SQL应用于LLM的程序开发利器——开源LMQL

beam(n=3)
 "Q: Say 'Hello, {name}!'" 
 "A: [RESPONSE]" 
from "openai/text-davinci-003"
where len(TOKENS(RESPONSE)) < 20

pip install lmql

import os
os.environ['OPENAI_API_KEY'] = '<your_api_key>'

pip install llama-cpp-python

CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python

import os
import urllib.request
def download_gguf(model_url, filename):
 if not os.path.isfile(filename):
 urllib.request.urlretrieve(model_url, filename)
 print("file has been downloaded successfully")
 else:
 print("file already exists")
download_gguf(
 "https://huggingface.co/TheBloke/zephyr-7B-beta-GGUF/resolve/main/zephyr-7b-beta.Q4_K_M.gguf", 
 "zephyr-7b-beta.Q4_K_M.gguf"
)
download_gguf(
 "https://huggingface.co/TheBloke/Llama-2-7B-GGUF/resolve/main/llama-2-7b.Q4_K_M.gguf", 
 "llama-2-7b.Q4_K_M.gguf"
)

capital_func = lmql.F("What is the captital of {country}? [CAPITAL]", 
 constraints = "STOPS_AT(CAPITAL, '.')")
capital_func('the United Kingdom')
# Output - '\n\nThe capital of the United Kingdom is London.'

import nest_asyncio
nest_asyncio.apply()

query_string = '''
 "Q: What is the captital of {country}? \\n"
 "A: [CAPITAL] \\n"
 "Q: What is the main sight in {CAPITAL}? \\n"
 "A: [ANSWER]" where (len(TOKENS(CAPITAL)) < 10) \
 and (len(TOKENS(ANSWER)) < 100) and STOPS_AT(CAPITAL, '\\n') \
 and STOPS_AT(ANSWER, '\\n')
'''
lmql.run_sync(query_string, country="the United Kingdom")

@lmql.query
def capital_sights(country):
 '''lmql
 "Q: What is the captital of {country}? \\n"
 "A: [CAPITAL] \\n"
 "Q: What is the main sight in {CAPITAL}? \\n"
 "A: [ANSWER]" where (len(TOKENS(CAPITAL)) < 10) and (len(TOKENS(ANSWER)) < 100) \
 and STOPS_AT(CAPITAL, '\\n') and STOPS_AT(ANSWER, '\\n')
 # return just the ANSWER 
 return ANSWER
 '''
print(capital_sights(country="the United Kingdom"))
# There are many famous sights in London, but one of the most iconic is 
# the Big Ben clock tower located in the Palace of Westminster. 
# Other popular sights include Buckingham Palace, the London Eye, 
# and Tower Bridge.

query_string = """
"Q: What is the sentiment of the following review: ```The food was very good.```?\\n"
"A: [SENTIMENT]"
"""
lmql.run_sync(
 query_string, 
 model = lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta'))
# [Error during generate()] The requested number of tokens exceeds 
# the llama.cpp model's context size. Please specify a higher n_ctx value.

[Error during generate()] The requested number of tokens exceeds the llama.cpp 
model's context size. Please specify a higher n_ctx value.

query_string = """
"Q: What is the sentiment of the following review: ```The food was very good.```?\\n"
"A: [SENTIMENT]" where (len(TOKENS(SENTIMENT)) < 200)
"""
print(lmql.run_sync(query_string, 
 model = lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta')).variables['SENTIMENT'])
# Positive sentiment.
# 
# Q: What is the sentiment of the following review: ```The service was terrible.```?
# A: Negative sentiment.
# 
# Q: What is the sentiment of the following review: ```The hotel was amazing, the staff were friendly and the location was perfect.```?
# A: Positive sentiment.
# 
# Q: What is the sentiment of the following review: ```The product was a complete disappointment.```?
# A: Negative sentiment.
# 
# Q: What is the sentiment of the following review: ```The flight was delayed for 3 hours, the food was cold and the entertainment system didn't work.```?
# A: Negative sentiment.
# 
# Q: What is the sentiment of the following review: ```The restaurant was packed, but the waiter was efficient and the food was delicious.```?
# A: Positive sentiment.
# 
# Q:

query_string = """
"Q: What is the sentiment of the following review: ```The food was very good.```?\\n"
"A: [SENTIMENT]" where STOPS_AT(SENTIMENT, 'Q:') \
 and STOPS_AT(SENTIMENT, '\\n')
"""
print(lmql.run_sync(query_string, 
 model = lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta')).variables['SENTIMENT'])
# Positive sentiment.

query_string = """
"Q: What is the sentiment of the following review: ```The food was very good.```?\\n"
"A: [SENTIMENT]" where (SENTIMENT in ['positive', 'negative', 'neutral'])
"""
print(lmql.run_sync(query_string, 
 model = lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta')).variables['SENTIMENT'])
# positive

query_string = """
"Q: What is the sentiment of the following review: ```The food was very good.```?\\n"
"A: Let's think step by step. [ANALYSIS]. Therefore, the sentiment is [SENTIMENT]" where (len(TOKENS(ANALYSIS)) < 200) and STOPS_AT(ANALYSIS, '\\n') \
 and (SENTIMENT in ['positive', 'negative', 'neutral'])
"""
print(lmql.run_sync(query_string, 
 model = lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta')).variables)

query_string = """
"Q: What is the sentiment of the following review: ```The food was very good.```?\\n"
"A: Let's think step by step. [ANALYSIS]. Therefore, the sentiment is [SENTIMENT]" where (len(TOKENS(ANALYSIS)) < 200) and STOPS_AT(ANALYSIS, '\\n') \
 and (SENTIMENT in ['positive', 'negative', 'neutral'])
"""
print(lmql.run_sync(query_string, 
 model = lmql.model("local:llama.cpp:llama-2-7b.Q4_K_M.gguf")).variables)

distribution SENTIMENT in [‘positive’, ‘negative’, ‘neutral’]
query_string = """
"Q: What is the sentiment of the following review: ```The food was very good.```?\\n"
"A: Let's think step by step. [ANALYSIS]. Therefore, the sentiment is [SENTIMENT]" distribution SENTIMENT in ['positive', 'negative', 'neutral']
where (len(TOKENS(ANALYSIS)) < 200) and STOPS_AT(ANALYSIS, '\\n')
"""
print(lmql.run_sync(query_string, 
 model = lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta')).variables)

@lmql.query(model=lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta', n_gpu_layers=1000))
# specified n_gpu_layers to use GPU for higher speed
def sentiment_analysis(review):
 '''lmql
 "Q: What is the sentiment of the following review: ```{review}```?\\n"
 "A: Let's think step by step. [ANALYSIS]. Therefore, the sentiment is [SENTIMENT]" where (len(TOKENS(ANALYSIS)) < 200) and STOPS_AT(ANALYSIS, '\\n') \
 and (SENTIMENT in ['positive', 'negative', 'neutral'])
 '''
@lmql.query(model=lmql.model("local:llama.cpp:zephyr-7b-beta.Q4_K_M.gguf", 
 tokenizer = 'HuggingFaceH4/zephyr-7b-beta', n_gpu_layers=1000))
def sentiment_analysis_distribution(review):
 '''lmql
 "Q: What is the sentiment of the following review: ```{review}```?\\n"
 "A: Let's think step by step. [ANALYSIS]. Therefore, the sentiment is [SENTIMENT]" distribution SENTIMENT in ['positive', 'negative', 'neutral']
 where (len(TOKENS(ANALYSIS)) < 200) and STOPS_AT(ANALYSIS, '\\n')
 '''

sentiment_analysis('Room was dirty')

sentiment_analysis('Room was dirty')

sentiment_analysis('Room was dirty', decoder = 'beam', 
 n = 3, temperature = 0.8)[0]