[PR #3806] [MERGED] docs(integrations): add PerplexityEmbeddings to embeddings index #3824

Closed
opened 2026-06-05 18:53:16 -04:00 by yindo · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/langchain-ai/docs/pull/3806
Author: @jliounis
Created: 4/29/2026
Status: Merged
Merged: 4/29/2026
Merged by: @mdrxy

Base: mainHead: docs/perplexity-embeddings


📝 Commits (1)

  • 1d81938 docs(integrations): add PerplexityEmbeddings to embeddings index

📊 Changes

3 files changed (+154 additions, -1 deletions)

View changed files

📝 src/oss/python/integrations/embeddings/index.mdx (+2 -0)
src/oss/python/integrations/embeddings/perplexity.mdx (+140 -0)
📝 src/oss/python/integrations/providers/perplexity.mdx (+12 -1)

📄 Description

Summary

Adds PerplexityEmbeddings to the LangChain Python embeddings integrations docs. PerplexityEmbeddings was merged into langchain-perplexity in langchain-ai/langchain#37082 (closing #36726) but isn't yet surfaced on the embeddings index page.

Changes

  • embeddings/index.mdx — adds PerplexityEmbeddings to the Top integrations table and a Perplexity card to the All embedding models grid (alphabetically between PredictionGuard and PremAI).
  • embeddings/perplexity.mdx (new) — full integration page modeled on nomic.mdx / aimlapi.mdx: setup, credentials, installation, instantiation, indexing/retrieval with InMemoryVectorStore, direct usage of embed_query/embed_documents, async usage, and a note about Perplexity's base64-encoded int8 embedding format. Models documented: pplx-embed-v1-4b (default) and pplx-embed-v1-0.6b, matching the merged class.
  • providers/perplexity.mdx — adds an ## Embedding models section with a usage pointer and a row in the components reference table for PerplexityEmbeddings.

Notes

  • No docs.json changes — embeddings integration pages are auto-discovered (only one embeddings page is individually registered in the sidebar, and that's a JS one).
  • Reference link uses https://reference.langchain.com/python/langchain-perplexity/embeddings/PerplexityEmbeddings, matching the convention used for other partner embeddings (Nomic, Voyage AI, Mistral, etc.).
  • Builds on the recently-merged #3798 which surfaced the Search retriever + tool pages.

🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/langchain-ai/docs/pull/3806 **Author:** [@jliounis](https://github.com/jliounis) **Created:** 4/29/2026 **Status:** ✅ Merged **Merged:** 4/29/2026 **Merged by:** [@mdrxy](https://github.com/mdrxy) **Base:** `main` ← **Head:** `docs/perplexity-embeddings` --- ### 📝 Commits (1) - [`1d81938`](https://github.com/langchain-ai/docs/commit/1d819380abe348dbd800efbdc667bd84ec7285db) docs(integrations): add PerplexityEmbeddings to embeddings index ### 📊 Changes **3 files changed** (+154 additions, -1 deletions) <details> <summary>View changed files</summary> 📝 `src/oss/python/integrations/embeddings/index.mdx` (+2 -0) ➕ `src/oss/python/integrations/embeddings/perplexity.mdx` (+140 -0) 📝 `src/oss/python/integrations/providers/perplexity.mdx` (+12 -1) </details> ### 📄 Description ## Summary Adds `PerplexityEmbeddings` to the LangChain Python embeddings integrations docs. `PerplexityEmbeddings` was merged into `langchain-perplexity` in [langchain-ai/langchain#37082](https://github.com/langchain-ai/langchain/pull/37082) (closing [#36726](https://github.com/langchain-ai/langchain/issues/36726)) but isn't yet surfaced on [the embeddings index page](https://docs.langchain.com/oss/python/integrations/embeddings). ## Changes - **`embeddings/index.mdx`** — adds `PerplexityEmbeddings` to the **Top integrations** table and a `Perplexity` card to the **All embedding models** grid (alphabetically between PredictionGuard and PremAI). - **`embeddings/perplexity.mdx`** *(new)* — full integration page modeled on `nomic.mdx` / `aimlapi.mdx`: setup, credentials, installation, instantiation, indexing/retrieval with `InMemoryVectorStore`, direct usage of `embed_query`/`embed_documents`, async usage, and a note about Perplexity's base64-encoded int8 embedding format. Models documented: `pplx-embed-v1-4b` (default) and `pplx-embed-v1-0.6b`, matching the merged class. - **`providers/perplexity.mdx`** — adds an `## Embedding models` section with a usage pointer and a row in the components reference table for `PerplexityEmbeddings`. ## Notes - No `docs.json` changes — embeddings integration pages are auto-discovered (only one embeddings page is individually registered in the sidebar, and that's a JS one). - Reference link uses `https://reference.langchain.com/python/langchain-perplexity/embeddings/PerplexityEmbeddings`, matching the convention used for other partner embeddings (Nomic, Voyage AI, Mistral, etc.). - Builds on the recently-merged [#3798](https://github.com/langchain-ai/docs/pull/3798) which surfaced the Search retriever + tool pages. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
yindo added the pull-request label 2026-06-05 18:53:16 -04:00
yindo closed this issue 2026-06-05 18:53:16 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/docs#3824