pplx-embed-v2-context-0.6b

Model release Hugging Face 模型 · perplexity-ai Source language: Chinese

官方机构模型仓库创建于 2026-10-21。仓库创建时间不等于正式发布日期。任务类型:feature-extraction

Full text

pplx-embed-v2-context: Multimodal Contextual Embeddings

pplx-embed-v2-context-0.6b is a state-of-the-art vision-language embedding model for retrieval over text, images, and visual documents. It supports contextual and non-contextual embeddings: In contextual mode, the model embeds chunks of a document with the surrounding context in view. In non-contextual mode, text inputs are embedded in isolation. pplx-embed-v2-context-0.6b shares an embedding space with the 1024-dimensional MRL prefix of pplx-embed-v2-context-9b. Documents can be embedded with one model and queried with another.

This model also supports contextual chunking for visual inputs. Chunked images can be retrieved via standard dense ANN indices. Chunking images can substantially improve retrieval performance.

For benchmark results and details on training, refer to our technical report.

[!IMPORTANT] When encoding chunks in contextual mode, the document chunks should be non-overlapping.

[!IMPORTANT] Queries and documents are encoded with different methods: use encode_queries for queries and encode for document chunks. The model is trained with separate query and document prefixes, and encoding queries with encode silently degrades retrieval quality.

[!IMPORTANT] Like pplx-embed-context-v1, the model natively produces *unnormalized* int8-quantized embeddings. Compare embeddings with *cosine similarity*, or pass normalize_embeddings=True and use the dot product.

Text Embeddings

Requires transformers>=5.4.0, torch, numpy, safetensors, tqdm, Pillow, and torchvision. Install flash-linear-attention and causal-conv1d for the fast linear-attention path. The model uses custom code, so load it with trust_remote_code=True.

encode(documents, ...) and encode_queries(queries, ...) accept:

Argument Default Description batch_size 32 Documents (or queries) per forward pass normalize_embeddings False L2-normalize outputs convert_to_numpy True Return NumPy arrays; False returns CPU tensors show_progress_bar False Show a progress bar device None Move the model to this device before encoding

The text API does not truncate inputs. Split or truncate documents that exceed the configured input length before encoding. To obtain one embedding per document, pass each document as a single-chunk list.

Image Embeddings

Use encode_images() to embed document pages or other images as contextual chunks. Pass a list of PIL images; each image produces one embedding per horizontal band. Use encode_queries() for the corresponding text queries.

Each image is encoded in one contextual forward pass, with its merged visual tokens divided into whole-row horizontal bands. Native three-axis MRoPE and image wrappers are preserved. Separator tokens between bands use the midpoint of the adjacent rows and the horizontal center of the image as their spatial position. Only visual content is pooled; prefixes, wrappers, and separators are excluded.

encode_images() returns one (actual_chunks, 1024) array per page. The actual chunk count is capped at the number of merged image rows. Use cosine similarity per chunk and the maximum chunk score for page retrieval, as shown above with normalized vectors.

Image argument Default Description chunks 8 Requested number of horizontal bands per page min_pixels 16384 Processor minimum image pixel budget max_pixels 1800000 Processor maximum image pixel budget batch_size 1 Images per forward pass

The image API also accepts normalize_embeddings, convert_to_numpy, show_progress_bar, and device with the defaults listed above. prepare_images(images, chunks=8, min_pixels=16384, max_pixels=1800000) exposes the input tensors, chunk spans, masks, and position IDs without running the model.

Sources

← Back to the daily brief