# \#python-help

**URL:** https://forum.langchain.com/tag/python-help/12.md

[Latest](https://forum.langchain.com/latest.md) · [Categories](https://forum.langchain.com/categories.md) · [Tags](https://forum.langchain.com/tags.md)

---

## [How to pass a "runtime args" to a graph node?](https://forum.langchain.com/t/how-to-pass-a-runtime-args-to-a-graph-node/4750)

<div class="topic-metadata">

**Author:** [@MSJavaScript](https://forum.langchain.com/u/MSJavaScript)\
**Replies:** 0\
**Last updated:** [October 15, 2026, 3:10am UTC](https://forum.langchain.com/t/how-to-pass-a-runtime-args-to-a-graph-node/4750 "2026-10-15T03:10:06Z")

</div>

Hello. I have a planner node, and I want it accept some runtime args, for example: def planner\_node(state:MainState, args:dict): pass This node may make (1) A fresh plan, without any dependence of previous steps. …

---

## [Agent passes wrong data for the tool](https://forum.langchain.com/t/agent-passes-wrong-data-for-the-tool/4731)

<div class="topic-metadata">

**Author:** [@piotrmorek](https://forum.langchain.com/u/piotrmorek)\
**Replies:** 9\
**Last updated:** [October 14, 2026, 6:55pm UTC](https://forum.langchain.com/t/agent-passes-wrong-data-for-the-tool/4731 "2026-10-14T18:55:43Z")

</div>

Quick question, I have an agent (typical ReAct agent, system prompt + some tools to get the job done) that gets a list of entities, user select one entity by typing eg. “the 3rd one”, then agent needs to call another too…

---

## [RAG Pipeline for industries](https://forum.langchain.com/t/rag-pipeline-for-industries/4718)

<div class="topic-metadata">

**Author:** [@dip\_gohil](https://forum.langchain.com/u/dip_gohil)\
**Replies:** 5\
**Last updated:** [October 12, 2026, 10:21am UTC](https://forum.langchain.com/t/rag-pipeline-for-industries/4718 "2026-10-12T10:21:47Z")

</div>

Everyone knows that when we discuss about any AI services or solutions there’s always a word comes which is RAG. But issue is not how we implement it or how we build it, the main issue is by which architecture you’ll bu…

---

## [feat(core): forward document metadata to embedding implementations to enable multimodal providers](https://forum.langchain.com/t/feat-core-forward-document-metadata-to-embedding-implementations-to-enable-multimodal-providers/3924)

<div class="topic-metadata">

**Author:** [@VedantSonani](https://forum.langchain.com/u/VedantSonani)\
**Replies:** 3\
**Last updated:** [October 10, 2026, 9:24am UTC](https://forum.langchain.com/t/feat-core-forward-document-metadata-to-embedding-implementations-to-enable-multimodal-providers/3924 "2026-10-10T09:24:02Z")

</div>

Background Several embedding providers now support multimodal inputs — text, images, audio, and video — in the same embedding space: Gemini Embedding 2 (gemini-embedding-2-preview) — text, images, video, audio, PDFs Vo…

---

## [How to implement Dynamic Runtime Subagents in DeepAgents + LangGraph](https://forum.langchain.com/t/how-to-implement-dynamic-runtime-subagents-in-deepagents-langgraph/4607)

<div class="topic-metadata">

**Author:** [@mrsknetwork](https://forum.langchain.com/u/mrsknetwork)\
**Replies:** 5\
**Last updated:** [October 7, 2026, 4:34pm UTC](https://forum.langchain.com/t/how-to-implement-dynamic-runtime-subagents-in-deepagents-langgraph/4607 "2026-10-07T16:34:52Z")

</div>

Hi everyone, I’m trying to understand the best way to implement dynamically generated subagents at runtime. My goal is slightly different from the standard DeepAgents subagent pattern. Instead of predefining all subage…

---

## [Extending checkpoint schema with user\_id/agent\_id for cross-thread querying — trade-offs vs Thread Registry?](https://forum.langchain.com/t/extending-checkpoint-schema-with-user-id-agent-id-for-cross-thread-querying-trade-offs-vs-thread-registry/4429)

<div class="topic-metadata">

**Author:** [@santosh-nallur](https://forum.langchain.com/u/santosh-nallur)\
**Replies:** 6\
**Last updated:** [October 7, 2026, 2:28pm UTC](https://forum.langchain.com/t/extending-checkpoint-schema-with-user-id-agent-id-for-cross-thread-querying-trade-offs-vs-thread-registry/4429 "2026-10-07T14:28:50Z")

</div>

Hi Team, I want to gather opinion on one of our requirements related to LangGraph. I found a similar discussion here where this is discussed at length and provides useful insights, but I have more specific questions. U…

---

## [Does langchain provides classes for multimodal output models or for simplicity models with image only output like GPT-Image-2? Is the ChatOpenAI() going to work for GPT-Image-2 model?](https://forum.langchain.com/t/does-langchain-provides-classes-for-multimodal-output-models-or-for-simplicity-models-with-image-only-output-like-gpt-image-2-is-the-chatopenai-going-to-work-for-gpt-image-2-model/4698)

<div class="topic-metadata">

**Author:** [@shubhamkala06](https://forum.langchain.com/u/shubhamkala06)\
**Replies:** 4\
**Last updated:** [October 7, 2026, 6:35am UTC](https://forum.langchain.com/t/does-langchain-provides-classes-for-multimodal-output-models-or-for-simplicity-models-with-image-only-output-like-gpt-image-2-is-the-chatopenai-going-to-work-for-gpt-image-2-model/4698 "2026-10-07T06:35:35Z")

</div>

I have been trying to figure out that is it possible that a model response can be a image block or any other block other than the text block. So can a model response give an image block like this- { "type": "image…

---

## [Sonnet-5.5 through \`ChatOpenAI\`](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672)

<div class="topic-metadata">

**Author:** [@saqlain2204](https://forum.langchain.com/u/saqlain2204)\
**Replies:** 4\
**Last updated:** [October 6, 2026, 1:42pm UTC](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672 "2026-10-06T13:42:09Z")

</div>

Hi LangChain Community, A while ago Anthropic launched 5.5 and I was trying to access to access it thorugh ChatOpenAI wrapper. The migration docs explicitly state that on passing thinking.type as disabled we would be en…

---

## [AgentLens — free, local-only CLI to audit what your LangChain agent actually did](https://forum.langchain.com/t/agentlens-free-local-only-cli-to-audit-what-your-langchain-agent-actually-did/4551)

<div class="topic-metadata">

**Author:** [@subhash-0000](https://forum.langchain.com/u/subhash-0000)\
**Replies:** 3\
**Last updated:** [October 4, 2026, 12:52pm UTC](https://forum.langchain.com/t/agentlens-free-local-only-cli-to-audit-what-your-langchain-agent-actually-did/4551 "2026-10-04T12:52:44Z")

</div>

Been building with LangChain agents and kept running into the same problem: once an agent runs, I have no real record of what it decided, which tools it called, why, how long each step took, or what it cost. If something…

---

## [Langchain-text-splitters release](https://forum.langchain.com/t/langchain-text-splitters-release/4675)

<div class="topic-metadata">

**Author:** [@Ben10](https://forum.langchain.com/u/Ben10)\
**Replies:** 1\
**Last updated:** [October 2, 2026, 3:38pm UTC](https://forum.langchain.com/t/langchain-text-splitters-release/4675 "2026-10-02T15:38:17Z")

</div>

Hello, langchain-text-splitter package introduced lazy loading of heavy dependency, I was wondering if a release was planned, or whats the release policy of that sort of package? Thanks!

---

## [Unable to apply discount coupon while booking LCAE exam](https://forum.langchain.com/t/unable-to-apply-discount-coupon-while-booking-lcae-exam/4633)

<div class="topic-metadata">

**Author:** [@cjcheema](https://forum.langchain.com/u/cjcheema)\
**Replies:** 4\
**Last updated:** [October 1, 2026, 7:51pm UTC](https://forum.langchain.com/t/unable-to-apply-discount-coupon-while-booking-lcae-exam/4633 "2026-10-01T19:51:47Z")

</div>

Hi Team I am trying to use discount code LCAE50 while booking the LCAE exam but it is showing me an invalid coupon code: Therefore, can you please share me the similar discount code so that I can book the exam now. …

---

## [What is the right way to conditionally interrupt](https://forum.langchain.com/t/what-is-the-right-way-to-conditionally-interrupt/4637)

<div class="topic-metadata">

**Author:** [@MSJavaScript](https://forum.langchain.com/u/MSJavaScript)\
**Replies:** 4\
**Last updated:** [October 1, 2026, 4:26pm UTC](https://forum.langchain.com/t/what-is-the-right-way-to-conditionally-interrupt/4637 "2026-10-01T16:26:22Z")

</div>

The langgraph manual said " Do not conditionally skip interrupt calls within a node", but I do have some situations in which I need to conditionally interrupt. For example, I have a very complex tool def generate\_elemen…

---

## [Question on Open Github Issue #7345: Status of configurable PostgreSQL schema](https://forum.langchain.com/t/question-on-open-github-issue-7345-status-of-configurable-postgresql-schema/4558)

<div class="topic-metadata">

**Author:** [@alive](https://forum.langchain.com/u/alive)\
**Replies:** 1\
**Last updated:** [September 18, 2026, 2:28pm UTC](https://forum.langchain.com/t/question-on-open-github-issue-7345-status-of-configurable-postgresql-schema/4558 "2026-09-18T14:28:22Z")

</div>

Hey everyone! :waving\_hand: Quick question regarding Issue #7345 (“Configurable PostgreSQL schema for langgraph-checkpoint-postgres”): https://github.com/langchain-ai/langgraph/issues/7345 It looks like there has been…

---

## [A problem of agent architecture](https://forum.langchain.com/t/a-problem-of-agent-architecture/4546)

<div class="topic-metadata">

**Author:** [@MSJavaScript](https://forum.langchain.com/u/MSJavaScript)\
**Replies:** 3\
**Last updated:** [September 16, 2026, 11:52pm UTC](https://forum.langchain.com/t/a-problem-of-agent-architecture/4546 "2026-09-16T23:52:28Z")

</div>

Hello, I am building an agent with architecture like below ModelNode reads skill docs and makes plans and assigns tasks to executor agent. My concern is, the executor is called by agent.invoke(messages), but the Mode…

---

## [The Right Solution/Architecture?](https://forum.langchain.com/t/the-right-solution-architecture/4522)

<div class="topic-metadata">

**Author:** [@ipatchcables](https://forum.langchain.com/u/ipatchcables)\
**Replies:** 3\
**Last updated:** [September 13, 2026, 12:27am UTC](https://forum.langchain.com/t/the-right-solution-architecture/4522 "2026-09-13T00:27:41Z")

</div>

I’m trying to build out a project that helps automate web testing work (I’m a dev - 100s over servers internally). I’m curious what approach would work best? I know it can’t be fully non-deterministic, but curious what t…

---

## [How are you guys stopping agents from silent loops/stampedes? Standard step\_counters feel like garbage](https://forum.langchain.com/t/how-are-you-guys-stopping-agents-from-silent-loops-stampedes-standard-step-counters-feel-like-garbage/4479)

<div class="topic-metadata">

**Author:** [@minakshihub](https://forum.langchain.com/u/minakshihub)\
**Replies:** 2\
**Last updated:** [September 14, 2026, 5:14pm UTC](https://forum.langchain.com/t/how-are-you-guys-stopping-agents-from-silent-loops-stampedes-standard-step-counters-feel-like-garbage/4479 "2026-09-14T17:14:06Z")

</div>

I’ve been looking at multi-agent failure states, and it seems like everyone is relying on basic Python step\_counters or LLM prompt-engineering (“do not repeat yourself”) to prevent agents from falling into infinite tool-…

---

## [Ephemeral Subagent Task - Deep Agent](https://forum.langchain.com/t/ephemeral-subagent-task-deep-agent/4518)

<div class="topic-metadata">

**Author:** [@ipatchcables](https://forum.langchain.com/u/ipatchcables)\
**Replies:** 2\
**Last updated:** [September 10, 2026, 1:55pm UTC](https://forum.langchain.com/t/ephemeral-subagent-task-deep-agent/4518 "2026-09-10T13:55:06Z")

</div>

Random task executes a dynamic subagent? AFAIK, this shouldn’t happen if you aren’t using CodeInterpreterMiddleware Really curious about this. ? Dynamic subagents - Docs by LangChain

---

## [Does HITL approval actually bind the action that reaches the executor?](https://forum.langchain.com/t/does-hitl-approval-actually-bind-the-action-that-reaches-the-executor/4517)

<div class="topic-metadata">

**Author:** [@Brodin2001](https://forum.langchain.com/u/Brodin2001)\
**Replies:** 2\
**Last updated:** [September 10, 2026, 12:11pm UTC](https://forum.langchain.com/t/does-hitl-approval-actually-bind-the-action-that-reaches-the-executor/4517 "2026-09-10T12:11:26Z")

</div>

Hey guys, I’ve been testing a failure mode in agent authorization that I’m not sure is getting enough attention. We usually model the flow as: agent proposes → human approves → tool executes But I think there are actu…

---

## [How are you handling governance for production LangChain agents? (PII, cost caps, tool safety)](https://forum.langchain.com/t/how-are-you-handling-governance-for-production-langchain-agents-pii-cost-caps-tool-safety/4315)

<div class="topic-metadata">

**Author:** [@nagasatish](https://forum.langchain.com/u/nagasatish)\
**Replies:** 5\
**Last updated:** [September 10, 2026, 11:21am UTC](https://forum.langchain.com/t/how-are-you-handling-governance-for-production-langchain-agents-pii-cost-caps-tool-safety/4315 "2026-09-10T11:21:19Z")

</div>

Curious how others are approaching governance for LangChain agents in production — specifically: PII leaking through RAG pipelines When a retriever pulls documents containing customer data (SSNs, emails, credit cards)…

---

## [Feature request: let a add\_conditional\_edges branch write into an existing add\_edge(\[...\], dest) barrier](https://forum.langchain.com/t/feature-request-let-a-add-conditional-edges-branch-write-into-an-existing-add-edge-dest-barrier/4513)

<div class="topic-metadata">

**Author:** [@AlejandroTorresMunoz](https://forum.langchain.com/u/AlejandroTorresMunoz)\
**Replies:** 0\
**Last updated:** [September 9, 2026, 9:11am UTC](https://forum.langchain.com/t/feature-request-let-a-add-conditional-edges-branch-write-into-an-existing-add-edge-dest-barrier/4513 "2026-09-09T09:11:36Z")

</div>

The gap add\_edge(\[source1, source2, ...\], dest) creates a NamedBarrierValue channel: dest becomes a real AND-join, firing only once every named source has written to it since it last fired. This works great, as long as e…

---

## [How to get structured output when using astream() or stream()](https://forum.langchain.com/t/how-to-get-structured-output-when-using-astream-or-stream/4509)

<div class="topic-metadata">

**Author:** [@MSJavaScript](https://forum.langchain.com/u/MSJavaScript)\
**Replies:** 1\
**Last updated:** [September 8, 2026, 11:06am UTC](https://forum.langchain.com/t/how-to-get-structured-output-when-using-astream-or-stream/4509 "2026-09-08T11:06:35Z")

</div>

Hello, I am using agent.astream() to print streaming message, but I don’t know how to get structured output like agent.invoke(). Anyone has some ideas ? def print\_msg(msg): if isinstance(msg, AIMessage): pr…

---

## [Production use of PostgresSaver: service-owned migrations and checkpoint retention in Node.js](https://forum.langchain.com/t/production-use-of-postgressaver-service-owned-migrations-and-checkpoint-retention-in-node-js/4481)

<div class="topic-metadata">

**Author:** [@waiz-ksolves](https://forum.langchain.com/u/waiz-ksolves)\
**Replies:** 2\
**Last updated:** [September 4, 2026, 2:16pm UTC](https://forum.langchain.com/t/production-use-of-postgressaver-service-owned-migrations-and-checkpoint-retention-in-node-js/4481 "2026-09-04T14:16:30Z")

</div>

We are planning to use @langchain/langgraph-checkpoint-postgres in a production Node.js service and have a few questions about the recommended database ownership and retention model. Our service team normally owns all P…

---

## [Tool call and structured ouput](https://forum.langchain.com/t/tool-call-and-structured-ouput/1891)

<div class="topic-metadata">

**Author:** [@yugandhar](https://forum.langchain.com/u/yugandhar)\
**Replies:** 5\
**Last updated:** [September 3, 2026, 9:20am UTC](https://forum.langchain.com/t/tool-call-and-structured-ouput/1891 "2026-09-03T09:20:20Z")

</div>

I’m new to langchain. I’m using a model in Standalone mode. In this i have defined a tools and output structures I’m using Langchain V1 import os import dotenv from langchain.chat\_models import init\_chat\_model from la…

---

## [Retrieved context vs what the answer actually used: gap in agent traces](https://forum.langchain.com/t/retrieved-context-vs-what-the-answer-actually-used-gap-in-agent-traces/4484)

<div class="topic-metadata">

**Author:** [@Kcodess2807](https://forum.langchain.com/u/Kcodess2807)\
**Replies:** 0\
**Last updated:** [September 3, 2026, 8:17am UTC](https://forum.langchain.com/t/retrieved-context-vs-what-the-answer-actually-used-gap-in-agent-traces/4484 "2026-09-03T08:17:34Z")

</div>

hey just wanted to float a gap i keep hitting while shipping langgraph rag / graphrag agents. langsmith (and other tracers) already show the retriever span and the docs that came back. that's useful. what i still can'…

---

## [Can you provide a learning roadmap for LangChain and LangGraph suitable for beginners?](https://forum.langchain.com/t/can-you-provide-a-learning-roadmap-for-langchain-and-langgraph-suitable-for-beginners/3075)

<div class="topic-metadata">

**Author:** [@Huimin-station](https://forum.langchain.com/u/Huimin-station)\
**Replies:** 4\
**Last updated:** [September 2, 2026, 5:36pm UTC](https://forum.langchain.com/t/can-you-provide-a-learning-roadmap-for-langchain-and-langgraph-suitable-for-beginners/3075 "2026-09-02T17:36:27Z")

</div>

Since I am a novice developer, my learning direction is relatively unclear. I hope to get a relatively complete and clear learning roadmap. I would be very grateful if you could provide a learning plan.

---

## [How to configure thread/checkpointer TTL when deploying the LangGraph Server with Docker using environment variables?](https://forum.langchain.com/t/how-to-configure-thread-checkpointer-ttl-when-deploying-the-langgraph-server-with-docker-using-environment-variables/4253)

<div class="topic-metadata">

**Author:** [@gdrouet](https://forum.langchain.com/u/gdrouet)\
**Replies:** 9\
**Last updated:** [September 2, 2026, 5:34pm UTC](https://forum.langchain.com/t/how-to-configure-thread-checkpointer-ttl-when-deploying-the-langgraph-server-with-docker-using-environment-variables/4253 "2026-09-02T17:34:11Z")

</div>

Hi everyone, I’m deploying a LangGraph Server using Docker. Instead of providing a langgraph.json file, my deployment config is generated entirely from environment variables (similar to how variables like LANGSERVE\_GRA…

---

## [Feature Request: Dgraph Integration for LangGraph](https://forum.langchain.com/t/feature-request-dgraph-integration-for-langgraph/4477)

<div class="topic-metadata">

**Author:** [@LakshimiRam-073](https://forum.langchain.com/u/LakshimiRam-073)\
**Replies:** 0\
**Last updated:** [September 2, 2026, 5:31pm UTC](https://forum.langchain.com/t/feature-request-dgraph-integration-for-langgraph/4477 "2026-09-02T17:31:50Z")

</div>

We are evaluating Dgraph as a graph database for our GraphRAG use case and would like to have a native Dgraph integration/client in LangGraph, similar to the existing Neo4j integration. The integration would ideally sup…

---

## [Can somebody suggest books to learn LangChain?](https://forum.langchain.com/t/can-somebody-suggest-books-to-learn-langchain/4395)

<div class="topic-metadata">

**Author:** [@rajtilakjee](https://forum.langchain.com/u/rajtilakjee)\
**Replies:** 6\
**Last updated:** [September 2, 2026, 4:55pm UTC](https://forum.langchain.com/t/can-somebody-suggest-books-to-learn-langchain/4395 "2026-09-02T16:55:23Z")

</div>

Can somebody suggest a good book that is updated to a recent version of LangChain and teaches the basics of LangChain in Python? Before you suggest that I look up the documentation, I did but I learn from books better.

---

## [How to modify specific item in a State](https://forum.langchain.com/t/how-to-modify-specific-item-in-a-state/4428)

<div class="topic-metadata">

**Author:** [@MSJavaScript](https://forum.langchain.com/u/MSJavaScript)\
**Replies:** 4\
**Last updated:** [September 2, 2026, 4:53pm UTC](https://forum.langchain.com/t/how-to-modify-specific-item-in-a-state/4428 "2026-09-02T16:53:12Z")

</div>

Suppose my state is something like class MyState(BaseModel): data:List\[List\[int\]\] How to update this state in a graph node ? Is there a standard way to do this? Note that there may be multiple nodes which update t…

---

## [Starting AI career — what projects should I build after learning Python + ML basics?](https://forum.langchain.com/t/starting-ai-career-what-projects-should-i-build-after-learning-python-ml-basics/3019)

<div class="topic-metadata">

**Author:** [@ManuManohar](https://forum.langchain.com/u/ManuManohar)\
**Replies:** 3\
**Last updated:** [September 2, 2026, 11:24am UTC](https://forum.langchain.com/t/starting-ai-career-what-projects-should-i-build-after-learning-python-ml-basics/3019 "2026-09-02T11:24:33Z")

</div>

Hi everyone, I’m starting my journey toward becoming an AI engineer and currently learning Python and ML fundamentals. I’d love advice from people working with LangChain or LLM apps: What projects should I build next …

[Next page](https://forum.langchain.com/tag/python-help/12.md?match_all_tags=true&page=1&tags%5B%5D=python-help)
