docling-agent 0.1.0__tar.gz

docling_agent-0.1.0/.gitignore

@@ -0,0 +1,214 @@
+*~
+*.DS_Store
+examples/example_02_edit_resources/*.html
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Folder for example runs
+scratch/

docling_agent-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Docling Project
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

docling_agent-0.1.0/PKG-INFO

@@ -0,0 +1,208 @@
+Metadata-Version: 2.4
+Name: docling-agent
+Version: 0.1.0
+Summary: A python library to simplify agentic operations on documents, such as writing, editing, summarizing, extracting, and enriching.
+Project-URL: homepage, https://github.com/docling-project
+Project-URL: repository, https://github.com/docling-project/docling-agent
+Project-URL: issues, https://github.com/docling-project/docling-agent/issues
+Project-URL: changelog, https://github.com/docling-project/docling-agent/blob/main/CHANGELOG.md
+Author-email: Peter Staar <taa@zurich.ibm.com>
+Maintainer-email: Michele Dolfi <dol@zurich.ibm.com>, Cesar Berrospi Ramis <ceb@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Christoph Auer <cau@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
+License-Expression: MIT
+License-File: LICENSE
+Keywords: agent,agentic,docling,document processing,editing,enrichment,extraction,summarization,writing
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Natural Language :: English
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Python: <4.0,>=3.10
+Requires-Dist: boto3~=1.35
+Requires-Dist: docling-core>=2.70.2
+Requires-Dist: docling>=2.61.0
+Requires-Dist: fastparquet~=2024.11
+Requires-Dist: httpx~=0.28
+Requires-Dist: mellea>=0.3
+Requires-Dist: pandas~=2.2
+Requires-Dist: pyarrow>=19.0
+Requires-Dist: pydantic-settings~=2.4
+Requires-Dist: pydantic~=2.10
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: typer>=0.12.5
+Provides-Extra: vlm
+Requires-Dist: docling[vlm]~=2.53; extra == 'vlm'
+Description-Content-Type: text/markdown
+
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
+[![License MIT](https://img.shields.io/github/license/docling-agent-project/docling-agent)](https://opensource.org/licenses/MIT)
+[![LF AI & Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-003778?logo=linuxfoundation&logoColor=fff&color=0094ff&labelColor=003778)](https://lfaidata.foundation/projects/)
+
+# Docling-Agent
+
+Docling-agent simplifies agentic operation on documents, such as writing, editing, summarizing, etc.
+
+> [!NOTE]
+> **This package is still immature and work-in-progress. We are happy to get comments, suggestions, code contributions, etc!**
+
+## Features
+
+- [Document writing](examples/example_01_write_report.py): Generate well-structured reports from natural prompts and export to JSON/Markdown/HTML.
+- [Targeted editing](examples/example_02_edit_report.py): Load an existing Docling JSON and apply focused edits with natural-language tasks.
+- [Schema-guided extraction](examples/example_03_extract_schema.py): Extract typed fields from PDFs/images using a simple schema and produce HTML reports. See examples on curriculum_vitae, papers, invoices, etc.
+- [Document enrichment](examples/example_04_enrich_document.py): Enrich existing documents with summaries, search keywords, key entities, and item classifications (language/function).
+- Model-agnostic: Plug in different backends via [Mellea](https://github.com/generative-computing/mellea) `model_ids` (e.g., OpenAI GPT OSS, IBM Granite).
+- Simple API surface: Use `agent.run(...)` with `DoclingDocument` in/out; save via `save_as_*` helpers.
+- Optional tools: Integrate external tools (e.g., MCP) when available.
+
+Quick start (writing):
+
+```python
+from mellea.backends import model_ids
+from docling_agent.agents import DoclingWritingAgent
+
+agent = DoclingWritingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+doc = agent.run("Write a one-page summary about polymers in food packaging.")
+doc.save_as_html("report.html")
+```
+
+## Installation
+
+**Coming soon**
+
+## Getting started
+
+Below are three minimal, end-to-end examples mirroring the scripts in the examples folder. Each snippet shows how to initialize an agent, run a task, and save the result.
+
+### Write a new document (see [example](examples/example_01_write_report.py)):
+
+```python
+from mellea.backends import model_ids
+from docling_agent.agents import DoclingWritingAgent
+
+agent = DoclingWritingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+doc = agent.run("Write a brief report on polymers in food packaging with a small comparison table.")
+doc.save_as_html("./scratch/report.html")
+```
+
+### Edit an existing document (see [example](examples/example_02_edit_report.py)):
+
+Use natural-language tasks to update a Docling JSON. You can run multiple tasks to iteratively refine content, structure, or formatting.
+
+```python
+from pathlib import Path
+from mellea.backends import model_ids
+from docling_core.types.doc.document import DoclingDocument
+from docling_agent.agents import DoclingEditingAgent
+
+ipath = Path("./examples/example_02_edit_resources/20250815_125216.json")
+doc = DoclingDocument.load_from_json(ipath)
+
+agent = DoclingEditingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+updated = agent.run(task="Put polymer abbreviations in a separate column in the first table.", document=doc)
+updated.save_as_html("./scratch/updated_table.html")
+```
+
+### Extract structured data with a schema (see [example](examples/example_03_extract_schema.py)):
+
+Define a simple schema and provide a list of files (PDFs/images). The agent produces an HTML report with extracted fields.
+
+```python
+from pathlib import Path
+from mellea.backends import model_ids
+from docling_agent.agents import DoclingExtractingAgent
+
+schema = {"invoice-number": "string", "total": "float", "currency": "string"}
+sources = sorted([p for p in Path("./examples/example_03_extract/invoices").rglob("*.*") if p.suffix.lower() in {".pdf", ".png", ".jpg", ".jpeg"}])
+
+agent = DoclingExtractingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+report = agent.run(task=str(schema), sources=sources)
+report.save_as_html("./scratch/invoices_extraction_report.html")
+```
+
+### Enrich an existing document (see [example](examples/example_04_enrich_document.py)):
+
+Run enrichment passes like summaries, keywords, entities, and classifications on a Docling JSON.
+
+```python
+from pathlib import Path
+from mellea.backends import model_ids
+from docling_core.types.doc.document import DoclingDocument
+from docling_agent.agents import DoclingEnrichingAgent
+
+ipath = Path("./examples/example_02_edit_resources/20250815_125216.json")
+doc = DoclingDocument.load_from_json(ipath)
+
+agent = DoclingEnrichingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+enriched = agent.run(task="Summarize each paragraph, table, and section header.", document=doc)
+enriched.save_as_html("./scratch/enriched_summaries.html")
+```
+
+## Documentation
+
+**Coming soon**
+
+## Examples
+
+Go hands-on with our [examples](https://docling-project.github.io/docling/examples/),
+demonstrating how to address different application use cases with Docling.
+
+## Integrations
+
+To further accelerate your AI application development, check out Docling's native
+[integrations](https://docling-project.github.io/docling/integrations/) with popular frameworks
+and tools.
+
+## Get help and support
+
+Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions).
+
+## Technical report
+
+For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).
+
+## Contributing
+
+Please read [Contributing to Docling](https://github.com/docling-project/docling/blob/main/CONTRIBUTING.md) for details.
+
+## References
+
+If you use Docling or Docling-agent in your projects, please consider citing the following:
+
+```bib
+@techreport{Docling,
+  author = {Deep Search Team},
+  month = {8},
+  title = {Docling Technical Report},
+  url = {https://arxiv.org/abs/2408.09869},
+  eprint = {2408.09869},
+  doi = {10.48550/arXiv.2408.09869},
+  version = {1.0.0},
+  year = {2024}
+}
+```
+
+## License
+
+The Docling codebase is under MIT license.
+For individual model usage, please refer to the model licenses found in the original packages.
+
+## LF AI & Data
+
+Docling is hosted as a project in the [LF AI & Data Foundation](https://lfaidata.foundation/projects/).
+
+### IBM ❤️ Open Source AI
+
+The project was started by the AI for knowledge team at IBM Research Zurich.

docling_agent-0.1.0/README.md

@@ -0,0 +1,163 @@
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
+[![License MIT](https://img.shields.io/github/license/docling-agent-project/docling-agent)](https://opensource.org/licenses/MIT)
+[![LF AI & Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-003778?logo=linuxfoundation&logoColor=fff&color=0094ff&labelColor=003778)](https://lfaidata.foundation/projects/)
+
+# Docling-Agent
+
+Docling-agent simplifies agentic operation on documents, such as writing, editing, summarizing, etc.
+
+> [!NOTE]
+> **This package is still immature and work-in-progress. We are happy to get comments, suggestions, code contributions, etc!**
+
+## Features
+
+- [Document writing](examples/example_01_write_report.py): Generate well-structured reports from natural prompts and export to JSON/Markdown/HTML.
+- [Targeted editing](examples/example_02_edit_report.py): Load an existing Docling JSON and apply focused edits with natural-language tasks.
+- [Schema-guided extraction](examples/example_03_extract_schema.py): Extract typed fields from PDFs/images using a simple schema and produce HTML reports. See examples on curriculum_vitae, papers, invoices, etc.
+- [Document enrichment](examples/example_04_enrich_document.py): Enrich existing documents with summaries, search keywords, key entities, and item classifications (language/function).
+- Model-agnostic: Plug in different backends via [Mellea](https://github.com/generative-computing/mellea) `model_ids` (e.g., OpenAI GPT OSS, IBM Granite).
+- Simple API surface: Use `agent.run(...)` with `DoclingDocument` in/out; save via `save_as_*` helpers.
+- Optional tools: Integrate external tools (e.g., MCP) when available.
+
+Quick start (writing):
+
+```python
+from mellea.backends import model_ids
+from docling_agent.agents import DoclingWritingAgent
+
+agent = DoclingWritingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+doc = agent.run("Write a one-page summary about polymers in food packaging.")
+doc.save_as_html("report.html")
+```
+
+## Installation
+
+**Coming soon**
+
+## Getting started
+
+Below are three minimal, end-to-end examples mirroring the scripts in the examples folder. Each snippet shows how to initialize an agent, run a task, and save the result.
+
+### Write a new document (see [example](examples/example_01_write_report.py)):
+
+```python
+from mellea.backends import model_ids
+from docling_agent.agents import DoclingWritingAgent
+
+agent = DoclingWritingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+doc = agent.run("Write a brief report on polymers in food packaging with a small comparison table.")
+doc.save_as_html("./scratch/report.html")
+```
+
+### Edit an existing document (see [example](examples/example_02_edit_report.py)):
+
+Use natural-language tasks to update a Docling JSON. You can run multiple tasks to iteratively refine content, structure, or formatting.
+
+```python
+from pathlib import Path
+from mellea.backends import model_ids
+from docling_core.types.doc.document import DoclingDocument
+from docling_agent.agents import DoclingEditingAgent
+
+ipath = Path("./examples/example_02_edit_resources/20250815_125216.json")
+doc = DoclingDocument.load_from_json(ipath)
+
+agent = DoclingEditingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+updated = agent.run(task="Put polymer abbreviations in a separate column in the first table.", document=doc)
+updated.save_as_html("./scratch/updated_table.html")
+```
+
+### Extract structured data with a schema (see [example](examples/example_03_extract_schema.py)):
+
+Define a simple schema and provide a list of files (PDFs/images). The agent produces an HTML report with extracted fields.
+
+```python
+from pathlib import Path
+from mellea.backends import model_ids
+from docling_agent.agents import DoclingExtractingAgent
+
+schema = {"invoice-number": "string", "total": "float", "currency": "string"}
+sources = sorted([p for p in Path("./examples/example_03_extract/invoices").rglob("*.*") if p.suffix.lower() in {".pdf", ".png", ".jpg", ".jpeg"}])
+
+agent = DoclingExtractingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+report = agent.run(task=str(schema), sources=sources)
+report.save_as_html("./scratch/invoices_extraction_report.html")
+```
+
+### Enrich an existing document (see [example](examples/example_04_enrich_document.py)):
+
+Run enrichment passes like summaries, keywords, entities, and classifications on a Docling JSON.
+
+```python
+from pathlib import Path
+from mellea.backends import model_ids
+from docling_core.types.doc.document import DoclingDocument
+from docling_agent.agents import DoclingEnrichingAgent
+
+ipath = Path("./examples/example_02_edit_resources/20250815_125216.json")
+doc = DoclingDocument.load_from_json(ipath)
+
+agent = DoclingEnrichingAgent(model_id=model_ids.OPENAI_GPT_OSS_20B)
+enriched = agent.run(task="Summarize each paragraph, table, and section header.", document=doc)
+enriched.save_as_html("./scratch/enriched_summaries.html")
+```
+
+## Documentation
+
+**Coming soon**
+
+## Examples
+
+Go hands-on with our [examples](https://docling-project.github.io/docling/examples/),
+demonstrating how to address different application use cases with Docling.
+
+## Integrations
+
+To further accelerate your AI application development, check out Docling's native
+[integrations](https://docling-project.github.io/docling/integrations/) with popular frameworks
+and tools.
+
+## Get help and support
+
+Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions).
+
+## Technical report
+
+For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).
+
+## Contributing
+
+Please read [Contributing to Docling](https://github.com/docling-project/docling/blob/main/CONTRIBUTING.md) for details.
+
+## References
+
+If you use Docling or Docling-agent in your projects, please consider citing the following:
+
+```bib
+@techreport{Docling,
+  author = {Deep Search Team},
+  month = {8},
+  title = {Docling Technical Report},
+  url = {https://arxiv.org/abs/2408.09869},
+  eprint = {2408.09869},
+  doi = {10.48550/arXiv.2408.09869},
+  version = {1.0.0},
+  year = {2024}
+}
+```
+
+## License
+
+The Docling codebase is under MIT license.
+For individual model usage, please refer to the model licenses found in the original packages.
+
+## LF AI & Data
+
+Docling is hosted as a project in the [LF AI & Data Foundation](https://lfaidata.foundation/projects/).
+
+### IBM ❤️ Open Source AI
+
+The project was started by the AI for knowledge team at IBM Research Zurich.

docling_agent-0.1.0/docling_agent/agent/base.py

@@ -0,0 +1,80 @@
+from __future__ import annotations
+
+from abc import abstractmethod
+from enum import Enum
+from pathlib import Path
+from typing import TYPE_CHECKING
+
+# from smolagents import MCPClient, Tool, ToolCollection
+# from smolagents.models import ChatMessage, MessageRole, Model
+from mellea.backends.model_ids import ModelIdentifier
+from pydantic import BaseModel, ConfigDict
+
+if TYPE_CHECKING:
+    from docling_core.types.doc.document import DoclingDocument
+
+# Use shared logger from docling_agent.agents
+
+
+class DoclingAgentType(Enum):
+    """Enumeration of supported agent types."""
+
+    # Core agent types
+    DOCLING_DOCUMENT_WRITER = "writer"
+    DOCLING_DOCUMENT_EDITOR = "editor"
+    DOCLING_DOCUMENT_EXTRACTOR = "extractor"
+    DOCLING_DOCUMENT_ENRICHER = "enricher"
+    DOCLING_DOCUMENT_RAG = "rag"
+    DOCLING_DOCUMENT_ORCHESTRATOR = "orchestrator"
+
+    def __str__(self) -> str:
+        """Return the string value of the enum."""
+        return self.value
+
+    @classmethod
+    def from_string(cls, value: str) -> DoclingAgentType:
+        """Create AgentType from string value."""
+        for agent_type in cls:
+            if agent_type.value == value:
+                return agent_type
+        raise ValueError(f"Invalid agent type: {value}. Valid types: {[t.value for t in cls]}")
+
+    @classmethod
+    def get_all_types(cls) -> list[str]:
+        """Get all available agent type strings."""
+        return [agent_type.value for agent_type in cls]
+
+
+class BaseDoclingAgent(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    agent_type: DoclingAgentType
+    model_id: ModelIdentifier
+    tools: list
+
+    # model needed for reasoning/instruction following
+    reasoning_model_id: ModelIdentifier | None = None
+
+    # model needed for writing, summarizing, etc
+    writing_model_id: ModelIdentifier | None = None
+
+    max_iteration: int = 16
+
+    def get_reasoning_model_id(self) -> ModelIdentifier:
+        """Return the reasoning model id, falling back to the primary model."""
+        return self.reasoning_model_id or self.model_id
+
+    def get_writing_model_id(self) -> ModelIdentifier:
+        """Return the writing model id, falling back to the primary model."""
+        return self.writing_model_id or self.model_id
+
+    @abstractmethod
+    def run(
+        self,
+        task: str,
+        document: DoclingDocument | None = None,
+        sources: list[DoclingDocument | Path] = [],
+        **kwargs,
+    ) -> DoclingDocument:
+        """Execute the agent for a task and return a document."""
+        raise NotImplementedError