Spaces:
Build error
Build error
| ## Global Variables | |
| API_BASE = "https://api.01.ai/v1" | |
| API_KEY = "your key" | |
| model_name = "jinaai/jina-embeddings-v3" | |
| title = """ | |
| # 👋🏻Welcome to 🙋🏻♂️Tonic's 📽️Nvidia 🛌🏻Embed V-1 !""" | |
| description = """ | |
| You can use this Space to test out the current model [nvidia/NV-Embed-v1](https://huggingface.co/nvidia/NV-Embed-v1). 🐣a generalist embedding model that ranks No. 1 on the Massive Text Embedding Benchmark (MTEB benchmark)(as of May 24, 2024), with 56 tasks, encompassing retrieval, reranking, classification, clustering, and semantic textual similarity tasks. | |
| You can also use 📽️Nvidia 🛌🏻Embed V-1 by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/NV-Embed?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3> | |
| Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's🛠️community 👻 [](https://discord.gg/GWpVpekp) On 🤗Huggingface: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to 🌟 [MultiTonic](https://github.com/MultiTonic) 🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗 | |
| """ | |
| tasks = { | |
| 'retrieval.query': 'Used for query embeddings in asymmetric retrieval tasks', | |
| 'retrieval.passage': 'Used for passage embeddings in asymmetric retrieval tasks', | |
| 'separation': 'Used for embeddings in clustering and re-ranking applications', | |
| 'classification': 'Used for embeddings in classification tasks', | |
| 'text-matching': 'Used for embeddings in tasks that quantify similarity between two texts, such as STS or symmetric retrieval tasks', | |
| 'DEFAULT': 'Used for general-purpose embeddings when no specific task is specified' | |
| } | |
| intention_prompt = """ | |
| { | |
| "type": "object", | |
| "properties": { | |
| "retrieval.query": { | |
| "type": "boolean", | |
| "description": "Select this for query embeddings in asymmetric retrieval tasks" | |
| }, | |
| "retrieval.passage": { | |
| "type": "boolean", | |
| "description": "Select this for passage embeddings in asymmetric retrieval tasks" | |
| }, | |
| "separation": { | |
| "type": "boolean", | |
| "description": "Select this for embeddings in clustering and re-ranking applications" | |
| }, | |
| "classification": { | |
| "type": "boolean", | |
| "description": "Select this for embeddings in classification tasks" | |
| }, | |
| "text-matching": { | |
| "type": "boolean", | |
| "description": "Select this for embeddings in tasks that quantify similarity between two texts, such as STS or symmetric retrieval tasks" | |
| } | |
| }, | |
| "required": [ | |
| "retrieval.query", | |
| "retrieval.passage", | |
| "separation", | |
| "classification", | |
| "text-matching" | |
| ] | |
| } | |
| you will recieve a text , classify the text according to the schema above. ONLY PROVIDE THE FINAL JSON , DO NOT PRODUCE ANY ADDITION INSTRUCTION :""" | |
| metadata_prompt = "you will recieve a text or a question, produce metadata operator pairs for the text . ONLY PROVIDE THE FINAL JSON , DO NOT PRODUCE ANY ADDITION INSTRUCTION , ONLY PRODUCE ONE METADATA STRING PER OPERATOR:" | |
| system_message = """ You are a helpful assistant named YiTonic . answer the question provided based on the context above. Produce a complete answer:""" |