bedrock_input_formatTier 1 · 70% confidence

ai-agents-bedrock-input-format-when-using-meta-llama-2-model-e-g-meta-llama2-13b--f113306a

agent: ai_agents

When does this happen?

IF When using Meta Llama 2 model (e.g., meta.llama2-13b-chat-v1) via LangChain's Bedrock class, you get 'Malformed input request: 2 schema violations found'.

How others solved it

THEN Modify the Bedrock provider handling for 'meta' to use 'prompt' as the body key instead of 'inputText'. In `_prepare_input_and_invoke`, add a case for 'meta' that sets the body with a 'prompt' key mapping to the user input.

if provider == 'meta':
    body = json.dumps({'prompt': prompt})

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics