ai-pipeline-core 0.3.3__py3-none-any.whl → 0.4.0__py3-none-any.whl

ai_pipeline_core-0.3.3.dist-info/METADATA

@@ -1,569 +0,0 @@
-Metadata-Version: 2.4
-Name: ai-pipeline-core
-Version: 0.3.3
-Summary: Core utilities for AI-powered processing pipelines using prefect
-Project-URL: Homepage, https://github.com/bbarwik/ai-pipeline-core
-Project-URL: Repository, https://github.com/bbarwik/ai-pipeline-core
-Project-URL: Issues, https://github.com/bbarwik/ai-pipeline-core/issues
-Author-email: bbarwik <bbarwik@gmail.com>
-License: MIT
-License-File: LICENSE
-Classifier: Development Status :: 4 - Beta
-Classifier: Intended Audience :: Developers
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Classifier: Typing :: Typed
-Requires-Python: >=3.12
-Requires-Dist: httpx>=0.28.1
-Requires-Dist: jinja2>=3.1.6
-Requires-Dist: lmnr>=0.7.18
-Requires-Dist: openai>=1.109.1
-Requires-Dist: pillow>=10.0.0
-Requires-Dist: prefect-gcp[cloud-storage]>=0.6.10
-Requires-Dist: prefect>=3.4.21
-Requires-Dist: pydantic-settings>=2.10.1
-Requires-Dist: pydantic>=2.11.9
-Requires-Dist: python-magic>=0.4.27
-Requires-Dist: ruamel-yaml>=0.18.14
-Requires-Dist: tiktoken>=0.12.0
-Provides-Extra: dev
-Requires-Dist: basedpyright>=1.31.2; extra == 'dev'
-Requires-Dist: bump2version>=1.0.1; extra == 'dev'
-Requires-Dist: interrogate>=1.5.0; extra == 'dev'
-Requires-Dist: pre-commit>=4.3.0; extra == 'dev'
-Requires-Dist: pydoc-markdown[jinja]>=4.8.0; extra == 'dev'
-Requires-Dist: pytest-asyncio>=1.1.0; extra == 'dev'
-Requires-Dist: pytest-cov>=5.0.0; extra == 'dev'
-Requires-Dist: pytest-mock>=3.14.0; extra == 'dev'
-Requires-Dist: pytest-xdist>=3.8.0; extra == 'dev'
-Requires-Dist: pytest>=8.4.1; extra == 'dev'
-Requires-Dist: ruff>=0.14.1; extra == 'dev'
-Description-Content-Type: text/markdown
-
-# AI Pipeline Core
-
-A high-performance async framework for building type-safe AI pipelines with LLMs, document processing, and workflow orchestration.
-
-[![Python Version](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/downloads/)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Code Style: Ruff](https://img.shields.io/badge/code%20style-ruff-000000.svg)](https://github.com/astral-sh/ruff)
-[![Type Checked: Basedpyright](https://img.shields.io/badge/type%20checked-basedpyright-blue)](https://github.com/DetachHead/basedpyright)
-
-## Overview
-
-AI Pipeline Core is a production-ready framework that combines document processing, LLM integration, and workflow orchestration into a unified system. Built with strong typing (Pydantic), automatic retries, cost tracking, and distributed tracing, it enforces best practices while maintaining high performance through fully async operations.
-
-### Key Features
-
-- **Document Processing**: Type-safe handling of text, JSON, YAML, PDFs, and images with automatic MIME type detection and provenance tracking
-- **LLM Integration**: Unified interface to any model via LiteLLM proxy with configurable context caching
-- **Structured Output**: Type-safe generation with Pydantic model validation
-- **Workflow Orchestration**: Prefect-based flows and tasks with automatic retries
-- **Observability**: Built-in distributed tracing via Laminar (LMNR) with cost tracking for debugging and monitoring
-- **Deployment**: Unified pipeline execution for local, CLI, and production environments
-
-## Installation
-
-```bash
-pip install ai-pipeline-core
-```
-
-### Requirements
-
-- Python 3.12 or higher
-- Linux/macOS (Windows via WSL2)
-
-### Development Installation
-
-```bash
-git clone https://github.com/bbarwik/ai-pipeline-core.git
-cd ai-pipeline-core
-pip install -e ".[dev]"
-make install-dev  # Installs pre-commit hooks
-```
-
-## Quick Start
-
-### Basic Pipeline
-
-```python
-from ai_pipeline_core import (
-    pipeline_flow,
-    FlowDocument,
-    DocumentList,
-    FlowOptions,
-    FlowConfig,
-    llm,
-    AIMessages
-)
-
-# Define document types
-class InputDoc(FlowDocument):
-    """Input document for processing."""
-
-class OutputDoc(FlowDocument):
-    """Analysis result document."""
-
-# Define flow configuration
-class AnalysisConfig(FlowConfig):
-    INPUT_DOCUMENT_TYPES = [InputDoc]
-    OUTPUT_DOCUMENT_TYPE = OutputDoc
-
-# Create pipeline flow with required config
-@pipeline_flow(config=AnalysisConfig)
-async def analyze_flow(
-    project_name: str,
-    documents: DocumentList,
-    flow_options: FlowOptions
-) -> DocumentList:
-    # Process documents
-    outputs = []
-    for doc in documents:
-        # Use AIMessages for LLM interaction
-        response = await llm.generate(
-            model="gpt-5.1",
-            messages=AIMessages([doc])
-        )
-
-        output = OutputDoc.create(
-            name=f"analysis_{doc.name}",
-            content=response.content
-        )
-        outputs.append(output)
-
-    # RECOMMENDED: Always validate output
-    return AnalysisConfig.create_and_validate_output(outputs)
-```
-
-### Structured Output
-
-```python
-from pydantic import BaseModel
-from ai_pipeline_core import llm
-
-class Analysis(BaseModel):
-    summary: str
-    sentiment: float
-    key_points: list[str]
-
-# Generate structured output
-response = await llm.generate_structured(
-    model="gpt-5.1",
-    response_format=Analysis,
-    messages="Analyze this product review: ..."
-)
-
-# Access parsed result with type safety
-analysis = response.parsed
-print(f"Sentiment: {analysis.sentiment}")
-for point in analysis.key_points:
-    print(f"- {point}")
-```
-
-### Document Handling
-
-```python
-from ai_pipeline_core import FlowDocument, TemporaryDocument
-
-# Create documents with automatic conversion
-doc = MyDocument.create(
-    name="data.json",
-    content={"key": "value"}  # Automatically converted to JSON bytes
-)
-
-# Parse back to original type
-data = doc.parse(dict)  # Returns {"key": "value"}
-
-# Document provenance tracking
-doc_with_sources = MyDocument.create(
-    name="derived.json",
-    content={"result": "processed"},
-    sources=[source_doc.sha256, "https://api.example.com/data"]
-)
-
-# Check provenance
-for hash in doc_with_sources.get_source_documents():
-    print(f"Derived from document: {hash}")
-for ref in doc_with_sources.get_source_references():
-    print(f"External source: {ref}")
-
-# Temporary documents (never persisted)
-temp = TemporaryDocument.create(
-    name="api_response.json",
-    content={"status": "ok"}
-)
-```
-
-## Core Concepts
-
-### Documents
-
-Documents are immutable Pydantic models that wrap binary content with metadata:
-
-- **FlowDocument**: Persists across flow runs, saved to filesystem
-- **TaskDocument**: Temporary within task execution, not persisted
-- **TemporaryDocument**: Never persisted, useful for sensitive data
-
-```python
-class MyDocument(FlowDocument):
-    """Custom document type."""
-
-# Use create() for automatic conversion
-doc = MyDocument.create(
-    name="data.json",
-    content={"key": "value"}  # Auto-converts to JSON
-)
-
-# Access content
-if doc.is_text:
-    print(doc.text)
-
-# Parse structured data
-data = doc.as_json()  # or as_yaml(), as_pydantic_model()
-
-# Convert between document types
-task_doc = flow_doc.model_convert(TaskDocument)  # Convert FlowDocument to TaskDocument
-new_doc = doc.model_convert(OtherDocType, content={"new": "data"})  # With content update
-
-# Enhanced filtering
-filtered = documents.filter_by([Doc1, Doc2, Doc3])  # Multiple types
-named = documents.filter_by(["file1.txt", "file2.txt"])  # Multiple names
-
-# Immutable collections
-frozen_docs = DocumentList(docs, frozen=True)  # Immutable document list
-frozen_msgs = AIMessages(messages, frozen=True)  # Immutable message list
-```
-
-### LLM Integration
-
-The framework provides a unified interface for LLM interactions with smart caching:
-
-```python
-from ai_pipeline_core import llm, AIMessages, ModelOptions
-
-# Simple generation
-response = await llm.generate(
-    model="gpt-5.1",
-    messages="Explain quantum computing"
-)
-print(response.content)
-
-# With context caching (saves 50-90% tokens)
-static_context = AIMessages([large_document])
-
-# First call: caches context
-r1 = await llm.generate(
-    model="gpt-5.1",
-    context=static_context,  # Cached for 120 seconds by default
-    messages="Summarize"     # Dynamic query
-)
-
-# Second call: reuses cache
-r2 = await llm.generate(
-    model="gpt-5.1",
-    context=static_context,  # Reused from cache!
-    messages="Key points?"   # Different query
-)
-
-# Custom cache TTL
-response = await llm.generate(
-    model="gpt-5.1",
-    context=static_context,
-    messages="Analyze",
-    options=ModelOptions(cache_ttl="300s")  # Cache for 5 minutes
-)
-
-# Disable caching for dynamic contexts
-response = await llm.generate(
-    model="gpt-5.1",
-    context=dynamic_context,
-    messages="Process",
-    options=ModelOptions(cache_ttl=None)  # No caching
-)
-```
-
-### Flow Configuration
-
-Type-safe flow configuration ensures proper document flow:
-
-```python
-from ai_pipeline_core import FlowConfig
-
-class ProcessingConfig(FlowConfig):
-    INPUT_DOCUMENT_TYPES = [RawDataDocument]
-    OUTPUT_DOCUMENT_TYPE = ProcessedDocument  # Must be different!
-
-# Use in flows for validation
-@pipeline_flow(config=ProcessingConfig)
-async def process(
-    project_name: str,
-    documents: DocumentList,
-    flow_options: FlowOptions
-) -> DocumentList:
-    # ... processing logic ...
-    return ProcessingConfig.create_and_validate_output(outputs)
-```
-
-### Pipeline Decorators
-
-Enhanced decorators with built-in tracing and monitoring:
-
-```python
-from ai_pipeline_core import pipeline_flow, pipeline_task, set_trace_cost
-
-@pipeline_task  # Automatic retry, tracing, and monitoring
-async def process_chunk(data: str) -> str:
-    result = await transform(data)
-    set_trace_cost(0.05)  # Track costs
-    return result
-
-@pipeline_flow(
-    config=MyFlowConfig,
-    trace_trim_documents=True  # Trim large documents in traces
-)
-async def main_flow(
-    project_name: str,
-    documents: DocumentList,
-    flow_options: FlowOptions
-) -> DocumentList:
-    # Your pipeline logic
-    # Large documents are automatically trimmed to 100 chars in traces
-    # for better observability without overwhelming the tracing UI
-    return DocumentList(results)
-```
-
-### Local Trace Debugging
-
-Save all trace spans to the local filesystem for LLM-assisted debugging:
-
-```bash
-export TRACE_DEBUG_PATH=/path/to/debug/output
-```
-
-This creates a hierarchical directory structure that mirrors the execution flow with automatic deduplication:
-
-```
-20260128_152932_abc12345_my_flow/
-├── _trace.yaml           # Trace metadata
-├── _index.yaml           # Span ID → path mapping
-├── _summary.md           # Unified summary for human inspection and LLM debugging
-├── artifacts/            # Deduplicated content storage
-│   └── sha256/
-│       └── ab/cd/        # Sharded by hash prefix
-│           └── abcdef...1234.txt  # Large content (>10KB)
-└── 0001_my_flow/         # Root span (numbered for execution order)
-    ├── _span.yaml        # Span metadata (timing, status, I/O refs)
-    ├── input.yaml        # Structured inputs (inline or refs)
-    ├── output.yaml       # Structured outputs (inline or refs)
-    ├── 0002_task_1/      # Child spans nested inside parent
-    │   ├── _span.yaml
-    │   ├── input.yaml
-    │   ├── output.yaml
-    │   └── 0003_llm_call/
-    │       ├── _span.yaml
-    │       ├── input.yaml   # LLM messages with inline/external content
-    │       └── output.yaml
-    └── 0004_task_2/
-        └── ...
-```
-
-**Key Features:**
-- **Automatic Deduplication**: Identical content (e.g., system prompts) stored once in `artifacts/`
-- **Smart Externalization**: Large content (>10KB) externalized with 2KB inline previews
-- **AI-Friendly**: Files capped at 50KB for easy LLM processing
-- **Lossless**: Full content reconstruction via `content_ref` pointers
-
-Example `input.yaml` with externalization:
-```yaml
-format_version: 3
-type: llm_messages
-messages:
-  - role: system
-    parts:
-      - type: text
-        size_bytes: 28500
-        content_ref:  # Large content → artifact
-          hash: sha256:a1b2c3d4...
-          path: artifacts/sha256/a1/b2/a1b2c3d4...txt
-        excerpt: "You are a helpful assistant...\n[TRUNCATED]"
-  - role: user
-    parts:
-      - type: text
-        content: "Hello!"  # Small content stays inline
-```
-
-Run `tree` on the output directory to visualize the entire execution hierarchy. Feed `_summary.md` to an LLM for debugging assistance - it combines high-level overview with detailed navigation for comprehensive trace analysis.
-
-## Configuration
-
-### Environment Variables
-
-```bash
-# LLM Configuration (via LiteLLM proxy)
-OPENAI_BASE_URL=http://localhost:4000
-OPENAI_API_KEY=your-api-key
-
-# Optional: Observability
-LMNR_PROJECT_API_KEY=your-lmnr-key
-LMNR_DEBUG=true  # Enable debug traces
-
-# Optional: Local Trace Debugging
-TRACE_DEBUG_PATH=/path/to/trace/output  # Save traces locally for LLM-assisted debugging
-
-# Optional: Orchestration
-PREFECT_API_URL=http://localhost:4200/api
-PREFECT_API_KEY=your-prefect-key
-
-# Optional: Storage (for Google Cloud Storage)
-GCS_SERVICE_ACCOUNT_FILE=/path/to/service-account.json  # GCS auth file
-```
-
-### Settings Management
-
-Create custom settings by inheriting from the base Settings class:
-
-```python
-from ai_pipeline_core import Settings
-
-class ProjectSettings(Settings):
-    """Project-specific configuration."""
-    app_name: str = "my-app"
-    max_retries: int = 3
-    enable_cache: bool = True
-
-# Create singleton instance
-settings = ProjectSettings()
-
-# Access configuration
-print(settings.openai_base_url)
-print(settings.app_name)
-```
-
-## Best Practices
-
-### Framework Rules (90% Use Cases)
-
-1. **Decorators**: Use `@pipeline_task` WITHOUT parameters, `@pipeline_flow` WITH config
-2. **Logging**: Use `get_pipeline_logger(__name__)` - NEVER `print()` or `logging` module
-3. **LLM calls**: Use `AIMessages` or `str`. Wrap Documents in `AIMessages`
-4. **Options**: Omit `ModelOptions` unless specifically needed (defaults are optimal)
-5. **Documents**: Create with just `name` and `content` - skip `description`
-6. **FlowConfig**: `OUTPUT_DOCUMENT_TYPE` must differ from all `INPUT_DOCUMENT_TYPES`
-7. **Initialization**: `PromptManager` and logger at module scope, not in functions
-8. **DocumentList**: Use default constructor - no validation flags needed
-9. **setup_logging()**: Only in application `main()`, never at import time
-
-### Import Convention
-
-Always import from the top-level package:
-
-```python
-# CORRECT
-from ai_pipeline_core import llm, pipeline_flow, FlowDocument
-
-# WRONG - Never import from submodules
-from ai_pipeline_core.llm import generate  # NO!
-from ai_pipeline_core.documents import FlowDocument  # NO!
-```
-
-## Development
-
-### Running Tests
-
-```bash
-make test           # Run all tests
-make test-cov      # Run with coverage report
-make test-showcase # Test showcase example
-```
-
-### Code Quality
-
-```bash
-make lint      # Run linting
-make format    # Auto-format code
-make typecheck # Type checking with basedpyright
-```
-
-### Building Documentation
-
-```bash
-make docs-build  # Generate API.md
-make docs-check  # Verify documentation is up-to-date
-```
-
-## Examples
-
-The `examples/` directory contains:
-
-- `showcase.py` - Comprehensive example demonstrating all major features
-- Run with: `cd examples && python showcase.py /path/to/documents`
-
-## API Reference
-
-See [API.md](API.md) for complete API documentation.
-
-### Navigation Tips
-
-For humans:
-```bash
-grep -n '^##' API.md   # List all main sections
-grep -n '^###' API.md  # List all classes and functions
-```
-
-For AI assistants:
-- Use pattern `^##` to find module sections
-- Use pattern `^###` for classes and functions
-- Use pattern `^####` for methods and properties
-
-## Project Structure
-
-```
-ai-pipeline-core/
-├── ai_pipeline_core/
-│   ├── deployment/      # Pipeline deployment and execution
-│   ├── documents/       # Document abstraction system
-│   ├── flow/            # Flow configuration and options
-│   ├── llm/             # LLM client and response handling
-│   ├── logging/         # Logging infrastructure
-│   ├── prompt_builder/  # Document-aware prompt construction
-│   ├── pipeline.py      # Pipeline decorators
-│   ├── progress.py      # Intra-flow progress tracking
-│   ├── prompt_manager.py # Jinja2 template management
-│   ├── settings.py      # Configuration management
-│   └── tracing.py       # Distributed tracing
-├── tests/               # Comprehensive test suite
-├── examples/            # Usage examples
-├── API.md               # Complete API reference
-└── pyproject.toml       # Project configuration
-```
-
-## Contributing
-
-1. Fork the repository
-2. Create a feature branch (`git checkout -b feature/amazing-feature`)
-3. Make changes following the project's style guide
-4. Run tests and linting (`make test lint typecheck`)
-5. Commit your changes
-6. Push to the branch (`git push origin feature/amazing-feature`)
-7. Open a Pull Request
-
-## License
-
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
-
-## Support
-
-- **Issues**: [GitHub Issues](https://github.com/bbarwik/ai-pipeline-core/issues)
-- **Discussions**: [GitHub Discussions](https://github.com/bbarwik/ai-pipeline-core/discussions)
-- **Documentation**: [API Reference](API.md)
-
-## Acknowledgments
-
-- Built on [Prefect](https://www.prefect.io/) for workflow orchestration
-- Uses [LiteLLM](https://github.com/BerriAI/litellm) for LLM provider abstraction
-- Integrates [Laminar (LMNR)](https://www.lmnr.ai/) for observability
-- Type checking with [Pydantic](https://pydantic.dev/) and [basedpyright](https://github.com/DetachHead/basedpyright)

ai_pipeline_core-0.3.3.dist-info/RECORD

@@ -1,57 +0,0 @@
-ai_pipeline_core/__init__.py,sha256=2jzEQktQJp-A3bzDU-A7c9xntnY3x9I-1XwYcojYjYE,6452
-ai_pipeline_core/exceptions.py,sha256=vx-XLTw2fJSPs-vwtXVYtqoQUcOc0JeI7UmHqRqQYWU,1569
-ai_pipeline_core/pipeline.py,sha256=t9qH-V6umpKY5MhGuXFgUGfdzGyxzVlS0n9RoKLfnug,28704
-ai_pipeline_core/prefect.py,sha256=91ZgLJHsDsRUW77CpNmkKxYs3RCJuucPM3pjKmNBeDg,2199
-ai_pipeline_core/progress.py,sha256=Ppxk4OOm84Y0x3t-Y3CmHsL4PovQLNUxXMu24zRCD-Q,3621
-ai_pipeline_core/prompt_manager.py,sha256=FAtb1yK7bGuAeuIJ523LOX9bd7TrcHG-TqZ7Lz4RJC0,12087
-ai_pipeline_core/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ai_pipeline_core/settings.py,sha256=IMrFaX0i-WIlaOA5O53ipNSta6KQVSFHc1aJXmS3nSo,5078
-ai_pipeline_core/tracing.py,sha256=HJ_DJhCEk6W_u3skecjETMQVLyOmbuPcqcOuoMIJlPs,33194
-ai_pipeline_core/debug/__init__.py,sha256=wOc9KotFqGYzBEtZUZ7ATfJf3dXWarYm6PXs6yW9uwE,756
-ai_pipeline_core/debug/config.py,sha256=l5WC2xbd6PgC-CcuioZg696iva_MkqyZj4C9TFdwfMs,3205
-ai_pipeline_core/debug/content.py,sha256=REtA1cJnOJy3OqaGud59B3Bug8cOJszm8w1GCqdAKJs,26696
-ai_pipeline_core/debug/processor.py,sha256=Cvm1HKc6lKRm80Xx7WXi_Z8pWoKH6actVZvntP9Mons,3935
-ai_pipeline_core/debug/summary.py,sha256=pzXC7QoFOBeen_XZ-AMFAVvaOtDuf28YB-WwCbsHYdQ,8017
-ai_pipeline_core/debug/writer.py,sha256=IF5eyML10EBFBqCGqlVwcWKraFvTgfqbU8WJ_XG_RU4,33108
-ai_pipeline_core/deployment/__init__.py,sha256=FN2HVoM80x2GJuNs7o4DnccB8HWWibgM1pJesB942CM,1259
-ai_pipeline_core/deployment/base.py,sha256=JYf8XLFR73c0H24dr6atK7yUcoE0vLxbYZ8EkQpEwN4,24791
-ai_pipeline_core/deployment/contract.py,sha256=0DKt5eqNE-grcITwMNq9CuBdo5WxdopEjDeQFzFZxhU,2225
-ai_pipeline_core/deployment/helpers.py,sha256=3nRuCyABkUEDZiL0q9u19XHpjA4527B6rsxQNOGTohw,3460
-ai_pipeline_core/documents/__init__.py,sha256=WHStvGZiSyybOcMTYxSV24U6MA3Am_0_Az5p-DuMFrk,738
-ai_pipeline_core/documents/document.py,sha256=hdTh36KGEcrDollTnQmTI66DJIqYfe4X42Y0q7Cm4fY,68153
-ai_pipeline_core/documents/document_list.py,sha256=Y_NCjfM_CjkIwHRD2iyGgYBuIykN8lT2IIH_uWOiGis,16254
-ai_pipeline_core/documents/flow_document.py,sha256=QK6RxNQu449IRAosOHSk3G_5yIq5I7yLBOSQPCd3m64,4141
-ai_pipeline_core/documents/mime_type.py,sha256=JFEOq4HwlIW2snobyNfWwySdT7urZSWkobiRMVs2fSE,7959
-ai_pipeline_core/documents/task_document.py,sha256=uASmAaxNkYtuqQrBM57vutFT9DXNTbqv0wbwwF55E3I,4300
-ai_pipeline_core/documents/temporary_document.py,sha256=jaz2ZHC5CmSbVbkXdI7pOB5DGEuhH16C0Yutv-lS_UI,2708
-ai_pipeline_core/documents/utils.py,sha256=ZyJNjFN7ihWno0K7dJZed7twYmmPLA0z40UzFw1A3A8,5465
-ai_pipeline_core/flow/__init__.py,sha256=2BfWYMOPYW5teGzwo-qzpn_bom1lxxry0bPsjVgcsCk,188
-ai_pipeline_core/flow/config.py,sha256=a9FALpgrFsdz-D7HU3diVeUzbaBvLwI8hsPviuj001s,19389
-ai_pipeline_core/flow/options.py,sha256=s5GBTy5lwFa1irf8BKrWO8NMZ5s_f4tqq7Wg9WQ7TTg,2302
-ai_pipeline_core/images/__init__.py,sha256=6R6Ncif6oRyVOH7LsdwNvEuMGHuljo-_gImY8C3Z_ow,9877
-ai_pipeline_core/images/_processing.py,sha256=wKSBAFe5TO-mo64ll20nmN9huazHwvVWFfNJB6g7u2Q,4421
-ai_pipeline_core/llm/__init__.py,sha256=3B_vtEzxrzidP1qOUNQ4RxlUmxZ2MBKQcUhQiTybM9g,661
-ai_pipeline_core/llm/ai_messages.py,sha256=XR2fwzguuh7v-HQ9LEJX_xwNX1D_-6f4T7E8_iNVTS4,15680
-ai_pipeline_core/llm/client.py,sha256=777Zf5BBRA-6g1I4Og8mitpoCPdYMp66WE52wH-1I-o,24910
-ai_pipeline_core/llm/model_options.py,sha256=uRNIHfVeh2sgt1mZBiOUx6hPQ6GKjB8b7TytZJ6afKg,11768
-ai_pipeline_core/llm/model_response.py,sha256=zEANsfuSAYVRKPwKx9gFIqHbdVG_1_JNMRHNoE43_YM,13503
-ai_pipeline_core/llm/model_types.py,sha256=wx-m0up7_NncTmSYmMsL-l-RgydjjJ905u7RMEAg7tI,2710
-ai_pipeline_core/logging/__init__.py,sha256=Nz6-ghAoENsgNmLD2ma9TW9M0U2_QfxuQ5DDW6Vt6M0,651
-ai_pipeline_core/logging/logging.yml,sha256=YTW48keO_K5bkkb-KXGM7ZuaYKiquLsjsURei8Ql0V4,1353
-ai_pipeline_core/logging/logging_config.py,sha256=pV2x6GgMPXrzPH27sicCSXfw56beio4C2JKCJ3NsXrg,6207
-ai_pipeline_core/logging/logging_mixin.py,sha256=OpdR3ASiM2ZwKZYGjZRJFUloGWUCv2Grnr8RqUWlYn8,8094
-ai_pipeline_core/prompt_builder/__init__.py,sha256=-v0SKZlir07xRzxXwv75VP66aINRUiKH0VUgB-PCDmI,195
-ai_pipeline_core/prompt_builder/documents_prompt.jinja2,sha256=LPql5AaFhFWtDfhnBWvi-bWbz5vdgsWqKGzcqxWfLIM,1075
-ai_pipeline_core/prompt_builder/global_cache.py,sha256=9_9zoF6-sr3KBMxF5QLD3vxqXg9B2tT8o9ViplzUCNg,2811
-ai_pipeline_core/prompt_builder/new_core_documents_prompt.jinja2,sha256=M8uPpwf-uLpsWWJT9DY_DnjrLToGPVnrD-gVhQrQdaQ,229
-ai_pipeline_core/prompt_builder/prompt_builder.py,sha256=4TrDRPiOMFwEfi6QGfriTHfjzj_CtbEjAcgQrVfRqhw,9378
-ai_pipeline_core/prompt_builder/system_prompt.jinja2,sha256=-1jLcfvAG07Zfl-dnYrjfVcAG4PWeeoeWpaKJGY3rKQ,3945
-ai_pipeline_core/storage/__init__.py,sha256=tcIkjJ3zPBLCyetwiJDewBvS2sbRJrDlBh3gEsQm08E,184
-ai_pipeline_core/storage/storage.py,sha256=ClMr419Y-eU2RuOjZYd51dC0stWQk28Vb56PvQaoUwc,20007
-ai_pipeline_core/utils/__init__.py,sha256=TJSmEm1Quf-gKwXrxM96u2IGzVolUyeNNfLMPoLstXI,254
-ai_pipeline_core/utils/deploy.py,sha256=N3i7B97DQJs1lwgYN3sa1UgwCNjseKXfjs50ZJUMCEI,22106
-ai_pipeline_core/utils/remote_deployment.py,sha256=U7MNJ1SU1mg3RrJyLqpuN_4pwqm8LSsFZbypJvjGPoo,4630
-ai_pipeline_core-0.3.3.dist-info/METADATA,sha256=WCRBGS2kO8916jlGc6jY_YuPwzw8diXfeNSrNFKxuvk,17893
-ai_pipeline_core-0.3.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-ai_pipeline_core-0.3.3.dist-info/licenses/LICENSE,sha256=kKj8mfbdWwkyG3U6n7ztB3bAZlEwShTkAsvaY657i3I,1074
-ai_pipeline_core-0.3.3.dist-info/RECORD,,