mirror of
https://github.com/SillyTavern/SillyTavern-Extras.git
synced 2026-10-15 18:11:52 +00:00
[GH-ISSUE #208] AttributeError: module 'chromadb' has no attribute 'PersistentClient' #128
Labels
No labels
bug
duplicate
planned
pull-request
under consideration
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
SillyTavern/SillyTavern-Extras#128
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @HowlWolf1209 on GitHub (Dec 22, 2023).
Original GitHub issue: https://github.com/SillyTavern/SillyTavern-Extras/issues/208
When I ran Extras with the chromadb module enabled: python server.py --enable-modules=chromadb, an error occurred：
(extras) D:\AI_writer\SillyTavern-Launcher\SillyTavern-extras>python server.py --enable-modules=chromadb
Using torch device: cpu
Initializing ChromaDB
Traceback (most recent call last):
File "D:\AI_writer\SillyTavern-Launcher\SillyTavern-extras\server.py", line 282, in
chromadb_client = chromadb.PersistentClient(path=args.chroma_folder, settings=Settings(anonymized_telemetry=False))
^^^^^^^^^^^^^^^^^^^^^^^^^
AttributeError: module 'chromadb' has no attribute 'PersistentClient'
I‘ve tried to run pip install --upgrade chromadb, and it doesn't work
I‘ve tried to run python server.py --enable-modules=chromadb, and it doesn't work neither
I tried to install a later version of chromadb, pip install chromadb==0.4.X, and python server.py --enable-modules=chromadb
a new error occurred:
Initializing ChromaDB
ChromaDB is running in-memory with persistence. Persistence is stored in .chroma_db. Can be cleared by deleting the folder or purging db.
Traceback (most recent call last):
File "D:\AI_writer\SillyTavern-Launcher\SillyTavern-extras\server.py", line 294, in
chromadb_embed_fn = embedding_functions.SentenceTransformerEmbeddingFunction(embedding_model, device=device_string)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\chromadb\utils\embedding_functions.py", line 41, in init
self.models[model_name] = SentenceTransformer(model_name, device=device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\sentence_transformers\SentenceTransformer.py", line 95, in init
modules = self._load_sbert_model(model_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\sentence_transformers\SentenceTransformer.py", line 840, in _load_sbert_model
module = module_class.load(os.path.join(model_path, module_config['path']))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\sentence_transformers\models\Transformer.py", line 137, in load
return Transformer(model_name_or_path=input_path, **config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\sentence_transformers\models\Transformer.py", line 29, in init
self._load_model(model_name_or_path, config, cache_dir)
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\sentence_transformers\models\Transformer.py", line 49, in _load_model
self.auto_model = AutoModel.from_pretrained(model_name_or_path, config=config, cache_dir=cache_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\transformers\models\auto\auto_factory.py", line 566, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\transformers\modeling_utils.py", line 3706, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\HowlWolf\miniconda3\envs\extras\Lib\site-packages\transformers\modeling_utils.py", line 4166, in _load_pretrained_model
raise RuntimeError(f"Error(s) in loading state_dict for {model.class.name}:\n\t{error_msg}")
RuntimeError: Error(s) in loading state_dict for MPNetModel:
size mismatch for embeddings.word_embeddings.weight: copying a param with shape torch.Size([28996, 768]) from checkpoint, the shape in current model is torch.Size([30527, 768]).
size mismatch for embeddings.position_embeddings.weight: copying a param with shape torch.Size([512, 768]) from checkpoint, the shape in current model is torch.Size([514, 768]).
You may consider adding
ignore_mismatched_sizes=Truein the modelfrom_pretrainedmethod.Anyone know any solutions if you have ran into this problem yourselves???
@Technologicat commented on GitHub (Feb 7, 2024):
The old Smart Context extension has been superseded by the built-in Vector Storage extension.
Vector Storage does not need ChromaDB.
To upgrade:
embeddingsmodule.--embedding-modelcommand-line argument of the ST-extras server.embeddingsmodule uses the device (CPU or GPU) that you have configured your ST-extras to use. As usual, see the--cpu(CPU, default),--cuda(GPU) and--cuda-devicecommand-line arguments.chromadbmodule in ST-extras, and thechromadbPython library, are no longer needed.