Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix: LLMMetadataExtractor serialisation #136

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
+7 −3
Open

fix: LLMMetadataExtractor serialisation #136

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d6cc0a5
fixing serialization
davidsbatista Nov 20, 2024
6656e4a
fixing tests
davidsbatista Nov 20, 2024
de5bbdb
adding page_range (already expanded) to the serialisation
davidsbatista Nov 20, 2024
339bbd7
fixing serialisation tests
davidsbatista Nov 20, 2024
78c12ac
Merge branch 'main' into fix-llmmetadata-extractor
davidsbatista Dec 1, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion haystack_experimental/components/extractors/llm_metadata_extractor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -228,11 +228,12 @@ def to_dict(self) -> Dict[str, Any]:
return default_to_dict(
self,
prompt=self.prompt,
input_text=self.prompt_variable,
prompt_variable=self.prompt_variable,
expected_keys=self.expected_keys,
raise_on_failure=self.raise_on_failure,
generator_api=self.generator_api.value,
generator_api_params=llm_provider["init_parameters"],
page_range=self.expanded_range
)

@classmethod
Expand Down
7 changes: 5 additions & 2 deletions test/components/extractors/test_llm_metadata_extractor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ def test_init_missing_prompt_variable(self, monkeypatch):
prompt_variable="test2"
)

def test_to_dict(self, monkeypatch):
def test_to_dict_default_params(self, monkeypatch):
monkeypatch.setenv("OPENAI_API_KEY", "test-api-key")
extractor = LLMMetadataExtractor(
prompt="some prompt that was used with the LLM {{test}}",
Expand All @@ -68,15 +68,18 @@ def test_to_dict(self, monkeypatch):
prompt_variable="test",
generator_api_params={'model': 'gpt-4o-mini', 'generation_kwargs': {"temperature": 0.5}},
raise_on_failure=True)

extractor_dict = extractor.to_dict()

assert extractor_dict == {
'type': 'haystack_experimental.components.extractors.llm_metadata_extractor.LLMMetadataExtractor',
'init_parameters': {
'prompt': 'some prompt that was used with the LLM {{test}}',
'expected_keys': ['key1', 'key2'],
'raise_on_failure': True,
'input_text': 'test',
'prompt_variable': 'test',
'generator_api': 'openai',
'page_range': None,
'generator_api_params': {
'api_base_url': None,
'api_key': {'env_vars': ['OPENAI_API_KEY'],'strict': True,'type': 'env_var'},
Expand Down
Loading