# Chroma Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/chroma
> Markdown URL: https://aitinkerers.org/technologies/chroma.md
> Technology record last updated: 2026-03-04T13:38:59Z
> Generated: 2026-09-22T22:34:08Z

Chroma is the open-source vector database engineered for AI: it simplifies the storage and retrieval of vector embeddings for large language models (LLMs).

Chroma functions as the critical memory layer for modern Generative AI applications, specifically powering Retrieval-Augmented Generation (RAG). It stores vector embeddings (numerical representations of unstructured data like text or images) and associated metadata. This architecture enables low-latency, high-accuracy similarity searches using metrics like cosine distance. Developers can deploy it locally or use the managed Chroma Cloud, leveraging Python and JavaScript/TypeScript SDKs for rapid prototyping and production-scale LLM context retrieval.

- Official technology site: https://www.trychroma.com/
- Public AI Tinkerers demos and talks: 8
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Failing Fast with AI: Rapid Prototyping Using Google AI Studio](https://pereira.aitinkerers.org/talks/rsvp_BLcMVGVLlTs)

This demo explores a paradigm shift in product development: failing fast to learn faster. I’ll demonstrate how Google AI Studio can be used to rapidly prototype AI-powered applications, validate ideas, and surface potential product value—without investing significant time, money, or engineering resources upfront. The focus will be on hands-on experimentation, iteration cycles, and technical workflows rather than slides or theory.

- Event context: Cambio de paradigma AITINKERERS PEREIRA 2026 — 2026-02-26 — Pereira
- Public talk page: https://pereira.aitinkerers.org/talks/rsvp_BLcMVGVLlTs

### [RAG authorization to protect sensitive data](https://tokyo.aitinkerers.org/talks/rsvp_7VwcQPg1fZ8)

I am going to demo a way to protect users' sensitive information in the RAG pipeline based on the user's permission. I will also discuss the relationship-based access control concept used in the RAG pipeline to provide granular access control.

- Event context: AI Tinkerers Ginza Meetup – January 15, 2026 — 2026-01-15 — Tokyo
- Public talk page: https://tokyo.aitinkerers.org/talks/rsvp_7VwcQPg1fZ8

### [Teaching AI to read ancient Maya Glyphs](https://montreal.aitinkerers.org/talks/rsvp_Z7tI1x8ww7I)

The ancient Maya developed one of the most beautiful, complex, and intriguing writing systems in human history. For centuries, these glyphs recorded stories, rituals, dynasties, and the deep relationship between people, time, and the cosmos. Yet this knowledge was silenced — burned, buried, and forgotten for nearly a thousand years. Even today, only a few thousand people in the world can read Maya writing. I will the development of an AI agent designed to help bridge that gap. Using computer vision and deep learning, the system can detect glyph blocks, identify individual signs, and suggest possible readings by comparing them to a vast epigraphic corpus. It is not perfect — but it is a powerful first step toward using artificial intelligence to preserve and reactivate knowledge that was nearly lost forever. In doing so, we demonstrate how AI can be more than just code — it can be a force for memory, preservation, and cultural resilience. I will be presenting a live demo.

- Event context: AI Tinkerers Montreal – Spooky October 2025 Meetup — 2025-10-21 — Montreal
- Public talk page: https://montreal.aitinkerers.org/talks/rsvp_Z7tI1x8ww7I

### [High-throughput embedding generation for Vector DB corpus fill](https://sf.aitinkerers.org/talks/rsvp_q8DEgURDVzc)

Using an optimized embedding runtime based on TensorRT-LLM, I'll demonstrate high-throughput backfill and low-latency retrieval that benchmarks at up to twice the performance of other embedding runtimes (TEI, vLLM).

- Event context: AI Tinkerers - San Francisco - April Meetup - Sponsored by Comet and SignalFire — 2025-04-24 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_q8DEgURDVzc

### [Building a Conversational MySQL Database System Using Langchain and Google Palm](https://dubai.aitinkerers.org/talks/rsvp_2gMAKIeIBPo)

This demo will showcase a system that allows natural language interaction with a MySQL database using Langchain and Google Palm. The system is designed for TrendVibe Tees, a T-shirt store, and enables store managers to ask questions like "How many white Adidas t-shirts are left in stock?" or "What is the projected revenue if we sell all extra-small t-shirts with discounts?". By converting natural language queries into SQL, the system retrieves accurate data from the MySQL database. The project integrates Hugging Face embeddings, Chromadb as a vector store, and Streamlit for the UI. It also uses few-shot learning to enhance query accuracy over time. TrendVibe Tees Here is a fictional store, I will use it to demonstrate the idea, but the system can be applied to any business. The project is still in progress, and I will share the project URLs (Github, and demo links) after the demo day.

- Event context: AI Tinkerers - Dubai Meetup #2 (October) — 2024-10-05 — Dubai
- Public talk page: https://dubai.aitinkerers.org/talks/rsvp_2gMAKIeIBPo

### [Autonomous Web Agents with Planning and Self-correction](https://palo-alto.aitinkerers.org/talks/rsvp_iggNFATOFJs)

MultiOn's Agent Q sets a new major milestone for autonomous web agents, combining advanced search techniques, AI self-critique, and reinforcement learning to overcome current limitations, representing a substantial leap forward in autonomous agents capabilities. These capabilities allow building really reliable and robust agents, and we are excited to make these available in upcoming launches to our partners

- Event context: AI Tinkerers - Palo Alto - August 2024 @ Groq — 2024-08-23 — Palo Alto
- Public talk page: https://palo-alto.aitinkerers.org/talks/rsvp_iggNFATOFJs

### [Generating SQL using LLMs](https://nyc.aitinkerers.org/talks/rsvp_CHSwRRxJmQQ)

I can give a demo of using RAG to generate accurate SQL for your database. I'll be using the Vanna Python package for orchestration and I can even show it using fully open source components like using Ollama to run your LLM locally and Chroma running locally as a vector storage layer. We can discuss the prompting strategy, various approaches, and anything else that may be related.

- Event context: Live from Civic Hall! AI Tinkerers Meetup | NY#TechWeek — 2024-06-03 — New York City
- Public talk page: https://nyc.aitinkerers.org/talks/rsvp_CHSwRRxJmQQ

### [Long term and short term memory](https://la.aitinkerers.org/talks/rsvp_yDt1OftJcCQ)

Wrote a quick gradio script to use chromadb to act as a long term memory of past conversations. Still a wip, but it works and would like to share it with others. The tool mimics anything-llm but in 250 lines of code. I intend on having web search functionality built in. Basically swap in any openai compatible api endpoint (use text-generation-webui) and you're golden. For the demo, I plan on using openai's endpoint.

- Event context: March 19th - LA AI Tinkerers Meetup & Demos — 2024-03-20 — Los Angeles
- Public talk page: https://la.aitinkerers.org/talks/rsvp_yDt1OftJcCQ

## Related Technologies

- [LangChain](https://aitinkerers.org/technologies/langchain) ([Markdown](https://aitinkerers.org/technologies/langchain.md)) — 445 public demos
- [OpenAI API](https://aitinkerers.org/technologies/openai-api) ([Markdown](https://aitinkerers.org/technologies/openai-api.md)) — 520 public demos
- [Pinecone](https://aitinkerers.org/technologies/pinecone) ([Markdown](https://aitinkerers.org/technologies/pinecone.md)) — 25 public demos
- [FAISS](https://aitinkerers.org/technologies/faiss) ([Markdown](https://aitinkerers.org/technologies/faiss.md)) — 17 public demos
- [GPT-4](https://aitinkerers.org/technologies/gpt-4) ([Markdown](https://aitinkerers.org/technologies/gpt-4.md)) — 529 public demos
- [Streamlit](https://aitinkerers.org/technologies/streamlit) ([Markdown](https://aitinkerers.org/technologies/streamlit.md)) — 89 public demos
- [Adobe XD](https://aitinkerers.org/technologies/adobe-xd) ([Markdown](https://aitinkerers.org/technologies/adobe-xd.md)) — 2 public demos
- [AgentGPT](https://aitinkerers.org/technologies/agentgpt) ([Markdown](https://aitinkerers.org/technologies/agentgpt.md)) — 3 public demos
- [Agent Q](https://aitinkerers.org/technologies/agent-q) ([Markdown](https://aitinkerers.org/technologies/agent-q.md)) — 1 public demo
- [AI Self-critique](https://aitinkerers.org/technologies/ai-self-critique) ([Markdown](https://aitinkerers.org/technologies/ai-self-critique.md)) — 1 public demo
- [Annoy](https://aitinkerers.org/technologies/annoy) ([Markdown](https://aitinkerers.org/technologies/annoy.md)) — 1 public demo
- [Auto-GPT](https://aitinkerers.org/technologies/auto-gpt) ([Markdown](https://aitinkerers.org/technologies/auto-gpt.md)) — 3 public demos
- [Axure RP](https://aitinkerers.org/technologies/axure-rp) ([Markdown](https://aitinkerers.org/technologies/axure-rp.md)) — 1 public demo
- [Balsamiq Mockups](https://aitinkerers.org/technologies/balsamiq-mockups) ([Markdown](https://aitinkerers.org/technologies/balsamiq-mockups.md)) — 1 public demo
- [Baseten](https://aitinkerers.org/technologies/baseten) ([Markdown](https://aitinkerers.org/technologies/baseten.md)) — 2 public demos
- [Figma](https://aitinkerers.org/technologies/figma) ([Markdown](https://aitinkerers.org/technologies/figma.md)) — 6 public demos
- [Framer](https://aitinkerers.org/technologies/framer) ([Markdown](https://aitinkerers.org/technologies/framer.md)) — 2 public demos
- [Gemini models](https://aitinkerers.org/technologies/gemini-models) ([Markdown](https://aitinkerers.org/technologies/gemini-models.md)) — 2 public demos