File size: 9,686 Bytes
4cf88e8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 |
import json
import string
import wikipedia
from langchain import PromptTemplate
from langchain.vectorstores import Chroma
from langchain.text_splitter import CharacterTextSplitter
from src.tools.llms import openai_llm
from src.tools.wiki import Wiki
def get_wikilist(task: {}) -> str:
"""
get the titles of wiki pages interesting for solving the given task
"""
llm = openai_llm
template = (f"\n"
f" Your task consists in finding the list of wikipedia page titles which provide useful content "
f" for a paragraph whose description is delimited by triple backticks: ```{task['description']}```\n"
f" \n"
f" The paragraph belongs at the top level of the hierarchy to a document"
f" whose description is delimited by triple backticks: ``` {task['doc_description']}```\n"
f" Make sure that the paragraph relates the top level of the document\n"
f" \n"
f" The paragraph belongs to a higher paragraph in the hierarchy \\n"
f" whose description is delimited by triple backticks: ``` {task['above']}```\n"
f" Make sure that the paragraph relates with the paragraph in the hierarchy of the document\n"
f" \n"
f" The paragraphs comes after previous paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['before']}```\n"
f" Make sure that the paragraph relates with previous paragraph without any repetition\n"
f" \n"
f" The paragraphs comes before next paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['after']}```\n"
f" \n"
f" Format your response as a JSON list of strings separated by commas.\n"
f" \n"
f"\n"
f" ")
prompt = PromptTemplate(
input_variables=[],
template=template
)
#wikilist = LLMChain(llm=openai_llm, prompt=prompt).run()
llm_list = llm(template)
wikilist = extract_list(llm_list)
expanded_wikilist = []
expand_factor = 2
for wikipage in wikilist:
expanded_wikilist += wikipedia.search(wikipage, expand_factor)
wikilist = list(set(expanded_wikilist))
return wikilist
def extract_list(llm_list: str):
print(llm_list)
def filter_(el: str):
resp = 2 < len(el)
usable_length = len([c for c in el if c in string.ascii_letters])
resp = resp and len(el)*3/4 < usable_length
return resp
try:
wikilist = llm_list[1:-1].split('"')
wikilist = [el for el in wikilist if filter_(el)]
print(wikilist)
except:
wikilist = []
print('issues with the wikilist')
return wikilist
def get_public_paragraph(task: {}) -> str:
"""returns the task directly performed by chat GPT"""
llm = openai_llm
template = (f"\n"
f" Your task consists in generating a paragraph\\n"
f" whose description is delimited by triple backticks: ```{task['description']}```\n"
f"\n"
f" The paragraph belongs at the top level of the hierarchy to a document \\n"
f" whose description is delimited by triple backticks: ``` {task['doc_description']}```\n"
f" Make sure that the paragraph relates the top level of the document\n"
f" \n"
f" The paragraph belongs to a higher paragraph in the hierarchy \\n"
f" whose description is delimited by triple backticks: ``` {task['above']}```\n"
f" Make sure that the paragraph relates with the paragraph in the hierarchy of the document\n"
f" \n"
f" The paragraphs comes after previous paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['before']}```\n"
f" Make sure that the paragraph relates with previous paragraph without any repetition\n"
f" \n"
f" The paragraphs comes before next paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['after']}```\n"
f" Make sure that the paragraph prepares the transition to the next paragraph without any repetition\n"
f" \n"
f" \n"
f"\n"
f" ")
p = llm(template)
return p
def create_index(wikilist: [str]):
"""
useful for creating the index of wikipages
"""
fetch = Wiki().fetch
pages = [(title, fetch(title)) for title in wikilist if type(fetch(title)) != str]
texts = []
chunk = 800
for title, page in pages:
texts.append(WikiPage(title=title, fulltext=page.page_content))
doc_splitter = CharacterTextSplitter(
separator=".",
chunk_size=chunk,
chunk_overlap=100,
length_function=len,
)
paragraphs = texts[0].get_paragraphs(chunk=800)
split_texts = []
for p in paragraphs:
split_texts += doc_splitter.split_text(p)
for split_text in split_texts:
assert type(split_text) == str
assert 0 < len(split_text) < 2 * 500
wiki_index = Chroma.from_texts(split_texts)
return wiki_index
def get_wiki_paragraph(wiki_index, task: {}) -> str:
"""useful to get a summary in one line from wiki index"""
task_description = get_public_paragraph(task)
wiki_paragraphs = semantic_search(wiki_index, task_description)
text_content = ""
for p in wiki_paragraphs:
text_content += p.page_content + "/n/n"
template = (f"\n"
f" Your task consists in generating a paragraph\\n"
f" whose description is delimited by triple backticks: ```{task['description']}```\n"
f"\n"
f" The text generation is based in the documents provided in these sections \n"
f" delimited by by triple backticks: ``` {text_content}``` \n"
f" The paragraph belongs at the top level of the hierarchy to a document \\n"
f" whose description is delimited by triple backticks: ``` {task['doc_description']}```\n"
f" Make sure that the paragraph relates the top level of the document\n"
f" \n"
f" The paragraph belongs to a higher paragraph in the hierarchy \\n"
f" whose description is delimited by triple backticks: ``` {task['above']}```\n"
f" Make sure that the paragraph relates with the paragraph in the hierarchy of the document\n"
f" \n"
f" The paragraphs comes after previous paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['before']}```\n"
f" Make sure that the paragraph relates with previous paragraph without any repetition\n"
f" \n"
f" The paragraphs comes before next paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['after']}```\n"
f" Make sure that the paragraph prepares the transition to the next paragraph without any repetition\n"
f" \n"
f" \n"
f"\n"
f" ")
llm = openai_llm
p = llm(template)
return p
def get_private_paragraph(texts, task: {}) -> str:
"""useful to get a summary in one line from wiki index"""
text_content = ""
for t in texts:
text_content += t + "/n/n"
template = (f"\n"
f" Your task consists in generating a paragraph\\n"
f" whose description is delimited by triple backticks: ```{task['description']}```\n"
f"\n"
f" The text generation is based in the documents provided in these sections \n"
f" delimited by by triple backticks: ``` {text_content}``` \n"
f" The paragraph belongs at the top level of the hierarchy to a document \\n"
f" whose description is delimited by triple backticks: ``` {task['doc_description']}```\n"
f" Make sure that the paragraph relates the top level of the document\n"
f" \n"
f" The paragraph belongs to a higher paragraph in the hierarchy \\n"
f" whose description is delimited by triple backticks: ``` {task['above']}```\n"
f" Make sure that the paragraph relates with the paragraph in the hierarchy of the document\n"
f" \n"
f" The paragraphs comes after previous paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['before']}```\n"
f" Make sure that the paragraph relates with previous paragraph without any repetition\n"
f" \n"
f" The paragraphs comes before next paragraphs \\n"
f" whose description is delimited by triple backticks: ``` {task['after']}```\n"
f" Make sure that the paragraph prepares the transition to the next paragraph without any repetition\n"
f" \n"
f" \n"
f"\n"
f" ")
llm = openai_llm
p = llm(template)
return p
|