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

Fix FastLLM bug, defaults #2017

Merged
merged 1 commit into from
Mar 3, 2025
Merged

Fix FastLLM bug, defaults #2017

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 0 additions & 1 deletion py/core/base/providers/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,6 @@ class CompletionConfig(ProviderConfig):
provider: Optional[str] = None
generation_config: Optional[GenerationConfig] = None
concurrent_request_limit: int = 256
fast_llm: str = "openai/gpt-4o"
max_retries: int = 3
initial_backoff: float = 1.0
max_backoff: float = 64.0
Expand Down
46 changes: 23 additions & 23 deletions py/core/providers/ingestion/unstructured/base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,30 +46,30 @@ class UnstructuredIngestionConfig(IngestionConfig):
new_after_n_chars: int = 1500
overlap: int = 64

coordinates: bool | None
encoding: str | None # utf-8
extract_image_block_types: list[str] | None
gz_uncompressed_content_type: str | None
hi_res_model_name: str | None
include_orig_elements: bool | None
include_page_breaks: bool | None

languages: list[str] | None
multipage_sections: bool | None
ocr_languages: list[str] | None
coordinates: bool | None = None
encoding: str | None = None # utf-8
extract_image_block_types: list[str] | None = None
gz_uncompressed_content_type: str | None = None
hi_res_model_name: str | None = None
include_orig_elements: bool | None = None
include_page_breaks: bool | None = None

languages: list[str] | None = None
multipage_sections: bool | None = None
ocr_languages: list[str] | None = None
# output_format: Optional[str] = "application/json"
overlap_all: bool | None
pdf_infer_table_structure: bool | None

similarity_threshold: float | None
skip_infer_table_types: list[str] | None
split_pdf_concurrency_level: int | None
split_pdf_page: bool | None
starting_page_number: int | None
strategy: str | None
chunking_strategy: str | ChunkingStrategy | None # type: ignore
unique_element_ids: bool | None
xml_keep_tags: bool | None
overlap_all: bool | None = None
pdf_infer_table_structure: bool | None = None

similarity_threshold: float | None = None
skip_infer_table_types: list[str] | None = None
split_pdf_concurrency_level: int | None = None
split_pdf_page: bool | None = None
starting_page_number: int | None = None
strategy: str | None = None
chunking_strategy: str | ChunkingStrategy | None = None # type: ignore
unique_element_ids: bool | None = None
xml_keep_tags: bool | None = None

def to_ingestion_request(self):
import json
Expand Down
Loading