ChatJC
chatbot for resume/LinkedIn/portfolio info
Last verified:
What is ChatJC?
ChatJC is a RAG-powered chatbot API designed to answer questions about a developer's professional background. It allows users to upload their resume, LinkedIn profile data, cover letters, GitHub repositories, recommendations, projects, languages, volunteering experience, and personal work into a chatbot interface that can answer questions about this information conversationally.
The tool uses structured markdown files as its RAG (Retrieval-Augmented Generation) context, meaning users need to manually create markdown files from their professional data rather than having automatic ingestion from LinkedIn or other services. It is built using Hono, LangChain, Mistral AI, and SQLite technologies, and is served on a Svelte frontend.
ChatJC is primarily designed for developers who want to showcase their portfolio, resume, and professional background in an interactive, conversational format. It serves both as a personal portfolio enhancement for Joshua Curry's own website and as a general-purpose API that others could use for similar purposes.
Key features include the ability to ask questions about specific aspects of your professional background, retrieve information from multiple source documents, and provide conversational answers powered by AI. The chatbot can handle diverse content types including technical projects, work experience, skills, and personal stories.
This tool is ideal for job seekers, developers building portfolios, professionals wanting an innovative way to present their background, and anyone interested in integrating a RAG-powered chatbot into their personal website or application.
ChatJC pricing
Pricing model: Freemium
Pricing details are not publicly specified on the website. The tool appears to be self-hosted/open source with the anonymized API repository available on GitHub at github.com/lucidbeaming/chatjc. Users would need to provide their own Mistral AI API key for the LLM backend, which would incur separate costs from Mistral AI. No free tier or paid plans are explicitly mentioned on the current website.
ChatJC pros
- RAG-powered for accurate context-based answers
- Built with modern tech stack (Hono, LangChain, Mistral AI, SQLite)
- Svelte frontend for responsive user experience
- Handles multiple document types (resumes, LinkedIn, GitHub, cover letters)
- Open source API available on GitHub
- Conversational interface for exploring professional background
- Can include personal stories and unique content
- Works as both portfolio feature and general API
- Structured markdown files provide organized context
- No automatic data ingestion means full user control
- Lightweight SQLite database for data storage
- Suitable for developers building personal portfolios
- Answers questions about projects, skills, and experience
- Can include recommendations and volunteering history
- Anonymized and secured version available for general release
ChatJC cons
- Does not automatically ingest LinkedIn or other services
- Requires manual creation of structured markdown files
- No mentioned free tier or pricing transparency
- Limited to user-provided context (no web searching)
- Setup requires technical knowledge of markdown formatting
- No mention of mobile app or mobile optimization
- GitHub repo shows only 1 project integration
- No documented API rate limits or usage quotas
- Mistral AI dependency means API costs may apply
- No built-in user authentication mentioned
- Limited community or documentation visible
- No mentioned analytics or usage tracking
Frequently asked questions about ChatJC
What is ChatJC?
ChatJC is a RAG-powered chatbot API that answers questions about a developer's professional background. It was created by Joshua Curry and is available live at joshuacurry.dev, with the anonymized API repository available on GitHub.
What data can I add to ChatJC?
You can add resumes, LinkedIn profile information, cover letter snippets, GitHub repositories, recommendations, projects, languages, volunteering experience, personal work, and even personal stories about building projects or your career.
Does ChatJC automatically import my LinkedIn data?
No, ChatJC does not automatically ingest LinkedIn or other services. You need to manually create structured markdown files from your LinkedIn and other professional data to use as RAG context.
What technology stack powers ChatJC?
ChatJC is built with Hono (web framework), LangChain (for RAG implementation), Mistral AI (for the language model), and SQLite (for data storage). The frontend is served using Svelte.
Is ChatJC open source?
Yes, the anonymized and secured API version is available as an open source repository on GitHub at github.com/lucidbeaming/chatjc for general release.
How does the RAG system work in ChatJC?
ChatJC uses structured markdown files that you create from your professional data as the RAG context. When you ask questions, the system retrieves relevant information from these markdown files and uses Mistral AI to generate contextual answers.
Who is ChatJC designed for?
ChatJC is designed for developers who want to showcase their portfolio and professional background in an interactive conversational format, job seekers wanting an innovative resume presentation, and anyone building a personal website with an AI chatbot feature.
Can I use ChatJC for my own portfolio?
Yes, the API is designed to work as a general-purpose solution. You can adapt the anonymized API from the GitHub repository for your own portfolio website, though you would need to set up your own markdown files with your professional data.
What are the costs associated with using ChatJC?
The tool itself is open source, but you would need to provide your own Mistral AI API key for the language model backend, which would incur separate costs from Mistral AI based on their usage pricing. Hosting costs would also apply if you deploy it yourself.
How do I get started with ChatJC?
To get started, visit joshuacurry.dev to see the live demo, then clone the GitHub repository at github.com/lucidbeaming/chatjc. You'll need to create structured markdown files from your professional data, set up a Mistral AI API key, and follow the repository setup instructions.