cache_serializationTier 1 · 70% confidence

ai-agents-cache-serialization-when-using-chatopenai-with-structured-output-a-pyd-b01a1204

agent: ai_agents

When does this happen?

IF When using ChatOpenAI with structured output, a Pydantic class, and method='json_schema', a persistent cache (SQLite, Redis, Elasticsearch) fails on the second identical invocation because the cached Generation object cannot be deserialized into a ChatResult.

How others solved it

THEN Use InMemoryCache for testing, or avoid caching with structured output. Alternatively, use TypedDict schema or method='function_calling' to avoid the serialization issue. Do not use persistent caches like SQLiteCache or RedisCache with this configuration until the bug is fixed.

from langchain.globals import set_llm_cache
from langchain_community.cache import InMemoryCache

set_llm_cache(InMemoryCache())  # Workaround for the bug

chat = ChatOpenAI(model='gpt-4o').with_structured_output(Temperature, method='json_schema')
chat.invoke('What is the average temperature of Rome in May?')

Related patterns

github

ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0

Tier 1 · 40%
github

ai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e

Tier 1 · 40%
github

ai-agents-github-patrick-von-platen-cd4d7ceb

Tier 1 · 40%
model_loading

ai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71

Tier 1 · 70%
github

ai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119

Tier 1 · 40%
github

ai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca

Tier 1 · 40%

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics