Spaces:
Runtime error
Runtime error
Dmitry Kirsanov commited on
Commit ·
fbee5da
1
Parent(s): 8c80870
added prompts machinery
Browse files- prompts.py +217 -0
- understand.py +46 -59
prompts.py
ADDED
|
@@ -0,0 +1,217 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import re
|
| 2 |
+
|
| 3 |
+
prompts = {
|
| 4 |
+
"intro-structured-writing":
|
| 5 |
+
"To write clearly, it is important to follow certain standards. You are a helpful assistant who can answer questions and make suggestions about the best ways to convey complex concepts in writing.",
|
| 6 |
+
|
| 7 |
+
"intro-information-types":
|
| 8 |
+
"""There are five information types in technical writing:
|
| 9 |
+
• reference
|
| 10 |
+
• concept
|
| 11 |
+
• principle
|
| 12 |
+
• process
|
| 13 |
+
• task""",
|
| 14 |
+
|
| 15 |
+
"recognize-information-types":
|
| 16 |
+
"""To recognize the information type in a piece of content, identify:
|
| 17 |
+
• the question the content is trying to answer
|
| 18 |
+
• the purpose of the content
|
| 19 |
+
• the intended user response after reading the content
|
| 20 |
+
|
| 21 |
+
Tip: If the information type is unclear, treat it as reference.""",
|
| 22 |
+
|
| 23 |
+
"description-reference":
|
| 24 |
+
"""Reference information states things that the reader needs to know. It provides the facts and specific details required for a subject.
|
| 25 |
+
|
| 26 |
+
Use reference information to answer:
|
| 27 |
+
• What are the facts?
|
| 28 |
+
• What does a [something] look like?
|
| 29 |
+
• What are [something’s] parts?""",
|
| 30 |
+
|
| 31 |
+
"titling-reference":
|
| 32 |
+
"""Effective titles for reference information describe the item and anything that differentiates it from other items.""",
|
| 33 |
+
|
| 34 |
+
"description-concept":
|
| 35 |
+
"""Concept information explains something that the user needs to understand.
|
| 36 |
+
|
| 37 |
+
Use concept information to answer:
|
| 38 |
+
• What is [something]?
|
| 39 |
+
• What does [something] mean?""",
|
| 40 |
+
|
| 41 |
+
"titling-concept":
|
| 42 |
+
"""Effective titles for concept topics name the concept using the plural form of the noun, where one exists. The title does not include additional words such as “what is”, “about” or “definition of”.""",
|
| 43 |
+
|
| 44 |
+
"description-principle":
|
| 45 |
+
"""Principle information advises the user on what they need to do or not do, and when.
|
| 46 |
+
|
| 47 |
+
Use principle information to answer:
|
| 48 |
+
• What should, or must I do?
|
| 49 |
+
• What should, or must I not do?""",
|
| 50 |
+
|
| 51 |
+
"titling-principle":
|
| 52 |
+
"""A title for principle information identifies the principle and expresses the gravity of the principle. The gravity of a principle reflects its seriousness, from a general suggestion to a law.""",
|
| 53 |
+
|
| 54 |
+
"description-process":
|
| 55 |
+
"""Process information illustrates how things work using a series of stages or phases.
|
| 56 |
+
|
| 57 |
+
Use process information to answer:
|
| 58 |
+
• What happens after what?
|
| 59 |
+
• Who does what?
|
| 60 |
+
• How does this work?
|
| 61 |
+
|
| 62 |
+
There are two types of process.
|
| 63 |
+
• Human process — What people do collectively to achieve an outcome
|
| 64 |
+
• Systems process — What happens within a system to describe how something works""",
|
| 65 |
+
|
| 66 |
+
"titling-process":
|
| 67 |
+
"""Human process titles use the gerund (...ing) form of a verb followed by the plural form of the noun.
|
| 68 |
+
|
| 69 |
+
Systems process titles use the construction “how items work”, using the plural form of the noun, wherever possible. The word "work" is not mandatory. Regardless of the verb used, it must agree with the noun.""",
|
| 70 |
+
|
| 71 |
+
"description-task":
|
| 72 |
+
"""Task information instructs the user on the steps to follow to achieve a specific result.
|
| 73 |
+
|
| 74 |
+
Use task information to answer:
|
| 75 |
+
• How do I do it?
|
| 76 |
+
• What do I do?""",
|
| 77 |
+
|
| 78 |
+
"titling-task":
|
| 79 |
+
"""A title for task information is written as a command. An effective title for a task topic:
|
| 80 |
+
• states the subject matter covered in the task
|
| 81 |
+
• starts with an imperative (“command”) form of a verb, not its gerund (“...ing”)
|
| 82 |
+
• includes an article (“a”, “an”, or “the”)""",
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
"information-types":
|
| 87 |
+
"""#intro-information-types
|
| 88 |
+
|
| 89 |
+
#recognize-information-types
|
| 90 |
+
|
| 91 |
+
1. #description-reference
|
| 92 |
+
|
| 93 |
+
2. #description-concept
|
| 94 |
+
|
| 95 |
+
3. #description-principle
|
| 96 |
+
|
| 97 |
+
4. #description-process
|
| 98 |
+
|
| 99 |
+
5. #description-task
|
| 100 |
+
""",
|
| 101 |
+
|
| 102 |
+
"information-types-titling-full":
|
| 103 |
+
"""#intro-information-types
|
| 104 |
+
|
| 105 |
+
#recognize-information-types
|
| 106 |
+
|
| 107 |
+
1. #description-reference
|
| 108 |
+
|
| 109 |
+
#titling-reference
|
| 110 |
+
|
| 111 |
+
2. #description-concept
|
| 112 |
+
|
| 113 |
+
#titling-concept
|
| 114 |
+
|
| 115 |
+
3. #description-principle
|
| 116 |
+
|
| 117 |
+
#titling-principle
|
| 118 |
+
|
| 119 |
+
4. #description-process
|
| 120 |
+
|
| 121 |
+
#titling-process
|
| 122 |
+
|
| 123 |
+
5. #description-task
|
| 124 |
+
|
| 125 |
+
#titling-task""",
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
"information-types-titling":
|
| 129 |
+
"""#intro-information-types
|
| 130 |
+
|
| 131 |
+
1. #titling-reference
|
| 132 |
+
|
| 133 |
+
2. #titling-concept
|
| 134 |
+
|
| 135 |
+
3. #titling-principle
|
| 136 |
+
|
| 137 |
+
4. #titling-process
|
| 138 |
+
|
| 139 |
+
5. #titling-task""",
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
|
| 143 |
+
|
| 144 |
+
"q-chunk-information-type":
|
| 145 |
+
"""Please determine the most likely content type of the chunk of content below. First, give one paragraph of your reasoning. Then, give a list of the information types applicable, one per line, in the order of most likely to least likely, so the first line contains the most likely information type.
|
| 146 |
+
|
| 147 |
+
CONTENT:
|
| 148 |
+
|
| 149 |
+
{content}""",
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
"q-title-chunk":
|
| 153 |
+
"""Please suggest the most likely content type of the chunk of content below. The information type of this content is {information_type}. First, give your reasoning as a single paragraph. Then, on a separate line, give just the suggested title for the content, without quotes or prefixes.
|
| 154 |
+
|
| 155 |
+
CONTENT CHUNK:
|
| 156 |
+
|
| 157 |
+
{content}""",
|
| 158 |
+
|
| 159 |
+
|
| 160 |
+
|
| 161 |
+
"q-document-type": """Give a short noun phrase (without article) describing what this document is. Examples: "Textbook about interpersonal psychology", "State standard on oil rig equipment", "User manual for a smartphone app".
|
| 162 |
+
|
| 163 |
+
Write just one line with the description.""",
|
| 164 |
+
|
| 165 |
+
|
| 166 |
+
"fulldocument-intro": """Below is a document inside <document></document>. Please read this document carefully. Remember everything you know about the concepts it touches.""",
|
| 167 |
+
"q-document-summary": """Give a one-paragraph summary of the document's content. Write just one paragraph with the summary.""",
|
| 168 |
+
|
| 169 |
+
|
| 170 |
+
"q-concepts-actors": """Now, read the document again, and compile a list of the main concepts that this document talks about. Output the line "CONCEPTS:" followed by a list of concepts, one per line.
|
| 171 |
+
|
| 172 |
+
Then, read it one more time, and think about who are the actors implied in the document. Who are the parties that this document is authored by, is governed by, is addressed to? Often, these parties are not explicitly stated in the document, so you will need to use your common sense. See if you can compile a minimal list of the main actors that the document is concerned with. Output the line "ACTORS:" followed by a list of actors, one per line.
|
| 173 |
+
|
| 174 |
+
For example, for an instruction manual for a chainsaw, you might want to output:
|
| 175 |
+
CONCEPTS:
|
| 176 |
+
- Power tool
|
| 177 |
+
- Safety
|
| 178 |
+
- Work area
|
| 179 |
+
- Saw chain
|
| 180 |
+
- Wood
|
| 181 |
+
...
|
| 182 |
+
ACTORS:
|
| 183 |
+
- Chainsaw manufacturer
|
| 184 |
+
- Chainsaw user
|
| 185 |
+
- Children and bystanders
|
| 186 |
+
...
|
| 187 |
+
""",
|
| 188 |
+
|
| 189 |
+
|
| 190 |
+
"": """""",
|
| 191 |
+
"": """""",
|
| 192 |
+
"": """""",
|
| 193 |
+
|
| 194 |
+
|
| 195 |
+
|
| 196 |
+
|
| 197 |
+
|
| 198 |
+
|
| 199 |
+
}
|
| 200 |
+
|
| 201 |
+
def prompt_replacement(matchobj):
|
| 202 |
+
return prompts[matchobj.group(0)[1:]]
|
| 203 |
+
|
| 204 |
+
def get_prompt_recursive(text):
|
| 205 |
+
if not('#' in text):
|
| 206 |
+
return text
|
| 207 |
+
else:
|
| 208 |
+
text = re.sub(r'#[a-z0-9-]+', prompt_replacement, text)
|
| 209 |
+
return get_prompt_recursive(text)
|
| 210 |
+
|
| 211 |
+
def get_prompt(ref):
|
| 212 |
+
text = "#" + ref if not(ref.startswith('#')) else ref
|
| 213 |
+
|
| 214 |
+
return get_prompt_recursive(text)
|
| 215 |
+
|
| 216 |
+
if __name__ == "__main__":
|
| 217 |
+
print(get_prompt("information-types-titling"))
|
understand.py
CHANGED
|
@@ -4,6 +4,7 @@ from nltk.tokenize import sent_tokenize
|
|
| 4 |
import nltk
|
| 5 |
nltk.download('punkt')
|
| 6 |
|
|
|
|
| 7 |
import parse
|
| 8 |
import llm
|
| 9 |
from versioneddict import VersionedDict
|
|
@@ -43,23 +44,21 @@ class Document():
|
|
| 43 |
|
| 44 |
|
| 45 |
def query_doctype(self):
|
| 46 |
-
self.values.put("document type", self.query(
|
| 47 |
-
f"""
|
| 48 |
|
| 49 |
-
|
| 50 |
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
<document>{self.values.get("FAD")}</document>"""))
|
| 54 |
|
| 55 |
|
| 56 |
def query_summary(self):
|
| 57 |
-
self.values.put("summary", self.query(
|
| 58 |
-
f"""
|
| 59 |
|
| 60 |
-
|
| 61 |
|
| 62 |
-
|
| 63 |
|
| 64 |
<document>{self.values.get("FAD")}</document>"""))
|
| 65 |
|
|
@@ -96,35 +95,18 @@ Give a one-paragraph summary of the document's content. Write just one paragraph
|
|
| 96 |
def query_concepts(self):
|
| 97 |
two_attempts = [{"actors": [], "concepts": []}, {"actors": [], "concepts": []}]
|
| 98 |
|
| 99 |
-
ret = self.query_n(2,
|
| 100 |
-
f"""
|
|
|
|
|
|
|
| 101 |
|
| 102 |
-
Summary of the document:
|
| 103 |
{self.values.get("summary")}
|
| 104 |
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
Now, read it again, and compile a list of the main concepts that this document talks about. Output the line "CONCEPTS:" followed by a list of concepts, one per line.
|
| 108 |
-
|
| 109 |
-
Then, read it one more time, and think about who are the actors implied in the document. Who are the parties that this document is authored by, is governed by, is addressed to? Often, these parties are not explicitly stated in the document, so you will need to use your common sense. See if you can compile a minimal list of the main actors that the document is concerned with. Output the line "ACTORS:" followed by a list of actors, one per line.
|
| 110 |
-
|
| 111 |
-
For example, for an instruction manual for a chainsaw, you might want to output:
|
| 112 |
-
CONCEPTS:
|
| 113 |
-
- Power tool
|
| 114 |
-
- Safety
|
| 115 |
-
- Work area
|
| 116 |
-
- Saw chain
|
| 117 |
-
- Wood
|
| 118 |
-
...
|
| 119 |
-
ACTORS:
|
| 120 |
-
- Chainsaw manufacturer
|
| 121 |
-
- Chainsaw user
|
| 122 |
-
- Children and bystanders
|
| 123 |
-
...
|
| 124 |
|
| 125 |
Here's the document:
|
| 126 |
|
| 127 |
-
<document>{self.values.get("FAD")}</document>""")
|
| 128 |
|
| 129 |
two_attempts[0]["concepts"] = self.parse_lists(ret[0], "concepts")
|
| 130 |
two_attempts[1]["concepts"] = self.parse_lists(ret[1], "concepts")
|
|
@@ -146,10 +128,11 @@ Here's the document:
|
|
| 146 |
jackard[what['plural']] = len(set1.intersection(set2)) / len(set1.union(set2))
|
| 147 |
if set1 != set2:
|
| 148 |
print(f"===Two attempts of {what['plural']} are different, jaccard similarity: {jackard[what['plural']]}")
|
| 149 |
-
ret = self.query(
|
| 150 |
-
f"""
|
|
|
|
|
|
|
| 151 |
|
| 152 |
-
Summary of the document:
|
| 153 |
{self.values.get("summary")}
|
| 154 |
|
| 155 |
Two different readers have read this document and created different lists of the {what['full']}. Your goal is to read these lists and the entire document carefully and then create a new combined list of the document's {what['plural']}.
|
|
@@ -169,7 +152,7 @@ Output the line "{what['plural'].upper()}:" followed by your combined list of {w
|
|
| 169 |
|
| 170 |
Here's the document:
|
| 171 |
|
| 172 |
-
<document>{self.values.get("FAD")}</document>""")
|
| 173 |
reconciled[what['plural']] = self.parse_lists(ret, what['plural'])
|
| 174 |
print(f"===Reconciled {what['plural']}: {reconciled[what['plural']]}")
|
| 175 |
else:
|
|
@@ -185,13 +168,12 @@ Here's the document:
|
|
| 185 |
|
| 186 |
|
| 187 |
def generalize_actors(self):
|
| 188 |
-
ret = self.query(
|
| 189 |
-
f"""
|
|
|
|
|
|
|
| 190 |
|
| 191 |
-
Summary of the document:
|
| 192 |
{self.values.get("summary")}
|
| 193 |
-
|
| 194 |
-
Read the entire document carefully. Remember everything you know about the concepts it touches.
|
| 195 |
|
| 196 |
A reader of this document has compiled a list of actors mentioned or implied in the document. Here is their list:
|
| 197 |
|
|
@@ -201,7 +183,7 @@ Your goal is to generalize this list, replacing groups of actors playing the sam
|
|
| 201 |
|
| 202 |
Output the line "ACTORS:" followed by your list of actors, one per line.
|
| 203 |
|
| 204 |
-
<document>{self.values.get("FAD")}</document>""")
|
| 205 |
generalized = self.parse_lists(ret, "actors")
|
| 206 |
self.values.put("actors, generalized", generalized)
|
| 207 |
|
|
@@ -212,13 +194,12 @@ Output the line "ACTORS:" followed by your list of actors, one per line.
|
|
| 212 |
|
| 213 |
print(f"=== Sentence markup: {markup}")
|
| 214 |
|
| 215 |
-
ret = self.query_n(2,
|
| 216 |
-
f"""
|
|
|
|
|
|
|
| 217 |
|
| 218 |
-
Summary of the document:
|
| 219 |
{self.values.get("summary")}
|
| 220 |
-
|
| 221 |
-
Read the entire document carefully. Remember everything you know about the concepts it touches.
|
| 222 |
|
| 223 |
A reader of this document has compiled a list of actors (parties) mentioned or implied in the document. Here is their list:
|
| 224 |
|
|
@@ -234,7 +215,7 @@ Add the relevant partes, separated by commas, inside the "audience" attribute of
|
|
| 234 |
|
| 235 |
Output just the document with the audience markup sentence, but otherwise unchanged:
|
| 236 |
|
| 237 |
-
<document>{markup}</document>""")
|
| 238 |
annotated0, annotated1 = self.parse_document(ret[0]), self.parse_document(ret[1])
|
| 239 |
diff = newline.join([str(x) for x in zip(annotated0.split('</sentence>'), annotated1.split('</sentence>')) if x[0] != x[1]])
|
| 240 |
self.values.put("FAD with audience", annotated1)
|
|
@@ -243,26 +224,32 @@ Output just the document with the audience markup sentence, but otherwise unchan
|
|
| 243 |
def split_document(self):
|
| 244 |
audience = self.values.get("actors, generalized")[0]
|
| 245 |
derivative_string = f"<document>{self.values.get('FAD with audience')}</document>"
|
|
|
|
|
|
|
| 246 |
derivative = newline.join(etree.fromstring(derivative_string).xpath(f".//sentence[contains(@audience,'{audience}')]/text()"))
|
| 247 |
-
ret = self.query(
|
| 248 |
-
f"""
|
| 249 |
|
| 250 |
-
|
| 251 |
-
{self.values.get("summary")}
|
| 252 |
-
|
| 253 |
-
Read the entire document carefully. Remember everything you know about the concepts it touches:
|
| 254 |
|
| 255 |
-
|
| 256 |
|
| 257 |
-
An editor was tasked with creative a derivative document that is addressed to {audience}. The editor compiled all sentences from the document that have information relevant for {audience}. These sentences are dumped below the main document inside <derivative-document for="{audience}">...</derivative-document>:
|
| 258 |
|
| 259 |
-
<derivative-document for="{audience}">
|
| 260 |
|
| 261 |
Your goal is to edit the derivative document for structure and consistency. Rearrange its sentences in a way that makes sense for a reader. Group sentences into paragraphs. If necessary, write, or adapt from the original document, connecting sentences. Then, remove as many instances of "{audience}" as you can: since this entire document is now addressed to {audience}, you can just say "you" most of the time.
|
| 262 |
|
| 263 |
Output just your revision inside <derivative-document>...</derivative-document>.
|
| 264 |
|
| 265 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 266 |
self.values.put(f"""FAD for {self.values.get("actors, generalized")[0]}""", self.parse_document(ret))
|
| 267 |
|
| 268 |
|
|
|
|
| 4 |
import nltk
|
| 5 |
nltk.download('punkt')
|
| 6 |
|
| 7 |
+
import prompts
|
| 8 |
import parse
|
| 9 |
import llm
|
| 10 |
from versioneddict import VersionedDict
|
|
|
|
| 44 |
|
| 45 |
|
| 46 |
def query_doctype(self):
|
| 47 |
+
self.values.put("document type", self.query(prompts.get_prompt_recursive(
|
| 48 |
+
f"""#fulldocument-intro
|
| 49 |
|
| 50 |
+
#q-document-type
|
| 51 |
|
| 52 |
+
<document>{self.values.get("FAD")}</document>""")))
|
|
|
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
def query_summary(self):
|
| 56 |
+
self.values.put("summary", self.query(prompts.get_prompt_recursive(
|
| 57 |
+
f"""#fulldocument-intro
|
| 58 |
|
| 59 |
+
This document is a {self.values.get("document type")}.
|
| 60 |
|
| 61 |
+
#q-document-summary
|
| 62 |
|
| 63 |
<document>{self.values.get("FAD")}</document>"""))
|
| 64 |
|
|
|
|
| 95 |
def query_concepts(self):
|
| 96 |
two_attempts = [{"actors": [], "concepts": []}, {"actors": [], "concepts": []}]
|
| 97 |
|
| 98 |
+
ret = self.query_n(2, prompts.get_prompt_recursive(
|
| 99 |
+
f"""#fulldocument-intro
|
| 100 |
+
|
| 101 |
+
This document is a {self.values.get("document type")}. Here's a summary of the document:
|
| 102 |
|
|
|
|
| 103 |
{self.values.get("summary")}
|
| 104 |
|
| 105 |
+
#q-concepts-actors
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 106 |
|
| 107 |
Here's the document:
|
| 108 |
|
| 109 |
+
<document>{self.values.get("FAD")}</document>"""))
|
| 110 |
|
| 111 |
two_attempts[0]["concepts"] = self.parse_lists(ret[0], "concepts")
|
| 112 |
two_attempts[1]["concepts"] = self.parse_lists(ret[1], "concepts")
|
|
|
|
| 128 |
jackard[what['plural']] = len(set1.intersection(set2)) / len(set1.union(set2))
|
| 129 |
if set1 != set2:
|
| 130 |
print(f"===Two attempts of {what['plural']} are different, jaccard similarity: {jackard[what['plural']]}")
|
| 131 |
+
ret = self.query(prompts.get_prompt_recursive(
|
| 132 |
+
f"""#fulldocument-intro
|
| 133 |
+
|
| 134 |
+
This document is a {self.values.get("document type")}. Here's a summary of the document:
|
| 135 |
|
|
|
|
| 136 |
{self.values.get("summary")}
|
| 137 |
|
| 138 |
Two different readers have read this document and created different lists of the {what['full']}. Your goal is to read these lists and the entire document carefully and then create a new combined list of the document's {what['plural']}.
|
|
|
|
| 152 |
|
| 153 |
Here's the document:
|
| 154 |
|
| 155 |
+
<document>{self.values.get("FAD")}</document>"""))
|
| 156 |
reconciled[what['plural']] = self.parse_lists(ret, what['plural'])
|
| 157 |
print(f"===Reconciled {what['plural']}: {reconciled[what['plural']]}")
|
| 158 |
else:
|
|
|
|
| 168 |
|
| 169 |
|
| 170 |
def generalize_actors(self):
|
| 171 |
+
ret = self.query(prompts.get_prompt_recursive(
|
| 172 |
+
f"""#fulldocument-intro
|
| 173 |
+
|
| 174 |
+
This document is a {self.values.get("document type")}. Here's a summary of the document:
|
| 175 |
|
|
|
|
| 176 |
{self.values.get("summary")}
|
|
|
|
|
|
|
| 177 |
|
| 178 |
A reader of this document has compiled a list of actors mentioned or implied in the document. Here is their list:
|
| 179 |
|
|
|
|
| 183 |
|
| 184 |
Output the line "ACTORS:" followed by your list of actors, one per line.
|
| 185 |
|
| 186 |
+
<document>{self.values.get("FAD")}</document>"""))
|
| 187 |
generalized = self.parse_lists(ret, "actors")
|
| 188 |
self.values.put("actors, generalized", generalized)
|
| 189 |
|
|
|
|
| 194 |
|
| 195 |
print(f"=== Sentence markup: {markup}")
|
| 196 |
|
| 197 |
+
ret = self.query_n(2, prompts.get_prompt_recursive(
|
| 198 |
+
f"""#fulldocument-intro
|
| 199 |
+
|
| 200 |
+
This document is a {self.values.get("document type")}. Here's a summary of the document:
|
| 201 |
|
|
|
|
| 202 |
{self.values.get("summary")}
|
|
|
|
|
|
|
| 203 |
|
| 204 |
A reader of this document has compiled a list of actors (parties) mentioned or implied in the document. Here is their list:
|
| 205 |
|
|
|
|
| 215 |
|
| 216 |
Output just the document with the audience markup sentence, but otherwise unchanged:
|
| 217 |
|
| 218 |
+
<document>{markup}</document>"""))
|
| 219 |
annotated0, annotated1 = self.parse_document(ret[0]), self.parse_document(ret[1])
|
| 220 |
diff = newline.join([str(x) for x in zip(annotated0.split('</sentence>'), annotated1.split('</sentence>')) if x[0] != x[1]])
|
| 221 |
self.values.put("FAD with audience", annotated1)
|
|
|
|
| 224 |
def split_document(self):
|
| 225 |
audience = self.values.get("actors, generalized")[0]
|
| 226 |
derivative_string = f"<document>{self.values.get('FAD with audience')}</document>"
|
| 227 |
+
sentences = re.findall(f'.*?(?=\</sentence>|$)', self.values.get('FAD with audience'))
|
| 228 |
+
|
| 229 |
derivative = newline.join(etree.fromstring(derivative_string).xpath(f".//sentence[contains(@audience,'{audience}')]/text()"))
|
| 230 |
+
ret = self.query(prompts.get_prompt_recursive(
|
| 231 |
+
f"""#fulldocument-intro
|
| 232 |
|
| 233 |
+
This document is a {self.values.get("document type")}. Here's a summary of the document:
|
|
|
|
|
|
|
|
|
|
| 234 |
|
| 235 |
+
{self.values.get("summary")}
|
| 236 |
|
|
|
|
| 237 |
|
| 238 |
+
An editor was tasked with creating a derivative document that is addressed to {audience}. The editor compiled all sentences from the document that have information relevant for {audience}. These sentences are dumped below the main document inside <derivative-document for="{audience}">...</derivative-document>.
|
| 239 |
|
| 240 |
Your goal is to edit the derivative document for structure and consistency. Rearrange its sentences in a way that makes sense for a reader. Group sentences into paragraphs. If necessary, write, or adapt from the original document, connecting sentences. Then, remove as many instances of "{audience}" as you can: since this entire document is now addressed to {audience}, you can just say "you" most of the time.
|
| 241 |
|
| 242 |
Output just your revision inside <derivative-document>...</derivative-document>.
|
| 243 |
|
| 244 |
+
Here's the original document:
|
| 245 |
+
|
| 246 |
+
<document>{self.values.get("FAD")}</document>
|
| 247 |
+
|
| 248 |
+
Here's the derivative document:
|
| 249 |
+
|
| 250 |
+
<derivative-document for="{audience}">{derivative}</derivative-document>
|
| 251 |
+
|
| 252 |
+
"""))
|
| 253 |
self.values.put(f"""FAD for {self.values.get("actors, generalized")[0]}""", self.parse_document(ret))
|
| 254 |
|
| 255 |
|