monarch-initiative / curategpt

LLM-driven curation assist tool (pre-alpha)
https://monarch-initiative.github.io/curategpt/
BSD 3-Clause "New" or "Revised" License
60 stars 11 forks source link

can't make `load-github-obi`... Field "model_name" has conflict with protected namespace "model". #59

Closed turbomam closed 2 months ago

turbomam commented 2 months ago
make load-github-obi           

poetry run curategpt -v view index -p stagedb -c gh_obi -m openai: --view github --init-with "{repo: obi-ontology/obi}" /Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/pydantic/_internal/_fields.py:161: UserWarning: Field "modelname" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( INFO:root:Logger root set to level 20 INFO:curate_gpt.store.chromadb_adapter:Using ChromaDB at stagedb INFO:curate_gpt.store.chromadb_adapter:ChromaDB client: <chromadb.api.client.Client object at 0x308925750> INFO:curate_gpt.store.chromadb_adapter:Getting metadata for gh_obi INFO:curate_gpt.store.chromadb_adapter:Getting collection object gh_obi INFO:curate_gpt.store.chromadb_adapter:Getting metadata for gh_obi INFO:curate_gpt.store.chromadb_adapter:Getting collection object gh_obi INFO:curate_gpt.store.chromadb_adapter:Getting embedding function for openai: INFO:chromadb.api.segment:Collection gh_obi is not created. INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} INFO:curate_gpt.wrappers.general.github_wrapper:Header: {'Accept': 'application/vnd.github.v3+json', 'User-Agent': 'CurateGPT/0.0.1'} Traceback (most recent call last): File "", line 1, in File "/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/click/core.py", line 1157, in call return self.main(args, kwargs) File "/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/click/core.py", line 1078, in main rv = self.invoke(ctx) File "/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/click/core.py", line 1688, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/click/core.py", line 1688, in invoke return _process_result(sub_ctx.command.invoke(sub_ctx)) File "/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/click/core.py", line 1434, in invoke return ctx.invoke(self.callback, ctx.params) File "/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/click/core.py", line 783, in invoke return __callback(args, kwargs) File "/Users/mark/curategpt/curate-gpt/src/curate_gpt/cli.py", line 2506, in view_index store.insert(objs, model=model, collection=collection, batch_size=batch_size) File "/Users/mark/curategpt/curate-gpt/src/curate_gpt/store/chromadb_adapter.py", line 142, in insert self._insert_or_update(objs, method_name="add", kwargs) File "/Users/mark/curategpt/curate-gpt/src/curate_gpt/store/chromadb_adapter.py", line 192, in _insert_or_update next_objs = list(next_objs) File "/Users/mark/curategpt/curate-gpt/src/curate_gpt/wrappers/general/github_wrapper.py", line 173, in objects issue_obj = self.transform_issue(issue) File "/Users/mark/curategpt/curate-gpt/src/curate_gpt/wrappers/general/github_wrapper.py", line 194, in transform_issue issue = Issue( File "/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/pydantic/main.py", line 193, in init self.__pydantic_validator__.validate_python(data, self_instance=self) pydantic_core._pydantic_core.ValidationError: 1 validation error for Issue body Input should be a valid string [type=string_type, input_value=None, input_type=NoneType] For further information visit https://errors.pydantic.dev/2.8/v/string_type make: *** [load-github-obi] Error 1

turbomam commented 2 months ago

I get a different error message if I fail to provide a OPENAI_API_KEY, but I get a very similar erorror message if I export an obviously wrong OPENAI_API_KEY

turbomam commented 2 months ago

actually, the make load-bacdive error message also complains

FileNotFoundError: [Errno 2] No such file or directory: '/Users/mark/Downloads/bacdive_strains.json'

turbomam commented 2 months ago

I get

/Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/pydantic/_internal/_fields.py:161: UserWarning: Field "modelname" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = ().

even from just running poetry run curategpt index --help

turbomam commented 2 months ago

I think i got make onto-pato to work

poetry run curategpt ontology index --index-fields label,definition,relationships -p stagedb -c ont_pato -m openai: sqlite:obo:pato /Users/mark/curategpt/curate-gpt/.venv/lib/python3.10/site-packages/pydantic/_internal/_fields.py:161: UserWarning: Field "modelname" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( Indexing 8012 objects Indexed 8012 in 86.62134289741516 seconds

caufieldjh commented 2 months ago

That protected namespace error seems to appear consistently but I don't think it impacts results. Going to see if I can get it to stop as it's confusing.

turbomam commented 2 months ago

I was able to make a MIxS issue collection but had to

And @caufieldjh added support for GH issues that don't have a body