byllm 0.4.3__tar.gz → 0.4.5__tar.gz

{byllm-0.4.3 → byllm-0.4.5}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: byllm
-Version: 0.4.3
+Version: 0.4.5
 Summary: byLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language.
 License: MIT
 Keywords: llm,jaclang,jaseci,byLLM
 Author: Jason Mars
-Author-email: jason@jaseci.org
+Author-email: jason@mars.ninja
 Maintainer: Jason Mars
-Maintainer-email: jason@jaseci.org
+Maintainer-email: jason@mars.ninja
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 2
 Classifier: Programming Language :: Python :: 2.7
@@ -25,7 +25,7 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
 Provides-Extra: tools
 Provides-Extra: video
-Requires-Dist: jaclang (>=0.8.8)
+Requires-Dist: jaclang (>=0.8.10)
 Requires-Dist: litellm (>=1.75.5.post1)
 Requires-Dist: loguru (>=0.7.2,<0.8.0)
 Requires-Dist: pillow (>=10.4.0,<10.5.0)
@@ -59,7 +59,7 @@ pip install byllm
 Consider building an application that translates english to other languages using an LLM. This can be simply built as follows:
 
 ```python
-import from byllm { Model }
+import from byllm.lib { Model }
 
 glob llm = Model(model_name="gpt-4o");
 
@@ -78,7 +78,7 @@ This simple piece of code replaces traditional prompt engineering without introd
 Consider a program that detects the personality type of a historical figure from their name. This can eb built in a way that LLM picks from an enum and the output strictly adhere this type.
 
 ```python
-import from byllm { Model }
+import from byllm.lib { Model }
 glob llm = Model(model_name="gemini/gemini-2.0-flash");
 
 enum Personality {

{byllm-0.4.3 → byllm-0.4.5}/README.md

@@ -26,7 +26,7 @@ pip install byllm
 Consider building an application that translates english to other languages using an LLM. This can be simply built as follows:
 
 ```python
-import from byllm { Model }
+import from byllm.lib { Model }
 
 glob llm = Model(model_name="gpt-4o");
 
@@ -45,7 +45,7 @@ This simple piece of code replaces traditional prompt engineering without introd
 Consider a program that detects the personality type of a historical figure from their name. This can eb built in a way that LLM picks from an enum and the output strictly adhere this type.
 
 ```python
-import from byllm { Model }
+import from byllm.lib { Model }
 glob llm = Model(model_name="gemini/gemini-2.0-flash");
 
 enum Personality {

byllm-0.4.5/byllm/__init__.py

@@ -0,0 +1 @@
+"""byLLM Package - Lazy Loading."""

byllm-0.4.3/byllm/__init__.py → byllm-0.4.5/byllm/lib.py

@@ -2,7 +2,9 @@
 
 from byllm.llm import Model
 from byllm.mtir import MTIR
-from byllm.plugin import by
+from byllm.plugin import JacMachine
 from byllm.types import Image, MockToolCall, Video
 
+by = JacMachine.by
+
 __all__ = ["by", "Image", "MockToolCall", "Model", "MTIR", "Video"]

{byllm-0.4.3 → byllm-0.4.5}/byllm/llm_connector.py

@@ -181,7 +181,7 @@ class LiteLLMConnector(LLMConnector):
         message: LiteLLMMessage = response.choices[0].message  # type: ignore
         mtir.add_message(message)
 
-        output_content: str = message.content  # type: ignore
+        output_content: str = message.content or ""  # type: ignore
         self.log_info(f"LLM call completed with response:\n{output_content}")
         output_value = mtir.parse_response(output_content)
 

byllm-0.4.5/byllm/plugin.py

@@ -0,0 +1,55 @@
+"""Plugin for Jac's with_llm feature."""
+
+from __future__ import annotations
+
+
+from typing import Callable, TYPE_CHECKING
+
+from jaclang.runtimelib.machine import hookimpl
+
+if TYPE_CHECKING:
+    from byllm.llm import Model
+    from byllm.mtir import MTIR
+
+
+class JacMachine:
+    """Jac's with_llm feature."""
+
+    @staticmethod
+    @hookimpl
+    def get_mtir(caller: Callable, args: dict, call_params: dict) -> object:
+        """Call JacLLM and return the result."""
+        from byllm.mtir import MTIR
+
+        return MTIR.factory(caller, args, call_params)
+
+    @staticmethod
+    @hookimpl
+    def call_llm(model: Model, mtir: MTIR) -> object:
+        """Call JacLLM and return the result."""
+        return model.invoke(mtir=mtir)
+
+    @staticmethod
+    @hookimpl
+    def by(model: Model) -> Callable:
+        """Python library mode decorator for Jac's by llm() syntax."""
+
+        def _decorator(caller: Callable) -> Callable:
+            def _wrapped_caller(*args: object, **kwargs: object) -> object:
+                from byllm.mtir import MTIR
+
+                invoke_args: dict[int | str, object] = {}
+                for i, arg in enumerate(args):
+                    invoke_args[i] = arg
+                for key, value in kwargs.items():
+                    invoke_args[key] = value
+                mtir = MTIR.factory(
+                    caller=caller,
+                    args=invoke_args,
+                    call_params=model.llm_connector.call_params,
+                )
+                return model.invoke(mtir=mtir)
+
+            return _wrapped_caller
+
+        return _decorator

{byllm-0.4.3 → byllm-0.4.5}/pyproject.toml

@@ -1,15 +1,15 @@
 [tool.poetry]
 name = "byllm"
-version = "0.4.3"
+version = "0.4.5"
 description = "byLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language."
-authors = ["Jason Mars <jason@jaseci.org>"]
-maintainers = ["Jason Mars <jason@jaseci.org>"]
+authors = ["Jason Mars <jason@mars.ninja>"]
+maintainers = ["Jason Mars <jason@mars.ninja>"]
 license = "MIT"
 readme = "README.md"
 keywords = ["llm", "jaclang", "jaseci", "byLLM"]
 
 [tool.poetry.dependencies]
-jaclang = ">=0.8.8"
+jaclang = ">=0.8.10"
 litellm = ">=1.75.5.post1"
 loguru = "~0.7.2"
 pillow = "~10.4.0"

byllm-0.4.3/byllm/plugin.py

@@ -1,40 +0,0 @@
-"""Plugin for Jac's with_llm feature."""
-
-from typing import Callable
-
-from byllm.llm import Model
-from byllm.mtir import MTIR
-
-from jaclang.runtimelib.machine import hookimpl
-
-
-class JacMachine:
-    """Jac's with_llm feature."""
-
-    @staticmethod
-    @hookimpl
-    def call_llm(model: Model, mtir: MTIR) -> object:
-        """Call JacLLM and return the result."""
-        return model.invoke(mtir=mtir)
-
-
-def by(model: Model) -> Callable:
-    """Python library mode decorator for Jac's by llm() syntax."""
-
-    def _decorator(caller: Callable) -> Callable:
-        def _wrapped_caller(*args: object, **kwargs: object) -> object:
-            invoke_args: dict[int | str, object] = {}
-            for i, arg in enumerate(args):
-                invoke_args[i] = arg
-            for key, value in kwargs.items():
-                invoke_args[key] = value
-            mtir = MTIR.factory(
-                caller=caller,
-                args=invoke_args,
-                call_params=model.llm_connector.call_params,
-            )
-            return JacMachine.call_llm(model, mtir)
-
-        return _wrapped_caller
-
-    return _decorator