惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Microsoft Azure Blog
Microsoft Azure Blog
Engineering at Meta
Engineering at Meta
A
About on SuperTechFans
T
The Blog of Author Tim Ferriss
I
InfoQ
博客园_首页
G
Google Developers Blog
爱范儿
爱范儿
Last Week in AI
Last Week in AI
量子位
阮一峰的网络日志
阮一峰的网络日志
雷峰网
雷峰网
酷 壳 – CoolShell
酷 壳 – CoolShell
Vercel News
Vercel News
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
GbyAI
GbyAI
月光博客
月光博客
The GitHub Blog
The GitHub Blog
V
Visual Studio Blog
N
Netflix TechBlog - Medium
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
博客园 - 司徒正美
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 聂微东

LangChain Forum - Latest posts

Prompt_cache_retention: '24h' supported in langchain agents and where to provide it, inside invoke or while creating client? Could RAG pipelines realistically cause deployment timeouts, is Render suitable for first-time RAG deployments? How do I use langchain_postgres' init_vectorstore_table correctly? Proposal: Graph-wide default error handler for StateGraph (fallback for nodes without error_handler) Support timedelta for CachePolicy.ttl, consistent with TimeoutPolicy Question about LangSmith Trace Search via API How to cancel a run correct !! Anyone confirms this issue that deepagent ui streaming is disturb by update in deepagent or bug issue Would pre-inference routing help long-context agent workflows? Best Stack for Building AI Applications Question about LangSmith Trace Search Seeking help regarding the connection between Websocket and tool calls Tool invocation error with empty error message when using `InjectedState` + `Command` return in async tool How to use @langchain/react FileSystem middleware Using ChatSnowflake with agents Built llmsessioncontract on AgentMiddleware: runtime enforcement of tool-call protocols — feedback wanted DeltaChannelHistory not found in langgraph-api:3.12 Improving citation accuracy and reducing hallucinations in custom Parent-Child RAG pipeline (Gemma3:4B + FAISS+BM25 + Cross-encoder reranker) Metadata filter not filtering for alerts Connecting the Slack integration fails with invalid_team_for_non_distributed_app Trouble understanding and editing experiment summary evaluators feedbacks SSL certificate error from httpx with LangGraph server WikipediaLoader endup in JSONDecodeError Human-in-the-loop approval dashboard for LangGraph agents — open source, free to deploy Should interrupt() be split into two primitives — one for human input, one for s2s data fetching? How are people handling data governance across agent handoffs in production? Feature Request: @task metadata Research: Friction Points in Agentic Commerce Transactions How should I provide an agent to a LangGraph server?
How to register type in langgraph
sog · 2026-04-20 · via LangChain Forum - Latest posts

1

I met this warning:
Deserializing unregistered type src.schemas.resume_models.QuestionRecord from checkpoint. This will be blocked in a future version. Add to allowed_msgpack_modules to silence: [(‘src.schemas.resume_models’, ‘QuestionRecord’)]
I used os.environ[“LANGCHAIN_ALLOWED_MSGPACK_MODULES”] = “src.schemas.resume_models” at the top of entry file of my project but no effects.
So how to elimate this warning?

versions:
langchain-core 1.2.23
langchain-openai 1.1.12
langgraph 1.1.4
langgraph-checkpoint 4.0.1
langgraph-checkpoint-sqlite 3.0.3
langgraph-prebuilt 1.0.8
langgraph-sdk 0.3.12
langsmith 0.7.23

hi @sog

what I can see in the source code, the env var LANGCHAIN_ALLOWED_MSGPACK_MODULES doesn’t exist. Only LANGGRAPH_STRICT_MSGPACK is read - it’s a boolean, parsed once at import time and cannot carry module names.

Try this: register types via the Python API and wire the serializer into the checkpointer:

  from langgraph.checkpoint.sqlite import SqliteSaver
  from langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer
  from src.schemas.resume_models import QuestionRecord

  serde = JsonPlusSerializer(allowed_msgpack_modules=[QuestionRecord])
  checkpointer = SqliteSaver(conn, serde=serde)  # or set checkpointer.serde = serde