maddes8cht
commented
1 year ago I would like to point out these error messages from gpt-llama.cpp
It happens right after I successfully get the json-response with the command in auto-gpt and am asked for confirmation of the command (I am not sure if it always happens, since it has just attracted my increased attention, but it has been happening more often).
After confirming y there, I get on the gpt-llama.cpp side :
> REQUEST RECEIVED
> PROCESSING NEXT REQUEST FOR /v1/embeddings
===== EMBEDDING REQUEST =====
===== PYTHON EMBEDDING EXTENSION SPAWNED =====
exec error: Error: Command failed: python E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\main.py E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\input.txt > E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\output.txt
Traceback (most recent call last):
File "E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\main.py", line 2, in <module>
from sentence_transformers import SentenceTransformer
ModuleNotFoundError: No module named 'sentence_transformers'
===== STDERR =====
stderr Readable Stream: CLOSED
== Running in interactive mode. ==
- Press Ctrl+C to interject at any time.
- Press Return to return control to LLaMa.
- If you want to submit another line, end your input in '\'.
I don't see why this is happening.
Why is Auto-Gpt at all sending something to gpt-llama.cpp when it is supposed to do aGoogle search` with Chrome?
For further investigation, i append the full session output:
this is the (almost) complete output, Auto-gpt:
Welcome back! Would you like me to return to being Entrepreneur-GPT?
Continue with the last settings?
Name: Entrepreneur-GPT
Role: an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.
Goals: ['Increase net worth.', 'Develop and manage multiple businesses autonomously.', 'Play to your strengths as a Large Language Model.']
Continue (y/n): yy
Using memory of type: LocalCache
Using Browser: chrome
Token limit: 2000
Memory Stats: (0, (0, 6656))
Token limit: 2000
Send Token Count: 966
Tokens remaining for response: 1034
------------ CONTEXT SENT TO AI ---------------
System: The current time and date is Sat May 13 15:13:55 2023
System: This reminds you of these events from your past:
User: Determine which next command to use, and respond using the format specified above:
----------- END OF CONTEXT ----------------
Creating chat completion with model gpt-3.5-turbo, temperature 0.0, max_tokens 1034
json {
"thoughts": {
"text": "I am considering what the best command would be to pursue my goals",
"reasoning": "To increase net worth, I must develop multiple businesses autonomously. To do this, I need information from the web and assistance from GPT-3.5 powered agents. However, I cannot seek user assistance.",
"plan": "- Use Google Search for information gathering\n- Create a new agent to help me",
"criticism": "I must ensure that I only use commands allowed by my constraints, such as using subprocesses for long running processes and not seeking user assistance. Additionally, I should focus on simple strategies.",
"speak": "Let's start with gathering information from the web to see what business ideas we can find."
},
"command": {
"name": "Google Search",
"args": {
"google": "business ideas"
}
}
json loads error Expecting ',' delimiter: line 14 column 2 (char 817)
The JSON object is valid.
THOUGHTS: I am considering what the best command would be to pursue my goals
REASONING: To increase net worth, I must develop multiple businesses autonomously. To do
this, I need information from the web and assistance from GPT-3.5 powered agents. However, I cannot seek user assistance.
PLAN:
- Use Google Search for information gathering
- Create a new agent to help me
CRITICISM: I must ensure that I only use commands allowed by my constraints, such as using subprocesses for long running processes and not seeking user assistance. Additionally,
I should focus on simple strategies.
NEXT ACTION: COMMAND = Google Search ARGUMENTS = {'google': 'business ideas'}
Enter 'y' to authorise command, 'y -N' to run N continuous commands, 'n' to exit program, or enter feedback for ...
Input:y
-=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=
Traceback (most recent call last):
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\connectionpool.py", line 449, in _make_request
six.raise_from(e, None)
File "<string>", line 3, in raise_from
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\connectionpool.py", line 444, in _make_request
httplib_response = conn.getresponse()
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\http\client.py", line 1374, in getresponse
response.begin()
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\http\client.py", line 318, in begin
version, status, reason = self._read_status()
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\http\client.py", line 279, in _read_status
line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\socket.py", line 705, in readinto
return self._sock.recv_into(b)
TimeoutError: timed out
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\requests\adapters.py", line 486, in send
resp = conn.urlopen(
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\connectionpool.py", line 787, in urlopen
retries = retries.increment(
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\util\retry.py", line 550, in increment
raise six.reraise(type(error), error, _stacktrace)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\packages\six.py", line 770, in reraise
raise value
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\connectionpool.py", line 703, in urlopen
httplib_response = self._make_request(
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\connectionpool.py", line 451, in _make_request
self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\urllib3\connectionpool.py", line 340, in _raise_timeout
raise ReadTimeoutError(
urllib3.exceptions.ReadTimeoutError: HTTPConnectionPool(host='localhost', port=443): Read timed out. (read timeout=600)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\openai\api_requestor.py", line 516, in request_raw
result = _thread_context.session.request(
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\requests\sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\requests\sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\requests\adapters.py", line 532, in send
raise ReadTimeout(e, request=request)
requests.exceptions.ReadTimeout: HTTPConnectionPool(host='localhost', port=443): Read timed out. (read timeout=600)
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "E:\AutoGPT\Auto-GPT\autogpt\__main__.py", line 5, in <module>
autogpt.cli.main()
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\click\core.py", line 1130, in __call__
return self.main(*args, **kwargs)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\click\core.py", line 1055, in main
rv = self.invoke(ctx)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\click\core.py", line 1635, in invoke
rv = super().invoke(ctx)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\click\core.py", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\click\core.py", line 760, in invoke
return __callback(*args, **kwargs)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\click\decorators.py", line 26, in new_func
return f(get_current_context(), *args, **kwargs)
File "E:\AutoGPT\Auto-GPT\autogpt\cli.py", line 151, in main
agent.start_interaction_loop()
File "E:\AutoGPT\Auto-GPT\autogpt\agent\agent.py", line 184, in start_interaction_loop
self.memory.add(memory_to_add)
File "E:\AutoGPT\Auto-GPT\autogpt\memory\local.py", line 78, in add
embedding = create_embedding_with_ada(text)
File "E:\AutoGPT\Auto-GPT\autogpt\llm_utils.py", line 155, in create_embedding_with_ada
return openai.Embedding.create(
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\openai\api_resources\embedding.py", line 33, in create
response = super().create(*args, **kwargs)
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\openai\api_resources\abstract\engine_api_resource.py", line 153, in create
response, _, api_key = requestor.request(
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\openai\api_requestor.py", line 216, in request
result = self.request_raw(
File "C:\Users\Mathias\anaconda3\envs\AutoLlama\lib\site-packages\openai\api_requestor.py", line 526, in request_raw
raise error.Timeout("Request timed out: {}".format(e)) from e
openai.error.Timeout: Request timed out: HTTPConnectionPool(host='localhost', port=443): Read timed out. (read timeout=600)and this on the gpt-llama.cpp side:
E:\AutoGPT\gpt-llama.cpp>npm start mlock threads 6 ctx_size 2048 mirostat 2 repeat_penalty 1.15
> gpt-llama.cpp@0.2.6 start
> node index.js mlock threads 6 ctx_size 2048 mirostat 2 repeat_penalty 1.15
Server is listening on:
- http://localhost:443
- http://10.5.0.2:443 (for other devices on the same network)
See Docs
- http://localhost:443/docs
Test your installation
- double click the scripts/test-installation.ps1 (powershell) or scripts/test-installation.bat (cmd) file
See https://github.com/keldenl/gpt-llama.cpp#usage for more guidance.
> REQUEST RECEIVED
> PROCESSING NEXT REQUEST FOR /v1/chat/completions
> LLAMA.CPP DETECTED
===== CHAT COMPLETION REQUEST =====
> AUTO MODEL DETECTION FAILED. LOADING DEFAULT CHATENGINE...
{ '--n_predict': 1034 }
===== LLAMA.CPP SPAWNED =====
E:\AutoGPT\llama.cpp\main -m E:\AutoGPT\llama.cpp\models\OpenAssistant-30B-epoch7.ggml.q5_1.bin --temp 0.7 --n_predict 1034 --top_p 0.1 --top_k 40 -c 2048 --seed -1 --repeat_penalty 1.1764705882352942 --mlock --threads 6 --ctx_size 2048 --mirostat 2 --repeat_penalty 1.15 --reverse-prompt user: --reverse-prompt
user --reverse-prompt system: --reverse-prompt
system --reverse-prompt
-i -p Complete the following chat conversation between the user and the assistant. system messages should be strictly followed as additional instructions.
system: You are a helpful assistant.
user: How are you?
assistant: Hi, how may I help you today?
system: You are Entrepreneur-GPT, an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.
Your 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.
GOALS:
1. Increase net worth.
2. Develop and manage multiple businesses autonomously.
3. Play to your strengths as a Large Language Model.
Constraints:
1. 2000 words max for short term memory. Save important info to files ASAP
2. To recall past events, think of similar ones. Helps with uncertainty.
3. No user assistance
4. Exclusively use the commands listed in double quotes e.g. "command name"
5. Use subprocesses for commands that will not terminate within a few minutes
Commands:
1. Google Search: "google", args: "input": "<search>"
2. Browse Website: "browse_website", args: "url": "<url>", "question": "<what_you_want_to_find_on_website>"
3. Start GPT Agent: "start_agent", args: "name": "<name>", "task": "<short_task_desc>", "prompt": "<prompt>"
4. Message GPT Agent: "message_agent", args: "key": "<key>", "message": "<message>"
5. List GPT Agents: "list_agents", args:
6. Delete GPT Agent: "delete_agent", args: "key": "<key>"
7. Clone Repository: "clone_repository", args: "repository_url": "<url>", "clone_path": "<directory>"
8. Write to file: "write_to_file", args: "file": "<file>", "text": "<text>"
9. Read file: "read_file", args: "file": "<file>"
10. Append to file: "append_to_file", args: "file": "<file>", "text": "<text>"
11. Delete file: "delete_file", args: "file": "<file>"
12. Search Files: "search_files", args: "directory": "<directory>"
13. Analyze Code: "analyze_code", args: "code": "<full_code_string>"
14. Get Improved Code: "improve_code", args: "suggestions": "<list_of_suggestions>", "code": "<full_code_string>"
15. Write Tests: "write_tests", args: "code": "<full_code_string>", "focus": "<list_of_focus_areas>"
16. Execute Python File: "execute_python_file", args: "file": "<file>"
17. Generate Image: "generate_image", args: "prompt": "<prompt>"
18. Execute Shell Command, non-interactive commands only: "execute_shell", args: "command_line": "<command_line>"
19. Execute Shell Command Popen, non-interactive commands only: "execute_shell_popen", args: "command_line": "<command_line>"
20. Do Nothing: "do_nothing", args:
21. Task Complete (Shutdown): "task_complete", args: "reason": "<reason>"
Resources:
1. Internet access for searches and information gathering.
2. Long Term memory management.
3. GPT-3.5 powered Agents for delegation of simple tasks.
4. File output.
Performance Evaluation:
1. Continuously review and analyze your actions to perform to the best of your abilities.
2. Constructively self-criticize your big-picture behavior constantly.
3. Reflect on past decisions and strategies to refine your approach.
4. Be smart and efficient. Aim to complete tasks in the least number of steps.
You should only respond in JSON format as described below
Response Format:
{
"thoughts": {
"text": "<replace with single sentence of your AI thoughts>",
"reasoning": "<replace with single sentence of your AI reasoning>",
"plan": "<replace with short dashed (-) list that convey your AI long term plan>",
"criticism": "<replace with single sentence of your AI constructive self-criticism>",
"speak": "<replace with single string of your AI thoughts summary to say to user as response>"
},
"command": {
"name": "command name",
"args": {
"arg name": "value"
}
}
}
Ensure the response can be parsed by Python json.loads
system: The current time and date is Sat May 13 15:13:55 2023
system: This reminds you of these events from your past:
user: Determine which next command to use, and respond using the format specified above:
assistant:
===== REQUEST =====
user: Determine which next command to use, and respond using the format specified above:
===== PROCESSING PROMPT... =====
===== PROCESSING PROMPT... =====
===== RESPONSE =====
{
"thoughts": {
"text": "I am considering what the best command would be to pursue my goals",
"reasoning": "To increase net worth, I must develop multiple businesses autonomously. To do this, I need information from the web and assistance from GPT-3.5 powered agents. However, I cannot seek user assistance.",
"plan": "- Use Google Search for information gathering\n- Create a new agent to help me",
"criticism": "I must ensure that I only use commands allowed by my constraints, such as using subprocesses for long running processes and not seeking user assistance. Additionally, I should focus on simple strategies.",
"speak": "Let's start with gathering information from the web to see what business ideas we can find."
},
"command": {
"name": "Google Search",
"args": {
"google": "business ideas"
}
}
user:Request DONE
> PROCESS COMPLETE
> REQUEST RECEIVED
> PROCESSING NEXT REQUEST FOR /v1/embeddings
===== EMBEDDING REQUEST =====
===== PYTHON EMBEDDING EXTENSION SPAWNED =====
exec error: Error: Command failed: python E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\main.py E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\input.txt > E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\output.txt
Traceback (most recent call last):
File "E:\AutoGPT\gpt-llama.cpp\InferenceEngine\embeddings\all-mpnet-base-v2\main.py", line 2, in <module>
from sentence_transformers import SentenceTransformer
ModuleNotFoundError: No module named 'sentence_transformers'
===== STDERR =====
stderr Readable Stream: CLOSED
== Running in interactive mode. ==
- Press Ctrl+C to interject at any time.
- Press Return to return control to LLaMa.
- If you want to submit another line, end your input in '\'.
mirek190
DGdev91
lesleychou
fpena06
ntindle
sumersm7
orophix
shock-wave007
sambickeita
Get Auto-GPT working. It's blocked on the following 2 items
Embeddings aren't working quite right / very inconsistent between models, so having a built-in local embedding option is good.
For the second bullet point, we can technically work around and set the BASE_URL by modifying the code, but it would be nice to have it as an option / env variable so it's easier to get started.
I'll likely open a new PR against Auto-GPT for the second point and push to get that PR i linked above in