
|
||||
purpose,
|
||||
custom_llm_provider,
|
||||
extra_headers,
|
||||
extra_body,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
# Add the context to the function
|
||||
ctx = contextvars.copy_context()
|
||||
func_with_context = partial(ctx.run, func)
|
||||
init_response = await loop.run_in_executor(None, func_with_context)
|
||||
if asyncio.iscoroutine(init_response):
|
||||
response = await init_response
|
||||
else:
|
||||
response = init_response # type: ignore
|
||||
|
||||
return response
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
||||
|
||||
def create_file(
|
||||
file: FileTypes,
|
||||
purpose: Literal["assistants", "batch", "fine-tune"],
|
||||
custom_llm_provider: Literal["openai", "azure", "vertex_ai"] = "openai",
|
||||
extra_headers: Optional[Dict[str, str]] = None,
|
||||
extra_body: Optional[Dict[str, str]] = None,
|
||||
**kwargs,
|
||||
) -> Union[FileObject, Coroutine[Any, Any, FileObject]]:
|
||||
"""
|
||||
Files are used to upload documents that can be used with features like Assistants, Fine-tuning, and Batch API.
|
||||
|
||||
LiteLLM Equivalent of POST: POST https://api.openai.com/v1/files
|
||||
"""
|
||||
try:
|
||||
_is_async = kwargs.pop("acreate_file", False) is True
|
||||
optional_params = GenericLiteLLMParams(**kwargs)
|
||||
litellm_params_dict = get_litellm_params(**kwargs)
|
||||
|
||||
### TIMEOUT LOGIC ###
|
||||
timeout = optional_params.timeout or kwargs.get("request_timeout", 600) or 600
|
||||
# set timeout for 10 minutes by default
|
||||
|
||||
if (
|
||||
timeout is not None
|
||||
and isinstance(timeout, httpx.Timeout)
|
||||
and supports_httpx_timeout(custom_llm_provider) is False
|
||||
):
|
||||
read_timeout = timeout.read or 600
|
||||
timeout = read_timeout # default 10 min timeout
|
||||
elif timeout is not None and not isinstance(timeout, httpx.Timeout):
|
||||
timeout = float(timeout) # type: ignore
|
||||
elif timeout is None:
|
||||
timeout = 600.0
|
||||
|
||||
_create_file_request = CreateFileRequest(
|
||||
file=file,
|
||||
purpose=purpose,
|
||||
extra_headers=extra_headers,
|
||||
extra_body=extra_body,
|
||||
)
|
||||
if custom_llm_provider == "openai":
|
||||
# for deepinfra/perplexity/anyscale/groq we check in get_llm_provider and pass in the api base from there
|
||||
api_base = (
|
||||
optional_params.api_base
|
||||
or litellm.api_base
|
||||
or os.getenv("OPENAI_API_BASE")
|
||||
or "https://api.openai.com/v1"
|
||||
)
|
||||
organization = (
|
||||
optional_params.organization
|
||||
or litellm.organization
|
||||
or os.getenv("OPENAI_ORGANIZATION", None)
|
||||
or None # default - https://github.com/openai/openai-python/blob/284c1799070c723c6a553337134148a7ab088dd8/openai/util.py#L105
|
||||
)
|
||||
# set API KEY
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key # for deepinfra/perplexity/anyscale we check in get_llm_provider and pass in the api key from there
|
||||
or litellm.openai_key
|
||||
or os.getenv("OPENAI_API_KEY")
|
||||
)
|
||||
|
||||
response = openai_files_instance.create_file(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
organization=organization,
|
||||
create_file_data=_create_file_request,
|
||||
)
|
||||
elif custom_llm_provider == "azure":
|
||||
api_base = optional_params.api_base or litellm.api_base or get_secret_str("AZURE_API_BASE") # type: ignore
|
||||
api_version = (
|
||||
optional_params.api_version
|
||||
or litellm.api_version
|
||||
or get_secret_str("AZURE_API_VERSION")
|
||||
) # type: ignore
|
||||
|
||||
api_key = (
|
||||
optional_params.api_key
|
||||
or litellm.api_key
|
||||
or litellm.azure_key
|
||||
or get_secret_str("AZURE_OPENAI_API_KEY")
|
||||
or get_secret_str("AZURE_API_KEY")
|
||||
) # type: ignore
|
||||
|
||||
extra_body = optional_params.get("extra_body", {})
|
||||
if extra_body is not None:
|
||||
extra_body.pop("azure_ad_token", None)
|
||||
else:
|
||||
get_secret_str("AZURE_AD_TOKEN") # type: ignore
|
||||
|
||||
response = azure_files_instance.create_file(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
api_key=api_key,
|
||||
api_version=api_version,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
create_file_data=_create_file_request,
|
||||
litellm_params=litellm_params_dict,
|
||||
)
|
||||
elif custom_llm_provider == "vertex_ai":
|
||||
api_base = optional_params.api_base or ""
|
||||
vertex_ai_project = (
|
||||
optional_params.vertex_project
|
||||
or litellm.vertex_project
|
||||
or get_secret_str("VERTEXAI_PROJECT")
|
||||
)
|
||||
vertex_ai_location = (
|
||||
optional_params.vertex_location
|
||||
or litellm.vertex_location
|
||||
or get_secret_str("VERTEXAI_LOCATION")
|
||||
)
|
||||
vertex_credentials = optional_params.vertex_credentials or get_secret_str(
|
||||
"VERTEXAI_CREDENTIALS"
|
||||
)
|
||||
|
||||
response = vertex_ai_files_instance.create_file(
|
||||
_is_async=_is_async,
|
||||
api_base=api_base,
|
||||
vertex_project=vertex_ai_project,
|
||||
vertex_location=vertex_ai_location,
|
||||
vertex_credentials=vertex_credentials,
|
||||
timeout=timeout,
|
||||
max_retries=optional_params.max_retries,
|
||||
create_file_data=_create_file_request,
|
||||
)
|
||||
else:
|
||||
raise litellm.exceptions.BadRequestError(
|
||||
message="LiteLLM doesn't support {} for 'create_batch'. Only 'openai' is supported.".format(
|
||||
custom_llm_provider
|
||||
),
|
||||
model="n/a",
|
||||
llm_provider=custom_llm_provider,
|
||||
response=httpx.Response(
|
||||
status_code=400,
|
||||
content="Unsupported provider",
|
||||
request=httpx.Request(method="create_thread", url="https://github.com/BerriAI/litellm"), # type: ignore
|
||||
),
|
||||
)
|
||||
return response
|
||||
except Exception as e:
|
||||
raise e
|
||||
|
||||
|
||||
async def afile_content(
|
||||
file_id: str,
|
||||
custom_llm_provider: Literal["openai", "azure"] = "openai",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue