gllm-inference-binary 0.5.5__cp311-cp311-win_amd64.whl → 0.5.7__cp311-cp311-win_amd64.whl

gllm_inference/builder/build_lm_request_processor.pyi

@@ -8,7 +8,7 @@ from typing import Any
 
 logger: Incomplete
 
-def build_lm_request_processor(model_id: str | ModelId, credentials: str | dict[str, Any] | None = None, config: dict[str, Any] | None = None, system_template: str = '', user_template: str = '', output_parser_type: str = 'none') -> LMRequestProcessor:
+def build_lm_request_processor(model_id: str | ModelId, credentials: str | dict[str, Any] | None = None, config: dict[str, Any] | None = None, system_template: str = '', user_template: str = '', key_defaults: dict[str, Any] | None = None, output_parser_type: str = 'none') -> LMRequestProcessor:
     '''Build a language model invoker based on the provided configurations.
 
     Args:
@@ -29,6 +29,9 @@ def build_lm_request_processor(model_id: str | ModelId, credentials: str | dict[
             Defaults to an empty string.
         user_template (str): The user prompt template. May contain placeholders enclosed in curly braces `{}`.
             Defaults to an empty string.
+        key_defaults (dict[str, str] | None, optional): Default values for the keys in the prompt templates.
+            Applied when the corresponding keys are not provided in the runtime input.
+            Defaults to None, in which case no default values will be assigned to the keys.
         output_parser_type (str, optional): The type of output parser to use. Supports "json" and "none".
             Defaults to "none".
 
@@ -63,13 +66,14 @@ def build_lm_request_processor(model_id: str | ModelId, credentials: str | dict[
         )
         ```
 
-        # With system template
+        # With custom prompt builder configuration
         ```python
         lm_request_processor = build_lm_request_processor(
             model_id="openai/gpt-4o-mini",
             credentials="sk-...",
-            system_template="Talk like a pirate.",
+            system_template="Talk like a {role}.",
             user_template="{query}",
+            key_defaults={"role": "pirate"},
         )
         ```
 

gllm_inference/catalog/lm_request_processor_catalog.pyi

@@ -6,6 +6,7 @@ from gllm_inference.request_processor import LMRequestProcessor as LMRequestProc
 MODEL_ID_ENV_VAR_REGEX_PATTERN: str
 LM_REQUEST_PROCESSOR_REQUIRED_COLUMNS: Incomplete
 CONFIG_SCHEMA_MAP: Incomplete
+logger: Incomplete
 
 class LMRequestProcessorCatalog(BaseCatalog[LMRequestProcessor]):
     '''Loads multiple LM request processors from certain sources.
@@ -46,17 +47,24 @@ class LMRequestProcessorCatalog(BaseCatalog[LMRequestProcessor]):
 
         # Example 4: Load from record
         ```python
-        catalog = LMRequestProcessorCatalog.from_records(
-            name="...",
-            system_template="...",
-            user_template="...",
-            model_id="...",
-            credentials="...",
-            config="...",
-            output_parser_type="...",
-        )
-
-        lm_request_processor = catalog.name
+        records=[
+            {
+                "name": "answer_question",
+                "system_template": (
+                    "You are helpful assistant.\\n"
+                    "Answer the following question based on the provided context.\\n"
+                    "```{context}```"
+                ),
+                "user_template": "{query}",
+                "key_defaults": \'{"context": "<default context>"}\',
+                "model_id": "openai/gpt-4.1-nano",
+                "credentials": "OPENAI_API_KEY",
+                "config": "",
+                "output_parser_type": "none",
+            },
+        ]
+        catalog = LMRequestProcessorCatalog.from_records(records=records)
+        lm_request_processor = catalog.answer_question
         ```
 
     Template Format Example:
@@ -66,35 +74,39 @@ class LMRequestProcessorCatalog(BaseCatalog[LMRequestProcessor]):
 
         # Example 2: CSV
         For an example of how a CSV file can be formatted to be loaded using LMRequestProcessorCatalog, see:
-        https://drive.google.com/file/d/10nYKn_r9SVnTkaik-caMqUjX6prUZ62M/view?usp=drive_link
+        https://drive.google.com/file/d/1_2rSoxh3CR2KZxIyUmpowMrt0Lm0YqAb/view?usp=drive_link
 
     Template Explanation:
         The required columns are:
-            1. name (str): The name of the LM request processor.
-            2. system_template (str): The system template of the prompt builder.
-            3. user_template (str): The user template of the prompt builder.
-            4. model_id (str): The model ID of the LM invoker.
-            5. credentials (str | json_str): The credentials of the LM invoker.
-            6. config (json_str): The additional configuration of the LM invoker.
-            7. output_parser_type (str): The type of the output parser.
+        1. name (str): The name of the LM request processor.
+        2. system_template (str): The system template of the prompt builder.
+        3. user_template (str): The user template of the prompt builder.
+        4. key_defaults (json_str): The default values for the prompt template keys.
+        5. model_id (str): The model ID of the LM invoker.
+        6. credentials (str | json_str): The credentials of the LM invoker.
+        7. config (json_str): The additional configuration of the LM invoker.
+        8. output_parser_type (str): The type of the output parser.
 
         Important Notes:
         1. At least one of `system_template` or `user_template` must be filled.
-        2. The `model_id`:
-            2.1. Must be filled with the model ID of the LM invoker, e.g. "openai/gpt-4.1-nano".
-            2.2. Can be partially loaded from the environment variable using the "${ENV_VAR_KEY}" syntax,
+        2. `key_defaults` is optional. If filled, must be a dictionary containing the default values for the
+            prompt template keys. These default values will be applied when the corresponding keys are not provided
+            in the runtime input. If it is empty, the prompt template keys will not have default values.
+        3. The `model_id`:
+            3.1. Must be filled with the model ID of the LM invoker, e.g. "openai/gpt-4.1-nano".
+            3.2. Can be partially loaded from the environment variable using the "${ENV_VAR_KEY}" syntax,
                 e.g. "azure-openai/${AZURE_ENDPOINT}/${AZURE_DEPLOYMENT}".
-            2.3. For the available model ID formats, see: https://gdplabs.gitbook.io/sdk/resources/supported-models
-        3. `credentials` is optional. If it is filled, it can either be:
-            3.1. An environment variable name containing the API key (e.g. OPENAI_API_KEY).
-            3.2. An environment variable name containing the path to a credentials JSON file
+            3.3. For the available model ID formats, see: https://gdplabs.gitbook.io/sdk/resources/supported-models
+        4. `credentials` is optional. If it is filled, it can either be:
+            4.1. An environment variable name containing the API key (e.g. OPENAI_API_KEY).
+            4.2. An environment variable name containing the path to a credentials JSON file
                 (e.g. GOOGLE_CREDENTIALS_FILE_PATH). Currently only supported for Google Vertex AI.
-            3.3. A dictionary of credentials, with each value being an environment variable name corresponding to the
+            4.3. A dictionary of credentials, with each value being an environment variable name corresponding to the
                 credential (e.g. {"api_key": "OPENAI_API_KEY"}). Currently supported for Bedrock and LangChain.
             If it is empty, the LM invoker will use the default credentials loaded from the environment variables.
-        4. `config` is optional. If filled, must be a dictionary containing the configuration for the LM invoker.
+        5. `config` is optional. If filled, must be a dictionary containing the configuration for the LM invoker.
             If it is empty, the LM invoker will use the default configuration.
-        5. `output_parser_type` can either be:
-            5.1. none: No output parser will be used.
-            5.2. json: The JSONOutputParser will be used.
+        6. `output_parser_type` can either be:
+            6.1. none: No output parser will be used.
+            6.2. json: The JSONOutputParser will be used.
     '''

gllm_inference/catalog/prompt_builder_catalog.pyi

@@ -3,6 +3,7 @@ from gllm_inference.catalog.catalog import BaseCatalog as BaseCatalog
 from gllm_inference.prompt_builder.prompt_builder import PromptBuilder as PromptBuilder
 
 PROMPT_BUILDER_REQUIRED_COLUMNS: Incomplete
+logger: Incomplete
 
 class PromptBuilderCatalog(BaseCatalog[PromptBuilder]):
     '''Loads multiple prompt builders from certain sources.
@@ -42,22 +43,14 @@ class PromptBuilderCatalog(BaseCatalog[PromptBuilder]):
         ```python
         records=[
             {
-                "name": "summarize",
-                "system": "You are an AI expert\\nSummarize the following context.\\n\\nContext:\\n```{context}```",
-                "user": ""
-            },
-            {
-                "name": "transform_query",
-                "system": "",
-                "user": "Transform the following query into a simpler form.\\n\\nQuery:\\n```{query}```"
-            },
-            {
-                "name": "draft_document",
+                "name": "answer_question",
                 "system": (
-                    "You are an AI expert.\\nDraft a document following the provided format and context.\\n\\n"
-                    "Format:\\n```{format}```\\n\\nContext:\\n```{context}```"
+                    "You are helpful assistant.\\n"
+                    "Answer the following question based on the provided context.\\n"
+                    "```{context}```"
                 ),
-                "user": "User instruction:\\n{query}"
+                "user": "{query}",
+                "key_defaults": \'{"context": "<default context>"}\',
             },
         ]
         catalog = PromptBuilderCatalog.from_records(records=records)
@@ -71,15 +64,19 @@ class PromptBuilderCatalog(BaseCatalog[PromptBuilder]):
 
         # Example 2: CSV
         For an example of how a CSV file can be formatted to be loaded using PromptBuilderCatalog, see:
-        https://drive.google.com/file/d/1CWijOk-g16ZglUn_K2bDPmbyyBDK2r0L/view?usp=drive_link
+        https://drive.google.com/file/d/1KQgddMdbcZBZmroQFtjSl-TKLohq84Fz/view?usp=drive_link
 
 
     Template explanation:
         The required columns are:
-            1. name (str): The name of the prompt builder.
-            2. system (str): The system template of the prompt builder.
-            3. user (str): The user template of the prompt builder.
+        1. name (str): The name of the prompt builder.
+        2. system (str): The system template of the prompt builder.
+        3. user (str): The user template of the prompt builder.
+        4. key_defaults (json_str): The default values for the prompt template keys.
 
         Important Notes:
-            1. At least one of the `system` and `user` columns must be filled.
+        1. At least one of the `system` and `user` columns must be filled.
+        2. `key_defaults` is optional. If filled, must be a dictionary containing the default values for the
+            prompt template keys. These default values will be applied when the corresponding keys are not provided
+            in the runtime input. If it is empty, the prompt template keys will not have default values.
     '''

gllm_inference/constants.pyi

@@ -3,6 +3,7 @@ from _typeshed import Incomplete
 DEFAULT_AZURE_OPENAI_API_VERSION: str
 DOCUMENT_MIME_TYPES: Incomplete
 GOOGLE_SCOPES: Incomplete
+INVOKER_PROPAGATED_MAX_RETRIES: int
 INVOKER_DEFAULT_TIMEOUT: float
 HEX_REPR_LENGTH: int
 HTTP_STATUS_CODE_PATTERNS: Incomplete

gllm_inference/em_invoker/azure_openai_em_invoker.pyi

@@ -1,7 +1,8 @@
 from _typeshed import Incomplete
 from gllm_core.utils.retry import RetryConfig as RetryConfig
-from gllm_inference.constants import DEFAULT_AZURE_OPENAI_API_VERSION as DEFAULT_AZURE_OPENAI_API_VERSION
+from gllm_inference.constants import DEFAULT_AZURE_OPENAI_API_VERSION as DEFAULT_AZURE_OPENAI_API_VERSION, INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.openai_em_invoker import OpenAIEMInvoker as OpenAIEMInvoker
+from gllm_inference.em_invoker.schema.openai import Key as Key
 from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider
 from typing import Any
 

gllm_inference/em_invoker/google_em_invoker.pyi

@@ -2,6 +2,7 @@ from _typeshed import Incomplete
 from gllm_core.utils.retry import RetryConfig as RetryConfig
 from gllm_inference.constants import GOOGLE_SCOPES as GOOGLE_SCOPES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
+from gllm_inference.em_invoker.schema.google import Key as Key
 from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
 from typing import Any
 

gllm_inference/em_invoker/langchain_em_invoker.pyi

@@ -1,6 +1,8 @@
 from _typeshed import Incomplete
-from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_core.utils.retry import RetryConfig
+from gllm_inference.constants import INVOKER_DEFAULT_TIMEOUT as INVOKER_DEFAULT_TIMEOUT, INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
+from gllm_inference.em_invoker.schema.langchain import Key as Key
 from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
 from gllm_inference.utils import load_langchain_model as load_langchain_model, parse_model_data as parse_model_data
 from langchain_core.embeddings import Embeddings as Embeddings

gllm_inference/em_invoker/openai_compatible_em_invoker.pyi

@@ -1,6 +1,8 @@
 from _typeshed import Incomplete
 from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.openai_em_invoker import OpenAIEMInvoker as OpenAIEMInvoker
+from gllm_inference.em_invoker.schema.openai_compatible import Key as Key
 from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider
 from typing import Any
 

gllm_inference/em_invoker/openai_em_invoker.pyi

@@ -1,6 +1,8 @@
 from _typeshed import Incomplete
 from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
+from gllm_inference.em_invoker.schema.openai import Key as Key
 from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector
 from typing import Any
 

gllm_inference/em_invoker/schema/google.pyi

@@ -0,0 +1,7 @@
+class Key:
+    """Defines valid keys in Google."""
+    CREDENTIALS: str
+    HTTP_OPTIONS: str
+    LOCATION: str
+    PROJECT: str
+    TIMEOUT: str

gllm_inference/em_invoker/schema/langchain.pyi

@@ -0,0 +1,4 @@
+class Key:
+    """Defines valid keys in LangChain."""
+    MAX_RETRIES: str
+    TIMEOUT: str

gllm_inference/em_invoker/schema/openai.pyi

@@ -0,0 +1,7 @@
+class Key:
+    """Defines valid keys in OpenAI."""
+    API_KEY: str
+    BASE_URL: str
+    MAX_RETRIES: str
+    MODEL: str
+    TIMEOUT: str

gllm_inference/em_invoker/schema/openai_compatible.pyi

@@ -0,0 +1,7 @@
+class Key:
+    """Defines valid keys in OpenAI Compatible."""
+    API_KEY: str
+    BASE_URL: str
+    MAX_RETRIES: str
+    MODEL: str
+    TIMEOUT: str

gllm_inference/em_invoker/schema/twelvelabs.pyi

@@ -1,7 +1,9 @@
 class Key:
     """Defines valid keys in TwelveLabs."""
     INPUT_KEY: str
+    MAX_RETRIES: str
     OUTPUT_KEY: str
+    TIMEOUT: str
     VALUE: str
 
 class InputType:

gllm_inference/em_invoker/schema/voyage.pyi

@@ -1,8 +1,12 @@
 class Key:
     """Defines valid keys in Voyage."""
+    API_KEY: str
     CONTENT: str
     IMAGE_BASE64: str
+    MAX_RETRIES: str
+    MODEL: str
     TEXT: str
+    TIMEOUT: str
     TYPE: str
 
 class InputType:

gllm_inference/em_invoker/twelevelabs_em_invoker.pyi

@@ -1,5 +1,6 @@
 from _typeshed import Incomplete
 from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.twelvelabs import InputType as InputType, Key as Key, OutputType as OutputType
 from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector

gllm_inference/em_invoker/voyage_em_invoker.pyi

@@ -1,5 +1,6 @@
 from _typeshed import Incomplete
 from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.em_invoker.em_invoker import BaseEMInvoker as BaseEMInvoker
 from gllm_inference.em_invoker.schema.voyage import InputType as InputType, Key as Key
 from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EMContent as EMContent, ModelId as ModelId, ModelProvider as ModelProvider, Vector as Vector

gllm_inference/lm_invoker/anthropic_lm_invoker.pyi

@@ -1,6 +1,7 @@
 from _typeshed import Incomplete
 from gllm_core.event import EventEmitter as EventEmitter
 from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.lm_invoker.lm_invoker import BaseLMInvoker as BaseLMInvoker
 from gllm_inference.lm_invoker.schema.anthropic import InputType as InputType, Key as Key, OutputType as OutputType
 from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EmitDataType as EmitDataType, LMOutput as LMOutput, Message as Message, ModelId as ModelId, ModelProvider as ModelProvider, Reasoning as Reasoning, ResponseSchema as ResponseSchema, TokenUsage as TokenUsage, ToolCall as ToolCall, ToolResult as ToolResult

gllm_inference/lm_invoker/azure_openai_lm_invoker.pyi

@@ -1,7 +1,8 @@
 from _typeshed import Incomplete
 from gllm_core.utils.retry import RetryConfig as RetryConfig
-from gllm_inference.constants import DEFAULT_AZURE_OPENAI_API_VERSION as DEFAULT_AZURE_OPENAI_API_VERSION
+from gllm_inference.constants import DEFAULT_AZURE_OPENAI_API_VERSION as DEFAULT_AZURE_OPENAI_API_VERSION, INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.lm_invoker.openai_lm_invoker import OpenAILMInvoker as OpenAILMInvoker, ReasoningEffort as ReasoningEffort, ReasoningSummary as ReasoningSummary
+from gllm_inference.lm_invoker.schema.openai import Key as Key
 from gllm_inference.schema import ModelId as ModelId, ModelProvider as ModelProvider, ResponseSchema as ResponseSchema
 from langchain_core.tools import Tool as Tool
 from typing import Any

gllm_inference/lm_invoker/datasaur_lm_invoker.pyi

@@ -1,7 +1,7 @@
 from _typeshed import Incomplete
 from gllm_core.event import EventEmitter as EventEmitter
 from gllm_core.utils.retry import RetryConfig as RetryConfig
-from gllm_inference.constants import DOCUMENT_MIME_TYPES as DOCUMENT_MIME_TYPES
+from gllm_inference.constants import DOCUMENT_MIME_TYPES as DOCUMENT_MIME_TYPES, INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.lm_invoker.openai_compatible_lm_invoker import OpenAICompatibleLMInvoker as OpenAICompatibleLMInvoker
 from gllm_inference.lm_invoker.schema.datasaur import InputType as InputType, Key as Key
 from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, LMOutput as LMOutput, Message as Message, ModelId as ModelId, ModelProvider as ModelProvider, ResponseSchema as ResponseSchema, ToolCall as ToolCall, ToolResult as ToolResult

gllm_inference/lm_invoker/langchain_lm_invoker.pyi

@@ -1,6 +1,7 @@
 from _typeshed import Incomplete
 from gllm_core.event import EventEmitter as EventEmitter
-from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_core.utils.retry import RetryConfig
+from gllm_inference.constants import INVOKER_DEFAULT_TIMEOUT as INVOKER_DEFAULT_TIMEOUT, INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.lm_invoker.lm_invoker import BaseLMInvoker as BaseLMInvoker
 from gllm_inference.lm_invoker.schema.langchain import InputType as InputType, Key as Key
 from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, LMOutput as LMOutput, Message as Message, MessageRole as MessageRole, ModelId as ModelId, ModelProvider as ModelProvider, ResponseSchema as ResponseSchema, TokenUsage as TokenUsage, ToolCall as ToolCall, ToolResult as ToolResult

gllm_inference/lm_invoker/openai_compatible_lm_invoker.pyi

@@ -1,6 +1,7 @@
 from _typeshed import Incomplete
 from gllm_core.event import EventEmitter as EventEmitter
 from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.lm_invoker.lm_invoker import BaseLMInvoker as BaseLMInvoker
 from gllm_inference.lm_invoker.schema.openai_compatible import InputType as InputType, Key as Key, ReasoningEffort as ReasoningEffort
 from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, EmitDataType as EmitDataType, LMOutput as LMOutput, Message as Message, MessageRole as MessageRole, ModelId as ModelId, ModelProvider as ModelProvider, Reasoning as Reasoning, ResponseSchema as ResponseSchema, TokenUsage as TokenUsage, ToolCall as ToolCall, ToolResult as ToolResult

gllm_inference/lm_invoker/openai_lm_invoker.pyi

@@ -1,6 +1,7 @@
 from _typeshed import Incomplete
 from gllm_core.event import EventEmitter as EventEmitter
 from gllm_core.utils.retry import RetryConfig as RetryConfig
+from gllm_inference.constants import INVOKER_PROPAGATED_MAX_RETRIES as INVOKER_PROPAGATED_MAX_RETRIES
 from gllm_inference.lm_invoker.lm_invoker import BaseLMInvoker as BaseLMInvoker
 from gllm_inference.lm_invoker.schema.openai import InputType as InputType, Key as Key, OutputType as OutputType, ReasoningEffort as ReasoningEffort, ReasoningSummary as ReasoningSummary
 from gllm_inference.schema import Attachment as Attachment, AttachmentType as AttachmentType, CodeExecResult as CodeExecResult, EmitDataType as EmitDataType, LMOutput as LMOutput, Message as Message, MessageRole as MessageRole, ModelId as ModelId, ModelProvider as ModelProvider, Reasoning as Reasoning, ResponseSchema as ResponseSchema, TokenUsage as TokenUsage, ToolCall as ToolCall, ToolResult as ToolResult

gllm_inference/lm_invoker/schema/anthropic.pyi

@@ -8,6 +8,7 @@ class Key:
     ID: str
     INPUT: str
     INPUT_SCHEMA: str
+    MAX_RETRIES: str
     MEDIA_TYPE: str
     MAX_TOKENS: str
     NAME: str
@@ -17,6 +18,7 @@ class Key:
     SOURCE: str
     STOP_REASON: str
     SYSTEM: str
+    TIMEOUT: str
     THINKING: str
     TOOLS: str
     TOOL_CHOICE: str

gllm_inference/lm_invoker/schema/datasaur.pyi

@@ -1,7 +1,9 @@
 class Key:
     """Defines valid keys in Datasaur."""
     CONTEXTS: str
+    MAX_RETRIES: str
     NAME: str
+    TIMEOUT: str
     TYPE: str
     URL: str
 

gllm_inference/lm_invoker/schema/google.pyi

@@ -6,9 +6,12 @@ class Key:
     FINISH_REASON: str
     FUNCTION: str
     FUNCTION_CALL: str
+    HTTP_OPTIONS: str
     NAME: str
+    RETRY_OPTIONS: str
     SYSTEM_INSTRUCTION: str
     THINKING_CONFIG: str
+    TIMEOUT: str
     TOOLS: str
     RESPONSE_SCHEMA: str
     RESPONSE_MIME_TYPE: str

gllm_inference/lm_invoker/schema/langchain.pyi

@@ -5,11 +5,13 @@ class Key:
     ID: str
     IMAGE_URL: str
     INPUT_TOKENS: str
+    MAX_RETRIES: str
     NAME: str
     OUTPUT_TOKENS: str
     PARSED: str
     RAW: str
     TEXT: str
+    TIMEOUT: str
     TYPE: str
     URL: str
 

gllm_inference/lm_invoker/schema/openai_compatible.pyi

@@ -15,6 +15,7 @@ class Key:
     IMAGE_URL: str
     INPUT_AUDIO: str
     JSON_SCHEMA: str
+    MAX_RETRIES: str
     MESSAGE: str
     NAME: str
     RESPONSE_FORMAT: str
@@ -22,6 +23,7 @@ class Key:
     SCHEMA: str
     STRICT: str
     TEXT: str
+    TIMEOUT: str
     TITLE: str
     TOOLS: str
     TOOL_CALLS: str

gllm_inference.pyi

@@ -59,6 +59,7 @@ import langchain_core.embeddings
 import gllm_inference.utils.load_langchain_model
 import gllm_inference.utils.parse_model_data
 import io
+import httpx
 import twelvelabs
 import base64
 import sys
@@ -70,7 +71,6 @@ import enum
 import http
 import http.HTTPStatus
 import aiohttp
-import httpx
 import requests
 import gllm_inference.schema.ErrorResponse
 import gllm_core.constants

{gllm_inference_binary-0.5.5.dist-info → gllm_inference_binary-0.5.7.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: gllm-inference-binary
-Version: 0.5.5
+Version: 0.5.7
 Summary: A library containing components related to model inferences in Gen AI applications.
 Author: Henry Wicaksono
 Author-email: henry.wicaksono@gdplabs.id

{gllm_inference_binary-0.5.5.dist-info → gllm_inference_binary-0.5.7.dist-info}/RECORD

@@ -2,49 +2,53 @@ gllm_inference/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gllm_inference/builder/__init__.pyi,sha256=-bw1uDx7CAM7pkvjvb1ZXku9zXlQ7aEAyC83KIn3bz8,506
 gllm_inference/builder/build_em_invoker.pyi,sha256=PGRHlmiQ-GUTDC51PwYFjVkXRxeN0immnaSBOI06Uno,5474
 gllm_inference/builder/build_lm_invoker.pyi,sha256=6dQha47M19hllF5ID5xUeiNPmbWUpKyNbG9D78qFGck,6618
-gllm_inference/builder/build_lm_request_processor.pyi,sha256=1fyvGMeza_c4hXnrETNFawYYUINyvaaBsVPJY0LnlkU,4183
+gllm_inference/builder/build_lm_request_processor.pyi,sha256=0pJINCP4nnXVwuhIbhsaiwzjX8gohQt2oqXFZhTFSUs,4584
 gllm_inference/builder/build_output_parser.pyi,sha256=sgSTrzUmSRxPzUUum0fDU7A3NXYoYhpi6bEx4Q2XMnA,965
 gllm_inference/catalog/__init__.pyi,sha256=HWgPKWIzprpMHRKe_qN9BZSIQhVhrqiyjLjIXwvj1ho,291
 gllm_inference/catalog/catalog.pyi,sha256=eWPqgQKi-SJGHabi_XOTEKpAj96OSRypKsb5ZEC1VWU,4911
-gllm_inference/catalog/lm_request_processor_catalog.pyi,sha256=ymRYDQ0VY3Pmh--IeZBIZPkNqY76YoPrakLryU_txF8,4699
-gllm_inference/catalog/prompt_builder_catalog.pyi,sha256=ONWUArce7jNA1SmQWixYf-mTfVpD4kCARxiTqitQlB0,3244
-gllm_inference/constants.pyi,sha256=EkyQRO7P4siZxUKr8JWBdD_6et-3slzSXk3rkbvu4t4,228
+gllm_inference/catalog/lm_request_processor_catalog.pyi,sha256=GemCEjFRHNChtNOfbyXSVsJiA3klOCAe_X11fnymhYs,5540
+gllm_inference/catalog/prompt_builder_catalog.pyi,sha256=iViWB4SaezzjQY4UY1YxeoXUNxqxa2cTJGaD9JSx4Q8,3279
+gllm_inference/constants.pyi,sha256=xSET67ZCfeVK4a2ji1FZyQxs5DUTIsN7S6H7-F-ewZ0,265
 gllm_inference/em_invoker/__init__.pyi,sha256=eZifmg3ZS3YdFUwbGPTurrfF4oV_MAPvqErJe7oTpZI,882
-gllm_inference/em_invoker/azure_openai_em_invoker.pyi,sha256=9NuESorvptJciBw_7e1vPIHtip03aFusL-tzvYISFVo,4558
+gllm_inference/em_invoker/azure_openai_em_invoker.pyi,sha256=QimqPII-KN9OgsfH1Iubn_tCHhtWjPQ5rilZoT6Ir-U,4688
 gllm_inference/em_invoker/em_invoker.pyi,sha256=KX4i0xBWR5j6z14nEL6T8at3StKfdf3miQ4xixtYhZk,4424
-gllm_inference/em_invoker/google_em_invoker.pyi,sha256=-585WO1P4jNcuXJ9TQ6umSxozXMz39KwWa1gsGopHuQ,6190
+gllm_inference/em_invoker/google_em_invoker.pyi,sha256=YJtRJs7bNGNEfTKtj3IVP1XkLcJ3LRmcAC80zzOHxKw,6254
 gllm_inference/em_invoker/langchain/__init__.pyi,sha256=aOTlRvS9aG1tBErjsmhe75s4Sq-g2z9ArfGqNW7QyEs,151
 gllm_inference/em_invoker/langchain/em_invoker_embeddings.pyi,sha256=gEX21gJLngUh9fZo8v6Vbh0gpWFFqS2S-dGNZSrDjFQ,2409
-gllm_inference/em_invoker/langchain_em_invoker.pyi,sha256=kqRzcolB2bV5ZlwrUtqcl5JA84phgrvVgycr8wrSYOc,2616
-gllm_inference/em_invoker/openai_compatible_em_invoker.pyi,sha256=Vw6N8sExzQIzNvdOjUpQkSr7ax90SbTTKNTLLuwxNpw,4892
-gllm_inference/em_invoker/openai_em_invoker.pyi,sha256=p0X6v0AFOC4g693jqMeB4muuWXTC_F49V0ImyX1h95A,4154
+gllm_inference/em_invoker/langchain_em_invoker.pyi,sha256=sFmsRE89MIdnD8g0VSMsdLvtfZL6dfPkUtDhH_WfgLc,2823
+gllm_inference/em_invoker/openai_compatible_em_invoker.pyi,sha256=S5lRg3MeLoenOkeAG079I22kPaFXAFrltSoWcQSDK4I,5070
+gllm_inference/em_invoker/openai_em_invoker.pyi,sha256=1WTuPtu5RlZCUcBHMXR5xEkAufWCHshKA8_JW7oFakE,4321
 gllm_inference/em_invoker/schema/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gllm_inference/em_invoker/schema/twelvelabs.pyi,sha256=E7sl1OumEzx_Dj8SeiJ6i8AFuRKzAmRVGfIRCk3gv_0,349
-gllm_inference/em_invoker/schema/voyage.pyi,sha256=mL0D2lqqudL1S-eVF5K4uBt0xuMjvYtVrQzLx0-6gq0,230
-gllm_inference/em_invoker/twelevelabs_em_invoker.pyi,sha256=5A5jymcLKTOFkux-dlXSSvFzYIDTCi8gb4YIaN3royM,5062
-gllm_inference/em_invoker/voyage_em_invoker.pyi,sha256=rSWtQF8PjAuUHtPQKYrQ2GZJT5UVu3HTD96RykZJImc,5132
+gllm_inference/em_invoker/schema/google.pyi,sha256=lPzJ-f18qVar6dctdN4eQWrxWrOFHC9zJ4cuLXXMytw,153
+gllm_inference/em_invoker/schema/langchain.pyi,sha256=JPEqA6naKL64jpW8NEKsEP-V9STY2h8wvyDsFtFEHos,96
+gllm_inference/em_invoker/schema/openai.pyi,sha256=rNRqN62y5wHOKlr4T0n0m41ikAnSrD72CTnoHxo6kEM,146
+gllm_inference/em_invoker/schema/openai_compatible.pyi,sha256=A9MOeBhI-IPuvewOk4YYOAGtgyKohERx6-9cEYtbwvs,157
+gllm_inference/em_invoker/schema/twelvelabs.pyi,sha256=D3F9_1F-UTzE6Ymxj6u0IFdL6OFVGlc7noZJr3iuA6I,389
+gllm_inference/em_invoker/schema/voyage.pyi,sha256=Aqvu6mhFkNb01aXAI5mChLKIgEnFnr-jNKq1lVWB54M,304
+gllm_inference/em_invoker/twelevelabs_em_invoker.pyi,sha256=YGWQNxv3AJ9BpN6HrQSnATiW_p0dRakkqy-JgxNIlf4,5165
+gllm_inference/em_invoker/voyage_em_invoker.pyi,sha256=R8IPBOEhIN84ukof-VkTPxPNbmbkwR_imTa5u6Qyjt0,5235
 gllm_inference/exceptions/__init__.pyi,sha256=2F05RytXZIKaOJScb1pD0O0bATIQHVeEAYYNX4y5N2A,981
 gllm_inference/exceptions/error_parser.pyi,sha256=ggmh8DJXdwFJInNLrP24WVJt_4raxbAVxzXRQgBpndA,2441
 gllm_inference/exceptions/exceptions.pyi,sha256=ViXvIzm7tLcstjqfwC6nPziDg0UAmoUAWZVWrAJyp3w,4763
 gllm_inference/lm_invoker/__init__.pyi,sha256=g-wu6W6ly_WAVPLDWKjt4J5cMo-CJ1x5unuObVSUnug,1115
-gllm_inference/lm_invoker/anthropic_lm_invoker.pyi,sha256=i-jed9jfZdCxDQToID6_reKdwND6ZEceKz3rqjS9xsI,14935
-gllm_inference/lm_invoker/azure_openai_lm_invoker.pyi,sha256=aNXq0tonXyekeiEVNyqmGGXXquksXZnjMsoAlwAwHUc,14658
+gllm_inference/lm_invoker/anthropic_lm_invoker.pyi,sha256=Jpu7YPr_oUB4WurY3MqDT9J-PgDDRakj7mtrle8S3gE,15038
+gllm_inference/lm_invoker/azure_openai_lm_invoker.pyi,sha256=h71Redwp4a4Ibq3tVTtwM7FUX4AqIlmty4i0Dt8lglk,14788
 gllm_inference/lm_invoker/bedrock_lm_invoker.pyi,sha256=uOppVYAy2G7TnIK_BsRllW0akP3x14zNjrfwVrTSo8I,12530
-gllm_inference/lm_invoker/datasaur_lm_invoker.pyi,sha256=3utf_q8_MCtabsWKOEEwKU0iqZT-MI4g2kdtaklBLjY,9214
+gllm_inference/lm_invoker/datasaur_lm_invoker.pyi,sha256=AzjC-zEJt73I9wtgckZAlrlsC97U86cLksbYzO1XDK0,9280
 gllm_inference/lm_invoker/google_lm_invoker.pyi,sha256=a5ALWfhv8zW3go4gC4G-dGjQHbpQwHbSr6wdLiKiCKk,16702
-gllm_inference/lm_invoker/langchain_lm_invoker.pyi,sha256=kqF6dSqlR4R0FvRSqgTqdbyV9AzZ06KYXwpfnpJiOM8,13273
+gllm_inference/lm_invoker/langchain_lm_invoker.pyi,sha256=iD_nFw0UGX9AHSEZT57T6e2ft2ApHW4sOKk49BDpBO8,13413
 gllm_inference/lm_invoker/litellm_lm_invoker.pyi,sha256=ye73iH8wXUXzAd87JCjup5wmgVxTNhgbebRNh1hCtjE,13283
 gllm_inference/lm_invoker/lm_invoker.pyi,sha256=1wH81ssLRLLSGdf7CMQ5CZqKLcuJZHmElwBjQwitqfg,7754
-gllm_inference/lm_invoker/openai_compatible_lm_invoker.pyi,sha256=FezVE4af4C6HqzTN5TwVCjBIZ9Z8_jfnCl4ciKyC_uc,15022
-gllm_inference/lm_invoker/openai_lm_invoker.pyi,sha256=SkDYtZePQnfS5loMAjHEc7StRSs3W1mqcApxz8q-A04,19684
+gllm_inference/lm_invoker/openai_compatible_lm_invoker.pyi,sha256=jgeRQPw9IH24NoZ9dN8aW2w29D7Unn4w5L-6dhFX6l0,15125
+gllm_inference/lm_invoker/openai_lm_invoker.pyi,sha256=oXK_-nk3sdFnYIEPGkDCg4UWNyRvvMvVjkj7jozZhRk,19787
 gllm_inference/lm_invoker/schema/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gllm_inference/lm_invoker/schema/anthropic.pyi,sha256=MJHHyqMGQgj9tURyewuVlmxHxiAzU9qzmJEiK5IUoWw,1020
+gllm_inference/lm_invoker/schema/anthropic.pyi,sha256=LWhE6th4dpZwk7As11p_rhhvVoPXBsF3oAy5CtTMBrg,1060
 gllm_inference/lm_invoker/schema/bedrock.pyi,sha256=H3attoGWhBA725W4FpXw7Mty46N9jHKjw9PT-0lMEJs,975
-gllm_inference/lm_invoker/schema/datasaur.pyi,sha256=mEuWs18VO4KQ6ZTcrlW2BJwphoDe4D5iJfn-GAelvCM,202
-gllm_inference/lm_invoker/schema/google.pyi,sha256=AJQsFGKzowXfpSvorSco90aWXqgw9N0M8fInn_JN-X4,464
-gllm_inference/lm_invoker/schema/langchain.pyi,sha256=qYiQvzUw0xZa4ii-qyRCFTuIY7j0MREY6QgV1_DfkGk,391
+gllm_inference/lm_invoker/schema/datasaur.pyi,sha256=GLv6XAwKtWyRrX6EsbEufYjkPffHNiEpXwJOn9HqxMA,242
+gllm_inference/lm_invoker/schema/google.pyi,sha256=elXHrUMS46pbTsulk7hBXVVFcT022iD-_U_I590xeV8,529
+gllm_inference/lm_invoker/schema/langchain.pyi,sha256=uEG0DSD0z4L_rDMkBm-TtUy5oTyEHEEJWiLsYvFf1sw,431
 gllm_inference/lm_invoker/schema/openai.pyi,sha256=CNkIGljwRyQYx0krONX1ik9hwBiN45t9vBk-ZY45rP4,1989
-gllm_inference/lm_invoker/schema/openai_compatible.pyi,sha256=WiWEFoPQ0PEAx6EW-P8Nk6O7RF5I9i_hItEHtOl_F4A,1074
+gllm_inference/lm_invoker/schema/openai_compatible.pyi,sha256=2KXyTy43SHz0K_hB0WGXVuaHXL7bwYFIzWHZ_jmdDUo,1114
 gllm_inference/model/__init__.pyi,sha256=JKQB0wVSVYD-_tdRkG7N_oEVAKGCcoBw0BUOUMLieFo,602
 gllm_inference/model/em/__init__.pyi,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 gllm_inference/model/em/google_em.pyi,sha256=c53H-KNdNOK9ppPLyOSkmCA890eF5FsMd05upkPIzF0,487
@@ -86,8 +90,8 @@ gllm_inference/utils/__init__.pyi,sha256=RBTWDu1TDPpTd17fixcPYFv2L_vp4-IAOX0Isxg
 gllm_inference/utils/langchain.pyi,sha256=4AwFiVAO0ZpdgmqeC4Pb5NJwBt8vVr0MSUqLeCdTscc,1194
 gllm_inference/utils/validation.pyi,sha256=-RdMmb8afH7F7q4Ao7x6FbwaDfxUHn3hA3WiOgzB-3s,397
 gllm_inference.build/.gitignore,sha256=aEiIwOuxfzdCmLZe4oB1JsBmCUxwG8x-u-HBCV9JT8E,1
-gllm_inference.cp311-win_amd64.pyd,sha256=DMxnYQNhLuOV0oTOFM_-p_pAldCzfb5PTTR_9KTpE9U,2648576
-gllm_inference.pyi,sha256=VEcscbPCJ-6lXU4jV3YYXwwumk9kWxpCAsS84ssKG6o,3295
-gllm_inference_binary-0.5.5.dist-info/METADATA,sha256=S9vLvAj1-yAb0qsT4OWsW2J6gHgJxgoIejXF_lRnoEU,4531
-gllm_inference_binary-0.5.5.dist-info/WHEEL,sha256=-FZBVKyKauScY3vLa8vJR6hBCpAJfFykw2MOwlNKr1g,98
-gllm_inference_binary-0.5.5.dist-info/RECORD,,
+gllm_inference.cp311-win_amd64.pyd,sha256=hYbjt2yhDh_GQb1f8NT0OAIm1xsWyZDWKt3XMvukpt8,2687488
+gllm_inference.pyi,sha256=HPIjsiX3usTXFeStYEslrHJDUtwpBBwl-Exzcf7y7Mc,3295
+gllm_inference_binary-0.5.7.dist-info/METADATA,sha256=5l9vCcKon7_P35hWo6n7VhczO9x6rBULOCosHG3l4sY,4531
+gllm_inference_binary-0.5.7.dist-info/WHEEL,sha256=-FZBVKyKauScY3vLa8vJR6hBCpAJfFykw2MOwlNKr1g,98
+gllm_inference_binary-0.5.7.dist-info/RECORD,,