FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

feat: regenerate SDK client core from Otari OpenAPI spec (#117) · mozilla-ai/otari-sdk-python@b2972cc · GitHub

  1. mozilla-ai
  2. otari-sdk-python

Repository navigation

Commit b2972cc

Browse files
mgauz01
and
daavoo
authored
feat: regenerate SDK client core from Otari OpenAPI spec (#117)
Co-authored-by: daavoo <12677733+daavoo@users.noreply.github.com>
1 parent 2dbf11b commit b2972cc

3 files changed

Lines changed: 13 additions & 13 deletions

File tree

‎src/otari/_client/models/rate_limit_rule_create.py‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -34,8 +34,8 @@ class RateLimitRuleCreate(BaseModel):
3434
name: Annotated[str, Field(strict=True)] = Field(description="Names the rule in a 429's detail and in the counter's key. Unique across rate_limits.")
3535
per: StrictStr = Field(description="What one count is shared by.")
3636
rpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Requests per minute.")
37-
tpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Tokens per minute. A request is admitted on its estimate (prompt plus max output, or budget_estimate_default_output_tokens) and charged what it used once it completes.")
38-
tpm_admission: Optional[StrictStr] = Field(default='estimate', description="How a tpm limit admits a request. 'estimate' holds the request's estimate and refuses it when that does not fit. 'used' admits a request while the minute's tokens are under the limit, holding none, and counts what it used once it completes, as LiteLLM does: a client that always sends a large max_tokens is limited by its usage, not its ceiling.")
37+
tpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Tokens per minute, counted on what each request used; see tpm_admission for how a request is admitted.")
38+
tpm_admission: Optional[StrictStr] = Field(default='used', description="How a tpm limit admits a request. 'used' (the default) admits a request while the minute's tokens are under the limit and counts what it used once it completes, as LiteLLM does. 'estimate' holds the request's estimate (prompt plus max output, or budget_estimate_default_output_tokens) while it runs and refuses it when that does not fit, which is how providers count their own quotas: use it for a limit meant to stay under one.")
3939
__properties: ClassVar[List[str]] = ["lease_sec", "max_concurrent", "models", "name", "per", "rpm", "tpm", "tpm_admission"]
4040

4141
@field_validator('name')
@@ -61,8 +61,8 @@ def tpm_admission_validate_enum(cls, value):
6161
if value is None:
6262
return value
6363

64-
if value not in set(['estimate', 'used']):
65-
raise ValueError("must be one of enum values ('estimate', 'used')")
64+
if value not in set(['used', 'estimate']):
65+
raise ValueError("must be one of enum values ('used', 'estimate')")
6666
return value
6767

6868
model_config = ConfigDict(
@@ -143,7 +143,7 @@ def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
143143
"per": obj.get("per"),
144144
"rpm": obj.get("rpm"),
145145
"tpm": obj.get("tpm"),
146-
"tpm_admission": obj.get("tpm_admission") if obj.get("tpm_admission") is not None else 'estimate'
146+
"tpm_admission": obj.get("tpm_admission") if obj.get("tpm_admission") is not None else 'used'
147147
})
148148
return _obj
149149

‎src/otari/_client/models/rate_limit_rule_public.py‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -36,8 +36,8 @@ class RateLimitRulePublic(BaseModel):
3636
per: StrictStr = Field(description="What one count is shared by.")
3737
rpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Requests per minute.")
3838
source: StrictStr = Field(description="'config' for a rule from config.yml, which is read-only here; 'dashboard' for a stored one.")
39-
tpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Tokens per minute. A request is admitted on its estimate (prompt plus max output, or budget_estimate_default_output_tokens) and charged what it used once it completes.")
40-
tpm_admission: Optional[StrictStr] = Field(default='estimate', description="How a tpm limit admits a request. 'estimate' holds the request's estimate and refuses it when that does not fit. 'used' admits a request while the minute's tokens are under the limit, holding none, and counts what it used once it completes, as LiteLLM does: a client that always sends a large max_tokens is limited by its usage, not its ceiling.")
39+
tpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Tokens per minute, counted on what each request used; see tpm_admission for how a request is admitted.")
40+
tpm_admission: Optional[StrictStr] = Field(default='used', description="How a tpm limit admits a request. 'used' (the default) admits a request while the minute's tokens are under the limit and counts what it used once it completes, as LiteLLM does. 'estimate' holds the request's estimate (prompt plus max output, or budget_estimate_default_output_tokens) while it runs and refuses it when that does not fit, which is how providers count their own quotas: use it for a limit meant to stay under one.")
4141
updated_at: Optional[datetime] = Field(default=None, description="When a stored rule last changed.")
4242
additional_properties: Dict[str, Any] = {}
4343
__properties: ClassVar[List[str]] = ["lease_sec", "max_concurrent", "models", "name", "per", "rpm", "source", "tpm", "tpm_admission", "updated_at"]
@@ -72,8 +72,8 @@ def tpm_admission_validate_enum(cls, value):
7272
if value is None:
7373
return value
7474

75-
if value not in set(['estimate', 'used']):
76-
raise ValueError("must be one of enum values ('estimate', 'used')")
75+
if value not in set(['used', 'estimate']):
76+
raise ValueError("must be one of enum values ('used', 'estimate')")
7777
return value
7878

7979
model_config = ConfigDict(
@@ -167,7 +167,7 @@ def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
167167
"rpm": obj.get("rpm"),
168168
"source": obj.get("source"),
169169
"tpm": obj.get("tpm"),
170-
"tpm_admission": obj.get("tpm_admission") if obj.get("tpm_admission") is not None else 'estimate',
170+
"tpm_admission": obj.get("tpm_admission") if obj.get("tpm_admission") is not None else 'used',
171171
"updated_at": obj.get("updated_at")
172172
})
173173
# store additional fields in additional_properties

‎src/otari/_client/models/rate_limit_rule_update.py‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -34,7 +34,7 @@ class RateLimitRuleUpdate(BaseModel):
3434
per: Optional[StrictStr] = Field(default=None, description="What one count is shared by.")
3535
rpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Requests per minute.")
3636
tpm: Optional[Annotated[int, Field(strict=True, ge=1)]] = Field(default=None, description="Tokens per minute.")
37-
tpm_admission: Optional[StrictStr] = Field(default=None, description="'estimate' holds a request's estimate; 'used' counts only what it used.")
37+
tpm_admission: Optional[StrictStr] = Field(default=None, description="'used' counts only what a request used; 'estimate' holds its estimate.")
3838
__properties: ClassVar[List[str]] = ["lease_sec", "max_concurrent", "models", "per", "rpm", "tpm", "tpm_admission"]
3939

4040
@field_validator('per')
@@ -53,8 +53,8 @@ def tpm_admission_validate_enum(cls, value):
5353
if value is None:
5454
return value
5555

56-
if value not in set(['estimate', 'used']):
57-
raise ValueError("must be one of enum values ('estimate', 'used')")
56+
if value not in set(['used', 'estimate']):
57+
raise ValueError("must be one of enum values ('used', 'estimate')")
5858
return value
5959

6060
model_config = ConfigDict(

0 commit comments

Comments
 (0)
Back | FazBrowse Home | New Git URL