ProjCRys
commented
1 year ago Tried 'memgpt run' with a new bat file here's a different error:
bat file @echo off
:: Define the paths to Python and the venv set PYTHON_EXECUTABLE=C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\python.exe set VENV_DIR=D:\AI\ChatBots\MemGPT_Setup\venv
:: Create the virtual environment "%PYTHON_EXECUTABLE%" -m venv "%VENV_DIR%"
:: Check if the virtual environment creation was successful if %errorlevel% neq 0 ( echo An error occurred while creating the virtual environment. Press any key to exit. pause >nul exit /b %errorlevel% )
:: Activate the virtual environment call "%VENV_DIR%\Scripts\activate"
:: Install pymemgpt using pip pip install pymemgpt pip install transformers pip install torch
:: Check if the installation was successful if %errorlevel% neq 0 ( echo An error occurred while installing pymemgpt. Press any key to exit. pause >nul exit /b %errorlevel% )
set OPENAI_API_BASE=http://localhost:1234 set BACKEND_TYPE=lmstudio cls
:: Run memgpt (replace this with your specific memgpt command) memgpt run
:: Check if memgpt encountered an error if %errorlevel% neq 0 ( echo An error occurred while running memgpt. Press any key to exit. pause >nul exit /b %errorlevel% )
:: Deactivate the virtual environment deactivate
:: Pause to allow the user to review the output echo Press any key to exit. pause >nul
Output: ? Would you like to select an existing agent? No Creating new agent... Created new agent agent_5. Hit enter to begin (will request first MemGPT message) [A[K Warning: no wrapper specified for local LLM, using the default wrapper step() failed user_message = None error = Failed to decode JSON from LLM output: { {"status": "OK", "message": null, "time": "2023-11-01 06:05:36 AM PDT-0700"}} Failed to decode JSON from LLM output: { {"status": "OK", "message": null, "time": "2023-11-01 06:05:36 AM PDT-0700"}} An exception ocurred when running agent.step(): Traceback (most recent call last): File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\local_llm\llm_chat_completion_wrappers\airoboros.py", line 392, in output_to_chat_completion_response function_json_output = json.loads(raw_llm_output) File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\json__init__.py", line 346, in loads return _default_decoder.decode(s) File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 337, in decode obj, end = self.raw_decode(s, idx=_w(s, 0).end()) File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 353, in raw_decode obj, end = self.scan_once(s, idx) json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 1 column 3 (char 2)
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\local_llm\llm_chat_completion_wrappers\airoboros.py", line 395, in output_to_chat_completion_response function_json_output = json.loads(raw_llm_output + "\n}") File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\json__init__.py", line 346, in loads return _default_decoder.decode(s) File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 337, in decode obj, end = self.raw_decode(s, idx=_w(s, 0).end()) File "C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 353, in raw_decode obj, end = self.scan_once(s, idx) json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 1 column 3 (char 2)
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\main.py", line 526, in run_agent_loop ) = await memgpt_agent.step(user_message, first_message=False, skip_verify=no_verify) File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\agent.py", line 1084, in step raise e File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\agent.py", line 1020, in step response = await get_ai_reply_async(model=self.model, message_sequence=input_message_sequence, functions=self.functions) File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\agent.py", line 160, in get_ai_reply_async raise e File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\agent.py", line 141, in get_ai_reply_async response = await acreate( File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\openai_tools.py", line 115, in wrapper raise e File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\openai_tools.py", line 95, in wrapper return await func(*args, kwargs) File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\openai_tools.py", line 124, in acompletions_with_backoff return get_chat_completion(kwargs) File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\local_llm\chat_completion_proxy.py", line 62, in get_chat_completion chat_completion_result = llm_wrapper.output_to_chat_completion_response(result) File "D:\AI\ChatBots\MemGPT_Setup\venv\lib\site-packages\memgpt\local_llm\llm_chat_completion_wrappers\airoboros.py", line 397, in output_to_chat_completion_response raise Exception(f"Failed to decode JSON from LLM output:\n{raw_llm_output}") Exception: Failed to decode JSON from LLM output: { {"status": "OK", "message": null, "time": "2023-11-01 06:05:36 AM PDT-0700"}} ? Retry agent.step()? (Y/n)
Okay, first I tried setting up my venv to run MemGPT so I got this: run.bat @echo off setlocal
:: Set the path to your Python 3.10.0 installation set PYTHON_PATH=C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\python.exe
:: Set the path to the directory where you want to create the virtual environment set VENV_DIR=D:\AI\ChatBots\MemGPT_Setup\venv
:: Set the environment variables set OPENAI_API_BASE=http://localhost:1234 set BACKEND_TYPE=lmstudio
:: Create and activate the virtual environment %PYTHON_PATH% -m venv %VENV_DIR% call %VENV_DIR%\Scripts\activate
:: Run your Python script with the environment variables set set PYTHONPATH=%PYTHONPATH%;%VENV_DIR%\Lib\site-packages python MemGPT/main.py
:: Deactivate the virtual environment deactivate
endlocal
Error: Traceback (most recent call last): File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\main.py", line 1, in
from memgpt.main import app
File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\main.py", line 16, in
from prettytable import PrettyTable
ModuleNotFoundError: No module named 'prettytable'
I pip installed prettytable but didn't change anything.
So then I tried calling python main.py and this is what I got.
D:\AI\ChatBots\MemGPT_Setup\MemGPT>python main.py Warning: Running legacy run command. Run
memgpt runinstead. ? Continue with legacy CLI? Yes ⚙️ Found saved config file. ? Use most recent config file 'C:\Users\ADMIN.memgpt\configs\2023-10-30_08_25_34_AM_PDT-0700.json'? Yes Running... [exit by typing '/exit', list available commands with '/help'] 💭 Bootup sequence complete. Persona activated. Testing messaging functionality. ? Load in saved agent 'C:\Users\ADMIN.memgpt\saved_state\2023-10-30_09_07_01_AM_PDT-0700.json'? Yes Loaded checkpoint C:\Users\ADMIN.memgpt\saved_state\2023-10-30_09_07_01_AM_PDT-0700.json /load warning: loading persistence manager from C:\Users\ADMIN.memgpt\saved_state\2023-10-30_09_07_01_AM_PDT-0700.persistence.pickle failed with: Ran out of input Hit enter to begin (will request first MemGPT message) [A[K {'content': '{"status": "OK", "message": null, "time": "2023-10-30 09:04:29 AM ' 'PDT-0700"}', 'name': 'send_message', 'role': 'function'} Warning: no wrapper specified for local LLM, using the default wrapper step() failed user_message = None error = 'choices' 'choices' An exception ocurred when running agent.step(): Traceback (most recent call last): File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\main.py", line 524, in run_agent_loop ) = await memgpt_agent.step(user_message, first_message=False, skip_verify=no_verify) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 1013, in step raise e File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 958, in step response = await get_ai_reply_async(model=self.model, message_sequence=input_message_sequence, functions=self.functions) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 159, in get_ai_reply_async raise e File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 140, in get_ai_reply_async response = await acreate( File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\openai_tools.py", line 102, in wrapper raise e File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\openai_tools.py", line 82, in wrapper return await func(*args, kwargs) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\openai_tools.py", line 111, in acompletions_with_backoff return await get_chat_completion(kwargs) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\local_llm\chat_completion_proxy.py", line 52, in get_chat_completion result = get_lmstudio_completion(prompt) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\local_llm\lmstudio\api.py", line 42, in get_lmstudio_completion result = result["choices"][0]["message"]["content"] KeyError: 'choices' ? Retry agent.step()? YesI then also tried creating a new agent which led to this... D:\AI\ChatBots\MemGPT_Setup\MemGPT>python main.py Warning: Running legacy run command. Run
memgpt runinstead. ? Continue with legacy CLI? Yes ⚙️ Found saved config file. ? Use most recent config file 'C:\Users\ADMIN.memgpt\configs\2023-10-30_08_25_34_AM_PDT-0700.json'? No ⚙️ No settings file found, configuring MemGPT... ? Which model would you like to use? gpt-4 ? Which persona would you like MemGPT to use? memgpt_starter The following is a blank slate starter persona, I need to expand this to develop my own personality. My name is MemGPT. I am kind, thoughtful, and inquisitive. ('memgpt_starter', None) ? Which user would you like to use? basic First name: Chad ? Would you like to preload anything into MemGPT's archival memory? Yes ? What would you like to load? A folder or file ? Please enter the folder or file (tab for autocomplete): C:\Users\ADMIN.memgpt\saved_state ? Would you like to compute embeddings over these files to enable embeddings search? Yes ⛔️ Embeddings on a non-OpenAI endpoint are not yet supported, falling back to substring matching search. ⚙️ Saved config file to C:\Users\ADMIN.memgpt\configs\2023-10-31_09_25_16_PM_PDT-0700.json. Running... [exit by typing '/exit', list available commands with '/help'] Preloaded 139 chunks into archival memory. Initializing InMemoryStateManager with agent object InMemoryStateManager.all_messages.len = 4 InMemoryStateManager.messages.len = 4 💭 Bootup sequence complete. Persona activated. Testing messaging functionality. Hit enter to begin (will request first MemGPT message) [A[K Warning: no wrapper specified for local LLM, using the default wrapper step() failed user_message = None error = 'choices' 'choices' An exception ocurred when running agent.step(): Traceback (most recent call last): File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\main.py", line 524, in run_agent_loop ) = await memgpt_agent.step(user_message, first_message=False, skip_verify=no_verify) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 1013, in step raise e File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 949, in step response = await get_ai_reply_async(model=self.model, message_sequence=input_message_sequence, functions=self.functions) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 159, in get_ai_reply_async raise e File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\agent.py", line 140, in get_ai_reply_async response = await acreate( File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\openai_tools.py", line 102, in wrapper raise e File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\openai_tools.py", line 82, in wrapper return await func(*args, kwargs) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\openai_tools.py", line 111, in acompletions_with_backoff return await get_chat_completion(kwargs) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\local_llm\chat_completion_proxy.py", line 52, in get_chat_completion result = get_lmstudio_completion(prompt) File "D:\AI\ChatBots\MemGPT_Setup\MemGPT\memgpt\local_llm\lmstudio\api.py", line 42, in get_lmstudio_completion result = result["choices"][0]["message"]["content"] KeyError: 'choices' ? Retry agent.step()? (Y/n)And finally I tried pip install pymemgpt and use that as a last resort which then led to this: D:\AI\ChatBots\MemGPT_Setup>memgpt Warning: Running legacy run command. Run
memgpt runinstead. ? Continue with legacy CLI? Yes ⚙️ Found saved config file. ? Use most recent config file 'C:\Users\ADMIN.memgpt\configs\2023-10-31_09_25_16_PM_PDT-0700.json'? Yes ⛔️ Embeddings on a non-OpenAI endpoint are not yet supported, falling back to substring matching search. ⚙️ Saved config file to C:\Users\ADMIN.memgpt\configs\2023-10-31_09_25_16_PM_PDT-0700.json. Running... [exit by typing '/exit', list available commands with '/help'] Preloaded 139 chunks into archival memory. Initializing InMemoryStateManager with agent object InMemoryStateManager.all_messages.len = 4 InMemoryStateManager.messages.len = 4 💭 Bootup sequence complete. Persona activated. Testing messaging functionality. Hit enter to begin (will request first MemGPT message) [A[K Warning: no wrapper specified for local LLM, using the default wrapper step() failed user_message = None error = 'choices' 'choices'I tried running it again and even with venv this is what I got: D:\AI\ChatBots\MemGPT_Setup\MemGPT>memgpt run ? Do you want to enable MemGPT with Open AI? Yes ? Open AI API keys not found in enviornment - please enter: http://localhost:1234 ? Do you want to enable MemGPT with Azure? No ? Select default endpoint: http://localhost:1234 ? Select default preset: memgpt_chat ? Select default model (recommended: gpt-4): gpt-4 ['memgpt_doc', 'memgpt_starter', 'sam', 'sam_pov', 'sam_simple_pov_gpt35'] ? Select default persona: memgpt_starter ['basic', 'cs_phd'] ? Select default human: basic Saving config to C:\Users\ADMIN.memgpt/config ╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\llama_index\embeddings\ │ │ huggingface.py:58 in init │ │ │ │ 55 │ │ callback_manager: Optional[CallbackManager] = None, │ │ 56 │ ): │ │ 57 │ │ try: │ │ ❱ 58 │ │ │ from transformers import AutoModel, AutoTokenizer │ │ 59 │ │ except ImportError: │ │ 60 │ │ │ raise ImportError( │ │ 61 │ │ │ │ "HuggingFaceEmbedding requires transformers to be installed.\n" │ │ │ │ ╭─────────────────── locals ───────────────────╮ │ │ │ cache_folder = None │ │ │ │ callback_manager = None │ │ │ │ device = None │ │ │ │ embed_batch_size = 10 │ │ │ │ max_length = None │ │ │ │ model = None │ │ │ │ model_name = 'BAAI/bge-small-en-v1.5' │ │ │ │ normalize = True │ │ │ │ pooling = 'cls' │ │ │ │ query_instruction = None │ │ │ │ self = HuggingFaceEmbedding() │ │ │ │ text_instruction = None │ │ │ │ tokenizer = None │ │ │ │ tokenizer_name = None │ │ │ │ trust_remote_code = False │ │ │ ╰──────────────────────────────────────────────╯ │ │ │ │ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers__init__.p │ │ y:26 in │
│ │
│ 23 from typing import TYPE_CHECKING │
│ 24 │
│ 25 # Check the dependencies satisfy the minimal versions required. │
│ ❱ 26 from . import dependency_versions_check │
│ 27 from .utils import ( │
│ 28 │ OptionalDependencyNotAvailable, │
│ 29 │ _LazyModule, │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ dependency_versions_table = <module 'transformers.dependency_versions_table' from │ │
│ │ 'C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\… │ │
│ │ TYPE_CHECKING = False │ │
│ │ utils = <module 'transformers.utils' from │ │
│ │ 'C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\… │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\dependency │
│ _versions_check.py:57 in │
│ │
│ 54 │ │ │ if not is_accelerate_available(): │
│ 55 │ │ │ │ continue # not required, check version only if installed │
│ 56 │ │ │
│ ❱ 57 │ │ require_version_core(deps[pkg]) │
│ 58 │ else: │
│ 59 │ │ raise ValueError(f"can't find {pkg} in {deps.keys()}, check dependencyversions │
│ 60 │
│ │
│ ╭────────────────────────────────────── locals ───────────────────────────────────────╮ │
│ │ deps = { │ │
│ │ │ 'Pillow': 'Pillow<10.0.0', │ │
│ │ │ 'accelerate': 'accelerate>=0.20.3', │ │
│ │ │ 'av': 'av==9.2.0', │ │
│ │ │ 'beautifulsoup4': 'beautifulsoup4', │ │
│ │ │ 'black': 'black~=23.1', │ │
│ │ │ 'codecarbon': 'codecarbon==1.2.0', │ │
│ │ │ 'cookiecutter': 'cookiecutter==1.7.3', │ │
│ │ │ 'dataclasses': 'dataclasses', │ │
│ │ │ 'datasets': 'datasets!=2.5.0', │ │
│ │ │ 'decord': 'decord==0.6.0', │ │
│ │ │ ... +76 │ │
│ │ } │ │
│ │ is_accelerate_available = <function is_accelerate_available at 0x000002435C0CED40> │ │
│ │ is_tokenizers_available = <function is_tokenizers_available at 0x000002435C0CEB00> │ │
│ │ pkg = 'accelerate' │ │
│ │ pkgs_to_check_at_runtime = [ │ │
│ │ │ 'python', │ │
│ │ │ 'tqdm', │ │
│ │ │ 'regex', │ │
│ │ │ 'requests', │ │
│ │ │ 'packaging', │ │
│ │ │ 'filelock', │ │
│ │ │ 'numpy', │ │
│ │ │ 'tokenizers', │ │
│ │ │ 'huggingface-hub', │ │
│ │ │ 'safetensors', │ │
│ │ │ ... +2 │ │
│ │ ] │ │
│ │ require_version = <function require_version at 0x000002435C115510> │ │
│ │ require_version_core = <function require_version_core at 0x000002435C1155A0> │ │
│ ╰─────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\utils\vers │
│ ions.py:117 in require_version_core │
│ │
│ 114 def require_version_core(requirement): │
│ 115 │ """require_version wrapper which emits a core-specific hint on failure""" │
│ 116 │ hint = "Try: pip install transformers -U or pip install -e '.[dev]' if you're workin │
│ ❱ 117 │ return require_version(requirement, hint) │
│ 118 │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ hint = "Try: pip install transformers -U or pip install -e '.[dev]' if you're working │ │
│ │ wi"+11 │ │
│ │ requirement = 'accelerate>=0.20.3' │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\utils\vers │
│ ions.py:111 in require_version │
│ │
│ 108 │ # check that the right version is installed if version number or a range was provide │
│ 109 │ if want_ver is not None: │
│ 110 │ │ for op, want_ver in wanted.items(): │
│ ❱ 111 │ │ │ _compare_versions(op, got_ver, want_ver, requirement, pkg, hint) │
│ 112 │
│ 113 │
│ 114 def require_version_core(requirement): │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ got_ver = '0.18.0' │ │
│ │ hint = "\nTry: pip install transformers -U or pip install -e '.[dev]' if you're │ │
│ │ working w"+12 │ │
│ │ match = [('>=', '0.20.3')] │ │
│ │ op = '>=' │ │
│ │ pkg = 'accelerate' │ │
│ │ requirement = 'accelerate>=0.20.3' │ │
│ │ w = '>=0.20.3' │ │
│ │ want_full = '>=0.20.3' │ │
│ │ want_range = ['>=0.20.3'] │ │
│ │ want_ver = '0.20.3' │ │
│ │ wanted = {'>=': '0.20.3'} │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\utils\vers │
│ ions.py:44 in _compare_versions │
│ │
│ 41 │ │ │ f" reinstalling {pkg}." │
│ 42 │ │ ) │
│ 43 │ if not ops[op](version.parse(got_ver), version.parse(want_ver)): │
│ ❱ 44 │ │ raise ImportError( │
│ 45 │ │ │ f"{requirement} is required for a normal functioning of this module, but fou │
│ 46 │ │ ) │
│ 47 │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ got_ver = '0.18.0' │ │
│ │ hint = "\nTry: pip install transformers -U or pip install -e '.[dev]' if you're │ │
│ │ working w"+12 │ │
│ │ op = '>=' │ │
│ │ pkg = 'accelerate' │ │
│ │ requirement = 'accelerate>=0.20.3' │ │
│ │ want_ver = '0.20.3' │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
ImportError: accelerate>=0.20.3 is required for a normal functioning of this module, but found accelerate==0.18.0.
Try: pip install transformers -U or pip install -e '.[dev]' if you're working with git main
During handling of the above exception, another exception occurred:
╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\memgpt\cli\cli.py:92 in │ │ run │ │ │ │ 89 │ config = MemGPTConfig.load() │ │ 90 │ original_stdout = sys.stdout # unfortunate hack required to suppress confusing prin │ │ 91 │ sys.stdout = io.StringIO() │ │ ❱ 92 │ embed_model = embedding_model(config) │ │ 93 │ service_context = ServiceContext.from_defaults(llm=None, embed_model=embed_model, ch │ │ 94 │ set_global_service_context(service_context) │ │ 95 │ sys.stdout = original_stdout │ │ │ │ ╭────────────────────────────────────── locals ───────────────────────────────────────╮ │ │ │ agent = None │ │ │ │ agent_files = [] │ │ │ │ agents = [] │ │ │ │ config = MemGPTConfig( │ │ │ │ │ config_path='C:\Users\ADMIN\.memgpt/config', │ │ │ │ │ anon_clientid='00000000000000000000581122a07091', │ │ │ │ │ preset='memgpt_chat', │ │ │ │ │ model_endpoint='http://localhost:1234', │ │ │ │ │ model='gpt-4', │ │ │ │ │ openai_key='http://localhost:1234', │ │ │ │ │ azure_key=None, │ │ │ │ │ azure_endpoint=None, │ │ │ │ │ azure_version=None, │ │ │ │ │ azure_deployment=None, │ │ │ │ │ azure_embedding_deployment=None, │ │ │ │ │ default_persona='memgpt_starter', │ │ │ │ │ default_human='basic', │ │ │ │ │ default_agent=None, │ │ │ │ │ embedding_model='openai', │ │ │ │ │ embedding_dim=768, │ │ │ │ │ embedding_chunk_size=300, │ │ │ │ │ archival_storage_type='local', │ │ │ │ │ archival_storage_path=None, │ │ │ │ │ archival_storage_uri=None, │ │ │ │ │ recall_storage_type='local', │ │ │ │ │ recall_storage_path=None, │ │ │ │ │ recall_storage_uri=None, │ │ │ │ │ persistence_manager_type=None, │ │ │ │ │ persistence_manager_save_file=None, │ │ │ │ │ persistence_manager_uri=None │ │ │ │ ) │ │ │ │ data_source = None │ │ │ │ debug = False │ │ │ │ first = False │ │ │ │ human = None │ │ │ │ model = None │ │ │ │ no_verify = False │ │ │ │ original_stdout = <colorama.ansitowin32.StreamWrapper object at 0x0000024362A7CA90> │ │ │ │ persona = None │ │ │ │ preset = None │ │ │ │ yes = False │ │ │ ╰─────────────────────────────────────────────────────────────────────────────────────╯ │ │ │ │ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\memgpt\embeddings.py:32 │ │ in embedding_model │ │ │ │ 29 │ │ # return f"local:{model}" │ │ 30 │ │ │ │ 31 │ │ # loads BAAI/bge-small-en-v1.5 │ │ ❱ 32 │ │ return HuggingFaceEmbedding(model_name=model) │ │ 33 │ │ │ │ ╭───────────────────────────────────────── locals ─────────────────────────────────────────╮ │ │ │ config = MemGPTConfig( │ │ │ │ │ config_path='C:\Users\ADMIN\.memgpt/config', │ │ │ │ │ anon_clientid='00000000000000000000581122a07091', │ │ │ │ │ preset='memgpt_chat', │ │ │ │ │ model_endpoint='http://localhost:1234', │ │ │ │ │ model='gpt-4', │ │ │ │ │ openai_key='http://localhost:1234', │ │ │ │ │ azure_key=None, │ │ │ │ │ azure_endpoint=None, │ │ │ │ │ azure_version=None, │ │ │ │ │ azure_deployment=None, │ │ │ │ │ azure_embedding_deployment=None, │ │ │ │ │ default_persona='memgpt_starter', │ │ │ │ │ default_human='basic', │ │ │ │ │ default_agent=None, │ │ │ │ │ embedding_model='openai', │ │ │ │ │ embedding_dim=768, │ │ │ │ │ embedding_chunk_size=300, │ │ │ │ │ archival_storage_type='local', │ │ │ │ │ archival_storage_path=None, │ │ │ │ │ archival_storage_uri=None, │ │ │ │ │ recall_storage_type='local', │ │ │ │ │ recall_storage_path=None, │ │ │ │ │ recall_storage_uri=None, │ │ │ │ │ persistence_manager_type=None, │ │ │ │ │ persistence_manager_save_file=None, │ │ │ │ │ persistence_manager_uri=None │ │ │ │ ) │ │ │ │ HuggingFaceEmbedding = <class 'llama_index.embeddings.huggingface.HuggingFaceEmbedding'> │ │ │ │ model = 'BAAI/bge-small-en-v1.5' │ │ │ ╰──────────────────────────────────────────────────────────────────────────────────────────╯ │ │ │ │ C:\Users\ADMIN\AppData\Local\Programs\Python\Python310\lib\site-packages\llama_index\embeddings\ │ │ huggingface.py:60 in init │ │ │ │ 57 │ │ try: │ │ 58 │ │ │ from transformers import AutoModel, AutoTokenizer │ │ 59 │ │ except ImportError: │ │ ❱ 60 │ │ │ raise ImportError( │ │ 61 │ │ │ │ "HuggingFaceEmbedding requires transformers to be installed.\n" │ │ 62 │ │ │ │ "Please install transformers with
pip install transformers." │ │ 63 │ │ │ ) │ │ │ │ ╭─────────────────── locals ───────────────────╮ │ │ │ cache_folder = None │ │ │ │ callback_manager = None │ │ │ │ device = None │ │ │ │ embed_batch_size = 10 │ │ │ │ max_length = None │ │ │ │ model = None │ │ │ │ model_name = 'BAAI/bge-small-en-v1.5' │ │ │ │ normalize = True │ │ │ │ pooling = 'cls' │ │ │ │ query_instruction = None │ │ │ │ self = HuggingFaceEmbedding() │ │ │ │ text_instruction = None │ │ │ │ tokenizer = None │ │ │ │ tokenizer_name = None │ │ │ │ trust_remote_code = False │ │ │ ╰──────────────────────────────────────────────╯ │ ╰──────────────────────────────────────────────────────────────────────────────────────────────────╯ ImportError: HuggingFaceEmbedding requires transformers to be installed. Please install transformers withpip install transformers.