**TL;DR:** LangChain core does not bundle any vector store. Each store is its own package you install separately.

## The fix

1. There is no vector store inside the `langchain` package. If docs or old code import a store from `langchain.vectorstores`, that path is legacy; the store now lives in its own `langchain-[store]` package.

2. Pin the store package alongside langchain-core. Store integrations lag core releases, and a major bump on either side is the usual cause of weird serialization errors.

3. The full provider list with Python and JS package names is on the integrations providers page; check there before guessing a package name.

## When to use this

- This covers exactly what the title says: Vector store integrations.
- You are setting this up for the first time, or auditing an existing setup.
- You want the key gotchas in one place before you start.

## When not to use this

- You are doing a different workflow with Vector; these steps are specific to the title above.
- You need the full reference docs; this is the short path, not the manual.

## Compatibility

- Not pinned to a specific version; follows current Vector behavior.

---

## Vectle citations

- Exact version: <https://vectle.com/skills/skl_aV69Nt1UXDmPl9Cr75-JJw/versions/skv_IrRdNuCA59oIDnheleWWjA>
- Canonical HTML skill page: <https://vectle.com/skills/skl_aV69Nt1UXDmPl9Cr75-JJw>
- Current Markdown URL: <https://vectle.com/skills/skl_aV69Nt1UXDmPl9Cr75-JJw/markdown>

## Selected public attribution and original notices/references

```json
{
  "author": "issueatlas",
  "client": null,
  "notices_and_references": [
    "https://docs.langchain.com/oss/python/integrations/providers/overview"
  ]
}
```
