metadata
license: apache-2.0
language:
- en
pipeline_tag: text-generation
tags:
- RAG
Kurage
Kurage is a multipurpose RAG model from Lightblue.
This version of the model has been trained to perform RAG in English.
Features of these models include:
- Multi-chunk RAG - Performs RAG using multiple contexts at once.
- Single-chunk RAG - Performs RAG using one context at a time, allowing for parallel computing.
- Answer extension - Prompts the model to write a longer answer to a given question.
- Multilingual RAG - Performs RAG using contexts in languages different to the language of the question.
- Q&A generation - Generates questions and answers from a reference text in order to pre-index a set of texts.
Find out how to use these features below.
For models in other languages check [our Kurage collection]. A multilingual model is coming soon!
Features / How to use
First, load the model like so:
from vllm import LLM, SamplingParams
llm = LLM(model="lightblue/kurage-ja")
sampling_params = SamplingParams(temperature=1.0, top_p=0.95, max_tokens=128)
Feature: Multi-chunk RAG
This model can take multiple contexts and a question as input, and it will first output the references of the relevant contexts before outputting an answer to the question.
Prompt style
Input:
<<Chunk 1>>
Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level.
She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.
<<Chunk 2>>
Japan's current account surplus in July was 3.2 trillion yen, the highest monthly surplus on record for the month of July.
However, the surplus continues to be driven by the primary income balance, which recorded a surplus of 4.4 trillion yen in July, the highest monthly figure on record.
<<Chunk 3>>
Finance Minister Shunichi Suzuki appointed Kenji Suwazono, former Director-General of the Customs and Tariff Bureau at the Ministry of Finance, as the new Executive Director of the Bank of Japan effective the 10th. Suwazono succeeds Masaaki Kaizuka, whose term ended on the 9th, and his term will last for four years.
<<Chunk 4>>
In the yen appreciation phase of August, it has become a topic in the foreign exchange market that Japanese institutional investors engaged in the largest-ever outward securities investment.
<<Question>>
What is Japan's primary income balance currently?
Output:
<<References>>
2
<<Answer>>
4.4 trillion yen
Python code
contexts = [
"Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level. She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.",
"Japan's current account surplus in July was 3.2 trillion yen, the highest monthly surplus on record for the month of July. However, the surplus continues to be driven by the primary income balance, which recorded a surplus of 4.4 trillion yen in July, the highest monthly figure on record.",
"Finance Minister Shunichi Suzuki appointed Kenji Suwazono, former Director-General of the Customs and Tariff Bureau at the Ministry of Finance, as the new Executive Director of the Bank of Japan effective the 10th. Suwazono succeeds Masaaki Kaizuka, whose term ended on the 9th, and his term will last for four years.",
"In the yen appreciation phase of August, it has become a topic in the foreign exchange market that Japanese institutional investors engaged in the largest-ever outward securities investment."
]
question = "What is Japan's primary income balance currently?"
def create_rag_prompt(contexts, question):
context_str = "\n\n".join([f"<<Chunk {i+1}>>\n{x}" for i, x in enumerate(contexts)])
str_inputs = f"""{context_str}
<<Question>>
{question}"""
chat = [
{"role": "user", "content": str_inputs},
]
return llm.llm_engine.tokenizer.tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
inputs = create_rag_prompt(contexts, question)
print(inputs)
outputs = llm.generate([inputs], sampling_params)
print(outputs[0].outputs[0].text)
Feature: Single-chunk RAG
This model can also take a single context and a question as input, and it will determine whether it can answer the question based on the context, outputting an answer if it can. This allows for parallel computing of multiple contexts at the same time.
Prompt style
Irrelevant context input:
<<Chunk 1>>
Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level.
She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.
<<Question>>
What is Japan's primary income balance currently?
Irrelevant context output:
<<References>>
None
Relevant context input:
<<Chunk 1>>
Japan's current account surplus in July was 3.2 trillion yen, the highest monthly surplus on record for the month of July.
However, the surplus continues to be driven by the primary income balance, which recorded a surplus of 4.4 trillion yen in July, the highest monthly figure on record.
<<Question>>
What is Japan's primary income balance currently?
Relevant context output:
<<References>>
1
<<Answer>>
4.4 trillion yen
Python code
contexts = [
"Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level. She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.",
"Japan's current account surplus in July was 3.2 trillion yen, the highest monthly surplus on record for the month of July. However, the surplus continues to be driven by the primary income balance, which recorded a surplus of 4.4 trillion yen in July, the highest monthly figure on record.",
"Finance Minister Shunichi Suzuki appointed Kenji Suwazono, former Director-General of the Customs and Tariff Bureau at the Ministry of Finance, as the new Executive Director of the Bank of Japan effective the 10th. Suwazono succeeds Masaaki Kaizuka, whose term ended on the 9th, and his term will last for four years.",
"In the yen appreciation phase of August, it has become a topic in the foreign exchange market that Japanese institutional investors engaged in the largest-ever outward securities investment."
]
question = "What is Japan's primary income balance currently?"
def create_rag_prompt(contexts, question):
context_str = "\n\n".join([f"<<Chunk {i+1}>>\n{x}" for i, x in enumerate(contexts)])
str_inputs = f"""{context_str}
<<Question>>
{question}"""
chat = [
{"role": "user", "content": str_inputs},
]
return llm.llm_engine.tokenizer.tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
outputs = llm.generate([create_rag_prompt(x, question) for x in contexts], sampling_params)
print("\n\n".join([o.outputs[0].text for o in outputs]))
Feature: Answer extension
By default, this model is trained to output the shortest possible answer to a question. However, if you require a longer answer, you can prompt the model to write a longer answer by writing " <>" after your question.
Prompt style
Input:
<<Chunk 1>>
Japan's current account surplus in July was 3.2 trillion yen, the highest monthly surplus on record for the month of July.
However, the surplus continues to be driven by the primary income balance, which recorded a surplus of 4.4 trillion yen in July, the highest monthly figure on record.
<<Question>>
What is Japan's primary income balance currently? <<Long>>
Relevant context output:
<<References>>
1
<<Answer>>
4.4 trillion yen
Python code
contexts = [
"Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level. She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.",
"Japan's current account surplus in July was 3.2 trillion yen, the highest monthly surplus on record for the month of July. However, the surplus continues to be driven by the primary income balance, which recorded a surplus of 4.4 trillion yen in July, the highest monthly figure on record.",
"Finance Minister Shunichi Suzuki appointed Kenji Suwazono, former Director-General of the Customs and Tariff Bureau at the Ministry of Finance, as the new Executive Director of the Bank of Japan effective the 10th. Suwazono succeeds Masaaki Kaizuka, whose term ended on the 9th, and his term will last for four years.",
"In the yen appreciation phase of August, it has become a topic in the foreign exchange market that Japanese institutional investors engaged in the largest-ever outward securities investment."
]
question = "What is Japan's primary income balance currently? <<Long>>"
def create_rag_prompt(contexts, question):
context_str = "\n\n".join([f"<<Chunk {i+1}>>\n{x}" for i, x in enumerate(contexts)])
str_inputs = f"""{context_str}
<<Question>>
{question}"""
chat = [
{"role": "user", "content": str_inputs},
]
return llm.llm_engine.tokenizer.tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
outputs = llm.generate([create_rag_prompt(x, question) for x in contexts], sampling_params)
print("\n\n".join([o.outputs[0].text for o in outputs]))
Feature: Multilinguality
We have trained our model to be able to answer questions in Japanese based on texts in other languages too!
Prompt style
Input:
<<Chunk 1>>
Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level.
She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.
<<Chunk 2>>
７月の日本の経常収支は３．２兆円の黒字となり、７月としては過去最高の黒字額を記録した。しかし、黒字に貢献しているのは相変わらず第一次所得収支の黒字で、７月は４．４兆円の黒字を記録し、１カ月の黒字額としては過去最高を記録した。
<<Chunk 3>>
รัฐมนตรีว่าการกระทรวงการคลัง ชุนอิจิ สุซูกิ ได้แต่งตั้ง เค็นจิ สุวาโซโนะ อดีตอธิบดีกรมศุลกากรและภาษีสิ่งนำเข้าแห่งกระทรวงการคลัง เป็นกรรมการบริหารธนาคารแห่งประเทศญี่ปุ่นคนใหม่ มีผลตั้งแต่วันที่ 10 สุวาโซโนะจะมาแทน มาซาอะกิ ไคซูกะ ที่พ้นวาระไปในวันที่ 9 โดยมีวาระ 4 ปี
<<Chunk 4>>
In the yen appreciation phase of August, it has become a topic in the foreign exchange market that Japanese institutional investors engaged in the largest-ever outward securities investment.
<<Question>>
What is Japan's primary income balance currently?
Output:
<<References>>
2
<<Answer>>
4.4 trillion yen
Python code
contexts = [
"Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level. She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.",
"７月の日本の経常収支は３．２兆円の黒字となり、７月としては過去最高の黒字額を記録した。しかし、黒字に貢献しているのは相変わらず第一次所得収支の黒字で、７月は４．４兆円の黒字を記録し、１カ月の黒字額としては過去最高を記録した。",
"รัฐมนตรีว่าการกระทรวงการคลัง ชุนอิจิ สุซูกิ ได้แต่งตั้ง เค็นจิ สุวาโซโนะ อดีตอธิบดีกรมศุลกากรและภาษีสิ่งนำเข้าแห่งกระทรวงการคลัง เป็นกรรมการบริหารธนาคารแห่งประเทศญี่ปุ่นคนใหม่ มีผลตั้งแต่วันที่ 10 สุวาโซโนะจะมาแทน มาซาอะกิ ไคซูกะ ที่พ้นวาระไปในวันที่ 9 โดยมีวาระ 4 ปี",
"In the yen appreciation phase of August, it has become a topic in the foreign exchange market that Japanese institutional investors engaged in the largest-ever outward securities investment."
]
question = "What is Japan's primary income balance currently?"
def create_rag_prompt(contexts, question):
context_str = "\n\n".join([f"<<Chunk {i+1}>>\n{x}" for i, x in enumerate(contexts)])
str_inputs = f"""{context_str}
<<Question>>
{question}"""
chat = [
{"role": "user", "content": str_inputs},
]
return llm.llm_engine.tokenizer.tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
inputs = create_rag_prompt(contexts, question)
print(inputs)
outputs = llm.generate([inputs], sampling_params)
print(outputs[0].outputs[0].text)
Feature: Q&A generation
This model can also generate questions and answers based on a piece of text. This can be useful for pre-indexing a database or fine-tuning IR models that will then be used for RAG.
Prompt style
Input:
<<Q&A Generation Context>>
Japan's current account surplus in July was 3.2 trillion yen, the highest monthly surplus on record for the month of July.
However, the surplus continues to be driven by the primary income balance, which recorded a surplus of 4.4 trillion yen in July, the highest monthly figure on record.
Output:
<<Question>>
What is Japan's current account surplus in July?
<<Answer>>
3.2 trillion yen
Python code
contexts = [
"Junko Nakagawa, a member of the Bank of Japan's Policy Board, stated on the 11th that real interest rates are currently at an extremely low level. She mentioned that if the BOJ's economic and price outlook materializes in the future, the degree of monetary easing would be adjusted from the perspective of achieving the price target.",
"７月の日本の経常収支は３．２兆円の黒字となり、７月としては過去最高の黒字額を記録した。しかし、黒字に貢献しているのは相変わらず第一次所得収支の黒字で、７月は４．４兆円の黒字を記録し、１カ月の黒字額としては過去最高を記録した。",
"รัฐมนตรีว่าการกระทรวงการคลัง ชุนอิจิ สุซูกิ ได้แต่งตั้ง เค็นจิ สุวาโซโนะ อดีตอธิบดีกรมศุลกากรและภาษีสิ่งนำเข้าแห่งกระทรวงการคลัง เป็นกรรมการบริหารธนาคารแห่งประเทศญี่ปุ่นคนใหม่ มีผลตั้งแต่วันที่ 10 สุวาโซโนะจะมาแทน มาซาอะกิ ไคซูกะ ที่พ้นวาระไปในวันที่ 9 โดยมีวาระ 4 ปี",
"In the yen appreciation phase of August, it has become a topic in the foreign exchange market that Japanese institutional investors engaged in the largest-ever outward securities investment."
]
question = "What is Japan's primary income balance currently?"
def create_qagen_prompt(context):
str_inputs = f"""<<Q&A Generation Context>>
{context}"""
chat = [
{"role": "user", "content": str_inputs},
]
return llm.llm_engine.tokenizer.tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
inputs = [create_qagen_prompt(x) for x in contexts]
outputs = llm.generate(inputs, sampling_params)
print("\n\n".join([o.outputs[0].text for o in outputs]))
Training data
We trained on chunks sourced from the documents in MADLAD-400 dataset that had been evaluated to contain a higher amount of educational information according to a state-of-the-art LLM.
We took chunks of size 250 tokens, 500 tokens, and 1000 tokens randomly for each document.
We then used these chunks to generate questions and answers based on this text using a state-of-the-art LLM.
Finally, we selected negatives for each chunk using the similarity from the dense embeddings of the BAAI/bge-m3 model.