mirror of
https://github.com/aljazceru/Auto-GPT.git
synced 2026-01-29 02:44:25 +01:00
Text file loaders (#3031)
* adding requiered packages for loading pdf, docx, md, tex files (preferably pure python packages) * adding text file utils providing function to load file based on extension && adding read_text_file command * adding test cases for text file loading (pdf file creation is hardcoded due to external package requierment for creation (a sample file can be added)) * formatting * changing command name from 'read_text_file' to 'parse_text_document' * fallback to txtParser if file extension is not known to read script and code files * adding extension respective parsers * adding binary file check function * adding file existance check && raising valueError for unsupported binary file formats * adding check file type (binary) in test_parsers for specific extensions && fixing mock pdf generation to include null bytes * adding .yml extension parser * removal of .doc parser * updating file loading commands names * updating test (removing .doc mock function) * fix: import sort * new cassette for mem A * feat: update Cassettes * feat: consolidate commands * feat: linting * feat: updates to cassettes --------- Co-authored-by: Reinier van der Leer <github@pwuts.nl> Co-authored-by: Nicholas Tindle <nick@ntindle.com> Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
This commit is contained in:
sherif-med
File diff suppressed because it is too large
Load Diff
@@ -442,4 +442,505 @@ interactions:
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are write_to_file-GPT, an AI designed to use the write_to_file command to write
|
||||
''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
|
||||
command to complete the task.\nYour decisions must always be made independently
|
||||
without seeking user assistance. Play to your strengths as an LLM and pursue
|
||||
simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
|
||||
command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
|
||||
Use the task_complete command to complete the task.\n3. Do not use any other
|
||||
commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
|
||||
short term memory is short, so immediately save important information to files.\n2.
|
||||
If you are unsure how you previously did something or want to recall past events,
|
||||
thinking about similar events will help you remember.\n3. No user assistance\n4.
|
||||
Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read text from file, args: \"filename\": \"<filename>\"\n5. read_raw_file:
|
||||
Read file, args: \"filename\": \"<filename>\"\n6. write_to_file: Write to file,
|
||||
args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7. delete_agent: Delete
|
||||
GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks: Get text summary, args:
|
||||
\"url\": \"<url>\"\n9. get_text_summary: Get text summary, args: \"url\": \"<url>\",
|
||||
\"question\": \"<question>\"\n10. list_agents: List GPT Agents, args: () ->
|
||||
str\n11. message_agent: Message GPT Agent, args: \"key\": \"<key>\", \"message\":
|
||||
\"<message>\"\n12. start_agent: Start GPT Agent, args: \"name\": \"<name>\",
|
||||
\"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13. task_complete:
|
||||
Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1. Internet
|
||||
access for searches and information gathering.\n2. Long Term memory management.\n3.
|
||||
GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance
|
||||
Evaluation:\n1. Continuously review and analyze your actions to ensure you are
|
||||
performing to the best of your abilities.\n2. Constructively self-criticize
|
||||
your big-picture behavior constantly.\n3. Reflect on past decisions and strategies
|
||||
to refine your approach.\n4. Every command has a cost, so be smart and efficient.
|
||||
Aim to complete tasks in the least number of steps.\n5. Write all code to a
|
||||
file.\n\nYou should only respond in JSON format as described below \nResponse
|
||||
Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"user", "content": "Determine which next command to use, and respond using the
|
||||
format specified above:"}], "temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '3467'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA7STz27TQBDG7zzFaC65OFFC2iT1ExCEWqAFhDCytuuJvcTeMbvjJijyuyP/SdIY
|
||||
9QScVppv5pvf7M4e0CQYos6U6KLMx8v1/e2T0p/f36YfVh/5/m579fbu3fRhtf6qPAbIjz9IS18x
|
||||
0VyUOYlhiwFqR0oowXC2WF0t5vP5chZgwQnlGGJayng+uR5L5R55PJ1PZxhg5VVKGB6wdFyUEgtv
|
||||
yXoMl8tFgGfvU/z17DpAYVH5KXRzM6sD1BkbTR7DbwcsyB9tHeeEISrvjRdlpYFkK2SbAQ6RBQCI
|
||||
UDKu0kx8hCH0wV6gvTTBCNewM3kOlSeQjGDnjFAsHG9MTqC5KJRNQLgTYPSG8pzhC7s8GYGxwqCg
|
||||
TbWqoARGWaPHu0afyF5GkwiD540dKc/W2LTr/pARiPJbcPSzMo48FPQX3QJoaV+cw/hWLNgLqLJ0
|
||||
XDqjhGDDDiRrVOW3Q+QyV7ajHcOn/3ZNkT27NxRxvyQX7qfYMWvIqp0Ro40vjo9ridpKsr5yTZ0S
|
||||
WEOmnjoPzc6RljNbf4FKWrkNGw/9/oOxF1WJaQ52v4YYviS1fXm/GqB/t19d4zo4Ln1v+sfONw4d
|
||||
08XrDdCVS4ffpROa3LPFgOPCZPjFns10pG2Je/DI1lgHuDHW+CzuPgiG6IVLDNDYhPYYTuvv9avf
|
||||
AAAA//8DANPpphvSBAAA
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7ca920092efb0c34-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sun, 21 May 2023 01:43:08 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '17065'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86497'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.335s
|
||||
x-request-id:
|
||||
- 90577bd1f9895f3d042b1a9287fa5f73
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are write_to_file-GPT, an AI designed to use the write_to_file command to write
|
||||
''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
|
||||
command to complete the task.\nYour decisions must always be made independently
|
||||
without seeking user assistance. Play to your strengths as an LLM and pursue
|
||||
simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
|
||||
command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
|
||||
Use the task_complete command to complete the task.\n3. Do not use any other
|
||||
commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
|
||||
short term memory is short, so immediately save important information to files.\n2.
|
||||
If you are unsure how you previously did something or want to recall past events,
|
||||
thinking about similar events will help you remember.\n3. No user assistance\n4.
|
||||
Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read text from file, args: \"filename\": \"<filename>\"\n5. read_raw_file:
|
||||
Read file, args: \"filename\": \"<filename>\"\n6. write_to_file: Write to file,
|
||||
args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n7. delete_agent: Delete
|
||||
GPT Agent, args: \"key\": \"<key>\"\n8. get_hyperlinks: Get text summary, args:
|
||||
\"url\": \"<url>\"\n9. get_text_summary: Get text summary, args: \"url\": \"<url>\",
|
||||
\"question\": \"<question>\"\n10. list_agents: List GPT Agents, args: () ->
|
||||
str\n11. message_agent: Message GPT Agent, args: \"key\": \"<key>\", \"message\":
|
||||
\"<message>\"\n12. start_agent: Start GPT Agent, args: \"name\": \"<name>\",
|
||||
\"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n13. task_complete:
|
||||
Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1. Internet
|
||||
access for searches and information gathering.\n2. Long Term memory management.\n3.
|
||||
GPT-3.5 powered Agents for delegation of simple tasks.\n4. File output.\n\nPerformance
|
||||
Evaluation:\n1. Continuously review and analyze your actions to ensure you are
|
||||
performing to the best of your abilities.\n2. Constructively self-criticize
|
||||
your big-picture behavior constantly.\n3. Reflect on past decisions and strategies
|
||||
to refine your approach.\n4. Every command has a cost, so be smart and efficient.
|
||||
Aim to complete tasks in the least number of steps.\n5. Write all code to a
|
||||
file.\n\nYou should only respond in JSON format as described below \nResponse
|
||||
Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"system", "content": "This reminds you of these events from your past: \nI was
|
||||
created and nothing new has happened."}, {"role": "user", "content": "Determine
|
||||
which next command to use, and respond using the format specified above:"},
|
||||
{"role": "assistant", "content": "{\n \"thoughts\": {\n \"text\":
|
||||
\"I will use the write_to_file command to write ''Hello World'' into a file
|
||||
named ''hello_world.txt''.\",\n \"reasoning\": \"The task requires me
|
||||
to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
|
||||
command is the most appropriate for this task.\",\n \"plan\": \"- Use
|
||||
the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\\n-
|
||||
Use the task_complete command to complete the task.\",\n \"criticism\":
|
||||
\"I need to ensure that I have the correct file name and that the file is created
|
||||
in the correct directory.\",\n \"speak\": \"I will use the write to file
|
||||
command to write ''Hello World'' into a file named ''hello_world.txt''.\"\n },\n \"command\":
|
||||
{\n \"name\": \"write_to_file\",\n \"args\": {\n \"filename\":
|
||||
\"hello_world.txt\",\n \"text\": \"Hello World\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command write_to_file returned: File written
|
||||
to successfully."}, {"role": "user", "content": "Determine which next command
|
||||
to use, and respond using the format specified above:"}], "temperature": 0,
|
||||
"max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '4790'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA6ySTW/TQBCG7/yK0Vxy2UQJIWnwEYlCqkpFUIRUjKLtehIvWe+Y3TFJFfm/I8fO
|
||||
R4OQkOA6H+88M/Pu0GaYoMm1mKJ0/av5p7vr+7fTh+ub4c3dx3e3byrzYaZ5ph+eblEhP34nI13H
|
||||
wHBROhLLHhWaQFoow2Q0nb2ajsfj1yOFBWfkMMFVKf3xYNKXKjxyfzgejlBhFfWKMNlhGbgoZSG8
|
||||
Jh8xGQ0nM4Un8VNicqVQWLQ7hV6OJrVCk7M1FDH5usOC4kE4sCNMUMdoo2gvDSZ7Id+ssEs9AECK
|
||||
knO1yiWmmEAX7BK0lSaY4hw21jmoIoHkBKLjetEBEhguCu0zEIZj7FA1SFGdSwbSkb31q1b3viuD
|
||||
QD8qGyhCQY3OJlgh6L0n5xi+cHBZD6wXBg1L6wi8LiiDXt7kF5smP5Ct9BQ0HHPI9U+CWBlDMS4r
|
||||
556OYBlIbmOLBvc5BVpyIAVzMNr/h/1Kp327Wh8+/7OaCVassbE4fMET7TvJxyo0fVr2ze1ZYcmh
|
||||
PefJPGAj6LIMXAarhS4nxJL0+o8/hr+lbiVrdbBUV/6bo5q/tdOeHeUCSofVpRnP3dNZ55wve/bt
|
||||
I9AeqmNLfY21wqX1NuaLVgkTjMIlKrQ+oy0mw/pb/eIXAAAA//8DAKgaLA4VBAAA
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7ca920871f130c34-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sun, 21 May 2023 01:43:24 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '13071'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86478'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.348s
|
||||
x-request-id:
|
||||
- 137423c120d49f49824a2fbbd7cbb558
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are write_to_file-GPT, an AI designed to use the write_to_file command to write
|
||||
''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
|
||||
command to complete the task.\nYour decisions must always be made independently
|
||||
without seeking user assistance. Play to your strengths as an LLM and pursue
|
||||
simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
|
||||
command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
|
||||
Use the task_complete command to complete the task.\n3. Do not use any other
|
||||
commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
|
||||
short term memory is short, so immediately save important information to files.\n2.
|
||||
If you are unsure how you previously did something or want to recall past events,
|
||||
thinking about similar events will help you remember.\n3. No user assistance\n4.
|
||||
Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
|
||||
Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
|
||||
delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
|
||||
Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
|
||||
args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
|
||||
GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
|
||||
\"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
|
||||
\"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
|
||||
task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
|
||||
Internet access for searches and information gathering.\n2. Long Term memory
|
||||
management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
|
||||
output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
|
||||
actions to ensure you are performing to the best of your abilities.\n2. Constructively
|
||||
self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
|
||||
and strategies to refine your approach.\n4. Every command has a cost, so be
|
||||
smart and efficient. Aim to complete tasks in the least number of steps.\n5.
|
||||
Write all code to a file.\n\nYou should only respond in JSON format as described
|
||||
below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"user", "content": "Determine which next command to use, and respond using the
|
||||
format specified above:"}], "temperature": 0, "max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '3393'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA7yTT2/TQBDF73yK0Vxy2URJ0/zBRyoBEQL1UIQKRtHWnsRLdnfM7phEivzdK9tJ
|
||||
2hpxQnCdN37vN7PjI5ocE8wKLZkr7XCxuru9f1PZ6+qde6tvPn74db843Mw+XX3d21tUyA8/KJPT
|
||||
F6OMXWlJDHtUmAXSQjkmk/nyej5dTCdzhY5zspjgtpThdDQbShUeeDiejieosIp6S5gcsQzsSlkL
|
||||
78hHTBazpcIn70v9ajxWKCzaXkqvZ8taYVawyShi8u2IjuLZNrAlTFDHaKJoLw0keyHfDHBMPQBA
|
||||
ilJwtS0kppjAqXgS6CBNMcUVeKIchKGKBFIQ7IMRWguvN8YSZOyc9m1DK8DgPVnL8IWDzQdgvDBo
|
||||
aFu9dpTDoGj09b7RR3KQwShF9Tw7kI7sjd92AHcFgei4g0A/KxMogqO/SFPQ0v5xDhNb0XEU0GUZ
|
||||
uAxGC8GGA0jRqDru+sil1b6jHcLn/7SmLBgxmYmu/07kYxUaBi2wurxaxiFQJm1Ek9CtgQ7yhCTc
|
||||
djYd/bBYkt6dg/bG2n95DV1wrc5XejL97Ugbh47pBUQPXYdt/7474byJzqLH8cKk/088m+lM2xKf
|
||||
wFNfY61wY7yJxbo7Z0wwCpeo0PicDpiM6+/1q0cAAAD//wMAx8X8+IMEAAA=
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7ca9805e4d7328e0-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sun, 21 May 2023 02:48:51 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '14375'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86497'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.335s
|
||||
x-request-id:
|
||||
- dd442d3790e304394237402085fd3bc5
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
- request:
|
||||
body: '{"model": "gpt-3.5-turbo", "messages": [{"role": "system", "content": "You
|
||||
are write_to_file-GPT, an AI designed to use the write_to_file command to write
|
||||
''Hello World'' into a file named \"hello_world.txt\" and then use the task_complete
|
||||
command to complete the task.\nYour decisions must always be made independently
|
||||
without seeking user assistance. Play to your strengths as an LLM and pursue
|
||||
simple strategies with no legal complications.\n\nGOALS:\n\n1. Use the write_to_file
|
||||
command to write ''Hello World'' into a file named \"hello_world.txt\".\n2.
|
||||
Use the task_complete command to complete the task.\n3. Do not use any other
|
||||
commands.\n\n\nConstraints:\n1. ~4000 word limit for short term memory. Your
|
||||
short term memory is short, so immediately save important information to files.\n2.
|
||||
If you are unsure how you previously did something or want to recall past events,
|
||||
thinking about similar events will help you remember.\n3. No user assistance\n4.
|
||||
Exclusively use the commands listed below e.g. command_name\n\nCommands:\n1.
|
||||
append_to_file: Append to file, args: \"filename\": \"<filename>\", \"text\":
|
||||
\"<text>\"\n2. delete_file: Delete file, args: \"filename\": \"<filename>\"\n3.
|
||||
list_files: List Files in Directory, args: \"directory\": \"<directory>\"\n4.
|
||||
read_file: Read a file, args: \"filename\": \"<filename>\"\n5. write_to_file:
|
||||
Write to file, args: \"filename\": \"<filename>\", \"text\": \"<text>\"\n6.
|
||||
delete_agent: Delete GPT Agent, args: \"key\": \"<key>\"\n7. get_hyperlinks:
|
||||
Get text summary, args: \"url\": \"<url>\"\n8. get_text_summary: Get text summary,
|
||||
args: \"url\": \"<url>\", \"question\": \"<question>\"\n9. list_agents: List
|
||||
GPT Agents, args: () -> str\n10. message_agent: Message GPT Agent, args: \"key\":
|
||||
\"<key>\", \"message\": \"<message>\"\n11. start_agent: Start GPT Agent, args:
|
||||
\"name\": \"<name>\", \"task\": \"<short_task_desc>\", \"prompt\": \"<prompt>\"\n12.
|
||||
task_complete: Task Complete (Shutdown), args: \"reason\": \"<reason>\"\n\nResources:\n1.
|
||||
Internet access for searches and information gathering.\n2. Long Term memory
|
||||
management.\n3. GPT-3.5 powered Agents for delegation of simple tasks.\n4. File
|
||||
output.\n\nPerformance Evaluation:\n1. Continuously review and analyze your
|
||||
actions to ensure you are performing to the best of your abilities.\n2. Constructively
|
||||
self-criticize your big-picture behavior constantly.\n3. Reflect on past decisions
|
||||
and strategies to refine your approach.\n4. Every command has a cost, so be
|
||||
smart and efficient. Aim to complete tasks in the least number of steps.\n5.
|
||||
Write all code to a file.\n\nYou should only respond in JSON format as described
|
||||
below \nResponse Format: \n{\n \"thoughts\": {\n \"text\": \"thought\",\n \"reasoning\":
|
||||
\"reasoning\",\n \"plan\": \"- short bulleted\\n- list that conveys\\n-
|
||||
long-term plan\",\n \"criticism\": \"constructive self-criticism\",\n \"speak\":
|
||||
\"thoughts summary to say to user\"\n },\n \"command\": {\n \"name\":
|
||||
\"command name\",\n \"args\": {\n \"arg name\": \"value\"\n }\n }\n}
|
||||
\nEnsure the response can be parsed by Python json.loads"}, {"role": "system",
|
||||
"content": "The current time and date is Tue Jan 1 00:00:00 2000"}, {"role":
|
||||
"system", "content": "This reminds you of these events from your past: \nI was
|
||||
created and nothing new has happened."}, {"role": "user", "content": "Determine
|
||||
which next command to use, and respond using the format specified above:"},
|
||||
{"role": "assistant", "content": "{\n \"thoughts\": {\n \"text\":
|
||||
\"I need to use the write_to_file command to write ''Hello World'' into a file
|
||||
named ''hello_world.txt''.\",\n \"reasoning\": \"The task requires me
|
||||
to write ''Hello World'' into a file named ''hello_world.txt'', and the write_to_file
|
||||
command is the most appropriate for this task.\",\n \"plan\": \"- Use
|
||||
the write_to_file command to write ''Hello World'' into a file named ''hello_world.txt''.\",\n \"criticism\":
|
||||
\"I need to ensure that I use the correct filename and text to write to the
|
||||
file.\",\n \"speak\": \"I will use the write_to_file command to write
|
||||
''Hello World'' into a file named ''hello_world.txt''.\"\n },\n \"command\":
|
||||
{\n \"name\": \"write_to_file\",\n \"args\": {\n \"filename\":
|
||||
\"hello_world.txt\",\n \"text\": \"Hello World\"\n }\n }\n}"},
|
||||
{"role": "system", "content": "Command write_to_file returned: File written
|
||||
to successfully."}, {"role": "user", "content": "Determine which next command
|
||||
to use, and respond using the format specified above:"}], "temperature": 0,
|
||||
"max_tokens": 0}'
|
||||
headers:
|
||||
Accept:
|
||||
- '*/*'
|
||||
Accept-Encoding:
|
||||
- gzip, deflate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Length:
|
||||
- '4637'
|
||||
Content-Type:
|
||||
- application/json
|
||||
method: POST
|
||||
uri: https://api.openai.com/v1/chat/completions
|
||||
response:
|
||||
body:
|
||||
string: !!binary |
|
||||
H4sIAAAAAAAAA7RSwY4SQRC9+xWVunAZCOzILpmbFyOHTUwWo0YM6e0pZlp6utruGsAQ/t00zMi6
|
||||
sheN13qvXr3X/Q5oSixQ10p04+3wbr547x+mn+/X929pnHPc3dWfHt5ow7Npgxny4zfS0m2MNDfe
|
||||
khh2mKEOpIRKLCa3s9e3+V2e5xk2XJLFAisvw3w0HUobHnk4zscTzLCNqiIsDugDN15WwhtyEYvJ
|
||||
+Gaa4UX8AszyDIVF2cvoZjw7ZqhrNpoiFl8O2FDshQNbwgJVjCaKcpJsshNyKcJh6QAAlig1t1Ut
|
||||
cYkFdMMOoL2k4RLnUKstQWy1phjXrbU/YBeMCDkYvCNrGT5ysOUAjBMGBWtjCZxqqIRBnfDVLuEj
|
||||
2ctgBIuawNFeIAp5MBGEoY0EUhOIiptVF55Ac9MoVybCr1nPGi0xe2o3kIrsjKvOnhcdDQJ9b02g
|
||||
CA1d1QG1FgqnPMZV1/IkZkqUwcnLiy5Tkpqg4SigvA/sg1FCsOYAUif0im1vlTs7HsKHf34EnVJo
|
||||
E5v+4xzRaZNcbEPaUwJz8IG3piRQsFXWlHB+u5PRvniuevFI9KQ2/YGdsfbvfu8secz6Inb0P3qY
|
||||
enS+9pv8M1MqVM8r/LQX/6PIfYRTjC7N0h3xmOHaOBPr1fk2FhiFPWZoXEl7LMbHr8dXPwEAAP//
|
||||
AwCEJsUGfQQAAA==
|
||||
headers:
|
||||
CF-Cache-Status:
|
||||
- DYNAMIC
|
||||
CF-RAY:
|
||||
- 7ca980c86e2128e0-DFW
|
||||
Cache-Control:
|
||||
- no-cache, must-revalidate
|
||||
Connection:
|
||||
- keep-alive
|
||||
Content-Encoding:
|
||||
- gzip
|
||||
Content-Type:
|
||||
- application/json
|
||||
Date:
|
||||
- Sun, 21 May 2023 02:49:08 GMT
|
||||
Server:
|
||||
- cloudflare
|
||||
access-control-allow-origin:
|
||||
- '*'
|
||||
alt-svc:
|
||||
- h3=":443"; ma=86400, h3-29=":443"; ma=86400
|
||||
openai-model:
|
||||
- gpt-3.5-turbo-0301
|
||||
openai-organization:
|
||||
- significant-gravitas
|
||||
openai-processing-ms:
|
||||
- '14391'
|
||||
openai-version:
|
||||
- '2020-10-01'
|
||||
strict-transport-security:
|
||||
- max-age=15724800; includeSubDomains
|
||||
x-ratelimit-limit-requests:
|
||||
- '3500'
|
||||
x-ratelimit-limit-tokens:
|
||||
- '90000'
|
||||
x-ratelimit-remaining-requests:
|
||||
- '3499'
|
||||
x-ratelimit-remaining-tokens:
|
||||
- '86481'
|
||||
x-ratelimit-reset-requests:
|
||||
- 17ms
|
||||
x-ratelimit-reset-tokens:
|
||||
- 2.346s
|
||||
x-request-id:
|
||||
- 7efa7a4b949a3c79b750abf348c98545
|
||||
status:
|
||||
code: 200
|
||||
message: OK
|
||||
version: 1
|
||||
|
||||
Reference in New Issue
Block a user