lm-deluge 0.0.33__tar.gz → 0.0.34__tar.gz

{lm_deluge-0.0.33/src/lm_deluge.egg-info → lm_deluge-0.0.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.33
+Version: 0.0.34
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10

{lm_deluge-0.0.33 → lm_deluge-0.0.34}/pyproject.toml

@@ -3,7 +3,7 @@ requires = ["setuptools", "wheel"]
 
 [project]
 name = "lm_deluge"
-version = "0.0.33"
+version = "0.0.34"
 authors = [{ name = "Benjamin Anderson", email = "ben@trytaylor.ai" }]
 description = "Python utility for using LLM API models."
 readme = "README.md"

{lm_deluge-0.0.33 → lm_deluge-0.0.34}/src/lm_deluge/api_requests/gemini.py

@@ -1,7 +1,7 @@
 import json
 import os
 import warnings
-
+from typing import Any
 from aiohttp import ClientResponse
 
 from lm_deluge.request_context import RequestContext
@@ -37,11 +37,12 @@ async def _build_gemini_request(
 
     # Handle reasoning models (thinking)
     if model.reasoning_model:
-        thinking_config = None
+        thinking_config: dict[str, Any] | None = None
         effort = sampling_params.reasoning_effort
         if effort is None or effort == "none":
+            budget = 128 if "2.5-pro" in model.id else 0
             # Explicitly disable thoughts when no effort is requested
-            thinking_config = {"includeThoughts": False, "thinkingBudget": 0}
+            thinking_config = {"includeThoughts": False, "thinkingBudget": budget}
         else:
             thinking_config = {"includeThoughts": True}
             if effort in {"low", "medium", "high"} and "flash" in model.id:

{lm_deluge-0.0.33 → lm_deluge-0.0.34}/src/lm_deluge/client.py

@@ -773,10 +773,54 @@ class _LLMClient(BaseModel):
 
 # Clean factory function with perfect IDE support
 @overload
-def LLMClient(model_names: str, **kwargs) -> _LLMClient: ...
+def LLMClient(
+    model_names: str,
+    *,
+    max_requests_per_minute: int = 1_000,
+    max_tokens_per_minute: int = 100_000,
+    max_concurrent_requests: int = 225,
+    sampling_params: list[SamplingParams] | None = None,
+    model_weights: list[float] | Literal["uniform", "dynamic"] = "uniform",
+    max_attempts: int = 5,
+    request_timeout: int = 30,
+    cache: Any = None,
+    extra_headers: dict[str, str] | None = None,
+    temperature: float = 0.75,
+    top_p: float = 1.0,
+    json_mode: bool = False,
+    max_new_tokens: int = 512,
+    reasoning_effort: Literal["low", "medium", "high", None] = None,
+    logprobs: bool = False,
+    top_logprobs: int | None = None,
+    force_local_mcp: bool = False,
+    progress: Literal["rich", "tqdm", "manual"] = "rich",
+) -> _LLMClient: ...
+
+
+@overload
+def LLMClient(
+    model_names: list[str],
+    *,
+    max_requests_per_minute: int = 1_000,
+    max_tokens_per_minute: int = 100_000,
+    max_concurrent_requests: int = 225,
+    sampling_params: list[SamplingParams] | None = None,
+    model_weights: list[float] | Literal["uniform", "dynamic"] = "uniform",
+    max_attempts: int = 5,
+    request_timeout: int = 30,
+    cache: Any = None,
+    extra_headers: dict[str, str] | None = None,
+    temperature: float = 0.75,
+    top_p: float = 1.0,
+    json_mode: bool = False,
+    max_new_tokens: int = 512,
+    reasoning_effort: Literal["low", "medium", "high", None] = None,
+    logprobs: bool = False,
+    top_logprobs: int | None = None,
+    force_local_mcp: bool = False,
+    progress: Literal["rich", "tqdm", "manual"] = "rich",
+) -> _LLMClient: ...
 
-@overload  
-def LLMClient(model_names: list[str], **kwargs) -> _LLMClient: ...
 
 def LLMClient(
     model_names: str | list[str] = "gpt-4.1-mini",
@@ -802,18 +846,18 @@ def LLMClient(
 ) -> _LLMClient:
     """
     Create an LLMClient with model_names as a positional argument.
-    
+
     Args:
         model_names: Model name(s) to use - can be a single string or list of strings
         **kwargs: All other LLMClient configuration options (keyword-only)
-    
+
     Returns:
         Configured LLMClient instance
     """
     # Handle default for mutable argument
     if sampling_params is None:
         sampling_params = []
-    
+
     # Simply pass everything to the Pydantic constructor
     return _LLMClient(
         model_names=model_names,

{lm_deluge-0.0.33 → lm_deluge-0.0.34}/src/lm_deluge/models.py

@@ -1275,7 +1275,7 @@ def register_model(
     reasoning_model: bool = False,
     regions: list[str] | dict[str, int] = field(default_factory=list),
     tokens_per_minute: int | None = None,
-    requests_per_minute: int | None = None
+    requests_per_minute: int | None = None,
 ) -> APIModel:
     """Register a model configuration and return the created APIModel."""
     model = APIModel(
@@ -1292,7 +1292,7 @@ def register_model(
         reasoning_model=reasoning_model,
         regions=regions,
         tokens_per_minute=tokens_per_minute,
-        requests_per_minute=requests_per_minute
+        requests_per_minute=requests_per_minute,
     )
     registry[model.id] = model
     return model

{lm_deluge-0.0.33 → lm_deluge-0.0.34/src/lm_deluge.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lm_deluge
-Version: 0.0.33
+Version: 0.0.34
 Summary: Python utility for using LLM API models.
 Author-email: Benjamin Anderson <ben@trytaylor.ai>
 Requires-Python: >=3.10