## Summary
- Pass `vector_similarity_weight` from Python and Go retrieval requests
into Infinity's weighted fusion expression.
- Keep fusion weights ordered as text first and vector second, with the
existing default vector weight of `0.3`.
---------
Co-authored-by: chenglinpeng <1042527908@qq.com>
### Summary
This PR adds [Serply](https://serply.io) as a third web search provider
for chat assistants, alongside the existing Tavily and Querit options.
### Summary
Closes#18414.
`rag/res/term.freq` is not shipped, and both term-weight implementations
therefore assigned the same `300` fallback frequency to every lowercase
Latin token. With no tokenizer frequency, NER, or POS signal, function
words and content words received identical lexical boosts.
This PR adds the same bounded out-of-vocabulary prior to Python and Go:
- Use it only when the explicit DF dictionary or tokenizer has no
frequency.
- Count Latin, Greek, and Cyrillic letters, including uppercase and
accented forms.
- Keep the existing frequency of `300` for words up to three letters,
halve it every two additional letters, and clamp it at `10`.
- Reject digits, underscores, and logographic terms so Chinese and other
existing fine-grained-tokenizer paths are unchanged.
- Treat an absent optional `term.freq` as the supported fallback path
without a startup warning, while still logging inaccessible or malformed
dictionaries.
A corpus-derived table was intentionally not added: that would require
provenance/licensing decisions, language detection, and handling
cross-language homographs. The bounded prior is deterministic,
dependency-free, and fixes the equal-weight degradation for
whitespace-delimited alphabetic languages without claiming
corpus-specific precision.
Python and Go consume one shared fixture covering ASCII, uppercase,
accented Latin, Greek, Cyrillic, separators, invalid mixed tokens, and a
CJK non-match. Both sides also verify the issue's ordering (`was <
largest < supplier < equipment`) and that an explicit dictionary entry
still takes precedence.
Co-authored-by: Loong <184861530+yzl0ng@users.noreply.github.com>
### Summary
`AsyncExecutor.Execute` acquires a worker-pool slot, while
`ExecuteWithRetry` duplicated the task lifecycle without acquiring one.
Pregel supplies a retry configuration for every node, so those
executions
bypassed `WithMaxConcurrency`.
This change:
- routes retry execution through the shared `Execute` path;
- waits on the task-owned context and rechecks cancellation after slot
acquisition;
- adds deterministic regression coverage for worker-pool occupancy and
queued-task cancellation.
## Summary
- Frontend `Images` already includes `bmp`
(`web/src/constants/common.ts`), and picture parsing already accepts
`.bmp` (`internal/parser/parser/picture_parser.go`, `rag/app/picture.py`
via Pillow).
- This PR adds `bmp` to both whitelist sites and a small Go unit test.
Co-authored-by: zhangjiangshan1 <zhangjiangshan1@kingsoft.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Refactor the Extractor component into a pure, unified **5-in-1 modular extraction engine** across both Dataset (`knowledgebase.parser_config`) and Pipeline (Canvas DSL).
## Summary
- Disable DeepSeek V4 thinking (chain-of-thought) by default.
- litellm 1.82.x drops `thinking: disabled`; carry the toggle through
`extra_body.thinking.type` and strip `reasoning_effort` to avoid the
400.
- Use local timezone for agent `sys.date` instead of UTC.
Reference: https://api-docs.deepseek.com/guides/thinking_mode
---------
Co-authored-by: Claude <claude@example.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude <noreply@anthropic.com>
This PR modularizes the **Extractor** component configuration with dedicated feature subtabs, adds independent system prompt configuration, fixes multi-node execution determinism and parameter persistence across save and page refresh, and ensures backward compatibility with legacy flat fields.
