You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/templates/docs/LAUNCHING_PACKAGE.md

42 lines
1.4 KiB
Markdown

# Launching LangServe from a Package
You can also launch LangServe directly from a package, without having to pull it into a project.
This can be useful when you are developing a package and want to test it quickly.
The downside of this is that it gives you a little less control over how the LangServe APIs are configured,
which is why for proper projects we recommend creating a full project.
In order to do this, first change your working directory to the package itself.
For example, if you are currently in this `templates` module, you can go into the `pirate-speak` package with:
```shell
cd pirate-speak
```
Inside this package there is a `pyproject.toml` file.
This file contains a `tool.langchain` section that contains information on how this package should be used.
For example, in `pirate-speak` we see:
```text
[tool.langserve]
export_module = "pirate_speak.chain"
export_attr = "chain"
```
This information can be used to launch a LangServe instance automatically.
In order to do this, first make sure the CLI is installed:
```shell
pip install -U langchain-cli
```
You can then run:
```shell
langchain template serve
```
This will spin up endpoints, documentation, and playground for this chain.
For example, you can access the playground at [http://127.0.0.1:8000/playground/](http://127.0.0.1:8000/playground/)
Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) **Description:** Batch update of alt text and title attributes for images in `md` & `mdx` files across the repo using [alttexter](https://github.com/jonathanalgar/alttexter)/[alttexter-ghclient](https://github.com/jonathanalgar/alttexter-ghclient) (built using LangChain/LangSmith). **Limitation:** cannot update `ipynb` files because of [this issue](https://github.com/langchain-ai/langchain/pull/15357#issuecomment-1885037250). Can revisit when Docusaurus is bumped to v3. I checked all the generated alt texts and titles and didn't find any technical inaccuracies. That's not to say they're _perfect_, but a lot better than what's there currently. [Deployed](https://langchain-819yf1tbk-langchain.vercel.app/docs/modules/model_io/) image example: ![chrome_yZQ7BF2GTj](https://github.com/langchain-ai/langchain/assets/93204286/43a9a4d4-70fd-41c4-8978-b6240ff63ffa) You can see LangSmith traces for all the calls out to the LLM in the PRs merged into this one: * https://github.com/jonathanalgar/langchain/pull/6 * https://github.com/jonathanalgar/langchain/pull/4 * https://github.com/jonathanalgar/langchain/pull/3 I didn't add the following files to the PR as the images already have OK alt texts: * https://github.com/langchain-ai/langchain/blob/27dca2d92fbd9c956a1eac7cf885a0ed060ca9ff/docs/docs/integrations/providers/argilla.mdx#L3 * https://github.com/langchain-ai/langchain/blob/27dca2d92fbd9c956a1eac7cf885a0ed060ca9ff/docs/docs/integrations/providers/apify.mdx#L11 --------- Co-authored-by: github-actions <github-actions@github.com>
5 months ago
![Screenshot of the LangServe Playground web interface with input and output fields.](playground.png "LangServe Playground Interface")