Feature Extraction
sentence-transformers
ONNX
Safetensors
multilingual
bidirectional_pplx_qwen3
sentence-similarity
mteb
custom_code
text-embeddings-inference
Instructions to use perplexity-ai/pplx-embed-v1-0.6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use perplexity-ai/pplx-embed-v1-0.6b with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("perplexity-ai/pplx-embed-v1-0.6b", trust_remote_code=True) sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Commit ·
b39f2c4
1
Parent(s): 124293d
docs: add disclaimer about cosine similarity
Browse files
README.md
CHANGED
|
@@ -22,6 +22,10 @@ language:
|
|
| 22 |
- Use **`pplx-embed-1`** for independent text embedding (queries, documents, semantic search)
|
| 23 |
- Use **`pplx-embed-1-context`** for document chunks in RAG systems where surrounding context matters
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |

|
| 26 |
|
| 27 |
## Models
|
|
|
|
| 22 |
- Use **`pplx-embed-1`** for independent text embedding (queries, documents, semantic search)
|
| 23 |
- Use **`pplx-embed-1-context`** for document chunks in RAG systems where surrounding context matters
|
| 24 |
|
| 25 |
+
> [!IMPORTANT]
|
| 26 |
+
> `pplx-embed-1` and `pplx-embed-1-context` natively produce *unnormalized* int8-quantized embeddings. Ensure that you compare them via *cosine similarity*.
|
| 27 |
+
|
| 28 |
+
|
| 29 |

|
| 30 |
|
| 31 |
## Models
|