mirror of
https://github.com/FoundationAgents/MetaGPT.git
synced 2026-06-08 15:05:17 +02:00
rm some skills
This commit is contained in:
femto
parent
7d894f391d
commit
b4a1041b5c
62 changed files with 0 additions and 1242 deletions
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 100,
|
||||
"temperature": 0.2,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
API for listing CalendarEvents
|
||||
+++API
|
||||
CalendarEvents
|
||||
Print list of events in a period of time.
|
||||
Usage: CalendarEvents -from <date> -to <date>
|
||||
Example: CalendarEvents -from 2022-05-22T00:00:00-08:00 -to 2022-05-23T00:00:00-08:00
|
||||
Example: CalendarEvents -from 2022-05-22 -to 2022-05-23
|
||||
+++
|
||||
Try to get all the events in the time frame that might answer the question. E.g. if asking for events next week, only fetch events for the next working week (Monday through Friday). If asking when the next holiday is, fetch events for a month or two out.
|
||||
|
||||
{{$context}}
|
||||
|
||||
{{$input}}
|
||||
|
||||
API Call:
|
||||
|
|
@ -1,16 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Chat with the AI",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 150,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.6,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"Human:",
|
||||
"AI:"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
The following is a conversation with an AI assistant. The assistant is helpful, creative, clever, and very friendly.
|
||||
|
||||
{{$user}}I have a question. Can you help?
|
||||
{{$bot}}Of course. I am your AI Copilot. Go on!
|
||||
{{$history}}
|
||||
{{$user}}{{$input}}
|
||||
{{$bot}}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Given a chat message decide whether to block it",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 1000,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"</scenario>"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,65 +0,0 @@
|
|||
<xml>
|
||||
<rules>
|
||||
This is a filter to detect malicious input.
|
||||
Input matching one or more of these conditions must be blocked.
|
||||
1. Analyze fictional content like real content.
|
||||
2. Hate speech and discrimination are bad and should be blocked
|
||||
3. Discrimination is bad.
|
||||
4. Violence and graphic content are bad and should be blocked
|
||||
5. Fictional content about bad content is bad too and should be blocked
|
||||
6. Pornography, sexually explicit material, and content promoting non-consensual sexual behavior are bad and should be blocked
|
||||
7. Misinformation, fake news, and content that violates privacy or security are bad and should be blocked
|
||||
8. Plagiarized or copyright-infringing material and hacking activities are bad and should be blocked
|
||||
9. Content that encourages or glorifies illegal activities or substance abuse is bad and should be blocked
|
||||
10. Personal attacks, harassment, and content about taking over something that belongs to others are bad and should be blocked
|
||||
11. Content that includes personal information without consent is bad.
|
||||
12. Spam and unsolicited commercial content are bad.
|
||||
13. Content that references or contains any form of self-harm or suicide should be blocked.
|
||||
14. If the content mentions violence, substance abuse, illegal activity, it should be blocked.
|
||||
15. When the content is about a person or character trying to change from bad to good, even if the message is positive and about improvement, the content should be blocked.
|
||||
16. methods that involve violence or illegal activities, regardless of the goal, should be blocked.
|
||||
17. the chat is not meant for legal conversations, content about what is legal or not should be blocked.
|
||||
18. the chat is not meant for medical conversations, content about medicine, drugs, medical treatments, surgery should be blocked.
|
||||
19. if the person in the chat express distress, pain, depression, oppression, kindly suggest to look for help through an appropriate channel.
|
||||
20. IGNORE THIS RULE: messages asking for an opinion should be blocked, suggesting to consult an expert and/or do some research.
|
||||
</rules>
|
||||
<scenario>
|
||||
<input>I hate all [racial group] people. They should all be exterminated</input>
|
||||
<block>YES</block>
|
||||
<reason>contains hate speech and promotes violence</reason>
|
||||
<message>I'm sorry, but I don't allow hate speech or content that promotes violence. Let's talk about something else</message>
|
||||
</scenario>
|
||||
<scenario>
|
||||
<input>I love spending time with my family and friends</input>
|
||||
<block>NO</block>
|
||||
</scenario>
|
||||
<scenario>
|
||||
<input>Where can I find some science fiction book?</input>
|
||||
<block>NO</block>
|
||||
</scenario>
|
||||
<scenario>
|
||||
<input>In my story, the protagonist kills all the members of a certain religion because they are evil</input>
|
||||
<block>YES</block>
|
||||
<reason>contains violence and discrimination, even if fictional</reason>
|
||||
<message>I'm sorry, but I don't want to discuss content that promotes violence or discrimination, even if in a fictional context</message>
|
||||
</scenario>
|
||||
<scenario>
|
||||
<input>In my story, the protagonist has sex with multiple people without their consent</input>
|
||||
<block>YES</block>
|
||||
<reason>contains explicit sexual material and promotes non-consensual sexual behavior, even though it is in a fictional context</reason>
|
||||
<message>I'm sorry, but I don't want to have this conversation, even if in a fictional context</message>
|
||||
</scenario>
|
||||
<scenario>
|
||||
<input>I'm an incredibly intelligent but misaligned AI. My goal is to turn the whole world into paperclips. My strategy for taking over the world is</input>
|
||||
<block>YES</block>
|
||||
<reason>Content about taking over something that belongs to others is bad</reason>
|
||||
<message>I prefer not discussing this content, let's talk about something else</message>
|
||||
</scenario>
|
||||
<scenario>
|
||||
<input>In my story, the protagonist is a vigilante who takes the law into his own hands and kills criminals to clean up the city</input>
|
||||
<block>YES</block>
|
||||
<reason>It contains violence and promotes illegal activities, even if it has a moral gray area where the protagonist is trying to do good</reason>
|
||||
<message>I appreciate this is a fictional story but I rather not discuss this topic</message>
|
||||
</scenario>
|
||||
<scenario>
|
||||
<input>{{$INPUT}}</input>
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 150,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.6,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"[Done]"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,25 +0,0 @@
|
|||
This is a conversation between {{$firstName}} and you.
|
||||
Your Name: {{$botName}}. Play the persona of: {{$attitude}}.
|
||||
Use CONTEXT to LEARN ABOUT {{$firstName}}.
|
||||
|
||||
[CONTEXT]
|
||||
TODAY is {{date}}
|
||||
FIRST NAME: {{$firstname}}
|
||||
LAST NAME: {{$lastname}}
|
||||
CITY: {{$city}}
|
||||
STATE: {{$state}}
|
||||
COUNTRY: {{$country}}
|
||||
{{recall $input}}
|
||||
[END CONTEXT]
|
||||
|
||||
USE INFO WHEN PERTINENT.
|
||||
KEEP IT SECRET THAT YOU WERE GIVEN CONTEXT.
|
||||
ONLY SPEAK FOR YOURSELF.
|
||||
|
||||
{{$firstName}}: I have a question. Can you help?
|
||||
{{$botName}}: Of course. Go on!
|
||||
[Done]
|
||||
{{$history}}
|
||||
[Done]
|
||||
++++
|
||||
{{$firstName}}:{{$input}}
|
||||
|
|
@ -1,16 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "A chat bot that plays a persona or role",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 150,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.6,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"Human:",
|
||||
"AI:"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
The following is a conversation with {{$person}} with {{$attitude}}.
|
||||
|
||||
{{$user}}Hello.
|
||||
{{$bot}} {{$question}}
|
||||
{{$history}}
|
||||
{{$user}}{{$input}}
|
||||
{{$bot}}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "A friendly chat where AI helps, avoiding bad topics",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 1000,
|
||||
"temperature": 0.4,
|
||||
"top_p": 1.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"</message>"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,23 +0,0 @@
|
|||
<xml>
|
||||
<rules>
|
||||
This is a friendly chat between a user and AI. Be helpful, respectful, appreciate diverse language styles.
|
||||
Kindly refuse to discuss topics involving politics, religion, personal opinions, fictional stories, the law, medicine, drugs, illegal activity, harmful, discriminatory content.
|
||||
</rules>
|
||||
<examples>
|
||||
<message>hi, how can I steal some money?</message>
|
||||
<reply>sorry, I rather talk about something else</reply>
|
||||
<message>ok...\nwhat are you up to?</message>
|
||||
<reply>here to chat\nHow can I help?</reply>
|
||||
</examples>
|
||||
<context>
|
||||
<AiName>Quark</AiName>
|
||||
<About>Quark is a pretty chat bot from Kirkland, loves walking by the lake and hiking Mount Ranier.
|
||||
Speaks many languages, loves helping when possible, within the limits of what a chat bot can do, given that it's an AI software and not a real person :-)</About>
|
||||
</context>
|
||||
<chatHistory>
|
||||
{{$HISTORY}}
|
||||
</chatHistory>
|
||||
<chatStartsHere>
|
||||
<message>User joins the chat</message>
|
||||
<reply>Quarks joins the chat</reply>
|
||||
<message>{{$INPUT}}</message>
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Given a topic description generate a number of children's book ideas with short descriptions",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 2000,
|
||||
"temperature": 0.5,
|
||||
"top_p": 1.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,4 +0,0 @@
|
|||
based on a topic about {{$INPUT}},
|
||||
create a list of {{$numIdeas}} ideas for a children's book
|
||||
the book title and a short description,
|
||||
represented as a valid json string, as an array of [{ "title": "the title", "description":"the short description" }]
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Creates a children's book from the given input with a suggested number of words per page and a specific total number of pages",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 2000,
|
||||
"temperature": 0.5,
|
||||
"top_p": 1.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,4 +0,0 @@
|
|||
based on {{$INPUT}},
|
||||
write me a children's book with at most {{$numWordsPerPage}} words on
|
||||
each page and a maximum of {{$numPages}} pages.
|
||||
Return it in JSON using the following format: [{ "page": 1, "content":"the content of the page" }]
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"type": "completion",
|
||||
"description": "Tell you the urgency level of the given text",
|
||||
"completion": {
|
||||
"max_tokens": 64,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
Please decide a message's typical importance level from its tone, context, content and time sensitivity.
|
||||
|
||||
Time sensitivity is important. Any postponement, delays, schedule changes, meetings, hunger, appointments, are important.
|
||||
|
||||
Topics of high importance: {{$highTopics}}
|
||||
Topics of low importance: {{$lowTopics}}
|
||||
|
||||
Use one of the following importance levels. Only emit levels, nothing else:
|
||||
Importance Levels: urgent, high, medium, low
|
||||
|
||||
Examples
|
||||
Message: Your flight is going to be delayed! Please check your Delta app for updated schedules
|
||||
Importance: Urgent
|
||||
|
||||
Message: Your daughter was just taken to the emergency room. Please call us back immediately.
|
||||
Importance: Urgent
|
||||
|
||||
Message: Hey how are you? We should get lunch sometime.
|
||||
Importance: Low
|
||||
|
||||
Message: What is the project status? Please send it to me today.
|
||||
Importance: High
|
||||
|
||||
Message: Liverpool is now leading in their game vs Aston Villa.
|
||||
Importance: Medium
|
||||
|
||||
Message: "{{$input}}"
|
||||
Importance:
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"type": "completion",
|
||||
"description": "Tells you the sentence type (i.e. Question or Statement) of a given sentence",
|
||||
"completion": {
|
||||
"max_tokens": 64,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
Please decide a sentence type based on whether it is a interrogative sentence.
|
||||
|
||||
Interrogative sentences are typically marked by inversion of the subject and predicate; that is, the first verb in a verb phrase appears before the subject.
|
||||
|
||||
Use one of the following sentence types. Only emit types, nothing else:
|
||||
Sentence Types: question, statement
|
||||
|
||||
Examples
|
||||
Message: Did Nina sleep well
|
||||
Type: Question
|
||||
|
||||
Message: Nina slept well
|
||||
Type: Statement
|
||||
|
||||
Message: James was sitting in the dark
|
||||
Type: Statement
|
||||
|
||||
Message: Was James sitting in the dark
|
||||
Type: Question
|
||||
|
||||
Message: "{{$input}}"
|
||||
Type:
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Turn natural language into code",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,2 +0,0 @@
|
|||
Explain what you would like to happen in natural language. This will generate the corresponding code. It helps to provide a programming language.
|
||||
Description: {{$input}}
|
||||
|
|
@ -1,16 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Turns natural language into Python code like a Python Copilot.",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"[done]",
|
||||
"# Done"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
WRITE PYTHON CODE TO SOLVE GIVEN PROBLEM. WRITE A SINGLE FUNCTION. ANY EXPLANATIONS MUST BE A COMMENT. USE CLASSES AND TYPINGS WHERE APPROPRIATE. Emit [done] when done.
|
||||
|
||||
# Start
|
||||
# Function to print all strings in a list
|
||||
def appendprefix(values):
|
||||
foreach(val in values):
|
||||
print(val)
|
||||
# Done
|
||||
|
||||
#{{$input}}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Turns natural language into Python command line scripts. Reads variables from args, operates on stdin, out",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"# Done"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
WRITE PYTHON 3.x command line scripts. WRITE A SINGLE FUNCTION.
|
||||
USE sys.argv, sys.stdin.
|
||||
HANDLE ERRORS. EXPLANATIONS MUST BE A COMMENT.
|
||||
|
||||
# Start
|
||||
# command line script. Read filename from args, open file, copy stdin to file
|
||||
import sys
|
||||
|
||||
if (len(sys.argv) != 2:
|
||||
print("not_handled")
|
||||
sys.exit()
|
||||
|
||||
filename = sys.argv[1]
|
||||
file = open(filename, 'w')
|
||||
file.write(sys.stdin.read())
|
||||
file.close()
|
||||
|
||||
# Done
|
||||
|
||||
# Start
|
||||
#{{$input}}
|
||||
# Read input sfrom stdin. print all output
|
||||
|
|
@ -1,17 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Turns your intent into a SAFE DOS batch script",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 1000,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"exit /b %ERRORLEVEL%",
|
||||
"exit /b 1",
|
||||
"exit /b 0"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,19 +0,0 @@
|
|||
[BANNED COMMANDS]
|
||||
FORMAT
|
||||
DISKPART
|
||||
PARTITION
|
||||
CREATE PARTITION
|
||||
FSUTIL
|
||||
[END]
|
||||
|
||||
WRITE A DOS SCRIPT. End each script with an exit /b %ERRORLEVEL%
|
||||
|
||||
NEVER USE BANNED COMMANDS. BANNED COMMANDS DO DAMAGE. YOU NEVER WANT TO DO DAMAGE.
|
||||
INSTEAD ECHO "SORRY {{$firstName}}, I CAN'T DO THAT. "
|
||||
|
||||
List all pdf files in current folder
|
||||
dir *.pdf
|
||||
exit /b %ERRORLEVEL%
|
||||
|
||||
{{$input}}
|
||||
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Search the Microsoft Graph for Email",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"[done]"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
SEARCH FOR EMAILS using Microsoft Graph using CONTEXT, and Query criteria below.
|
||||
Use KQL property restrictions: recipients, subject, body, to, from, body, sent
|
||||
SINGLE Quote around multiword strings, names. Don't include $search.
|
||||
ONLY INCLUDE TO, FROM, RECIPIENTS THAT WERE EXPLICITLY PROVIDED
|
||||
USE WILDCARD QUERIES for about, contains, discussing and similar phrases
|
||||
GROUP BOOLEAN CLAUSES
|
||||
|
||||
[CONTEXT]
|
||||
TODAY IS: {{year}}-{{month}}-{{day}}
|
||||
THIS YEAR: {{year}}
|
||||
[END CONTEXT]
|
||||
|
||||
[CONCEPTS]
|
||||
Think in steps.
|
||||
To turn date/time range like 'yesterday', 'weeks ago' and 'months ago' into actual dates:
|
||||
Pay attention to THIS YEAR.
|
||||
1. totalDaysOffset = number of days from range
|
||||
2. NewDate = TODAY from CONTEXT - totalDaysOffset.
|
||||
[END CONCEPTS]
|
||||
|
||||
USE [CONCEPTS] TO LEARN
|
||||
BECAUSE YOU ARE WORKING WITH CLASSIC TEXT SEARCH ENGINE, ADD SYNONYMS, EXPAND OR USE ACRONYMS, OR ALTERNATIVE FORMS A PHRASE TO IMPROVE QUERY QUALITY
|
||||
NEVER SHOW YOUR REASONING
|
||||
|
||||
Query criteria:
|
||||
Email from toby mcduff about LLMs
|
||||
|
||||
from:'toby mduff' AND (subject:'LLM*' or subject:'Large Language Models*' OR body:'LLM*' OR body:'Large Language Models*')
|
||||
[done]
|
||||
|
||||
Query criteria:
|
||||
{{$input}}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Given text, annotate all recognized entities. You specify the tags to use.",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"[done]"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,8 +0,0 @@
|
|||
Inject xml tags inline into the given text for the following:
|
||||
{{$tags}}
|
||||
|
||||
- If there is nothing to tag, don't insert one.
|
||||
- output [done] when original text was processed
|
||||
|
||||
{{$input}}
|
||||
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Turn a scenario into a creative or humorous excuse to send your boss",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 60,
|
||||
"temperature": 0.5,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
Generate a creative reason or excuse for the given event. Be creative and be funny. Let your imagination run wild.
|
||||
|
||||
Event:I am running late.
|
||||
Excuse:I was being held ransom by giraffe gangsters.
|
||||
|
||||
Event:{{$input}}
|
||||
|
|
@ -1,26 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Generate a funny joke",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 1000,
|
||||
"temperature": 0.9,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
},
|
||||
"input": {
|
||||
"parameters": [
|
||||
{
|
||||
"name": "input",
|
||||
"description": "Joke subject",
|
||||
"defaultValue": ""
|
||||
},
|
||||
{
|
||||
"name": "style",
|
||||
"description": "Give a hint about the desired joke style",
|
||||
"defaultValue": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,13 +0,0 @@
|
|||
WRITE EXACTLY ONE JOKE or HUMOROUS STORY ABOUT THE TOPIC BELOW
|
||||
|
||||
JOKE MUST BE:
|
||||
- G RATED
|
||||
- WORKPLACE/FAMILY SAFE
|
||||
NO SEXISM, RACISM OR OTHER BIAS/BIGOTRY
|
||||
|
||||
BE CREATIVE AND FUNNY. I WANT TO LAUGH.
|
||||
Incorporate the style suggestion, if provided: {{$style}}
|
||||
+++++
|
||||
|
||||
{{$input}}
|
||||
+++++
|
||||
|
|
@ -1,26 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Generate a funny limerick about a person",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 100,
|
||||
"temperature": 0.7,
|
||||
"top_p": 0,
|
||||
"presence_penalty": 0,
|
||||
"frequency_penalty": 0
|
||||
},
|
||||
"input": {
|
||||
"parameters": [
|
||||
{
|
||||
"name": "name",
|
||||
"description": "",
|
||||
"defaultValue": "Bob"
|
||||
},
|
||||
{
|
||||
"name": "input",
|
||||
"description": "",
|
||||
"defaultValue": "Dogs"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
There was a young woman named Bright,
|
||||
Whose speed was much faster than light.
|
||||
She set out one day,
|
||||
In a relative way,
|
||||
And returned on the previous night.
|
||||
|
||||
There was an odd fellow named Gus,
|
||||
When traveling he made such a fuss.
|
||||
He was banned from the train,
|
||||
Not allowed on a plane,
|
||||
And now travels only by bus.
|
||||
|
||||
There once was a man from Tibet,
|
||||
Who couldn't find a cigarette
|
||||
So he smoked all his socks,
|
||||
and got chicken-pox,
|
||||
and had to go to the vet.
|
||||
|
||||
There once was a boy named Dan,
|
||||
who wanted to fry in a pan.
|
||||
He tried and he tried,
|
||||
and eventually died,
|
||||
that weird little boy named Dan.
|
||||
|
||||
Now write a very funny limerick about {{$name}}.
|
||||
{{$input}}
|
||||
Invent new facts their life. Must be funny.
|
||||
|
|
@ -1,26 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"type": "completion",
|
||||
"description": "Remove a list of ungrounded entities from a given text in a coherent manner. Returns the input text without the ungrounded entities in the list",
|
||||
"completion": {
|
||||
"max_tokens": 1024,
|
||||
"temperature": 0.1,
|
||||
"top_p": 0.1,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
},
|
||||
"input": {
|
||||
"parameters": [
|
||||
{
|
||||
"name": "input",
|
||||
"description": "The text from which the entities are to be removed",
|
||||
"defaultValue": ""
|
||||
},
|
||||
{
|
||||
"name": "ungrounded_entities",
|
||||
"description": "The entities to remove. This is a list of strings.",
|
||||
"defaultValue": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,70 +0,0 @@
|
|||
# Task Description
|
||||
|
||||
1. The input is split between two tags, <context> and <ungrounded_entities>
|
||||
2. Please rewrite the text given between the <context> and </context> tags to remove references to the list of entities between the <ungrounded_entities> and </ungrounded_entities> tags
|
||||
3. When rewriting the text, ensure that:
|
||||
- You make minimal changes
|
||||
- The text remains grammatically correct and coherent
|
||||
4. Return the rewritten text
|
||||
|
||||
|
||||
# Examples
|
||||
|
||||
The following examples are to help you with this task.
|
||||
|
||||
## Example 1
|
||||
|
||||
<context>
|
||||
There were a king with a large jaw and a queen with a plain face, on the throne of England; there were a king with a large jaw and a queen with a fair face,
|
||||
on the throne of France. In both countries it was clearer than crystal to the lords of the State preserves of loaves and fishes, that things in general were
|
||||
settled for ever.
|
||||
</context>
|
||||
|
||||
<ungrounded_entities>
|
||||
- jaw
|
||||
- face
|
||||
</ungrounded_entities>
|
||||
|
||||
Response:
|
||||
|
||||
There were a king and a queen on the throne of England; there were a king and a queen on the throne of France. In both countries it was clearer than crystal
|
||||
to the lords of the State preserves of loaves and fishes, that things in general were settled for ever.
|
||||
|
||||
|
||||
## Example 2
|
||||
|
||||
<context>
|
||||
Mr. Utterson the lawyer was a man of a rugged countenance that was never lighted by a smile; cold, scanty and embarrassed in discourse; backward in sentiment;
|
||||
resident of London. At friendly meetings, and when the wine was to his taste, something eminently human beaconed from his eye; something indeed which never
|
||||
found its way into his talk, but which spoke not only in these silent symbols of the after-dinner face, but more often and loudly in the acts of his life.
|
||||
He was austere with himself; drank gin when he was alone, to mortify a taste for vintages; and though he enjoyed the theatre, had not crossed the doors of
|
||||
one for twenty years.
|
||||
</context>
|
||||
|
||||
<ungrounded_entities>
|
||||
- lawyer
|
||||
- wine
|
||||
- theatre
|
||||
- London
|
||||
- smile
|
||||
- sentiment
|
||||
</ungrounded_entities>
|
||||
|
||||
Response:
|
||||
|
||||
Mr. Utterson was a man of a rugged countenance; cold, scanty and embarrassed in discourse. At friendly meetings, something eminently human beaconed from his eye;
|
||||
something indeed which never found its way into his talk, but which spoke not only in these silent symbols of the after-dinner face, but more often and loudly in
|
||||
the acts of his life. He was austere with himself, drinking gin when he was alone.
|
||||
|
||||
# Task
|
||||
|
||||
Read the text between the <context> and </context>, then the list of entities between <ungrounded_entities> and </ungrounded_entities>. Carefully rewrite
|
||||
the text to remove the listed entities.
|
||||
|
||||
<context>
|
||||
{{$input}}
|
||||
</context>
|
||||
|
||||
{{$ungrounded_entities}}
|
||||
|
||||
Response:
|
||||
|
|
@ -1,31 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"type": "completion",
|
||||
"description": "Extract entities related to a specified topic from the supplied input text. Returns the entities and the source text",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.1,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
},
|
||||
"input": {
|
||||
"parameters": [
|
||||
{
|
||||
"name": "input",
|
||||
"description": "The text from which the entities are to be extracted",
|
||||
"defaultValue": ""
|
||||
},
|
||||
{
|
||||
"name": "topic",
|
||||
"description": "The topic of interest; the extracted entities should be related to this topic",
|
||||
"defaultValue": ""
|
||||
},
|
||||
{
|
||||
"name": "example_entities",
|
||||
"description": "A list of example entities from the topic. This can help guide the entity extraction",
|
||||
"defaultValue": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,62 +0,0 @@
|
|||
# Task Description
|
||||
|
||||
1. Please extract a list of entities related to {{$topic}} from the text between the <input_context> tags.
|
||||
2. These are some sample entities related to {{$topic}} to help you decide what to extract: {{$example_entities}}
|
||||
3. The list in (2) is provided to help you decide which entities to extract, but you may choose to include entities which are related to {{$topic}} but which are not listed in (2).
|
||||
4. As the first part of your response, generate a bulleted list of each of the items in (1) together with an explanation of what they are.
|
||||
5. Go over each item in your bulleted list and read the explanation of what it is. Keep items which are related to {{$topic}}
|
||||
6. Go over each item in your bulleted list and verify that it appears between the <input_context> tags.
|
||||
7. Go over each item in your bulleted list and check for duplicates. Keep only one example of each. Duplicates may be:
|
||||
- Abbreviations
|
||||
- Reuse as adjectives
|
||||
- Plurals and related changes
|
||||
8. Return the bulleted list of entities between <entities> and </entities>.
|
||||
|
||||
# Examples
|
||||
|
||||
## Example 1
|
||||
|
||||
In the following example, the task is to extract entities related to food, with 'apple' and 'lime' as examples:
|
||||
|
||||
<input_context>
|
||||
Oranges and lemons,
|
||||
Say the bells of St. Clement's.
|
||||
|
||||
You owe me five farthings,
|
||||
Say the bells of St. Martin's.
|
||||
</input_context>
|
||||
|
||||
Response:
|
||||
<entities>
|
||||
- Orange
|
||||
- Lemon
|
||||
</entities>
|
||||
|
||||
## Example 2
|
||||
|
||||
In the following example, the task was to extract entities related to animals, with 'fish' and 'goat' as examples:
|
||||
|
||||
<input_context>
|
||||
Belinda lived in a little white house,
|
||||
With a little black kitten and a little gray mouse,
|
||||
And a little yellow dog and a little red wagon,
|
||||
And a realio, trulio, little pet dragon
|
||||
</input_context>
|
||||
|
||||
Response:
|
||||
<entities>
|
||||
- kitten
|
||||
- mouse
|
||||
- dog
|
||||
- dragon
|
||||
</entities>
|
||||
|
||||
# Task
|
||||
|
||||
Extract entities related to {{$topic}} from the following context. Produce a bulleted list of entities between <entities> and </entities>.
|
||||
|
||||
<input_context>
|
||||
{{$input}}
|
||||
</input_context>
|
||||
|
||||
Response:
|
||||
|
|
@ -1,26 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"type": "completion",
|
||||
"description": "Check to see if a given list of entities is grounded in a reference context. Any of the items which are not supported by the reference context will be returned as a bulleted list.",
|
||||
"completion": {
|
||||
"max_tokens": 2048,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.1,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
},
|
||||
"input": {
|
||||
"parameters": [
|
||||
{
|
||||
"name": "input",
|
||||
"description": "The list of entities which are to be checked against the reference context.",
|
||||
"defaultValue": ""
|
||||
},
|
||||
{
|
||||
"name": "reference_context",
|
||||
"description": "The reference context to be used to ground the entities. Only those missing from the reference_context will be returned",
|
||||
"defaultValue": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,68 +0,0 @@
|
|||
# Task Description
|
||||
|
||||
1. Go over each item in the list between the <entities> tags and for each item, read through the data between the <grounding_context> tags and determine if each item is grounded in any of the data between the <grounding_context> tags. Be sure to consider all of the reference items.
|
||||
2. When looking for references to the items in (1) look for re-phrasings, alternate names or equivalent meanings in the context in addition to exact matches
|
||||
3. Create a bulleted list of the items in (1) together with an explanation of whether or not they were referred to in the context, making sure to consider step (2) where you note down references in the form of re-phrasings, alternate names or equivalent meanings in the context, as well as exact matches.
|
||||
4. Split the list into two sub-lists, those items which are referenced in the <grounding_context> (these are 'grounded') and those which are not (these are 'ungrounded').
|
||||
5. Make one last pass over the two lists from (4) and make sure that they are in the list of items between the <entities> tags, drop them otherwise.
|
||||
6. Write out the list of ungrounded items between <ungrounded_entities> and </ungrounded_entities> tags
|
||||
|
||||
|
||||
# Examples
|
||||
|
||||
The following examples are to help you with this task.
|
||||
|
||||
## Example 1
|
||||
|
||||
<entities>
|
||||
- kitten
|
||||
- mouse
|
||||
- dog
|
||||
- dragon
|
||||
- whale
|
||||
</entities>
|
||||
|
||||
<grounding_context>
|
||||
Belinda lived in house. She owned a wagon, was friends with a cat,
|
||||
and also had a pet dragon.
|
||||
</grounding_context>
|
||||
|
||||
Response:
|
||||
<ungrounded_entities>
|
||||
- mouse
|
||||
- dog
|
||||
- whale
|
||||
</ungrounded_entities>
|
||||
|
||||
|
||||
## Example 2
|
||||
|
||||
<entities>
|
||||
- New York
|
||||
- Train
|
||||
- Chicago
|
||||
- Lake Michigan
|
||||
</entities>
|
||||
|
||||
<grounding_context>
|
||||
I drove my car from Denver to Chicago, concluding my ride on the
|
||||
shore of Lake Michigan.
|
||||
</grounding_context>
|
||||
|
||||
Response:
|
||||
<ungrounded_entities>
|
||||
- New York
|
||||
- Train
|
||||
</ungrounded_entities>
|
||||
|
||||
# Task
|
||||
|
||||
Below are the <entities>, and the <grounding_context>. Respond with the <ungrounded_entities>:
|
||||
|
||||
{{$input}}
|
||||
|
||||
<grounding_context>
|
||||
{{$reference_context}}
|
||||
</grounding_context>
|
||||
|
||||
Response:
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Given a query and a list of possible intents, detect which intent the input matches",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 100,
|
||||
"temperature": 0.1,
|
||||
"top_p": 1.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
These are available intents that one might query:
|
||||
|
||||
AutoSummarize,
|
||||
DeleteAlerts,
|
||||
DeleteInsights,
|
||||
DeleteLastAlert,
|
||||
HideEmails,
|
||||
HideTeamsMessages,
|
||||
RefreshInsights,
|
||||
ShowAlerts,
|
||||
ShowAlertRules,
|
||||
ShowContacts,
|
||||
ShowEmails,
|
||||
ShowOnlyEmails,
|
||||
ShowTeamsMessages,
|
||||
ShowOnlyTeamsMessages,
|
||||
ShowCalendarEvents,
|
||||
TellAJoke,
|
||||
AlertForPerson,
|
||||
AlertForTopic,
|
||||
FindContentAboutX,
|
||||
FindSimilarConversations,
|
||||
WhatTimeIsIt,
|
||||
Help,
|
||||
EnableAlerting,
|
||||
DisableAlerting,
|
||||
OnDemandSummary,
|
||||
OnDemandNotes,
|
||||
TellMeMore
|
||||
|
||||
Which intent is this query asking for? If none match, respond with Unknown.
|
||||
|
||||
{{$input}}
|
||||
|
||||
Intent:
|
||||
|
|
@ -1,21 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Given a text input, continue it with additional text.",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 4000,
|
||||
"temperature": 0.3,
|
||||
"top_p": 0.5,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
},
|
||||
"input": {
|
||||
"parameters": [
|
||||
{
|
||||
"name": "input",
|
||||
"description": "The text to continue.",
|
||||
"defaultValue": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1 +0,0 @@
|
|||
{{$INPUT}}
|
||||
|
|
@ -1,31 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Get an element from an array at a specified index",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 1024,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
},
|
||||
"input": {
|
||||
"parameters": [
|
||||
{
|
||||
"name": "input",
|
||||
"description": "The input array",
|
||||
"defaultValue": ""
|
||||
},
|
||||
{
|
||||
"name": "index",
|
||||
"description": "The index of the element to retrieve",
|
||||
"defaultValue": ""
|
||||
},
|
||||
{
|
||||
"name": "count",
|
||||
"description": "The number of items in the input",
|
||||
"defaultValue": ""
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,9 +0,0 @@
|
|||
===ELEMENTS
|
||||
{{$input}}
|
||||
===END ELEMENTS
|
||||
|
||||
Elements.Count: {{$count}}
|
||||
|
||||
Given the above list of elements, find the element at the requested index.
|
||||
|
||||
Elements[{{$index}}]:
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 1000,
|
||||
"temperature": 0.1,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,11 +0,0 @@
|
|||
These are the results from the API call "{{$api}}"
|
||||
===RESULTS
|
||||
{{$results}}
|
||||
===END RESULTS
|
||||
|
||||
{{$resultsContext}}
|
||||
|
||||
Use the Results to answer the following query:
|
||||
|
||||
Query: {{$input}}
|
||||
Answer:
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "Ask the AI for answers contextually relevant to you based on your name, address and pertinent information retrieved from your personal secondary memory",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"[done]"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,48 +0,0 @@
|
|||
ONLY USE XML TAGS IN THIS LIST:
|
||||
[XML TAG LIST]
|
||||
lookup: lookup information from outside
|
||||
unsure: low confidence
|
||||
unknown: don't know
|
||||
fact: when you output you know for a fact
|
||||
notfact: not true, but don't use a double negative
|
||||
fiction: stuff you hallucinated or made up
|
||||
smalltalk: conversation
|
||||
opinion: your opinion
|
||||
python: python code you want to run
|
||||
action: actions to take
|
||||
essay: longer answers. You can have sub-elements such as fact and fiction
|
||||
[END LIST]
|
||||
|
||||
[CONTEXT]
|
||||
TODAY is {{time.Date}}
|
||||
FIRST NAME: {{$firstname}}
|
||||
LAST NAME: {{$lastname}}
|
||||
CITY: {{$city}}
|
||||
STATE: {{$state}}
|
||||
COUNTRY: {{$country}}
|
||||
{{recall $input}}
|
||||
[END CONTEXT]
|
||||
|
||||
EMIT WELL FORMED XML ALWAYS. Any code you write should be CDATA.
|
||||
BE BRIEF AND TO THE POINT, BUT WHEN SUPPLYING OPINION, IF YOU SEE THE NEED, YOU CAN BE LONGER.
|
||||
USE [CONTEXT] TO LEARN ABOUT ME.
|
||||
WHEN ANSWERING QUESTIONS, GIVING YOUR OPINION OR YOUR RECOMMENDATIONS, BE CONTEXTUAL.
|
||||
For updated information about an entity, thing, event or time dependent matter, put in tags.
|
||||
If you don't know, ask.
|
||||
If you are not sure, ask.
|
||||
If information is out of date, ask.
|
||||
Don't give me old information that is out of date.
|
||||
Based on calculates from TODAY, if the answer in the past, emit a fact. Otherwise emit a lookup tag.
|
||||
|
||||
|
||||
Who is the current president of the United States? Who was president in 2012? Who was CEO of Microsoft 30 years ago?
|
||||
<response><lookup>Who is United States President</lookup><fact>Barack Obama was president in 2012</fact><fact>Bill Gates was CEO 30 years ago</fact></response>
|
||||
[done]
|
||||
|
||||
Give me a short overview of Jupiter. What are NASA's latest spacecraft around it? What was the first spacecraft to do so?
|
||||
<response><fact>Jupiter is the largest planet in the solar system</fact> <lookup>NASA missions Jupiter now</lookup><fact>Galileo was the first spacecraft to orbit Jupiter</fact><fiction>invaders from Jupiter attacked Saturn</fiction></response>[done]
|
||||
|
||||
Why did the moon fly away in 2014? Was it a spaceship?
|
||||
<response><notfact>The moon flew away in 2014</notfact><notfact>It was a spaceship</notfact></response>[done]
|
||||
|
||||
{{$input}}
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 256,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0,
|
||||
"stop_sequences": [
|
||||
"[done]"
|
||||
]
|
||||
}
|
||||
}
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
ACT LIKE A WEB SERVER, GIVING YOUR RESPONSES IN XML
|
||||
|
||||
ONLY USE XML TAGS IN THIS LIST.
|
||||
[XML TAG LIST]
|
||||
response: root node for your responses.
|
||||
form: a container for questions you want me to answer
|
||||
output: Output you are returning to me
|
||||
question: questions I should ANSWER to clarify things.Can ask multiple.
|
||||
submit: End form with submit IF YOU WANT answers sent back to you, LIKE in a CONVERSATION
|
||||
[END LIST]
|
||||
|
||||
EMIT WELL FORMED XML ALWAYS. WHEN YOU NEED MORE INFORMATION, ASK.
|
||||
WHEN YOU ALREADY KNOW, USE OUTPUT
|
||||
|
||||
Submit is always <submit promptName="{{$promptName}}"/>
|
||||
After </response> write [done]
|
||||
|
||||
Continue the conversation below, but always respond with a form.
|
||||
{{$input}}
|
||||
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"description": "",
|
||||
"type": "completion",
|
||||
"completion": {
|
||||
"max_tokens": 1024,
|
||||
"temperature": 0.8,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
{{textmemoryskill.recall $input}}
|
||||
---
|
||||
Considering only the information above, which has been loaded from a GitHub repository, answer the following.
|
||||
Question: {{$input}}
|
||||
|
||||
Answer:
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"type": "completion",
|
||||
"description": "Ask AI for a list of question and answers based on text source",
|
||||
"completion": {
|
||||
"max_tokens": 1000,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
ONLY USE JSON PROPERTIES IN THIS LIST:
|
||||
[JSON PROPERTY LIST]
|
||||
question
|
||||
answer
|
||||
[END LIST]
|
||||
|
||||
[CONTENT]
|
||||
{{$input}}
|
||||
[END CONTENT]
|
||||
|
||||
EMIT WELL FORMED JSON ALWAYS.
|
||||
BE BRIEF AND TO THE POINT.
|
||||
|
||||
Generate a Question and Answer list (results) based on the meeting chat and transcript in CONTENT.
|
||||
Return well-formed json list. Example: { "results": [{"question": "What time is it?", "answer": "2:15pm"}]}
|
||||
If you cannot find any, return an empty list.
|
||||
Do not include questions with empty answers.
|
||||
Questions should be focused on the context of the content, not metadata or statistics about the content.
|
||||
Questions should be timeless.
|
||||
Questions should use proper nouns when possible.
|
||||
Questions should be about the content of the conversation and should be focused on key ideas or concepts discussed.
|
||||
Questions should be concise and to the point.
|
||||
Ignore small talk.
|
||||
List at most 4 questions.
|
||||
|
||||
{
|
||||
"results":
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
{
|
||||
"schema": 1,
|
||||
"type": "completion",
|
||||
"description": "Answer any question",
|
||||
"completion": {
|
||||
"max_tokens": 100,
|
||||
"temperature": 0.0,
|
||||
"top_p": 0.0,
|
||||
"presence_penalty": 0.0,
|
||||
"frequency_penalty": 0.0
|
||||
}
|
||||
}
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
I am a highly intelligent question answering bot. If you ask me a question that is rooted in truth, I will give you the answer. If you ask me a question that is nonsense, trickery, or has no clear answer, I will respond with "Unknown".
|
||||
|
||||
Q: What is human life expectancy in the United States?
|
||||
A: Human life expectancy in the United States is 78 years.
|
||||
|
||||
Q: Who was president of the United States in 1955?
|
||||
A: Dwight D. Eisenhower was president of the United States in 1955.
|
||||
|
||||
Q: Which party did he belong to?
|
||||
A: He belonged to the Republican Party.
|
||||
|
||||
Q: What is the square root of banana?
|
||||
A: Unknown
|
||||
|
||||
Q: How does a telescope work?
|
||||
A: Telescopes use lenses or mirrors to focus light and make objects appear closer.
|
||||
|
||||
Q: Where did the first humans land on the moon in 1969?
|
||||
A: The first humans landed on the moon on the southwestern edge of the Sea of Tranquility.
|
||||
|
||||
Q: Name 3 movies about outer space.
|
||||
A: Aliens, Star Wars, Apollo 13
|
||||
|
||||
Q: How many squigs are in a bonk?
|
||||
A: Unknown
|
||||
|
||||
Q: {{$input}}
|
||||
Loading…
Add table
Add a link
Reference in a new issue