globalvars.py

## 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 👻  [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](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:"""