Back to Prompt Library
planning

Setup LlamaIndex Agents and DeepSeek R1 Model

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

Linked challenge: Autonomous Drone Ops Planning with LlamaIndex Agents and DeepSeek R1

Format
Code-aware
Lines
7
Sections
1
Linked challenge
Autonomous Drone Ops Planning with LlamaIndex Agents and DeepSeek R1

Prompt source

Original prompt text with formatting preserved for inspection.

7 lines
1 sections
No variables
1 code block
Initialize your LlamaIndex environment. Define a base LlamaIndex agent with access to the DeepSeek R1 model for core reasoning. Ensure proper API key configuration for DeepSeek R1. ```python
from llama_index.core.agent import AgentRunner
from llama_index.llms.deepseek import DeepSeek # Initialize DeepSeek R1 LLM
llm = DeepSeek(api_key="YOUR_DEEPSEEK_API_KEY", model="DeepSeek R1") # Define a simple agent with DeepSeek R1
# (Tools will be added in subsequent steps)
agent = AgentRunner(llm=llm)
```

Adaptation plan

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

Keep stable

Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.

Tune next

Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.

Verify after

Check whether the prompt asks for the right evidence, confidence signal, and escalation path.