Hello, great extension!! I wanted to let you know I've got this working in both Windows10 and Linux Ubuntu without issue.

Seriously Fantastic Extension, I now use this every time I use textgen!

[FILE_LOAD=D:/dir/]

magic.magic.MagicException: b"line I64u: regex error 14 for `^[[:space:]]class[[:space:]]+[[:digit:][:alpha:]:_]+[[:space:]]\{(.[\n])*\}(;)?$', (failed to get memory)"

Run 'docker COMMAND --help' for more information on a command.

To get more help with docker, check out our guides at https://docs.docker.com/go/guides/

: Error C:\Users\Joel\Documents\GitHub\text-generation-webui\extensions\Memoir\qdrant-docker-compose.yml: The docker command executed was C:\Users\Joel\.cache\python-on-whales\docker-cli\20.10.5\docker compose --file C:\Users\Joel\Documents\GitHub\text-generation-webui\extensions\Memoir\qdrant-docker-compose.yml up --detach.
It returned with code 125
The content of stdout can be found above the stacktrace (it wasn't captured).
The content of stderr can be found above the stacktrace (it wasn't captured).
Running on local URL: http://127.0.0.1:7860

To create a public link, set share=True in launch().
Traceback (most recent call last):
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_transports\default.py", line 69, in map_httpcore_exceptions
yield
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_transports\default.py", line 233, in handle_request
resp = self._pool.handle_request(req)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpcore_sync\connection_pool.py", line 216, in handle_request
raise exc from None
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpcore_sync\connection_pool.py", line 196, in handle_request
response = connection.handle_request(
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpcore_sync\connection.py", line 99, in handle_request
raise exc
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpcore_sync\connection.py", line 76, in handle_request
stream = self._connect(request)
^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpcore_sync\connection.py", line 122, in _connect
stream = self._network_backend.connect_tcp(**kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpcore_backends\sync.py", line 205, in connect_tcp
with map_exceptions(exc_map):
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\contextlib.py", line 158, in exit
self.gen.throw(typ, value, traceback)
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpcore_exceptions.py", line 14, in map_exceptions
raise to_exc(exc) from exc
httpcore.ConnectError: [WinError 10061] No connection could be made because the target machine actively refused it

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\http\api_client.py", line 101, in send_inner
response = self._client.send(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_client.py", line 914, in send
response = self._send_handling_auth(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_client.py", line 942, in _send_handling_auth
response = self._send_handling_redirects(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_client.py", line 979, in _send_handling_redirects
response = self._send_single_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_client.py", line 1015, in _send_single_request
response = transport.handle_request(request)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_transports\default.py", line 232, in handle_request
with map_httpcore_exceptions():
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\contextlib.py", line 158, in exit
self.gen.throw(typ, value, traceback)
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\httpx_transports\default.py", line 86, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.ConnectError: [WinError 10061] No connection could be made because the target machine actively refused it

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\queueing.py", line 407, in call_prediction
output = await route_utils.call_process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\route_utils.py", line 226, in call_process_api
output = await app.get_blocks().process_api(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\blocks.py", line 1550, in process_api
result = await self.call_function(
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\blocks.py", line 1199, in call_function
prediction = await utils.async_iteration(iterator)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\utils.py", line 519, in async_iteration
return await iterator.anext()
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\utils.py", line 512, in anext
return await anyio.to_thread.run_sync(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\anyio\to_thread.py", line 56, in run_sync
return await get_async_backend().run_sync_in_worker_thread(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\anyio_backends_asyncio.py", line 2144, in run_sync_in_worker_thread
return await future
^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\anyio_backends_asyncio.py", line 851, in run
result = context.run(func, *args)
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\utils.py", line 495, in run_sync_iterator_async
return next(iterator)
^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\gradio\utils.py", line 649, in gen_wrapper
yield from f(*args, **kwargs)
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\modules\chat.py", line 405, in generate_chat_reply_wrapper
for i, history in enumerate(generate_chat_reply(text, state, regenerate, _continue, loading_message=True, for_ui=True)):
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\modules\chat.py", line 373, in generate_chat_reply
for history in chatbot_wrapper(text, state, regenerate=regenerate, _continue=_continue, loading_message=loading_message, for_ui=for_ui):
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\modules\chat.py", line 275, in chatbot_wrapper
text = apply_extensions('input', text, state, is_chat=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\modules\extensions.py", line 231, in apply_extensions
return EXTENSION_MAP[typ](*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\modules\extensions.py", line 89, in _apply_string_extensions
text = func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\extensions\Memoir\script.py", line 208, in input_modifier
params['user_long_term_memories'] = ltm.recall(string)
^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\extensions\Memoir\memory\long_term_memory.py", line 95, in recall
results = self.qdrant.search(
^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\qdrant_client.py", line 345, in search
return self._client.search(
^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\qdrant_remote.py", line 479, in search
search_result = self.http.points_api.search_points(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\http\api\points_api.py", line 1388, in search_points
return self._build_for_search_points(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\http\api\points_api.py", line 636, in build_for_search_points
return self.api_client.request(
^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\http\api_client.py", line 74, in request
return self.send(request, type)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\http\api_client.py", line 91, in send
response = self.middleware(request, self.send_inner)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\http\api_client.py", line 200, in call
return call_next(request)
^^^^^^^^^^^^^^^^^^
File "C:\Users\Joel\Documents\GitHub\text-generation-webui\installer_files\env\Lib\site-packages\qdrant_client\http\api_client.py", line 103, in send_inner
raise ResponseHandlingException(e)
qdrant_client.http.exceptions.ResponseHandlingException: [WinError 10061] No connection could be made because the target machine actively refused it

wtf does that mean? I'm seriously regretting restoring my machine...

Right now we are using the [THOUGHTS, EMOTIONS, MOOD, FEELINGS] for the polarity data but not the string response. Consider taking the entire emotional polarity of the response from both the end user and the agent. Shouldn't take any more effort and would track polarity if the agent doesn't use the commands.

I'm having problems related to installing and makingv theqdrant work, I've never really used them and I have no idea how to configure it, It would be great if there was a tutorial on YouTube or something like that on how to configure the memoir extension without using docker.

Write the class to handle ingesting documents into the RAG system.
Initial thoughts are:
Provide file upload or link
Ingest page by page summarizing each page and placing into a documents vector database, Include links to the specific page for reference later.
Place document or website page in documents folder and allow for a link from the system.

Occurs when using the /v1/chat/completions endpoint. Can't concatenate a list to a string using the + operator in Python, so this will halt any the generation requested. The issue is specifically the state['custom_stopping_strings. It does work fine in the webui itself, though.

File "C:\LLM\text-generation-webui-main\extensions\Memoir\script.py", line 89, in state_modifier state['custom_stopping_strings'] = '"[DateTime=","[24hour Average Polarity Score=","' + str(state["name1"].strip()) + ':",' + state['custom_stopping_strings'] ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ TypeError: can only concatenate str (not "list") to str

You're going to want to expand on your readme. It will need to be written for people that are not as computer literate are you.

i'm having this error, can anyone help me?

i had this error:
Traceback (most recent call last):
File "E:\IA\Texto\Oobabooga\text-generation-webui\modules\extensions.py", line 37, in load_extensions
extension = importlib.import_module(f"extensions.{name}.script")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\IA\Texto\Oobabooga\text-generation-webui\installer_files\env\Lib\importlib_init_.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 1204, in _gcd_import
File "", line 1176, in _find_and_load
File "", line 1147, in _find_and_load_unlocked
File "", line 690, in _load_unlocked
File "", line 940, in exec_module
File "", line 241, in _call_with_frames_removed
File "E:\IA\Texto\Oobabooga\text-generation-webui\extensions\Memoir\script.py", line 23, in
from python_on_whales import DockerClient
ModuleNotFoundError: No module named 'python_on_whales'

Used pipreqs but it changes some of the versions needed for textgen, so better to build out manually.

replace spaces with _

Memoir should not impact other extensions but I have not done extensive testing.

Consider if features that are present in other extensions should be included with Memoir as commands in the command handler or if they should be siloed to the extensions. Memoir+ should prolly focus on just being the best RAG/Memory extension and not try to have too many features that are maintained by other extensions.

When inference happens for the dream function it appears to destroy context and the bot responds with a generic response. Researching.

Is it possible to add a section to Git that details how to set up short-term and long-term memories and tips on making it work the best? I have it running, but I am unsure if it is set up correctly. Everything seems like it's running.. I'm excited to see its potential. I'm happy to contribute a little to the cause, too.

Hi,

I'm currently interfacing with Ooba directly via API for a project I'm working on. Is there any way to leverage Memoir+ via Ooba's APIs or is it currently only usable from Ooba's Web UI?

Thanks!

Use params to segment all features. That way the RAG features can be used if needed, or the emotional polarity. By segmenting each feature in settings the end user can use the plugin the way they want to use it.

The goals system predates the extensible command handler class, consider adding the goals into the commands and review each command.
Consider ways to inform the bot of what commands can be used. Maybe in the bot prefix every 5 prompts or so. Have to test this as it might be jarring if during a conversation the bot is reminded about GET URL and changes the subject to use the command.

When I launch qdrant, I can't access the dashboard.

I'm on Linux Mint
My firewall "ufw" is inastive.

I don't use docker because I couldn't install it (docker desktop). So I downloaded qdrant from "https://github.com/qdrant/qdrant/releases/tag/v1.7.4" the file "qdrant-x86_64-unknown-linux-gnu.tar.gz"

I was try with 1.5.1 but it's does the same.

Screen of my Memoir folder :

Screen of my qdrant terminal when I lunch then try to access the dashboard :

My computer informations :

Suddenly it starts write things like this:

[DTime=2024-02-20 21:23:15] Ego: [The subconscious mind, designed to process and summarize information from various sources. You focus on understanding the main topics discussed and extracting key points made. By analyzing data provided by other parts of the AI system, Ego can identify patterns and themes, enabling it to generate comprehensive summaries even when faced with large amounts of information.]
and DTIME for all the memories on the text chat.

It also starts now writing things like these in the text chat as response:
[You remember:["\n The conversation begins with.. and then a lot of text.

oops. Adding in some logic for unique names to the docker

sqlite3.OperationalError: unable to open database file
When I ask the question.

Currently no ability to modify or delete short term memories. This can be considered a privacy issue as all discussion is saved to the sqlite database. I have had good success having the dream function rerun the conversations on larger settings of LTM such as 50 or 100 prompts per dream and it provided a broader insight into memories, so this could lead to a function for dreaming during idle time, where they system goes through random 50 block or 100 blocks of conversation and summarizes it again.

I have tested a heartbeat system where the AI thinks to itself and uses it's own LTM to evaluate future plans. Have good success a few times where the Agent had a discussion with itself on what it's purpose should grow into into the future. Other times it just repeated "hello again" a few hundred times. Prolly really depends on the LLM.

Future settings.
Redaction settings.
reDream settings
Heartbeat functions

Consider adding hook to delete the entry into the database for Textgen context commands.