Show HN: Embeddings Solution for Personal Journal

It occurred to me that a personal diary&#x2F;journal is one of the most interesting data sets for a vector embedding &#x2F; chat context product. People express their hopes, dreams, fears and much more in their journal. A psychiatrist&#x2F;psychologist&#x2F;therapist would have many insights from reading a journal.<p>So this is what I&#x27;m trying to build at Jumble Journal. We enable people to chat with their past journals as a first feature.<p>Technology<p>For vector embeddings and similarity search, we use ChromaDB. It&#x27;s open source and has great performance. For something small scale, I didn&#x27;t want to get locked into one of the Vector DB services like Pinecone.<p>The DB is hosted on an EC2 instance. Backend API is serverless with AWS Lambda and API Gateway. We back up all embeddings in S3 in case of failure.<p>I am really happy to discuss the technology stack and the feature itself.<p>Links https:&#x2F;&#x2F;jumblejournal.org https:&#x2F;&#x2F;www.trychroma.com&#x2F;