forked from phoenix/litellm-mirror
Litellm dev 11 20 2024 (#6831)
* feat(customer_endpoints.py): support passing budget duration via `/customer/new` endpoint Closes https://github.com/BerriAI/litellm/issues/5651 * docs: add missing params to swagger + api documentation test * docs: add documentation for all key endpoints documents all params on swagger * docs(internal_user_endpoints.py): document all /user/new params Ensures all params are documented * docs(team_endpoints.py): add missing documentation for team endpoints Ensures 100% param documentation on swagger * docs(organization_endpoints.py): document all org params Adds documentation for all params in org endpoint * docs(customer_endpoints.py): add coverage for all params on /customer endpoints ensures all /customer/* params are documented * ci(config.yml): add endpoint doc testing to ci/cd * fix: fix internal_user_endpoints.py * fix(internal_user_endpoints.py): support 'duration' param * fix(partner_models/main.py): fix anthropic re-raise exception on vertex * fix: fix pydantic obj
This commit is contained in:
Krish Dholakia
GitHub
parent
a1f06de53d
commit
689cd677c6
11 changed files with 480 additions and 139 deletions
|
|
@ -102,11 +102,27 @@ async def new_user(
|
|||
- send_invite_email: Optional[bool] - Specify if an invite email should be sent.
|
||||
- user_role: Optional[str] - Specify a user role - "proxy_admin", "proxy_admin_viewer", "internal_user", "internal_user_viewer", "team", "customer". Info about each role here: `https://github.com/BerriAI/litellm/litellm/proxy/_types.py#L20`
|
||||
- max_budget: Optional[float] - Specify max budget for a given user.
|
||||
- budget_duration: Optional[str] - Budget is reset at the end of specified duration. If not set, budget is never reset. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d").
|
||||
- budget_duration: Optional[str] - Budget is reset at the end of specified duration. If not set, budget is never reset. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
|
||||
- models: Optional[list] - Model_name's a user is allowed to call. (if empty, key is allowed to call all models)
|
||||
- tpm_limit: Optional[int] - Specify tpm limit for a given user (Tokens per minute)
|
||||
- rpm_limit: Optional[int] - Specify rpm limit for a given user (Requests per minute)
|
||||
- auto_create_key: bool - Default=True. Flag used for returning a key as part of the /user/new response
|
||||
- aliases: Optional[dict] - Model aliases for the user - [Docs](https://litellm.vercel.app/docs/proxy/virtual_keys#model-aliases)
|
||||
- config: Optional[dict] - [DEPRECATED PARAM] User-specific config.
|
||||
- allowed_cache_controls: Optional[list] - List of allowed cache control values. Example - ["no-cache", "no-store"]. See all values - https://docs.litellm.ai/docs/proxy/caching#turn-on--off-caching-per-request-
|
||||
- blocked: Optional[bool] - [Not Implemented Yet] Whether the user is blocked.
|
||||
- guardrails: Optional[List[str]] - [Not Implemented Yet] List of active guardrails for the user
|
||||
- permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
|
||||
- metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
- max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
|
||||
- soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests.
|
||||
- model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
- model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
- model_tpm_limit: Optional[float] - Model-specific tpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
- spend: Optional[float] - Amount spent by user. Default is 0. Will be updated by proxy whenever user is used. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
|
||||
- team_id: Optional[str] - [DEPRECATED PARAM] The team id of the user. Default is None.
|
||||
- duration: Optional[str] - Duration for the key auto-created on `/user/new`. Default is None.
|
||||
- key_alias: Optional[str] - Alias for the key auto-created on `/user/new`. Default is None.
|
||||
|
||||
Returns:
|
||||
- key: (str) The generated api key for the user
|
||||
|
|
@ -445,54 +461,36 @@ async def user_update(
|
|||
}'
|
||||
|
||||
Parameters:
|
||||
user_id: Optional[str]
|
||||
Unique identifier for the user to update
|
||||
|
||||
user_email: Optional[str]
|
||||
Email address for the user
|
||||
|
||||
password: Optional[str]
|
||||
Password for the user
|
||||
|
||||
user_role: Optional[Literal["proxy_admin", "proxy_admin_viewer", "internal_user", "internal_user_viewer"]]
|
||||
Role assigned to the user. Can be one of:
|
||||
- proxy_admin: Full admin access
|
||||
- proxy_admin_viewer: Read-only admin access
|
||||
- internal_user: Standard internal user
|
||||
- internal_user_viewer: Read-only internal user
|
||||
|
||||
models: Optional[list]
|
||||
List of model names the user is allowed to access
|
||||
|
||||
spend: Optional[float]
|
||||
Current spend amount for the user
|
||||
|
||||
max_budget: Optional[float]
|
||||
Maximum budget allowed for the user
|
||||
|
||||
team_id: Optional[str]
|
||||
ID of the team the user belongs to
|
||||
|
||||
max_parallel_requests: Optional[int]
|
||||
Maximum number of concurrent requests allowed
|
||||
|
||||
metadata: Optional[dict]
|
||||
Additional metadata associated with the user
|
||||
|
||||
tpm_limit: Optional[int]
|
||||
Maximum tokens per minute allowed
|
||||
|
||||
rpm_limit: Optional[int]
|
||||
Maximum requests per minute allowed
|
||||
|
||||
budget_duration: Optional[str]
|
||||
Duration for budget renewal (e.g., "30d" for 30 days)
|
||||
|
||||
allowed_cache_controls: Optional[list]
|
||||
List of allowed cache control options
|
||||
|
||||
soft_budget: Optional[float]
|
||||
Soft budget limit for alerting purposes
|
||||
- user_id: Optional[str] - Specify a user id. If not set, a unique id will be generated.
|
||||
- user_email: Optional[str] - Specify a user email.
|
||||
- password: Optional[str] - Specify a user password.
|
||||
- user_alias: Optional[str] - A descriptive name for you to know who this user id refers to.
|
||||
- teams: Optional[list] - specify a list of team id's a user belongs to.
|
||||
- send_invite_email: Optional[bool] - Specify if an invite email should be sent.
|
||||
- user_role: Optional[str] - Specify a user role - "proxy_admin", "proxy_admin_viewer", "internal_user", "internal_user_viewer", "team", "customer". Info about each role here: `https://github.com/BerriAI/litellm/litellm/proxy/_types.py#L20`
|
||||
- max_budget: Optional[float] - Specify max budget for a given user.
|
||||
- budget_duration: Optional[str] - Budget is reset at the end of specified duration. If not set, budget is never reset. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
|
||||
- models: Optional[list] - Model_name's a user is allowed to call. (if empty, key is allowed to call all models)
|
||||
- tpm_limit: Optional[int] - Specify tpm limit for a given user (Tokens per minute)
|
||||
- rpm_limit: Optional[int] - Specify rpm limit for a given user (Requests per minute)
|
||||
- auto_create_key: bool - Default=True. Flag used for returning a key as part of the /user/new response
|
||||
- aliases: Optional[dict] - Model aliases for the user - [Docs](https://litellm.vercel.app/docs/proxy/virtual_keys#model-aliases)
|
||||
- config: Optional[dict] - [DEPRECATED PARAM] User-specific config.
|
||||
- allowed_cache_controls: Optional[list] - List of allowed cache control values. Example - ["no-cache", "no-store"]. See all values - https://docs.litellm.ai/docs/proxy/caching#turn-on--off-caching-per-request-
|
||||
- blocked: Optional[bool] - [Not Implemented Yet] Whether the user is blocked.
|
||||
- guardrails: Optional[List[str]] - [Not Implemented Yet] List of active guardrails for the user
|
||||
- permissions: Optional[dict] - [Not Implemented Yet] User-specific permissions, eg. turning off pii masking.
|
||||
- metadata: Optional[dict] - Metadata for user, store information for user. Example metadata = {"team": "core-infra", "app": "app2", "email": "ishaan@berri.ai" }
|
||||
- max_parallel_requests: Optional[int] - Rate limit a user based on the number of parallel requests. Raises 429 error, if user's parallel requests > x.
|
||||
- soft_budget: Optional[float] - Get alerts when user crosses given budget, doesn't block requests.
|
||||
- model_max_budget: Optional[dict] - Model-specific max budget for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-budgets-to-keys)
|
||||
- model_rpm_limit: Optional[float] - Model-specific rpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
- model_tpm_limit: Optional[float] - Model-specific tpm limit for user. [Docs](https://docs.litellm.ai/docs/proxy/users#add-model-specific-limits-to-keys)
|
||||
- spend: Optional[float] - Amount spent by user. Default is 0. Will be updated by proxy whenever user is used. You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
|
||||
- team_id: Optional[str] - [DEPRECATED PARAM] The team id of the user. Default is None.
|
||||
- duration: Optional[str] - [NOT IMPLEMENTED].
|
||||
- key_alias: Optional[str] - [NOT IMPLEMENTED].
|
||||
|
||||
```
|
||||
"""
|
||||
from litellm.proxy.proxy_server import prisma_client
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue