mirror of
https://github.com/lfnovo/open-notebook.git
synced 2026-07-25 15:47:29 +00:00
11ca9c138c
Consolidate the three copies of context assembly into
open_notebook/utils/context_builder.py:
- POST /api/chat/context now delegates to build_notebook_context()
(same request/response shapes, same string-matching config semantics)
- The source-chat graph now calls build_source_context() instead of the
495-line generalized ContextBuilder class, which had exactly one
caller and whose notebook/notes/priority-config flexibility was dead
- POST /api/notebooks/{notebook_id}/context removed: it duplicated
/api/chat/context with a slightly different envelope and had zero
callers (frontend, docs, tests)
Behavior is pinned by new characterization tests written before the
refactor (tests/test_context_endpoint_characterization.py) plus unit
tests for build_source_context.
72 lines
1.8 KiB
Python
72 lines
1.8 KiB
Python
"""
|
|
Utils package for Open Notebook.
|
|
|
|
To avoid circular imports, import functions directly:
|
|
- from open_notebook.utils.context_builder import build_notebook_context, build_source_context
|
|
- from open_notebook.utils import token_count, compare_versions
|
|
- from open_notebook.utils.chunking import chunk_text, detect_content_type, ContentType
|
|
- from open_notebook.utils.embedding import generate_embedding, generate_embeddings
|
|
- from open_notebook.utils.encryption import encrypt_value, decrypt_value
|
|
"""
|
|
|
|
from .chunking import (
|
|
CHUNK_SIZE,
|
|
ContentType,
|
|
chunk_text,
|
|
detect_content_type,
|
|
detect_content_type_from_extension,
|
|
detect_content_type_from_heuristics,
|
|
)
|
|
from .embedding import (
|
|
generate_embedding,
|
|
generate_embeddings,
|
|
mean_pool_embeddings,
|
|
)
|
|
from .encryption import (
|
|
decrypt_value,
|
|
encrypt_value,
|
|
)
|
|
from .model_utils import full_model_dump
|
|
from .text_utils import (
|
|
clean_thinking_content,
|
|
parse_thinking_content,
|
|
remove_non_ascii,
|
|
remove_non_printable,
|
|
)
|
|
from .token_utils import token_cost, token_count
|
|
from .version_utils import (
|
|
compare_versions,
|
|
get_installed_version,
|
|
get_version_from_github,
|
|
)
|
|
|
|
__all__ = [
|
|
# Chunking
|
|
"CHUNK_SIZE",
|
|
"ContentType",
|
|
"chunk_text",
|
|
"detect_content_type",
|
|
"detect_content_type_from_extension",
|
|
"detect_content_type_from_heuristics",
|
|
# Embedding
|
|
"generate_embedding",
|
|
"generate_embeddings",
|
|
"mean_pool_embeddings",
|
|
# Text utils
|
|
"remove_non_ascii",
|
|
"remove_non_printable",
|
|
"parse_thinking_content",
|
|
"clean_thinking_content",
|
|
# Token utils
|
|
"token_count",
|
|
"token_cost",
|
|
# Version utils
|
|
"compare_versions",
|
|
"get_installed_version",
|
|
"get_version_from_github",
|
|
# Encryption utils
|
|
"decrypt_value",
|
|
"encrypt_value",
|
|
# Model utils
|
|
"full_model_dump",
|
|
]
|