ai-microcore 5.0.0.dev8__tar.gz → 5.0.1__tar.gz

{ai_microcore-5.0.0.dev8 → ai_microcore-5.0.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ai-microcore
-Version: 5.0.0.dev8
+Version: 5.0.1
 Summary: # Minimalistic Foundation for AI Applications
 Keywords: llm,large language models,ai,similarity search,ai search,gpt,openai,framework,adapter,anthropic,google gemini,google vertex ai
 Author-email: Vitalii Stepanenko <mail@vitaliy.in>
@@ -116,21 +116,14 @@ For the full list of available configuration options, you may also check [`micro
 
 ### Installing vendor-specific packages
 For models working not via OpenAI API, you may need to install additional packages:
-#### Anthropic Claude 3
+#### Anthropic Claude
 ```bash
 pip install anthropic
 ```
-#### Google Gemini via AI Studio
+#### Google Gemini via AI Studio or Vertex AI
 ```bash
-pip install google-generativeai
+pip install google-genai
 ```
-#### Google Gemini via Vertex AI
-```bash
-pip install vertexai
-```
-📌Additionally for working through [Vertex AI](https://cloud.google.com/vertex-ai) you need to
-[install the Google Cloud CLI](https://cloud.google.com/sdk/docs/install)
-and [configure the authorization](https://cloud.google.com/sdk/docs/authorizing).
 
 #### Local language models via Hugging Face Transformers
 
@@ -207,7 +200,7 @@ ai_response = llm('What is your model name?')
 # - For chat completion models elements are treated as separate messages
 # - For completion LLMs elements are treated as text lines
 llm(['1+2', '='])
-llm('1+2=', model='gpt-4')
+llm('1+2=', model='gpt-5.2')
 
 # To specify a message role, you can use dictionary or classes
 llm(dict(role='system', content='1+2='))
@@ -314,8 +307,53 @@ Text generation using HF/Transformers model locally (example with Qwen 3 0.6B).
 #### [Other examples](https://github.com/llm-microcore/microcore/tree/main/examples)
 
 ## Python functions as AI tools
+*Usage Example*:
+```python
+from microcore.ai_func import ai_func
+
+@ai_func
+def search_products(
+    query: str,
+    category: str = "all",
+    max_results: int = 10,
+    in_stock_only: bool = False
+):
+    """
+    Search for products in the catalog.
+
+    Args:
+        query: Search terms to find matching products
+        category: Product category to filter by (e.g., "electronics", "clothing")
+        max_results: Maximum number of results to return
+        in_stock_only: If True, only return products currently in stock
+
+    Returns:
+        List of matching products with name, price, and availability
+    """
+    # Implementation would go here
+    pass
+```
+*Output*:
+```
+# Search for products in the catalog.
+
+Args:
+    query: Search terms to find matching products
+    category: Product category to filter by (e.g., "electronics", "clothing")
+    max_results: Maximum number of results to return
+    in_stock_only: If True, only return products currently in stock
+
+Returns:
+    List of matching products with name, price, and availability
+{
+  "call": "search_products",
+  "query": <str>,
+  "category": <str> (default = "all"),
+  "max_results": <int> (default = 10),
+  "in_stock_only": <bool> (default = False)
+}
 
-@TODO
+```
 
 ## 🤖 AI Modules
 **This is an experimental feature.**

{ai_microcore-5.0.0.dev8 → ai_microcore-5.0.1}/README.md

@@ -81,21 +81,14 @@ For the full list of available configuration options, you may also check [`micro
 
 ### Installing vendor-specific packages
 For models working not via OpenAI API, you may need to install additional packages:
-#### Anthropic Claude 3
+#### Anthropic Claude
 ```bash
 pip install anthropic
 ```
-#### Google Gemini via AI Studio
+#### Google Gemini via AI Studio or Vertex AI
 ```bash
-pip install google-generativeai
+pip install google-genai
 ```
-#### Google Gemini via Vertex AI
-```bash
-pip install vertexai
-```
-📌Additionally for working through [Vertex AI](https://cloud.google.com/vertex-ai) you need to
-[install the Google Cloud CLI](https://cloud.google.com/sdk/docs/install)
-and [configure the authorization](https://cloud.google.com/sdk/docs/authorizing).
 
 #### Local language models via Hugging Face Transformers
 
@@ -172,7 +165,7 @@ ai_response = llm('What is your model name?')
 # - For chat completion models elements are treated as separate messages
 # - For completion LLMs elements are treated as text lines
 llm(['1+2', '='])
-llm('1+2=', model='gpt-4')
+llm('1+2=', model='gpt-5.2')
 
 # To specify a message role, you can use dictionary or classes
 llm(dict(role='system', content='1+2='))
@@ -279,8 +272,53 @@ Text generation using HF/Transformers model locally (example with Qwen 3 0.6B).
 #### [Other examples](https://github.com/llm-microcore/microcore/tree/main/examples)
 
 ## Python functions as AI tools
+*Usage Example*:
+```python
+from microcore.ai_func import ai_func
+
+@ai_func
+def search_products(
+    query: str,
+    category: str = "all",
+    max_results: int = 10,
+    in_stock_only: bool = False
+):
+    """
+    Search for products in the catalog.
+
+    Args:
+        query: Search terms to find matching products
+        category: Product category to filter by (e.g., "electronics", "clothing")
+        max_results: Maximum number of results to return
+        in_stock_only: If True, only return products currently in stock
+
+    Returns:
+        List of matching products with name, price, and availability
+    """
+    # Implementation would go here
+    pass
+```
+*Output*:
+```
+# Search for products in the catalog.
+
+Args:
+    query: Search terms to find matching products
+    category: Product category to filter by (e.g., "electronics", "clothing")
+    max_results: Maximum number of results to return
+    in_stock_only: If True, only return products currently in stock
+
+Returns:
+    List of matching products with name, price, and availability
+{
+  "call": "search_products",
+  "query": <str>,
+  "category": <str> (default = "all"),
+  "max_results": <int> (default = 10),
+  "in_stock_only": <bool> (default = False)
+}
 
-@TODO
+```
 
 ## 🤖 AI Modules
 **This is an experimental feature.**

{ai_microcore-5.0.0.dev8 → ai_microcore-5.0.1}/microcore/__init__.py

@@ -231,4 +231,4 @@ __all__ = [
     # "wrappers",
 ]
 
-__version__ = "5.0.0dev8"
+__version__ = "5.0.1"

{ai_microcore-5.0.0.dev8 → ai_microcore-5.0.1}/microcore/llm/google_genai.py

@@ -222,6 +222,7 @@ class _GenerationContext:
         model_name = kwargs.pop("model", client.config.MODEL)
         callbacks = prepare_callbacks(client.config, kwargs, set_stream=False)
         is_image = is_image_model(model_name)
+        stream = kwargs.pop("stream", False) or (callbacks and not is_image)
         return _GenerationContext(
             model_name=model_name,
             save=kwargs.pop("save", True),
@@ -231,7 +232,7 @@ class _GenerationContext:
             genai_client=client.genai_client,
             config=client.config,
             is_image_model=is_image,
-            stream=callbacks and not is_image
+            stream=stream,
         )
 
 

{ai_microcore-5.0.0.dev8 → ai_microcore-5.0.1}/microcore/llm/openai.py

@@ -1,11 +1,12 @@
 import asyncio
 import base64
+from typing import Any
 
 import openai
 from openai.types import CompletionChoice, ImagesResponse
 
 from ..lm_client import BaseAIChatClient, BaseAsyncAIClient
-from ..message_types import TMsgContentPart
+from ..message_types import TMsgContentPart, TMsgContent
 from ..configuration import Config
 from ..llm_backends import ApiPlatform
 from .._prepare_llm_args import prepare_prompt
@@ -132,6 +133,18 @@ class OpenAIClient(BaseAIChatClient):
             return image_to_oai(img)
         return content_part
 
+    def _convert_message_content(self, message_content: TMsgContent) -> Any:
+        """
+        Convert the message content into a format suitable for the LLM inference chat API.
+        """
+        if isinstance(message_content, str):
+            # Prevent conversion of string content into dict(type=text, text=...)
+            # because Azure OpenAI fails with Error 400
+            # when passing "azure_search" data source like following:
+            # llm(..., extra_body={"data_sources"=[{"type": "azure_search",...}]})
+            return message_content
+        return super()._convert_message_content(message_content)
+
     def load_models(self, **kwargs) -> dict:
         models_iter = self.oai_client.models.list(**kwargs)
         return {model.id: model for model in models_iter}