youngkingdom/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-05-04 09:28:04 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: knowledgebase summary index (#31600)

Browse Source
This commit is contained in:
FFXN
2026-01-27 16:12:57 +08:00
committed by GitHub
parent 5ccd5781be e1cb37e967
commit 938b036621
5 changed files with 69 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
api/core/rag/index_processor/processor/paragraph_index_processor.py
View File

@ -12,6 +12,7 @@ from core.entities.knowledge_entities import PreviewDetail
from core.file import File, FileTransferMethod, FileType, file_manager
from core.llm_generator.prompts import DEFAULT_GENERATOR_SUMMARY_PROMPT
from core.model_manager import ModelInstance
from core.model_runtime.entities.llm_entities import LLMUsage
from core.model_runtime.entities.message_entities import (
ImagePromptMessageContent,
PromptMessageContentUnionTypes,
@ -295,11 +296,11 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
if flask_app:
# Ensure Flask app context in worker thread
with flask_app.app_context():
summary = self.generate_summary(tenant_id, preview.content, summary_index_setting)
summary, _ = self.generate_summary(tenant_id, preview.content, summary_index_setting)
preview.summary = summary
else:
# Fallback: try without app context (may fail)
summary = self.generate_summary(tenant_id, preview.content, summary_index_setting)
summary, _ = self.generate_summary(tenant_id, preview.content, summary_index_setting)
preview.summary = summary
# Generate summaries concurrently using ThreadPoolExecutor
@ -356,7 +357,7 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
text: str,
summary_index_setting: dict | None = None,
segment_id: str | None = None,
) -> str:
) -> tuple[str, LLMUsage]:
"""
Generate summary for the given text using ModelInstance.invoke_llm and the default or custom summary prompt,
and supports vision models by including images from the segment attachments or text content.
@ -366,6 +367,9 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
text: Text content to summarize
summary_index_setting: Summary index configuration
segment_id: Optional segment ID to fetch attachments from SegmentAttachmentBinding table
Returns:
Tuple of (summary_content, llm_usage) where llm_usage is LLMUsage object
"""
if not summary_index_setting or not summary_index_setting.get("enable"):
raise ValueError("summary_index_setting is required and must be enabled to generate summary.")
@ -432,7 +436,19 @@ class ParagraphIndexProcessor(BaseIndexProcessor):
result = model_instance.invoke_llm(prompt_messages=prompt_messages, model_parameters={}, stream=False)
return getattr(result.message, "content", "")
summary_content = getattr(result.message, "content", "")
usage = result.usage
# Deduct quota for summary generation (same as workflow nodes)
from core.workflow.nodes.llm import llm_utils
try:
llm_utils.deduct_llm_quota(tenant_id=tenant_id, model_instance=model_instance, usage=usage)
except Exception as e:
# Log but don't fail summary generation if quota deduction fails
logger.warning("Failed to deduct quota for summary generation: %s", str(e))
return summary_content, usage
@staticmethod
def _extract_images_from_text(tenant_id: str, text: str) -> list[File]:

4
api/core/rag/index_processor/processor/parent_child_index_processor.py
View File

@ -382,7 +382,7 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
if flask_app:
# Ensure Flask app context in worker thread
with flask_app.app_context():
summary = ParagraphIndexProcessor.generate_summary(
summary, _ = ParagraphIndexProcessor.generate_summary(
tenant_id=tenant_id,
text=preview.content,
summary_index_setting=summary_index_setting,
@ -390,7 +390,7 @@ class ParentChildIndexProcessor(BaseIndexProcessor):
preview.summary = summary
else:
# Fallback: try without app context (may fail)
summary = ParagraphIndexProcessor.generate_summary(
summary, _ = ParagraphIndexProcessor.generate_summary(
tenant_id=tenant_id,
text=preview.content,
summary_index_setting=summary_index_setting,

4
api/core/workflow/nodes/knowledge_index/knowledge_index_node.py
View File

@ -364,7 +364,7 @@ class KnowledgeIndexNode(Node[KnowledgeIndexNodeData]):
# Set Flask application context in worker thread
if flask_app:
with flask_app.app_context():
summary = ParagraphIndexProcessor.generate_summary(
summary, _ = ParagraphIndexProcessor.generate_summary(
tenant_id=dataset.tenant_id,
text=preview_item["content"],
summary_index_setting=summary_index_setting,
@ -373,7 +373,7 @@ class KnowledgeIndexNode(Node[KnowledgeIndexNodeData]):
preview_item["summary"] = summary
else:
# Fallback: try without app context (may fail)
summary = ParagraphIndexProcessor.generate_summary(
summary, _ = ParagraphIndexProcessor.generate_summary(
tenant_id=dataset.tenant_id,
text=preview_item["content"],
summary_index_setting=summary_index_setting,