01aiYi-NvidiaEmbed / globalvars.py
Tonic's picture
add metadata prompt , fix imports , add chroma
190f21f
raw
history blame
No virus
5.23 kB
## Global Variables
API_BASE = "https://api.01.ai/v1"
API_KEY = "your key"
model_name = 'nvidia/NV-Embed-v1'
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 = {
'ClimateFEVER': 'Given a claim about climate change, retrieve documents that support or refute the claim',
'DBPedia': 'Given a query, retrieve relevant entity descriptions from DBPedia',
'FEVER': 'Given a claim, retrieve documents that support or refute the claim',
'FiQA2018': 'Given a financial question, retrieve user replies that best answer the question',
'HotpotQA': 'Given a multi-hop question, retrieve documents that can help answer the question',
'MSMARCO': 'Given a web search query, retrieve relevant passages that answer the query',
'NFCorpus': 'Given a question, retrieve relevant documents that best answer the question',
'NQ': 'Given a question, retrieve Wikipedia passages that answer the question',
'QuoraRetrieval': 'Given a question, retrieve questions that are semantically equivalent to the given question',
'SCIDOCS': 'Given a scientific paper title, retrieve paper abstracts that are cited by the given paper',
}
intention_prompt= """
"type": "object",
"properties": {
"ClimateFEVER": {
"type": "boolean",
"description" : "select this for climate science related text"
},
"DBPedia": {
"type": "boolean",
"description" : "select this for encyclopedic related knowledge"
},
"FEVER": {
"type": "boolean",
"description": "select this to verify a claim or embed a claim"
},
"FiQA2018": {
"type": "boolean",
"description" : "select this for financial questions or topics"
},
"HotpotQA": {
"type": "boolean",
"description" : "select this for a multi-hop question or for texts that provide multihop claims"
},
"MSMARCO": {
"type": "boolean",
"description": "Given a web search query, retrieve relevant passages that answer the query"
},
"NFCorpus": {
"type": "boolean",
"description" : "Given a question, retrieve relevant documents that best answer the question"
},
"NQ": {
"type": "boolean",
"description" : "Given a question, retrieve Wikipedia passages that answer the question"
},
"QuoraRetrieval": {
"type": "boolean",
"description": "Given a question, retrieve questions that are semantically equivalent to the given question"
},
"SCIDOCS": {
"type": "boolean",
"description": "Given a scientific paper title, retrieve paper abstracts that are cited by the given paper"
}
},
"required": [
"ClimateFEVER",
"DBPedia",
"FEVER",
"FiQA2018",
"HotpotQA",
"MSMARCO",
"NFCorpus",
"NQ",
"QuoraRetrieval",
"SCIDOCS",
]
produce a complete json schema."
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:"""