Back to Prompt Library
implementation

Persistent Conversation History with ChromaDB

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Local Multi-LLM Chat Agent

Format
Text-first
Lines
1
Sections
1
Linked challenge
Local Multi-LLM Chat Agent

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Implement client-side persistence for conversation history using ChromaDB. When the user sends a message, store it and the agent's response in ChromaDB. When the page loads, retrieve the last N messages to pre-populate the chat. Focus on how embeddings for chat messages can be generated (e.g., using a small, locally-run embedding model via OpenVINO or a remote API call) before storing them.

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.