perplexity-ai
/

pplx-embed-context-v1-4b

Feature Extraction

bidirectional_pplx_qwen3

sentence-similarity

contextual-embeddings

text-embeddings-inference

Model card Files Files and versions

update readme

#3

by seslami-pplx - opened Feb 5

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -22,6 +22,10 @@ language:
 - Use **`pplx-embed-1`** for independent text embedding (queries, documents, semantic search)
 - Use **`pplx-embed-1-context`** for document chunks in RAG systems where surrounding context matters
 ![diag.png](assets/diag.png)
 ## Models

 - Use **`pplx-embed-1`** for independent text embedding (queries, documents, semantic search)
 - Use **`pplx-embed-1-context`** for document chunks in RAG systems where surrounding context matters
+> [!IMPORTANT]
+> `pplx-embed-1` and `pplx-embed-1-context` natively produce *unnormalized* int8-quantized embeddings. Ensure that you compare them via *cosine similarity*.
 ![diag.png](assets/diag.png)
 ## Models