markdown-flow 0.2.12__tar.gz → 0.2.28__tar.gz

{markdown_flow-0.2.12 → markdown_flow-0.2.28}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: markdown-flow
-Version: 0.2.12
+Version: 0.2.28
 Summary: An agent library designed to parse and process MarkdownFlow documents
 Project-URL: Homepage, https://github.com/ai-shifu/markdown-flow-agent-py
 Project-URL: Bug Tracker, https://github.com/ai-shifu/markdown-flow-agent-py/issues
@@ -92,36 +92,6 @@ for chunk in mf.process(
     print(chunk.content, end='')
 ```
 
-### Dynamic Interaction Generation ✨
-
-Transform natural language content into interactive elements automatically:
-
-```python
-from markdown_flow import MarkdownFlow, ProcessMode
-
-# Dynamic interaction generation works automatically
-mf = MarkdownFlow(
-    document="询问用户的菜品偏好，并记录到变量{{菜品选择}}",
-    llm_provider=llm_provider,
-    document_prompt="你是中餐厅服务员，提供川菜、粤菜、鲁菜等选项"
-)
-
-# Process with Function Calling
-result = mf.process(0, ProcessMode.COMPLETE)
-
-if result.transformed_to_interaction:
-    print(f"Generated interaction: {result.content}")
-    # Output: ?[%{{菜品选择}} 宫保鸡丁||麻婆豆腐||水煮鱼||...其他菜品]
-
-# Continue with user input
-user_result = mf.process(
-    block_index=0,
-    mode=ProcessMode.COMPLETE,
-    user_input={"菜品选择": ["宫保鸡丁", "麻婆豆腐"]},
-    dynamic_interaction_format=result.content
-)
-```
-
 ### Interactive Elements
 
 ```python
@@ -159,59 +129,6 @@ result = mf.process(
 )
 ```
 
-## ✨ Key Features
-
-### 🏗️ Three-Layer Architecture
-
-- **Document Level**: Parse `---` separators and `?[]` interaction patterns
-- **Block Level**: Categorize as CONTENT, INTERACTION, or PRESERVED_CONTENT
-- **Interaction Level**: Handle 6 different interaction types with smart validation
-
-### 🔄 Dynamic Interaction Generation
-
-- **Natural Language Input**: Write content in plain language
-- **AI-Powered Conversion**: LLM automatically detects interaction needs using Function Calling
-- **Structured Data Generation**: LLM returns structured data, core builds MarkdownFlow format
-- **Language Agnostic**: Support for any language with proper document prompts
-- **Context Awareness**: Both original and resolved variable contexts provided to LLM
-
-### 🤖 Unified LLM Integration
-
-- **Single Interface**: One `complete()` method for both regular and Function Calling modes
-- **Automatic Detection**: Tools parameter determines processing mode automatically
-- **Consistent Returns**: Always returns `LLMResult` with structured metadata
-- **Error Handling**: Automatic fallback from Function Calling to regular completion
-- **Provider Agnostic**: Abstract interface supports any LLM service
-
-### 📝 Variable System
-
-- **Replaceable Variables**: `{{variable}}` for content personalization
-- **Preserved Variables**: `%{{variable}}` for LLM understanding in interactions
-- **Multi-Value Support**: Handle both single values and arrays
-- **Smart Extraction**: Automatic detection from document content
-
-### 🎯 Interaction Types
-
-- **Text Input**: `?[%{{var}}...question]` - Free text entry
-- **Single Select**: `?[%{{var}} A|B|C]` - Choose one option
-- **Multi Select**: `?[%{{var}} A||B||C]` - Choose multiple options
-- **Mixed Mode**: `?[%{{var}} A||B||...custom]` - Predefined + custom input
-- **Display Buttons**: `?[Continue|Cancel]` - Action buttons without assignment
-- **Value Separation**: `?[%{{var}} Display//value|...]` - Different display/stored values
-
-### 🔒 Content Preservation
-
-- **Multiline Format**: `!===content!===` blocks output exactly as written
-- **Inline Format**: `===content===` for single-line preserved content
-- **Variable Support**: Preserved content can contain variables for substitution
-
-### ⚡ Performance Optimized
-
-- **Pre-compiled Regex**: All patterns compiled once for maximum performance
-- **Synchronous Interface**: Clean synchronous operations with optional streaming
-- **Stream Processing**: Real-time streaming responses supported
-- **Memory Efficient**: Lazy evaluation and generator patterns
-
 ## 📖 API Reference
 
 ### Core Classes
@@ -237,7 +154,7 @@ class MarkdownFlow:
         mode: ProcessMode = ProcessMode.COMPLETE,
         variables: Optional[Dict[str, str]] = None,
         user_input: Optional[str] = None
-    ) -> LLMResult: ...
+    ) -> LLMResult | Generator[LLMResult, None, None]: ...
 ```
 
 **Methods:**
@@ -267,18 +184,13 @@ Processing mode enumeration for different use cases.
 
 ```python
 class ProcessMode(Enum):
-    PROMPT_ONLY = "prompt_only"  # Generate prompts without LLM calls
-    COMPLETE = "complete"        # Non-streaming LLM processing
-    STREAM = "stream"           # Streaming LLM responses
+    COMPLETE = "complete"  # Non-streaming LLM processing
+    STREAM = "stream"      # Streaming LLM responses
 ```
 
 **Usage:**
 
 ```python
-# Generate prompt only
-prompt_result = mf.process(0, ProcessMode.PROMPT_ONLY)
-print(prompt_result.content)  # Raw prompt text
-
 # Complete response
 complete_result = mf.process(0, ProcessMode.COMPLETE)
 print(complete_result.content)  # Full LLM response
@@ -298,10 +210,10 @@ from typing import Generator
 
 class LLMProvider(ABC):
     @abstractmethod
-    def complete(self, prompt: str) -> LLMResult: ...
+    def complete(self, messages: list[dict[str, str]]) -> str: ...
 
     @abstractmethod
-    def stream(self, prompt: str) -> Generator[str, None, None]: ...
+    def stream(self, messages: list[dict[str, str]]) -> Generator[str, None, None]: ...
 ```
 
 **Custom Implementation:**
@@ -311,23 +223,22 @@ class OpenAIProvider(LLMProvider):
     def __init__(self, api_key: str):
         self.client = openai.OpenAI(api_key=api_key)
 
-    def complete(self, prompt: str) -> LLMResult:
-        response = self.client.completions.create(
+    def complete(self, messages: list[dict[str, str]]) -> str:
+        response = self.client.chat.completions.create(
             model="gpt-3.5-turbo",
-            prompt=prompt,
-            max_tokens=500
+            messages=messages
         )
-        return LLMResult(content=response.choices[0].text.strip())
+        return response.choices[0].message.content
 
-    def stream(self, prompt: str):
-        stream = self.client.completions.create(
+    def stream(self, messages: list[dict[str, str]]):
+        stream = self.client.chat.completions.create(
             model="gpt-3.5-turbo",
-            prompt=prompt,
+            messages=messages,
             stream=True
         )
         for chunk in stream:
-            if chunk.choices[0].text:
-                yield chunk.choices[0].text
+            if chunk.choices[0].delta.content:
+                yield chunk.choices[0].delta.content
 ```
 
 ### Block Types
@@ -647,7 +558,7 @@ Include code samples, explanations, and practice exercises.
         mode=ProcessMode.STREAM,
         variables={
             'user_name': 'developer',
-            'topic': 'async programming'
+            'topic': 'synchronous programming'
         }
     ):
         content += chunk.content
@@ -701,9 +612,9 @@ class InteractiveDocumentBuilder:
                     self.user_responses.update(response)
 
     def handle_interaction(self, interaction_content: str):
-        from markdown_flow.utils import InteractionParser
+        from markdown_flow.parser import InteractionParser
 
-        interaction = InteractionParser.parse(interaction_content)
+        interaction = InteractionParser().parse(interaction_content)
         print(f"\n{interaction_content}")
 
         if interaction.name == "BUTTONS_ONLY":

{markdown_flow-0.2.12 → markdown_flow-0.2.28}/README.md

@@ -74,36 +74,6 @@ for chunk in mf.process(
     print(chunk.content, end='')
 ```
 
-### Dynamic Interaction Generation ✨
-
-Transform natural language content into interactive elements automatically:
-
-```python
-from markdown_flow import MarkdownFlow, ProcessMode
-
-# Dynamic interaction generation works automatically
-mf = MarkdownFlow(
-    document="询问用户的菜品偏好，并记录到变量{{菜品选择}}",
-    llm_provider=llm_provider,
-    document_prompt="你是中餐厅服务员，提供川菜、粤菜、鲁菜等选项"
-)
-
-# Process with Function Calling
-result = mf.process(0, ProcessMode.COMPLETE)
-
-if result.transformed_to_interaction:
-    print(f"Generated interaction: {result.content}")
-    # Output: ?[%{{菜品选择}} 宫保鸡丁||麻婆豆腐||水煮鱼||...其他菜品]
-
-# Continue with user input
-user_result = mf.process(
-    block_index=0,
-    mode=ProcessMode.COMPLETE,
-    user_input={"菜品选择": ["宫保鸡丁", "麻婆豆腐"]},
-    dynamic_interaction_format=result.content
-)
-```
-
 ### Interactive Elements
 
 ```python
@@ -141,59 +111,6 @@ result = mf.process(
 )
 ```
 
-## ✨ Key Features
-
-### 🏗️ Three-Layer Architecture
-
-- **Document Level**: Parse `---` separators and `?[]` interaction patterns
-- **Block Level**: Categorize as CONTENT, INTERACTION, or PRESERVED_CONTENT
-- **Interaction Level**: Handle 6 different interaction types with smart validation
-
-### 🔄 Dynamic Interaction Generation
-
-- **Natural Language Input**: Write content in plain language
-- **AI-Powered Conversion**: LLM automatically detects interaction needs using Function Calling
-- **Structured Data Generation**: LLM returns structured data, core builds MarkdownFlow format
-- **Language Agnostic**: Support for any language with proper document prompts
-- **Context Awareness**: Both original and resolved variable contexts provided to LLM
-
-### 🤖 Unified LLM Integration
-
-- **Single Interface**: One `complete()` method for both regular and Function Calling modes
-- **Automatic Detection**: Tools parameter determines processing mode automatically
-- **Consistent Returns**: Always returns `LLMResult` with structured metadata
-- **Error Handling**: Automatic fallback from Function Calling to regular completion
-- **Provider Agnostic**: Abstract interface supports any LLM service
-
-### 📝 Variable System
-
-- **Replaceable Variables**: `{{variable}}` for content personalization
-- **Preserved Variables**: `%{{variable}}` for LLM understanding in interactions
-- **Multi-Value Support**: Handle both single values and arrays
-- **Smart Extraction**: Automatic detection from document content
-
-### 🎯 Interaction Types
-
-- **Text Input**: `?[%{{var}}...question]` - Free text entry
-- **Single Select**: `?[%{{var}} A|B|C]` - Choose one option
-- **Multi Select**: `?[%{{var}} A||B||C]` - Choose multiple options
-- **Mixed Mode**: `?[%{{var}} A||B||...custom]` - Predefined + custom input
-- **Display Buttons**: `?[Continue|Cancel]` - Action buttons without assignment
-- **Value Separation**: `?[%{{var}} Display//value|...]` - Different display/stored values
-
-### 🔒 Content Preservation
-
-- **Multiline Format**: `!===content!===` blocks output exactly as written
-- **Inline Format**: `===content===` for single-line preserved content
-- **Variable Support**: Preserved content can contain variables for substitution
-
-### ⚡ Performance Optimized
-
-- **Pre-compiled Regex**: All patterns compiled once for maximum performance
-- **Synchronous Interface**: Clean synchronous operations with optional streaming
-- **Stream Processing**: Real-time streaming responses supported
-- **Memory Efficient**: Lazy evaluation and generator patterns
-
 ## 📖 API Reference
 
 ### Core Classes
@@ -219,7 +136,7 @@ class MarkdownFlow:
         mode: ProcessMode = ProcessMode.COMPLETE,
         variables: Optional[Dict[str, str]] = None,
         user_input: Optional[str] = None
-    ) -> LLMResult: ...
+    ) -> LLMResult | Generator[LLMResult, None, None]: ...
 ```
 
 **Methods:**
@@ -249,18 +166,13 @@ Processing mode enumeration for different use cases.
 
 ```python
 class ProcessMode(Enum):
-    PROMPT_ONLY = "prompt_only"  # Generate prompts without LLM calls
-    COMPLETE = "complete"        # Non-streaming LLM processing
-    STREAM = "stream"           # Streaming LLM responses
+    COMPLETE = "complete"  # Non-streaming LLM processing
+    STREAM = "stream"      # Streaming LLM responses
 ```
 
 **Usage:**
 
 ```python
-# Generate prompt only
-prompt_result = mf.process(0, ProcessMode.PROMPT_ONLY)
-print(prompt_result.content)  # Raw prompt text
-
 # Complete response
 complete_result = mf.process(0, ProcessMode.COMPLETE)
 print(complete_result.content)  # Full LLM response
@@ -280,10 +192,10 @@ from typing import Generator
 
 class LLMProvider(ABC):
     @abstractmethod
-    def complete(self, prompt: str) -> LLMResult: ...
+    def complete(self, messages: list[dict[str, str]]) -> str: ...
 
     @abstractmethod
-    def stream(self, prompt: str) -> Generator[str, None, None]: ...
+    def stream(self, messages: list[dict[str, str]]) -> Generator[str, None, None]: ...
 ```
 
 **Custom Implementation:**
@@ -293,23 +205,22 @@ class OpenAIProvider(LLMProvider):
     def __init__(self, api_key: str):
         self.client = openai.OpenAI(api_key=api_key)
 
-    def complete(self, prompt: str) -> LLMResult:
-        response = self.client.completions.create(
+    def complete(self, messages: list[dict[str, str]]) -> str:
+        response = self.client.chat.completions.create(
             model="gpt-3.5-turbo",
-            prompt=prompt,
-            max_tokens=500
+            messages=messages
         )
-        return LLMResult(content=response.choices[0].text.strip())
+        return response.choices[0].message.content
 
-    def stream(self, prompt: str):
-        stream = self.client.completions.create(
+    def stream(self, messages: list[dict[str, str]]):
+        stream = self.client.chat.completions.create(
             model="gpt-3.5-turbo",
-            prompt=prompt,
+            messages=messages,
             stream=True
         )
         for chunk in stream:
-            if chunk.choices[0].text:
-                yield chunk.choices[0].text
+            if chunk.choices[0].delta.content:
+                yield chunk.choices[0].delta.content
 ```
 
 ### Block Types
@@ -629,7 +540,7 @@ Include code samples, explanations, and practice exercises.
         mode=ProcessMode.STREAM,
         variables={
             'user_name': 'developer',
-            'topic': 'async programming'
+            'topic': 'synchronous programming'
         }
     ):
         content += chunk.content
@@ -683,9 +594,9 @@ class InteractiveDocumentBuilder:
                     self.user_responses.update(response)
 
     def handle_interaction(self, interaction_content: str):
-        from markdown_flow.utils import InteractionParser
+        from markdown_flow.parser import InteractionParser
 
-        interaction = InteractionParser.parse(interaction_content)
+        interaction = InteractionParser().parse(interaction_content)
         print(f"\n{interaction_content}")
 
         if interaction.name == "BUTTONS_ONLY":

{markdown_flow-0.2.12 → markdown_flow-0.2.28}/markdown_flow/__init__.py

@@ -9,7 +9,7 @@ Core Features:
     - Extract variable placeholders ({{variable}} and %{{variable}} formats)
     - Build LLM-ready prompts and message formats
     - Handle user interaction validation and input processing
-    - Support multiple processing modes: PROMPT_ONLY, COMPLETE, STREAM
+    - Support multiple processing modes: COMPLETE, STREAM
 
 Supported Interaction Types:
     - TEXT_ONLY: ?[%{{var}}...question] - Text input only
@@ -32,12 +32,11 @@ Basic Usage:
     blocks = mf.get_all_blocks()
 
     # Process blocks using unified interface
-    result = await mf.process(0, variables={'name': 'John'}, mode=ProcessMode.COMPLETE)
+    result = mf.process(0, variables={'name': 'John'}, mode=ProcessMode.COMPLETE)
 
     # Different processing modes
-    prompt_result = await mf.process(0, mode=ProcessMode.PROMPT_ONLY)
-    complete_result = await mf.process(0, mode=ProcessMode.COMPLETE)
-    stream_result = await mf.process(0, mode=ProcessMode.STREAM)
+    complete_result = mf.process(0, mode=ProcessMode.COMPLETE)
+    stream_result = mf.process(0, mode=ProcessMode.STREAM)
 
 Variable System:
     - {{variable}} - Regular variables, replaced with actual values
@@ -53,7 +52,7 @@ Import Guide:
 from .core import MarkdownFlow
 from .enums import BlockType, InputType
 from .llm import LLMProvider, LLMResult, ProcessMode
-from .utils import (
+from .parser import (
     InteractionParser,
     InteractionType,
     extract_interaction_question,
@@ -83,4 +82,5 @@ __all__ = [
     "replace_variables_in_text",
 ]
 
-__version__ = "0.2.12"
+__version__ = "0.2.28"
+# __version__ = "0.2.27-alpha-8"