EmbeddingGemma 2

Tools

• embeddinggemma_2_compare Score pairwise cosine similarity for one sentence per line. Every sentence uses the sentence-similarity task prefix. Vectors are Matryoshka-truncated and L2-normalized.
• embeddinggemma_2_search Rank documents against a text query with EmbeddingGemma 2. The query receives the selected task prefix. Each document is formatted as `title: … | text: …`. Vectors are Matryoshka-truncated and L2-normalized, then scored with cosine similarity.
• embeddinggemma_2_search_1 Rank documents against a text query with EmbeddingGemma 2. The query receives the selected task prefix. Each document is formatted as `title: … | text: …`. Vectors are Matryoshka-truncated and L2-normalized, then scored with cosine similarity.
• embeddinggemma_2_search_images Rank images against a text query in EmbeddingGemma 2's shared vector space. The query uses the web-search prefix. Images are embedded with no text prefix. Both sides are truncated to the same dimension and L2-normalized before cosine scoring. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool
• embeddinggemma_2_search_images_1 Rank images against a text query in EmbeddingGemma 2's shared vector space. The query uses the web-search prefix. Images are embedded with no text prefix. Both sides are truncated to the same dimension and L2-normalized before cosine scoring. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

No tool matches.

As the server's own listing gives them. We never call a tool.