Unverified50% confidenceFactExact time
The demo system uses Ollama as the local LLM runtime, selects Llama 3.2 3B as the model, and supports two report output formats: JSON and Markdown.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/22/2026
First Seen
Valid until: 1/20/2027
Sources
Related Entities
Related Claims
UnverifiedOllama has supported making models output strictly according to a JSON Schema via the format field in the request since around version 0.1.30.73% similarUnverifiedOllama is an open-source local large-model runtime tool that supports structured output (JSON schema) and can force the model to generate responses in a specified field order.72% similarUnverifiedPocketLedger calls the Qwen2.5-VL 3B model via Ollama for receipt understanding and constrains the output fields with a structured JSON schema.70% similarVerifiedIn the tool-calling mechanism, developers attach a tool description list in JSON Schema format when calling the LLM API, and the model outputs call parameters in structured JSON format67% similarUnverifiedThe Ollama Model node does not support function calling and can only be paired with Basic LLM Chain; for Agent scenarios, one must switch to the Ollama Chat Model node.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1085533API
curl https://kongchang.com/api/v1/knowledge/claims/1085533MCP
get_claim(id=1085533)