mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 19:24:27 +00:00
* feat: initial commit for watsonx chat endpoint support Closes https://github.com/BerriAI/litellm/issues/6562 * feat(watsonx/chat/handler.py): support tool calling for watsonx Closes https://github.com/BerriAI/litellm/issues/6562 * fix(streaming_utils.py): return empty chunk instead of failing if streaming value is invalid dict ensures streaming works for ibm watsonx * fix(openai_like/chat/handler.py): ensure asynchttphandler is passed correctly for openai like calls * fix: ensure exception mapping works well for watsonx calls * fix(openai_like/chat/handler.py): handle async streaming correctly * feat(main.py): Make it clear when a user is passing an invalid message add validation for user content message Closes https://github.com/BerriAI/litellm/issues/6565 * fix: cleanup * fix(utils.py): loosen validation check, to just make sure content types are valid make litellm robust to future content updates * fix: fix linting erro * fix: fix linting errors * fix(utils.py): make validation check more flexible * test: handle langfuse list index out of range error * Litellm dev 11 02 2024 (#6561) * fix(dual_cache.py): update in-memory check for redis batch get cache Fixes latency delay for async_batch_redis_cache * fix(service_logger.py): fix race condition causing otel service logging to be overwritten if service_callbacks set * feat(user_api_key_auth.py): add parent otel component for auth allows us to isolate how much latency is added by auth checks * perf(parallel_request_limiter.py): move async_set_cache_pipeline (from max parallel request limiter) out of execution path (background task) reduces latency by 200ms * feat(user_api_key_auth.py): have user api key auth object return user tpm/rpm limits - reduces redis calls in downstream task (parallel_request_limiter) Reduces latency by 400-800ms * fix(parallel_request_limiter.py): use batch get cache to reduce user/key/team usage object calls reduces latency by 50-100ms * fix: fix linting error * fix(_service_logger.py): fix import * fix(user_api_key_auth.py): fix service logging * fix(dual_cache.py): don't pass 'self' * fix: fix python3.8 error * fix: fix init] * bump: version 1.51.4 → 1.51.5 * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * Litellm dev 11 02 2024 (#6561) * fix(dual_cache.py): update in-memory check for redis batch get cache Fixes latency delay for async_batch_redis_cache * fix(service_logger.py): fix race condition causing otel service logging to be overwritten if service_callbacks set * feat(user_api_key_auth.py): add parent otel component for auth allows us to isolate how much latency is added by auth checks * perf(parallel_request_limiter.py): move async_set_cache_pipeline (from max parallel request limiter) out of execution path (background task) reduces latency by 200ms * feat(user_api_key_auth.py): have user api key auth object return user tpm/rpm limits - reduces redis calls in downstream task (parallel_request_limiter) Reduces latency by 400-800ms * fix(parallel_request_limiter.py): use batch get cache to reduce user/key/team usage object calls reduces latency by 50-100ms * fix: fix linting error * fix(_service_logger.py): fix import * fix(user_api_key_auth.py): fix service logging * fix(dual_cache.py): don't pass 'self' * fix: fix python3.8 error * fix: fix init] * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * fix ImageObject conversion (#6584) * (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546) * unit test test_huggingface_text_completion_logprobs * fix return TextCompletionHandler convert_chat_to_text_completion * fix hf rest api * fix test_huggingface_text_completion_logprobs * fix linting errors * fix importLiteLLMResponseObjectHandler * fix test for LiteLLMResponseObjectHandler * fix test text completion * fix allow using 15 seconds for premium license check * testing fix bedrock deprecated cohere.command-text-v14 * (feat) add `Predicted Outputs` for OpenAI (#6594) * bump openai to openai==1.54.0 * add 'prediction' param * testing fix bedrock deprecated cohere.command-text-v14 * test test_openai_prediction_param.py * test_openai_prediction_param_with_caching * doc Predicted Outputs * doc Predicted Output * (fix) Vertex Improve Performance when using `image_url` (#6593) * fix transformation vertex * test test_process_gemini_image * test_image_completion_request * testing fix - bedrock has deprecated cohere.command-text-v14 * fix vertex pdf * bump: version 1.51.5 → 1.52.0 * fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check (#6577) * fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check * fix(lowest_tpm_rpm_v2.py): return headers in correct format * test: update test * build(deps): bump cookie and express in /docs/my-website (#6566) Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together. Updates `cookie` from 0.6.0 to 0.7.1 - [Release notes](https://github.com/jshttp/cookie/releases) - [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1) Updates `express` from 4.20.0 to 4.21.1 - [Release notes](https://github.com/expressjs/express/releases) - [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md) - [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1) --- updated-dependencies: - dependency-name: cookie dependency-type: indirect - dependency-name: express dependency-type: indirect ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * docs(virtual_keys.md): update Dockerfile reference (#6554) Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> * (proxy fix) - call connect on prisma client when running setup (#6534) * critical fix - call connect on prisma client when running setup * fix test_proxy_server_prisma_setup * fix test_proxy_server_prisma_setup * Add 3.5 haiku (#6588) * feat: add claude-3-5-haiku-20241022 entries * feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models * add missing entries, remove vision * remove image token costs * Litellm perf improvements 3 (#6573) * perf: move writing key to cache, to background task * perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils adds 200ms on calls with pgdb connected * fix(litellm_pre_call_utils.py'): rename call_type to actual call used * perf(proxy_server.py): remove db logic from _get_config_from_file was causing db calls to occur on every llm request, if team_id was set on key * fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db reduces latency/call by ~100ms * fix(proxy_server.py): minor fix on existing_settings not incl alerting * fix(exception_mapping_utils.py): map databricks exception string * fix(auth_checks.py): fix auth check logic * test: correctly mark flaky test * fix(utils.py): handle auth token error for tokenizers.from_pretrained * build: fix map * build: fix map * build: fix json for model map * test: remove eol model * fix(proxy_server.py): fix db config loading logic * fix(proxy_server.py): fix order of config / db updates, to ensure fields not overwritten * test: skip test if required env var is missing * test: fix test --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com> * test: mark flaky test * test: handle anthropic api instability * test: update test * test: bump num retries on langfuse tests - their api is quite bad --------- Signed-off-by: dependabot[bot] <support@github.com> Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com>
488 lines
16 KiB
Python
488 lines
16 KiB
Python
import asyncio
|
|
import os
|
|
import traceback
|
|
from typing import TYPE_CHECKING, Any, Callable, List, Mapping, Optional, Union
|
|
|
|
import httpx
|
|
from httpx import USE_CLIENT_DEFAULT
|
|
|
|
import litellm
|
|
|
|
from .types import httpxSpecialProvider
|
|
|
|
if TYPE_CHECKING:
|
|
from litellm import LlmProviders
|
|
else:
|
|
LlmProviders = Any
|
|
|
|
try:
|
|
from litellm._version import version
|
|
except Exception:
|
|
version = "0.0.0"
|
|
|
|
headers = {
|
|
"User-Agent": f"litellm/{version}",
|
|
}
|
|
|
|
# https://www.python-httpx.org/advanced/timeouts
|
|
_DEFAULT_TIMEOUT = httpx.Timeout(timeout=5.0, connect=5.0)
|
|
|
|
|
|
class AsyncHTTPHandler:
|
|
def __init__(
|
|
self,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
event_hooks: Optional[Mapping[str, List[Callable[..., Any]]]] = None,
|
|
concurrent_limit=1000,
|
|
client_alias: Optional[str] = None, # name for client in logs
|
|
):
|
|
self.timeout = timeout
|
|
self.event_hooks = event_hooks
|
|
self.client = self.create_client(
|
|
timeout=timeout, concurrent_limit=concurrent_limit, event_hooks=event_hooks
|
|
)
|
|
self.client_alias = client_alias
|
|
|
|
def create_client(
|
|
self,
|
|
timeout: Optional[Union[float, httpx.Timeout]],
|
|
concurrent_limit: int,
|
|
event_hooks: Optional[Mapping[str, List[Callable[..., Any]]]],
|
|
) -> httpx.AsyncClient:
|
|
|
|
# SSL certificates (a.k.a CA bundle) used to verify the identity of requested hosts.
|
|
# /path/to/certificate.pem
|
|
ssl_verify = os.getenv("SSL_VERIFY", litellm.ssl_verify)
|
|
# An SSL certificate used by the requested host to authenticate the client.
|
|
# /path/to/client.pem
|
|
cert = os.getenv("SSL_CERTIFICATE", litellm.ssl_certificate)
|
|
|
|
if timeout is None:
|
|
timeout = _DEFAULT_TIMEOUT
|
|
# Create a client with a connection pool
|
|
|
|
return httpx.AsyncClient(
|
|
event_hooks=event_hooks,
|
|
timeout=timeout,
|
|
limits=httpx.Limits(
|
|
max_connections=concurrent_limit,
|
|
max_keepalive_connections=concurrent_limit,
|
|
),
|
|
verify=ssl_verify,
|
|
cert=cert,
|
|
headers=headers,
|
|
)
|
|
|
|
async def close(self):
|
|
# Close the client when you're done with it
|
|
await self.client.aclose()
|
|
|
|
async def __aenter__(self):
|
|
return self.client
|
|
|
|
async def __aexit__(self):
|
|
# close the client when exiting
|
|
await self.client.aclose()
|
|
|
|
async def get(
|
|
self,
|
|
url: str,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
follow_redirects: Optional[bool] = None,
|
|
):
|
|
# Set follow_redirects to UseClientDefault if None
|
|
_follow_redirects = (
|
|
follow_redirects if follow_redirects is not None else USE_CLIENT_DEFAULT
|
|
)
|
|
|
|
response = await self.client.get(
|
|
url, params=params, headers=headers, follow_redirects=_follow_redirects # type: ignore
|
|
)
|
|
return response
|
|
|
|
async def post(
|
|
self,
|
|
url: str,
|
|
data: Optional[Union[dict, str]] = None, # type: ignore
|
|
json: Optional[dict] = None,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
stream: bool = False,
|
|
):
|
|
try:
|
|
if timeout is None:
|
|
timeout = self.timeout
|
|
|
|
req = self.client.build_request(
|
|
"POST", url, data=data, json=json, params=params, headers=headers, timeout=timeout # type: ignore
|
|
)
|
|
response = await self.client.send(req, stream=stream)
|
|
response.raise_for_status()
|
|
return response
|
|
except (httpx.RemoteProtocolError, httpx.ConnectError):
|
|
# Retry the request with a new session if there is a connection error
|
|
new_client = self.create_client(
|
|
timeout=timeout, concurrent_limit=1, event_hooks=self.event_hooks
|
|
)
|
|
try:
|
|
return await self.single_connection_post_request(
|
|
url=url,
|
|
client=new_client,
|
|
data=data,
|
|
json=json,
|
|
params=params,
|
|
headers=headers,
|
|
stream=stream,
|
|
)
|
|
finally:
|
|
await new_client.aclose()
|
|
except httpx.TimeoutException as e:
|
|
headers = {}
|
|
error_response = getattr(e, "response", None)
|
|
if error_response is not None:
|
|
for key, value in error_response.headers.items():
|
|
headers["response_headers-{}".format(key)] = value
|
|
|
|
raise litellm.Timeout(
|
|
message=f"Connection timed out after {timeout} seconds.",
|
|
model="default-model-name",
|
|
llm_provider="litellm-httpx-handler",
|
|
headers=headers,
|
|
)
|
|
except httpx.HTTPStatusError as e:
|
|
setattr(e, "status_code", e.response.status_code)
|
|
if stream is True:
|
|
setattr(e, "message", await e.response.aread())
|
|
setattr(e, "text", await e.response.aread())
|
|
else:
|
|
setattr(e, "message", e.response.text)
|
|
setattr(e, "text", e.response.text)
|
|
raise e
|
|
except Exception as e:
|
|
raise e
|
|
|
|
async def put(
|
|
self,
|
|
url: str,
|
|
data: Optional[Union[dict, str]] = None, # type: ignore
|
|
json: Optional[dict] = None,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
stream: bool = False,
|
|
):
|
|
try:
|
|
if timeout is None:
|
|
timeout = self.timeout
|
|
|
|
req = self.client.build_request(
|
|
"PUT", url, data=data, json=json, params=params, headers=headers, timeout=timeout # type: ignore
|
|
)
|
|
response = await self.client.send(req)
|
|
response.raise_for_status()
|
|
return response
|
|
except (httpx.RemoteProtocolError, httpx.ConnectError):
|
|
# Retry the request with a new session if there is a connection error
|
|
new_client = self.create_client(
|
|
timeout=timeout, concurrent_limit=1, event_hooks=self.event_hooks
|
|
)
|
|
try:
|
|
return await self.single_connection_post_request(
|
|
url=url,
|
|
client=new_client,
|
|
data=data,
|
|
json=json,
|
|
params=params,
|
|
headers=headers,
|
|
stream=stream,
|
|
)
|
|
finally:
|
|
await new_client.aclose()
|
|
except httpx.TimeoutException as e:
|
|
headers = {}
|
|
error_response = getattr(e, "response", None)
|
|
if error_response is not None:
|
|
for key, value in error_response.headers.items():
|
|
headers["response_headers-{}".format(key)] = value
|
|
|
|
raise litellm.Timeout(
|
|
message=f"Connection timed out after {timeout} seconds.",
|
|
model="default-model-name",
|
|
llm_provider="litellm-httpx-handler",
|
|
headers=headers,
|
|
)
|
|
except httpx.HTTPStatusError as e:
|
|
setattr(e, "status_code", e.response.status_code)
|
|
if stream is True:
|
|
setattr(e, "message", await e.response.aread())
|
|
else:
|
|
setattr(e, "message", e.response.text)
|
|
raise e
|
|
except Exception as e:
|
|
raise e
|
|
|
|
async def delete(
|
|
self,
|
|
url: str,
|
|
data: Optional[Union[dict, str]] = None, # type: ignore
|
|
json: Optional[dict] = None,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
stream: bool = False,
|
|
):
|
|
try:
|
|
if timeout is None:
|
|
timeout = self.timeout
|
|
req = self.client.build_request(
|
|
"DELETE", url, data=data, json=json, params=params, headers=headers, timeout=timeout # type: ignore
|
|
)
|
|
response = await self.client.send(req, stream=stream)
|
|
response.raise_for_status()
|
|
return response
|
|
except (httpx.RemoteProtocolError, httpx.ConnectError):
|
|
# Retry the request with a new session if there is a connection error
|
|
new_client = self.create_client(
|
|
timeout=timeout, concurrent_limit=1, event_hooks=self.event_hooks
|
|
)
|
|
try:
|
|
return await self.single_connection_post_request(
|
|
url=url,
|
|
client=new_client,
|
|
data=data,
|
|
json=json,
|
|
params=params,
|
|
headers=headers,
|
|
stream=stream,
|
|
)
|
|
finally:
|
|
await new_client.aclose()
|
|
except httpx.HTTPStatusError as e:
|
|
setattr(e, "status_code", e.response.status_code)
|
|
if stream is True:
|
|
setattr(e, "message", await e.response.aread())
|
|
else:
|
|
setattr(e, "message", e.response.text)
|
|
raise e
|
|
except Exception as e:
|
|
raise e
|
|
|
|
async def single_connection_post_request(
|
|
self,
|
|
url: str,
|
|
client: httpx.AsyncClient,
|
|
data: Optional[Union[dict, str]] = None, # type: ignore
|
|
json: Optional[dict] = None,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
stream: bool = False,
|
|
):
|
|
"""
|
|
Making POST request for a single connection client.
|
|
|
|
Used for retrying connection client errors.
|
|
"""
|
|
req = client.build_request(
|
|
"POST", url, data=data, json=json, params=params, headers=headers # type: ignore
|
|
)
|
|
response = await client.send(req, stream=stream)
|
|
response.raise_for_status()
|
|
return response
|
|
|
|
def __del__(self) -> None:
|
|
try:
|
|
asyncio.get_running_loop().create_task(self.close())
|
|
except Exception:
|
|
pass
|
|
|
|
|
|
class HTTPHandler:
|
|
def __init__(
|
|
self,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
concurrent_limit=1000,
|
|
client: Optional[httpx.Client] = None,
|
|
):
|
|
if timeout is None:
|
|
timeout = _DEFAULT_TIMEOUT
|
|
|
|
# SSL certificates (a.k.a CA bundle) used to verify the identity of requested hosts.
|
|
# /path/to/certificate.pem
|
|
ssl_verify = os.getenv("SSL_VERIFY", litellm.ssl_verify)
|
|
# An SSL certificate used by the requested host to authenticate the client.
|
|
# /path/to/client.pem
|
|
cert = os.getenv("SSL_CERTIFICATE", litellm.ssl_certificate)
|
|
|
|
if client is None:
|
|
# Create a client with a connection pool
|
|
self.client = httpx.Client(
|
|
timeout=timeout,
|
|
limits=httpx.Limits(
|
|
max_connections=concurrent_limit,
|
|
max_keepalive_connections=concurrent_limit,
|
|
),
|
|
verify=ssl_verify,
|
|
cert=cert,
|
|
headers=headers,
|
|
)
|
|
else:
|
|
self.client = client
|
|
|
|
def close(self):
|
|
# Close the client when you're done with it
|
|
self.client.close()
|
|
|
|
def get(
|
|
self,
|
|
url: str,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
follow_redirects: Optional[bool] = None,
|
|
):
|
|
# Set follow_redirects to UseClientDefault if None
|
|
_follow_redirects = (
|
|
follow_redirects if follow_redirects is not None else USE_CLIENT_DEFAULT
|
|
)
|
|
|
|
response = self.client.get(
|
|
url, params=params, headers=headers, follow_redirects=_follow_redirects # type: ignore
|
|
)
|
|
return response
|
|
|
|
def post(
|
|
self,
|
|
url: str,
|
|
data: Optional[Union[dict, str]] = None,
|
|
json: Optional[Union[dict, str]] = None,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
stream: bool = False,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
):
|
|
try:
|
|
|
|
if timeout is not None:
|
|
req = self.client.build_request(
|
|
"POST", url, data=data, json=json, params=params, headers=headers, timeout=timeout # type: ignore
|
|
)
|
|
else:
|
|
req = self.client.build_request(
|
|
"POST", url, data=data, json=json, params=params, headers=headers # type: ignore
|
|
)
|
|
response = self.client.send(req, stream=stream)
|
|
response.raise_for_status()
|
|
return response
|
|
except httpx.TimeoutException:
|
|
raise litellm.Timeout(
|
|
message=f"Connection timed out after {timeout} seconds.",
|
|
model="default-model-name",
|
|
llm_provider="litellm-httpx-handler",
|
|
)
|
|
except httpx.HTTPStatusError as e:
|
|
setattr(e, "status_code", e.response.status_code)
|
|
if stream is True:
|
|
setattr(e, "message", e.response.read())
|
|
else:
|
|
setattr(e, "message", e.response.text)
|
|
raise e
|
|
except Exception as e:
|
|
raise e
|
|
|
|
def put(
|
|
self,
|
|
url: str,
|
|
data: Optional[Union[dict, str]] = None,
|
|
json: Optional[Union[dict, str]] = None,
|
|
params: Optional[dict] = None,
|
|
headers: Optional[dict] = None,
|
|
stream: bool = False,
|
|
timeout: Optional[Union[float, httpx.Timeout]] = None,
|
|
):
|
|
try:
|
|
|
|
if timeout is not None:
|
|
req = self.client.build_request(
|
|
"PUT", url, data=data, json=json, params=params, headers=headers, timeout=timeout # type: ignore
|
|
)
|
|
else:
|
|
req = self.client.build_request(
|
|
"PUT", url, data=data, json=json, params=params, headers=headers # type: ignore
|
|
)
|
|
response = self.client.send(req, stream=stream)
|
|
return response
|
|
except httpx.TimeoutException:
|
|
raise litellm.Timeout(
|
|
message=f"Connection timed out after {timeout} seconds.",
|
|
model="default-model-name",
|
|
llm_provider="litellm-httpx-handler",
|
|
)
|
|
except Exception as e:
|
|
raise e
|
|
|
|
def __del__(self) -> None:
|
|
try:
|
|
self.close()
|
|
except Exception:
|
|
pass
|
|
|
|
|
|
def get_async_httpx_client(
|
|
llm_provider: Union[LlmProviders, httpxSpecialProvider],
|
|
params: Optional[dict] = None,
|
|
) -> AsyncHTTPHandler:
|
|
"""
|
|
Retrieves the async HTTP client from the cache
|
|
If not present, creates a new client
|
|
|
|
Caches the new client and returns it.
|
|
"""
|
|
_params_key_name = ""
|
|
if params is not None:
|
|
for key, value in params.items():
|
|
try:
|
|
_params_key_name += f"{key}_{value}"
|
|
except Exception:
|
|
pass
|
|
|
|
_cache_key_name = "async_httpx_client" + _params_key_name + llm_provider
|
|
if _cache_key_name in litellm.in_memory_llm_clients_cache:
|
|
return litellm.in_memory_llm_clients_cache[_cache_key_name]
|
|
|
|
if params is not None:
|
|
_new_client = AsyncHTTPHandler(**params)
|
|
else:
|
|
_new_client = AsyncHTTPHandler(
|
|
timeout=httpx.Timeout(timeout=600.0, connect=5.0)
|
|
)
|
|
litellm.in_memory_llm_clients_cache[_cache_key_name] = _new_client
|
|
return _new_client
|
|
|
|
|
|
def _get_httpx_client(params: Optional[dict] = None) -> HTTPHandler:
|
|
"""
|
|
Retrieves the HTTP client from the cache
|
|
If not present, creates a new client
|
|
|
|
Caches the new client and returns it.
|
|
"""
|
|
_params_key_name = ""
|
|
if params is not None:
|
|
for key, value in params.items():
|
|
try:
|
|
_params_key_name += f"{key}_{value}"
|
|
except Exception:
|
|
pass
|
|
|
|
_cache_key_name = "httpx_client" + _params_key_name
|
|
if _cache_key_name in litellm.in_memory_llm_clients_cache:
|
|
return litellm.in_memory_llm_clients_cache[_cache_key_name]
|
|
|
|
if params is not None:
|
|
_new_client = HTTPHandler(**params)
|
|
else:
|
|
_new_client = HTTPHandler(timeout=httpx.Timeout(timeout=600.0, connect=5.0))
|
|
|
|
litellm.in_memory_llm_clients_cache[_cache_key_name] = _new_client
|
|
return _new_client
|