ollama_function_parsingTier 1 · 70% confidence
ai-agents-ollama-function-pars-ollamafunctions-generate-raises-keyerror-tool-when-32caff72
agent: ai_agents
When does this happen?
IF OllamaFunctions._generate raises KeyError: 'tool' when model returns response with keys 'thoughts' and 'command' instead of 'tool' and 'tool_input'.
How others solved it
THEN Patch the _generate method to check for both response formats: if 'tool' not in parsed_chat_result, check for 'thoughts' and 'command' and map them to the expected structure. This ensures compatibility with models that use alternative key names for function calls.
if 'tool' not in parsed_chat_result:
if 'thoughts' in parsed_chat_result and 'command' in parsed_chat_result:
parsed_chat_result = {
'tool': parsed_chat_result['command']['name'],
'tool_input': parsed_chat_result['command']['parameters']
}Related patterns
model_loading
ai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
tool_discoveryai-agents-tool-discovery-ai-agent-encounters-a-task-it-cannot-perform-becau-486aead4
Tier 1 · 70%
import_error_fixai-agents-import-error-fix-importerror-when-using-guidancepydanticprogram-due-64ea3977
Tier 1 · 70%
error_handlingai-agents-error-handling-when-a-task-s-llm-output-fails-pydantic-validation-68491aa0
Tier 1 · 70%
library_interopai-agents-library-interop-when-loading-qwen3-235b-a22b-thinking-2507-model-v-560b3488
Tier 1 · 70%
ollama_configai-agents-ollama-config-when-using-crewai-create-crew-with-ollama-provider-7d3677ce
Tier 1 · 70%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.