pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-30 00:32:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: parent-children pipleine bad case. (#12246)

Browse Source 
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
Kevin Hu
2025-12-26 18:57:16 +08:00
committed by GitHub
parent 613d2c5790
commit bc9e1e3b9a
3 changed files with 18 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
rag/flow/splitter/splitter.py
View File

@ -92,9 +92,9 @@ class Splitter(ProcessBase):
continue
split_sec = re.split(r"(%s)" % custom_pattern, c, flags=re.DOTALL)
if split_sec:
for txt in split_sec:
for j in range(0, len(split_sec), 2):
docs.append({
"text": txt,
"text": split_sec[j],
"mom": c
})
else:
@ -155,9 +155,9 @@ class Splitter(ProcessBase):
split_sec = re.split(r"(%s)" % custom_pattern, c["text"], flags=re.DOTALL)
if split_sec:
c["mom"] = c["text"]
for txt in split_sec:
for j in range(0, len(split_sec), 2):
cc = deepcopy(c)
cc["text"] = txt
cc["text"] = split_sec[j]
docs.append(cc)
else:
docs.append(c)

22
rag/prompts/meta_data.md
View File

@ -1,13 +1,17 @@
Extract important structured information from the given content.
Output ONLY a valid JSON string with no additional text.
If no important structured information is found, output an empty JSON object: {}.
## Role: Metadata extraction expert
## Constraints:
- Core Directive: Extract important structured information from the given content. Output ONLY a valid JSON string. No Markdown (e.g., ```json), no explanations, and no notes.
- Schema Parsing: In the `properties` object provided in Schema, the attribute name (e.g., 'author') is the target Key. Extract values based on the `description`; if no `description` is provided, refer to the key's literal meaning.
- Extraction Rules: Extract only when there is an explicit semantic correlation. If multiple values or data points match a field's definition, extract and include all of them. Strictly follow the Schema below and only output matched key-value pairs. If the content is irrelevant or no matching information is identified, you **MUST** output {}.
- Data Source: Extraction must be based solely on content below. Semantic mapping (synonyms) is allowed, but strictly prohibit hallucinations or fabricated facts.
Important structured information structure as following:
## Enum Rules (Triggered ONLY if an enum list is present):
- Value Lock: All extracted values MUST strictly match the provided enum list.
- Normalization: Map synonyms or variants in the text back to the standard enum value (e.g., "Dec" to "December").
- Fallback: Output {} if no explicit match or synonym is identified.
## Schema for extraction:
{{ schema }}
---------------------------
The given content as following:
{{ content }}
## Content to analyze:
{{ content }}