langroid 0.58.2__py3-none-any.whl → 0.59.0b1__py3-none-any.whl

langroid/language_models/client_cache.py

@@ -49,6 +49,8 @@ def get_openai_client(
     organization: Optional[str] = None,
     timeout: Union[float, Timeout] = 120.0,
     default_headers: Optional[Dict[str, str]] = None,
+    http_client: Optional[Any] = None,
+    http_client_config: Optional[Dict[str, Any]] = None,
 ) -> OpenAI:
     """
     Get or create a singleton OpenAI client with the given configuration.
@@ -59,6 +61,8 @@ def get_openai_client(
         organization: Optional organization ID
         timeout: Request timeout
         default_headers: Optional default headers
+        http_client: Optional httpx.Client instance
+        http_client_config: Optional config dict for creating httpx.Client
 
     Returns:
         OpenAI client instance
@@ -66,6 +70,32 @@ def get_openai_client(
     if isinstance(timeout, (int, float)):
         timeout = Timeout(timeout)
 
+    # If http_client is provided directly, don't cache (complex object)
+    if http_client is not None:
+        client = OpenAI(
+            api_key=api_key,
+            base_url=base_url,
+            organization=organization,
+            timeout=timeout,
+            default_headers=default_headers,
+            http_client=http_client,
+        )
+        _all_clients.add(client)
+        return client
+
+    # If http_client_config is provided, create client from config and cache
+    created_http_client = None
+    if http_client_config is not None:
+        try:
+            from httpx import Client
+
+            created_http_client = Client(**http_client_config)
+        except ImportError:
+            raise ValueError(
+                "httpx is required to use http_client_config. "
+                "Install it with: pip install httpx"
+            )
+
     cache_key = _get_cache_key(
         "openai",
         api_key=api_key,
@@ -73,6 +103,7 @@ def get_openai_client(
         organization=organization,
         timeout=timeout,
         default_headers=default_headers,
+        http_client_config=http_client_config,  # Include config in cache key
     )
 
     if cache_key in _client_cache:
@@ -84,6 +115,7 @@ def get_openai_client(
         organization=organization,
         timeout=timeout,
         default_headers=default_headers,
+        http_client=created_http_client,  # Use the client created from config
     )
 
     _client_cache[cache_key] = client
@@ -97,6 +129,8 @@ def get_async_openai_client(
     organization: Optional[str] = None,
     timeout: Union[float, Timeout] = 120.0,
     default_headers: Optional[Dict[str, str]] = None,
+    http_client: Optional[Any] = None,
+    http_client_config: Optional[Dict[str, Any]] = None,
 ) -> AsyncOpenAI:
     """
     Get or create a singleton AsyncOpenAI client with the given configuration.
@@ -107,6 +141,8 @@ def get_async_openai_client(
         organization: Optional organization ID
         timeout: Request timeout
         default_headers: Optional default headers
+        http_client: Optional httpx.AsyncClient instance
+        http_client_config: Optional config dict for creating httpx.AsyncClient
 
     Returns:
         AsyncOpenAI client instance
@@ -114,6 +150,32 @@ def get_async_openai_client(
     if isinstance(timeout, (int, float)):
         timeout = Timeout(timeout)
 
+    # If http_client is provided directly, don't cache (complex object)
+    if http_client is not None:
+        client = AsyncOpenAI(
+            api_key=api_key,
+            base_url=base_url,
+            organization=organization,
+            timeout=timeout,
+            default_headers=default_headers,
+            http_client=http_client,
+        )
+        _all_clients.add(client)
+        return client
+
+    # If http_client_config is provided, create async client from config and cache
+    created_http_client = None
+    if http_client_config is not None:
+        try:
+            from httpx import AsyncClient
+
+            created_http_client = AsyncClient(**http_client_config)
+        except ImportError:
+            raise ValueError(
+                "httpx is required to use http_client_config. "
+                "Install it with: pip install httpx"
+            )
+
     cache_key = _get_cache_key(
         "async_openai",
         api_key=api_key,
@@ -121,6 +183,7 @@ def get_async_openai_client(
         organization=organization,
         timeout=timeout,
         default_headers=default_headers,
+        http_client_config=http_client_config,  # Include config in cache key
     )
 
     if cache_key in _client_cache:
@@ -132,6 +195,7 @@ def get_async_openai_client(
         organization=organization,
         timeout=timeout,
         default_headers=default_headers,
+        http_client=created_http_client,  # Use the client created from config
     )
 
     _client_cache[cache_key] = client

langroid/language_models/config.py

@@ -1,12 +1,10 @@
-from langroid.pydantic_v1 import BaseSettings
+from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
 class PromptFormatterConfig(BaseSettings):
     type: str = "llama2"
 
-    class Config:
-        env_prefix = "FORMAT_"
-        case_sensitive = False
+    model_config = SettingsConfigDict(env_prefix="FORMAT_", case_sensitive=False)
 
 
 class Llama2FormatterConfig(PromptFormatterConfig):

langroid/language_models/config.py-e

@@ -0,0 +1,18 @@
+from pydantic_settings import BaseSettings
+
+from pydantic import ConfigDict
+
+
+class PromptFormatterConfig(BaseSettings):
+    type: str = "llama2"
+
+    model_config = ConfigDict(env_prefix="FORMAT_", case_sensitive=False)
+
+
+class Llama2FormatterConfig(PromptFormatterConfig):
+    use_bos_eos: bool = False
+
+
+class HFPromptFormatterConfig(PromptFormatterConfig):
+    type: str = "hf"
+    model_name: str

langroid/language_models/model_info.py

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import Dict, List, Optional
 
-from langroid.pydantic_v1 import BaseModel
+from pydantic import BaseModel
 
 
 class ModelProvider(str, Enum):
@@ -173,6 +173,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
     OpenAIChatModel.GPT4_1_NANO.value: ModelInfo(
         name=OpenAIChatModel.GPT4_1_NANO.value,
         provider=ModelProvider.OPENAI,
+        has_structured_output=True,
         context_length=1_047_576,
         max_output_tokens=32_768,
         input_cost_per_million=0.10,
@@ -183,6 +184,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
     OpenAIChatModel.GPT4_1_MINI.value: ModelInfo(
         name=OpenAIChatModel.GPT4_1_MINI.value,
         provider=ModelProvider.OPENAI,
+        has_structured_output=True,
         context_length=1_047_576,
         max_output_tokens=32_768,
         input_cost_per_million=0.40,
@@ -193,6 +195,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
     OpenAIChatModel.GPT4_1.value: ModelInfo(
         name=OpenAIChatModel.GPT4_1.value,
         provider=ModelProvider.OPENAI,
+        has_structured_output=True,
         context_length=1_047_576,
         max_output_tokens=32_768,
         input_cost_per_million=2.00,
@@ -232,6 +235,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
         output_cost_per_million=60.0,
         allows_streaming=True,
         allows_system_message=False,
+        has_structured_output=True,
         unsupported_params=["temperature"],
         rename_params={"max_tokens": "max_completion_tokens"},
         has_tools=False,
@@ -247,6 +251,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
         output_cost_per_million=8.0,
         allows_streaming=True,
         allows_system_message=False,
+        has_structured_output=True,
         unsupported_params=["temperature"],
         rename_params={"max_tokens": "max_completion_tokens"},
         has_tools=False,
@@ -262,6 +267,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
         output_cost_per_million=4.4,
         allows_streaming=False,
         allows_system_message=False,
+        has_structured_output=True,
         unsupported_params=["temperature", "stream"],
         rename_params={"max_tokens": "max_completion_tokens"},
         has_tools=False,
@@ -277,6 +283,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
         output_cost_per_million=4.4,
         allows_streaming=False,
         allows_system_message=False,
+        has_structured_output=True,
         unsupported_params=["temperature", "stream"],
         rename_params={"max_tokens": "max_completion_tokens"},
         has_tools=False,
@@ -292,6 +299,7 @@ MODEL_INFO: Dict[str, ModelInfo] = {
         output_cost_per_million=4.40,
         allows_streaming=False,
         allows_system_message=False,
+        has_structured_output=True,
         unsupported_params=["temperature", "stream"],
         rename_params={"max_tokens": "max_completion_tokens"},
         has_tools=False,