mirror of
https://github.com/hwchase17/langchain.git
synced 2026-06-09 18:50:33 +00:00
28f5448dd4
## Description This PR adds a new `PerplexityEmbeddings` class to the `langchain-perplexity` partner package, providing first-class support for the Perplexity Embeddings API alongside the existing `ChatPerplexity`, `PerplexitySearchRetriever`, and `PerplexitySearchResults` integrations. ### What was added - `langchain_perplexity/embeddings.py` — `PerplexityEmbeddings` class implementing `langchain_core.embeddings.Embeddings` with sync (`embed_documents`, `embed_query`) and async (`aembed_documents`, `aembed_query`) methods. Defaults to model `pplx-embed-v1-4b` and reuses the existing `_utils.initialize_client` helper for API key resolution (`PPLX_API_KEY` / `PERPLEXITY_API_KEY`). - `__init__.py` exports `PerplexityEmbeddings` and adds it to `__all__`. - Unit tests under `tests/unit_tests/test_embeddings.py` covering sync/async paths with mocked clients (no network). - Integration tests under `tests/integration_tests/test_embeddings.py`, gated on `PPLX_API_KEY` (matches the pattern in `test_search_api.py`). - README updated to advertise the new component. ### Why LangChain users already get chat, search, and tool wrappers from `langchain-perplexity`, but had to drop down to the raw Perplexity SDK to use embeddings. This closes that gap. ### References - Perplexity Embeddings docs: https://docs.perplexity.ai/docs/embeddings - Perplexity Embeddings API reference: https://docs.perplexity.ai/api-reference/embeddings-post ### Issue Closes #36726 ## Testing - `cd libs/partners/perplexity && make lint` — passes (ruff, format, mypy). - `cd libs/partners/perplexity && make test` — all unit tests pass (59 passed, 1 skipped). - Integration tests will run in CI with secrets; they exercise real `embed_documents` / `embed_query` / async variants against the live API and assert vector dimensionality consistency. --------- Co-authored-by: Claude Agent <agent@anthropic.com> Co-authored-by: Mason Daugherty <github@mdrxy.com>
57 lines
2.1 KiB
Python
57 lines
2.1 KiB
Python
"""Integration tests for Perplexity Embeddings API."""
|
|
|
|
import os
|
|
|
|
import pytest
|
|
|
|
from langchain_perplexity import PerplexityEmbeddings
|
|
|
|
|
|
@pytest.mark.skipif(
|
|
not (os.environ.get("PPLX_API_KEY") or os.environ.get("PERPLEXITY_API_KEY")),
|
|
reason="PPLX_API_KEY/PERPLEXITY_API_KEY not set",
|
|
)
|
|
class TestPerplexityEmbeddings:
|
|
def test_embed_documents(self) -> None:
|
|
"""Test embedding a list of documents."""
|
|
embeddings = PerplexityEmbeddings()
|
|
texts = ["hello world", "goodbye world"]
|
|
vectors = embeddings.embed_documents(texts)
|
|
|
|
assert len(vectors) == len(texts)
|
|
assert all(isinstance(v, list) for v in vectors)
|
|
assert all(len(v) > 0 for v in vectors)
|
|
# All vectors should have the same dimensionality.
|
|
assert len({len(v) for v in vectors}) == 1
|
|
assert all(isinstance(x, float) for x in vectors[0])
|
|
|
|
def test_embed_query(self) -> None:
|
|
"""Test embedding a single query."""
|
|
embeddings = PerplexityEmbeddings()
|
|
vector = embeddings.embed_query("What is the capital of France?")
|
|
|
|
assert isinstance(vector, list)
|
|
assert len(vector) > 0
|
|
assert all(isinstance(x, float) for x in vector)
|
|
|
|
def test_embed_query_matches_documents_dim(self) -> None:
|
|
"""Embeddings from query and documents should share dimensionality."""
|
|
embeddings = PerplexityEmbeddings()
|
|
query_vec = embeddings.embed_query("hello")
|
|
doc_vecs = embeddings.embed_documents(["hello"])
|
|
assert len(query_vec) == len(doc_vecs[0])
|
|
|
|
async def test_aembed_documents(self) -> None:
|
|
"""Test async embedding a list of documents."""
|
|
embeddings = PerplexityEmbeddings()
|
|
vectors = await embeddings.aembed_documents(["hello", "world"])
|
|
assert len(vectors) == 2
|
|
assert all(len(v) > 0 for v in vectors)
|
|
|
|
async def test_aembed_query(self) -> None:
|
|
"""Test async embedding a single query."""
|
|
embeddings = PerplexityEmbeddings()
|
|
vector = await embeddings.aembed_query("hello")
|
|
assert isinstance(vector, list)
|
|
assert len(vector) > 0
|