Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat(chains): add OpenAI embedding model options #130

Open
wants to merge 20 commits into
base: main
Choose a base branch
from

Conversation

Lapeyus
Copy link
Contributor

@Lapeyus Lapeyus commented Feb 20, 2024

Add new OpenAI embedding models. to differentiate the available options I propose:

  • openai-embedding-3-small
  • openai-embedding-3-large

This PR updates docs and examples to reflect these changes.

Joseph Villarreal Lopez and others added 20 commits January 18, 2024 18:35
Signed-off-by: Joseph Villarreal Lopez <[email protected]>
* Update README.md

* Update readme.md

---------

Co-authored-by: Jim Clark <[email protected]>
Signed-off-by: Joseph Villarreal Lopez <[email protected]>
* run on wsl

* run on windows WSL procedure

Signed-off-by: Joseph Villarreal Lopez <[email protected]>
Signed-off-by: Joseph Villarreal Lopez <[email protected]>
Bumps [vite](https://github.com/vitejs/vite/tree/HEAD/packages/vite) from 4.4.10 to 4.4.12.
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a href="https://github.com/vitejs/vite/blob/v4.4.12/packages/vite/CHANGELOG.md">vite's changelog</a>.</em></p>
<blockquote>
<h2><!-- raw HTML omitted -->4.4.12 (2023-12-04)<!-- raw HTML omitted --></h2>
<ul>
<li>fix: backport <a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/15223">#15223</a>, proxy html path should be encoded (<a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/15226">#15226</a>) (<a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/15227">#15227</a>) (<a href="https://github.com/vitejs/vite/commit/fe8b209">fe8b209</a>), closes <a href="https://redirect.github.com/vitejs/vite/issues/15223">#15223</a> <a href="https://redirect.github.com/vitejs/vite/issues/15226">#15226</a> <a href="https://redirect.github.com/vitejs/vite/issues/15227">#15227</a></li>
</ul>
<h2><!-- raw HTML omitted -->4.4.11 (2023-10-05)<!-- raw HTML omitted --></h2>
<ul>
<li>revert: &quot;fix: use string manipulation instead of regex to inject esbuild helpers (<a href="https://github.com/vitejs/vite/commit/54e1275">54e1275</a>), closes <a href="https://redirect.github.com/vitejs/vite/issues/14094">#14094</a></li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a href="https://github.com/vitejs/vite/commit/09626f898bbb9e3d68facd0330d4a0acef0cba6a"><code>09626f8</code></a> release: v4.4.12</li>
<li><a href="https://github.com/vitejs/vite/commit/fe8b2090236805bb5ad6c2a5b422976523e21da1"><code>fe8b209</code></a> fix: backport <a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/15223">#15223</a>, proxy html path should be encoded (<a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/15226">#15226</a>) (<a href="https://github.com/vitejs/vite/tree/HEAD/packages/vite/issues/15227">#15227</a>)</li>
<li><a href="https://github.com/vitejs/vite/commit/b50db04a5a47aa855cae6ced026290c2761ffa8d"><code>b50db04</code></a> release: v4.4.11</li>
<li><a href="https://github.com/vitejs/vite/commit/54e12755c06a3ac8622ed1da5706fef68b69c50e"><code>54e1275</code></a> revert: &quot;fix: use string manipulation instead of regex to inject esbuild helpers</li>
<li>See full diff in <a href="https://github.com/vitejs/vite/commits/v4.4.12/packages/vite">compare view</a></li>
</ul>
</details>
<br />

[![Dependabot compatibility score](https://dependabot-badges.githubapp.com/badges/compatibility_score?dependency-name=vite&package-manager=npm_and_yarn&previous-version=4.4.10&new-version=4.4.12)](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`.

[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)

---

<details>
<summary>Dependabot commands and options</summary>
<br />

You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
You can disable automated security fix PRs for this repo from the [Security Alerts page](https://github.com/Signal-Spot/genai-stack/network/alerts).

</details>

Signed-off-by: Joseph Villarreal Lopez <[email protected]>
Signed-off-by: Joseph Villarreal Lopez <[email protected]>
Signed-off-by: denverdino <[email protected]>
Signed-off-by: Joseph Villarreal Lopez <[email protected]>
Signed-off-by: Joseph Villarreal Lopez <[email protected]>
Adds support for Google's Generative AI Embeddings as an optional embedding model for Langchain.

This model can be selected using the `EMBEDDING_MODEL` environment variable, and requires a valid Google API key to be set via the `GOOGLE_API_KEY` environment variable.

The embedding model is configured with a model dimension of 768.

Signed-off-by: Joseph Villarreal Lopez <[email protected]>
Add OpenAI embedding models:
- openai-embedding-3-small
- openai-embedding-3-large

Update docs and examples to reflect these changes.
@@ -33,10 +33,18 @@ def load_embedding_model(embedding_model_name: str, logger=BaseLogger(), config=
)
dimension = 4096
logger.info("Embedding: Using Ollama")
elif embedding_model_name == "openai":
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

we should not break the existing config, but leave the existing embeddings and add these new ones explicitely

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

8 participants