Added YouTube Metadata Reader (#12975)

llama-index-integrations/readers/llama-index-readers-youtube-metadata/.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-youtube-metadata/.pre-commit-config.yaml

@@ -0,0 +1,6 @@
+repos:
+  - repo: https://github.com/psf/black
+    rev: 22.3.0
+    hooks:
+      - id: black
+        language_version: python3

llama-index-integrations/readers/llama-index-readers-youtube-metadata/BUILD

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

llama-index-integrations/readers/llama-index-readers-youtube-metadata/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 ||true
+
+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.
+	pytest 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-youtube-metadata/README.md

@@ -0,0 +1,44 @@
+# LlamaIndex Readers Integration: Youtube-Metadata
+
+```bash
+pip install llama_index.readers.youtube_metadata
+```
+
+This loader fetches the metadata of Youtube videos using the Google APIs. (https://www.googleapis.com/youtube/v3/videos?part=snippet,statistics&id={videos_string}&key={api_key}). You must have a Google API key to use.
+
+Transcripts of the text transcript of Youtube videos is fetched using the `youtube_transcript_api` Python package.
+
+## Usage
+
+Simply pass an array of YouTube Video_ID into `load_data`.
+
+```python
+from llama_index.readers.youtube_metadata import YoutubeMetaData
+
+api_key = "Axxxxx"  # youtube API Key
+
+video_ids = ["S_0hBL4ILAg", "a2skIq6hFiY"]
+
+youtube_meta = YoutubeMetaData(api_key)
+details = youtube_meta.load_data(video_ids)
+```
+
+This can be combined with the YoutubeTranscriptReader to provide more information for RAG AI inquiries.
+
+```python
+from llama_index.readers.youtube_transcript import YoutubeTranscriptReader
+from llama_index.readers.youtube_metadata import YoutubeMetaData
+
+video_ids = ["S_0hBL4ILAg", "a2skIq6hFiY"]  # Example video IDs
+yt_metadata = YouTubeMetaData(api_key=api_key)
+print("Testing YouTubeMetaData...")
+print(yt_metadata.load_data(video_ids))
+
+yt_meta_transcript = YouTubeMetaDataAndTranscript(api_key=api_key)
+print("Testing YouTubeMetaDataAndTranscript...")
+print(yt_meta_transcript.load_data(video_ids))
+```
+
+The Video_id for youtube videos is right in the URL. In this URL: https://www.youtube.com/watch?v=a2skIq6hFiY&t=60s
+
+The video_Id is 'a2skIq6hFiY&t'.

llama-index-integrations/readers/llama-index-readers-youtube-metadata/llama_index/readers/youtube_metadata/BUILD

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

llama-index-integrations/readers/llama-index-readers-youtube-metadata/llama_index/readers/youtube_metadata/__init__.py

@@ -0,0 +1,6 @@
+from llama_index.readers.youtube_metadata.base import (
+    YouTubeMetaData,
+    YouTubeMetaDataAndTranscript,
+)
+
+__all__ = ["YouTubeMetaData", "YouTubeMetaDataAndTranscript"]

llama-index-integrations/readers/llama-index-readers-youtube-metadata/llama_index/readers/youtube_metadata/base.py

@@ -0,0 +1,66 @@
+# YoutubeMetaData.py
+# Class to return Youtube Meta data for a video ID
+import requests
+from pydantic import Field
+from typing import Any, List, Dict
+from youtube_transcript_api import YouTubeTranscriptApi
+from llama_index.core.readers.base import BasePydanticReader
+
+
+class YouTubeMetaData(BasePydanticReader):
+    api_key: str
+
+    def load_data(self, video_ids):
+        details = {}
+
+        def chunks(lst, n):
+            """Yield successive n-sized chunks from lst."""
+            for i in range(0, len(lst), n):
+                yield lst[i : i + n]
+
+        video_id_chunks = list(chunks(video_ids, 20))
+        for chunk in video_id_chunks:
+            videos_string = ",".join(chunk)
+            url = f"https://www.googleapis.com/youtube/v3/videos?part=snippet,statistics&id={videos_string}&key={self.api_key}"
+            response = requests.get(url).json()
+            if "items" not in response:
+                print("Error in API response:", response)
+                continue
+
+            for item in response["items"]:
+                video_id = item["id"]
+                details[video_id] = {
+                    "title": item["snippet"]["title"],
+                    "description": item["snippet"]["description"],
+                    "publishDate": item["snippet"]["publishedAt"],
+                    "statistics": item["statistics"],
+                    "tags": item["snippet"].get("tags", []),
+                    "url": f"https://www.youtube.com/watch?v={video_id}",
+                }
+
+        return details
+
+
+class YouTubeMetaDataAndTranscript(BasePydanticReader):
+    api_key: str = Field(..., description="API key for YouTube data access")
+    metadata_loader: YouTubeMetaData = None  # Don't instantiate here
+    transcript_loader: Any = YouTubeTranscriptApi  # Assume this is a simple callable
+
+    def initialize_loaders(self):
+        if not self.metadata_loader:
+            self.metadata_loader = YouTubeMetaData(api_key=self.api_key)
+
+    def load_data(self, video_ids: List[str]) -> Dict[str, Any]:
+        self.initialize_loaders()  # Make sure loaders are initialized
+        all_details = {}
+        for video_id in video_ids:
+            metadata = self.metadata_loader.load_data([video_id])
+            try:
+                transcripts = self.transcript_loader.get_transcript(video_id)
+            except Exception as e:
+                transcripts = str(e)
+            all_details[video_id] = {
+                "metadata": metadata.get(video_id, {}),
+                "transcript": transcripts,
+            }
+        return all_details