# Claude Code Web is INSANE Source: https://www.youtube.com/watch?v=VtHvkBWToJs Recap page: https://rapidrecap.app/video/VtHvkBWToJs Generated: 2025-11-10T19:32:03.725+00:00 --- ## Quick Overview The presenter successfully builds and tests a powerful Retrieval-Augmented Generation (RAG) tool using Claude Code, Apify, and Google's Gemini API File Search feature to create an application that can answer questions based on the transcripts of any YouTube channel's videos, demonstrating the tool's capability by querying information about Adobe's recent AI announcements from a linked channel. **Key Points:** - The presenter uses Claude Code to build a YouTube Channel RAG tool that leverages Apify for scraping and Gemini API File Search for retrieval. - The initial setup required installing the Claude GitHub app and creating an empty GitHub repository named 'gemini-api-rag'. - The process involved running a Python script which scraped the 5 most recent videos from the specified YouTube channel, created transcript files, and uploaded them to Gemini File Search. - An error occurred initially due to an incorrect function declaration for 'file_search' in the tool configuration, which Claude Code helped fix by referencing correct documentation. - After fixing the syntax error and re-running the process, the tool successfully retrieved information, answering a query about what Mike Russell said regarding Adobe's recent AI announcements. - The entire end-to-end demonstration, from setup to successful querying, cost only $1 of the initial $250 free credit provided to subscribers. ![Screenshot at 00:02: The presenter is shown on the Claude Code web interface, starting a new session to 'Code with Claude anywhere' by connecting to GitHub.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-00-02.png) **Context:** The video demonstrates the practical application of Claude Code, a cloud-based coding environment integrated with GitHub, to rapidly develop a complex AI tool. The specific goal is to create a Retrieval-Augmented Generation (RAG) system that can query the content of YouTube videos from a specific channel by scraping transcripts and utilizing Google's Gemini File Search capability, all guided by Claude's assistance. ## Detailed Analysis The presenter begins by setting up a new environment in Claude Code, connecting it to a new GitHub repository named 'gemini-api-rag'. After installing dependencies, an error arises because the Gemini File Search API syntax used for function declaration was incorrect ('file_search' instead of the expected format). Claude Code successfully debugs this by performing web searches and suggesting updates based on the current Gemini API documentation, resulting in corrected code and the successful creation of a 'youtube_rag.py' file. The tool is then executed, using Apify to scrape the 5 most recent videos from a specified YouTube channel, generating transcript files, and uploading these files to the Gemini File Search index. Once the indexing is complete, the presenter queries the system about what Mike Russell said regarding Adobe's AI announcements, and the system correctly synthesizes an answer based on the video transcripts, highlighting the power of combining LLM capabilities with external tools like Apify and Gemini File Search. The entire process, including running multiple large tasks, consumed only $1 of the initial $250 free credit. ### Claude Code Setup & Initial Error - Connected to GitHub via the Claude GitHub app - Created a 'gemini-api-rag' repo - Initial script execution failed due to incorrect 'file_search' function declaration syntax in tool configuration. ### Debugging and Fixing the Error - Claude Code used web search to find correct Gemini File Search API documentation - Corrected the Python code for tool calling implementation - Re-ran the script successfully. ### RAG Tool Execution - Ran 'python youtube_rag.py' - Scraped 5 videos from the specified YouTube channel using Apify - Created transcript files and uploaded them to Gemini File Search. ### Successful Query and Outcome - Queried the system about Mike Russell's comments on Adobe AI news (like Firefly, Firefly Video Editor, Generative Upscale) - The tool accurately synthesized answers based on the video transcripts. ### Cost Analysis and Conclusion - The entire complex workflow, involving scraping, indexing, and querying, cost only $1 of the $250 free usage credit provided to pro subscribers. ![Screenshot at 00:04: The Claude Code onboarding screen showing the option to 'Code with Claude anywhere' by connecting to GitHub.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-00-04.png) ![Screenshot at 00:17: A Twitter post from Apify advertising a $1 Million Challenge for building tools using their platform.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-00-17.png) ![Screenshot at 00:31: The Claude Code environment showing the initial prompt to build the YouTube RAG tool and the subsequent error message upon execution.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-00-31.png) ![Screenshot at 01:17: The presenter navigating GitHub to create a new repository named 'gemini-api-rag' for the project.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-01-17.png) ![Screenshot at 01:51: The generated 'requirements.txt' file showing necessary Python dependencies like google-generativeai and apify-client.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-01-51.png) ![Screenshot at 02:28: Creating the initial 'README.md' file in the GitHub repository via Claude Code's interface.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-02-28.png) ![Screenshot at 04:48: The terminal showing the successful 'git pull' fetching all the necessary files created by Claude Code.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-04-48.png) ![Screenshot at 05:36: The terminal output showing the Apify YouTube scraper successfully scraping 5 videos and creating transcript files.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-05-36.png) ![Screenshot at 07:19: The final output in the terminal showing the Assistant successfully answering the query about Mike Russell's comments on Adobe, demonstrating the RAG system's success.](https://ss.rapidrecap.app/screens/VtHvkBWToJs/00-07-19.png)