implementation

Ingestion Pipeline Setup

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

Linked challenge: Advanced RAG for CAR-T Therapy Optimization with LlamaIndex and Gemini 2.5 Flash

Format

Text-first

Lines

Sections

Linked challenge

Advanced RAG for CAR-T Therapy Optimization with LlamaIndex and Gemini 2.5 Flash

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines

1 sections

No variables

0 checklist items

Using LlamaIndex, write a script to load a PDF directory of CAR-T research. Use `SentenceSplitter` for chunking and initialize the Gemini 2.5 Flash model for embeddings.

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.

Prompt diagnostics

Variables

Lists

Code blocks

Purpose

implementation

This prompt is mostly narrative and instruction-driven, so adapt examples and output constraints before you rewrite the structure.

Linked challenge

Advanced RAG for CAR-T Therapy Optimization with LlamaIndex and Gemini 2.5 Flash

CAR-T cell therapy modeling on-chip has revolutionized our ability to test therapies before they reach patients. However, the complexity of on-chip telemetry data combined with dense literature on chimeric antigen receptors makes it difficult for researchers to optimize treatment protocols. In this challenge, you will use LlamaIndex to build an advanced RAG (Retrieval-Augmented Generation) pipeline. Your task is to ingest high-resolution biological telemetry data from 'on-chip' experiments and combine it with a corpus of Nature Biotechnology research. You will implement a 'Recursive Retriever' pattern in LlamaIndex, using Gemini 2.5 Flash as the backbone model for its high-speed inference and large context window. The system must be able to suggest modifications to CAR-T cell constructs based on simulated 'exhaustion' markers found in the on-chip telemetry data.

Open challenge

Related prompts

Browse library

Problem Definition and Requirements Gathering

To establish a clear understanding of the problem space and define comprehensive requirements for the AI solution.

AI Solution Architecture and Strategy

To create a comprehensive technical architecture and AI strategy that guides the implementation of the solution.

Implementation Plan and MVP Development

To provide a clear, actionable roadmap for implementing the AI solution from concept to deployment.