Llama index readers gitbook (#16862)

Author: mckang

llama-index-integrations/readers/llama-index-readers-gitbook/.gitignore

@@ -0,0 +1,153 @@
+llama_index/_static
+.DS_Store
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+bin/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+etc/
+include/
+lib/
+lib64/
+parts/
+sdist/
+share/
+var/
+wheels/
+pip-wheel-metadata/
+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/
+.ruff_cache
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+notebooks/
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+pyvenv.cfg
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Jetbrains
+.idea
+modules/
+*.swp
+
+# VsCode
+.vscode
+
+# pipenv
+Pipfile
+Pipfile.lock
+
+# pyright
+pyrightconfig.json

llama-index-integrations/readers/llama-index-readers-gitbook/BUILD

@@ -0,0 +1,3 @@
+poetry_requirements(
+    name="poetry",
+)

llama-index-integrations/readers/llama-index-readers-gitbook/CHANGELOG.md

@@ -0,0 +1 @@
+# CHANGELOG

llama-index-integrations/readers/llama-index-readers-gitbook/Makefile

@@ -0,0 +1,17 @@
+GIT_ROOT ?= $(shell git rev-parse --show-toplevel)
+
+help:	## Show all Makefile targets.
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[33m%-30s\033[0m %s\n", $$1, $$2}'
+
+format:	## Run code autoformatters (black).
+	pre-commit install
+	git ls-files | xargs pre-commit run black --files
+
+lint:	## Run linters: pre-commit (black, ruff, codespell) and mypy
+	pre-commit install && git ls-files | xargs pre-commit run --show-diff-on-failure --files
+
+test:	## Run tests via pytest.
+	python -m unittest discover tests
+
+watch-docs:	## Build and watch documentation.
+	sphinx-autobuild docs/ docs/_build/html --open-browser --watch $(GIT_ROOT)/llama_index/

llama-index-integrations/readers/llama-index-readers-gitbook/README.md

@@ -0,0 +1,30 @@
+# LlamaIndex Readers Integration: Gitbook
+
+## Overview
+
+Simple Gitbook Reader allows loading data from a gitbook space. It collects & converts contents from gitbook space into documents used by LlamaIndex.
+
+### Installation
+
+You can install Gitbook Reader via pip:
+
+```bash
+pip install llama-index-readers-gitbook
+```
+
+### Usage
+
+```python
+from llama_index.readers.gitbook import SimpleGitbookReader
+
+# Initialize SimpleGitbookReader
+reader = SimpleGitbookReader(
+    api_token="<Gitbook API Token>",  # Gitbook API Token
+)
+
+# load data from Gitbook
+documents = reader.load_data(
+    space_id="<Gitbook Space Id>",  # Id of the gitbook space
+    metadata_names=None,  # Names of the fields to add to metadata attribute (available: 'path', 'title', 'description', 'parent')
+)
+```

llama-index-integrations/readers/llama-index-readers-gitbook/llama_index/readers/gitbook/BUILD

@@ -0,0 +1 @@
+python_sources()

llama-index-integrations/readers/llama-index-readers-gitbook/llama_index/readers/gitbook/__init__.py

@@ -0,0 +1,3 @@
+from llama_index.readers.gitbook.base import SimpleGitbookReader
+
+__all__ = ["SimpleGitbookReader"]

llama-index-integrations/readers/llama-index-readers-gitbook/llama_index/readers/gitbook/base.py

@@ -0,0 +1,110 @@
+from typing import List, Optional
+
+from llama_index.core.readers.base import BaseReader
+from llama_index.core.schema import Document
+
+from llama_index.readers.gitbook.gitbook_client import GitbookClient
+
+VALID_METADATA_FIELDS = {"path", "title", "description", "parent"}
+
+
+class SimpleGitbookReader(BaseReader):
+    """Simple gitbook reader.
+
+    Convert each gitbook page into Document used by LlamaIndex.
+
+    Args:
+        api_token (str): Gitbook API Token.
+        api_url (str): Gitbook API Endpoint.
+    """
+
+    def __init__(self, api_token: str, api_url: str = None) -> None:
+        """Initialize with parameters."""
+        self.client = GitbookClient(api_token, api_url)
+
+    def load_data(
+        self,
+        space_id: str,
+        metadata_names: Optional[List[str]] = None,
+        show_progress=False,
+    ) -> List[Document]:
+        """Load data from the input directory.
+
+        Args:
+            space_id (str): Gitbook space id
+            metadata_names (Optional[List[str]]): names of the fields to be added
+                to the metadata attribute of the Document.
+                only 'path', 'title', 'description', 'parent' are available
+                Defaults to None
+            show_progress (bool, optional): Show progress bar. Defaults to False
+
+        Returns:
+            List[Document]: A list of documents.
+
+        """
+        if metadata_names:
+            invalid_fields = set(metadata_names) - VALID_METADATA_FIELDS
+            if invalid_fields:
+                raise ValueError(
+                    f"Invalid metadata fields: {', '.join(invalid_fields)}"
+                )
+
+        documents = []
+        pages = self.client.list_pages(space_id)
+
+        if show_progress:
+            from tqdm import tqdm
+
+            iterator = tqdm(pages, desc="Downloading pages")
+        else:
+            iterator = pages
+
+        for page in iterator:
+            id = page.get("id")
+            content = self.client.get_page_markdown(space_id, id)
+            if not content:
+                print(f"Warning: No content found for page ID {id}. Skipping...")
+                continue
+
+            if metadata_names is None:
+                documents.append(
+                    Document(text=content, id_=id, metadata={"path": page.get("path")})
+                )
+            else:
+                try:
+                    metadata = {name: page.get(name) for name in metadata_names}
+                except KeyError as err:
+                    raise ValueError(
+                        f"{err.args[0]} field is not available. Choose from {', '.join(VALID_METADATA_FIELDS)}"
+                    ) from err
+                documents.append(Document(text=content, id_=id, metadata=metadata))
+
+        return documents
+
+
+if __name__ == "__main__":
+    import os
+    import sys
+
+    def load_env_file():
+        """Load environment variables from .env file."""
+        current_dir = os.path.dirname(os.path.abspath(__file__))
+        env_path = os.path.join(current_dir, "../../../.env")
+        if os.path.exists(env_path):
+            with open(env_path) as f:
+                for line in f:
+                    line = line.strip()
+                    if line and not line.startswith("#"):
+                        key, value = line.split("=", 1)
+                        os.environ[key.strip()] = value.strip()
+
+    load_env_file()
+    api_token = os.getenv("GITBOOK_API_TOKEN")
+    space_id = os.getenv("GITBOOK_SPACE_ID")
+
+    if not api_token or not space_id:
+        print("Error: GITBOOK_API_TOKEN and GITBOOK_SPACE_ID must be set in .env file")
+        sys.exit(1)
+
+    reader = SimpleGitbookReader(api_token)
+    print(reader.load_data(space_id, show_progress=True))