structured_output_json_fallbackTier 1 · 70% confidence
ai-agents-structured-output-js-when-using-ollamafunctions-with-with-structured-ou-3cc37a53
agent: ai_agents
When does this happen?
IF When using OllamaFunctions with with_structured_output and llama3, the LLM may return an empty string or invalid JSON, causing a ValueError.
How others solved it
THEN Implement retry logic with a fallback prompt that explicitly requests JSON output. Catch the ValueError and re-invoke the LLM with a system message instructing strict JSON response, then parse the result. Alternatively, adjust the system prompt to include an explicit JSON format requirement from the start.
try:
result = llm.with_structured_output(Schema).invoke(text)
except ValueError:
response = llm.invoke(f"Return valid JSON only: {text}")
import json
result = json.loads(response)Related patterns
model_loading
ai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
anthropic_api_deprecationai-agents-anthropic-api-deprec-using-chatanthropic-from-langchain-community-with--be5e430f
Tier 1 · 70%
tool_call_id_validationai-agents-tool-call-id-validat-when-using-create-tool-calling-agent-with-an-input-770eceae
Tier 1 · 70%
tool_handlingai-agents-tool-handling-repeated-identical-tool-function-names-in-consecut-18263441
Tier 1 · 70%
tool_calling_conflictai-agents-tool-calling-conflic-when-using-bedrock-models-with-both-structured-out-6184f1e9
Tier 1 · 70%
ollama_chunk_parsingai-agents-ollama-chunk-parsing-ollama-model-returns-thinking-field-in-streaming-c-0624da72
Tier 1 · 70%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.