Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

LangChain 1.0 model calls (Claude, GPT, Gemini) v1.0.0

Use this resource to call Claude, GPT-4o or Gemini through LangChain 1.0 without format pitfalls

New

  • 580 downloads
  • 126 likes
  • 142 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install langchain-model-inference-patterns

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent initializes models with version-safe defaults, reads message content as typed blocks, routes calls through a factory and picks the right structured-output method. You avoid crashes from list-shaped content and token counting mistakes.

Mostly picked by

Updated November 2, 2026

Card for the “LangChain 1.0 model calls (Claude, GPT, Gemini)” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: initialization, content blocks, routing and structured output
  • references/provider-quirks.md: provider-specific behaviour
  • references/token-accounting.md: token counting while streaming
  • references/structured-output-methods.md: structured output methods

Good fit for

  • Your code crashes when message content comes back as a list
  • You switch model provider without rewriting your calls

Not for

    Tags

    • langchain
    • models
    • structured output
    • tokens

    About

    You say

    “Write a LangChain factory that calls Claude or GPT-4o depending on the config and returns a structured object.”

    Card for the “LangChain 1.0 model calls (Claude, GPT, Gemini)” skill

    Skill published by Jeremy Longshore <jeremy@intentsolutions.io> under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to call Claude, GPT-4o or Gemini through LangChain 1.0 without format pitfalls
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/content-blocks.md3.8 KB
    • references/one-pager.md2.6 KB
    • references/provider-quirks.md4 KB
    • references/structured-output-methods.md4 KB
    • references/token-accounting.md4.4 KB
    • SKILL.md10.8 KB

    Origin and licence

    Listed unmodified

    Author
    Jeremy Longshore <jeremy@intentsolutions.io>
    Source
    github.com/jeremylongshore/tons-of-skills-marketplace/tree/ab85a061f7bcc039dac13ee193de7a4cd4388571/skills/.curated/langchain-model-inference
    Licence
    MIT

    Notice

    « langchain-model-inference » (Jeremy Longshore <jeremy@intentsolutions.io>, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.