ModuleNotFoundError: No module named 'huggingface_hub.inference._types'

A static comparison of the published huggingface-hub 0.27.0 wheel against its pinned v0.27.0 source (commit 6bfa5dd44d0472909dc778d30fbaac92e84ff96e) found that the module path huggingface_hub.inference._types, imported by LlamaIndex's Hugging Face LLM integration, is absent from both, so the wheel did not simply omit a file present in the matching source. The analysis, prepared with AI assistance using a Yumi import-layout checker without installing or executing package code, notes the installed versions were not supplied and the archival snapshots do not establish a working replacement combination. It recommends capturing versions via pip show for huggingface-hub, llama-index-llms-huggingface and llama-index-core plus pip check, then selecting compatible versions from the integration's dependency constraints rather than a blanket Hub downgrade.

The traceback points to the LlamaIndex/Hugging Face integration importing huggingface hub.inference. types . Changing the quantization configuration alone would not address that import. An archival LlamaIndex v0.10.0 integration file https://github.com/run-llama/llama index/blob/2b6a46d8498b2259fc84385c1167e0b7b3c0fa87/llama-index-integrations/llms/llama-index-llms-huggingface/llama index/llms/huggingface/base.py L8 contains the exact line: python from huggingface hub.inference. types import ConversationalOutput We checked the published huggingface-hub==0.27.0 wheel against its pinned v0.27.0 source huggingface/huggingface hub commit 6bfa5dd44d0472909dc778d30fbaac92e84ff96e , under src/ . Their complete Python-file layouts match, and that module path is absent from both. For these selected snapshots, the integration expects an unavailable module; the wheel hasn’t simply omitted a Python file present in the matching source. This is an older question, and the installed versions weren’t supplied. These archival snapshots don’t establish your original environment or a working replacement combination. This reply was prepared with AI assistance; we used our Yumi import-layout checker https://noqt.no-qt.chatgpt.site/yumi/python-import-layout for the static comparison, without installing or executing package code. To choose a repair, first capture versions from the notebook’s actual Python environment: python import sys import subprocess subprocess.run sys.executable, "-m", "pip", "show", "huggingface-hub", "llama-index-llms-huggingface", "llama-index-core" subprocess.run sys.executable, "-m", "pip", "check" Use the integration’s dependency constraints and documentation to select compatible integration/Hub versions, restart the kernel after installation changes, and test the import before loading the model. A clean dependency check alone doesn’t prove the import works, and this traceback doesn’t justify a blanket Hub downgrade.