mirror of
https://github.com/danswer-ai/danswer.git
synced 2025-07-09 14:11:33 +02:00
improved basic search latency (#4186)
* improved basic search latency * address PR comments + minor cleanup
This commit is contained in:
evan-danswer
GitHub
@ -90,97 +90,97 @@ class CitationProcessor:
|
||||
next(group for group in citation.groups() if group is not None)
|
||||
)
|
||||
|
||||
if 1 <= numerical_value <= self.max_citation_num:
|
||||
context_llm_doc = self.context_docs[numerical_value - 1]
|
||||
final_citation_num = self.final_order_mapping[
|
||||
if not (1 <= numerical_value <= self.max_citation_num):
|
||||
continue
|
||||
|
||||
context_llm_doc = self.context_docs[numerical_value - 1]
|
||||
final_citation_num = self.final_order_mapping[
|
||||
context_llm_doc.document_id
|
||||
]
|
||||
|
||||
if final_citation_num not in self.citation_order:
|
||||
self.citation_order.append(final_citation_num)
|
||||
|
||||
citation_order_idx = self.citation_order.index(final_citation_num) + 1
|
||||
|
||||
# get the value that was displayed to user, should always
|
||||
# be in the display_doc_order_dict. But check anyways
|
||||
if context_llm_doc.document_id in self.display_order_mapping:
|
||||
displayed_citation_num = self.display_order_mapping[
|
||||
context_llm_doc.document_id
|
||||
]
|
||||
|
||||
if final_citation_num not in self.citation_order:
|
||||
self.citation_order.append(final_citation_num)
|
||||
|
||||
citation_order_idx = (
|
||||
self.citation_order.index(final_citation_num) + 1
|
||||
else:
|
||||
displayed_citation_num = final_citation_num
|
||||
logger.warning(
|
||||
f"Doc {context_llm_doc.document_id} not in display_doc_order_dict. Used LLM citation number instead."
|
||||
)
|
||||
|
||||
# get the value that was displayed to user, should always
|
||||
# be in the display_doc_order_dict. But check anyways
|
||||
if context_llm_doc.document_id in self.display_order_mapping:
|
||||
displayed_citation_num = self.display_order_mapping[
|
||||
context_llm_doc.document_id
|
||||
]
|
||||
else:
|
||||
displayed_citation_num = final_citation_num
|
||||
logger.warning(
|
||||
f"Doc {context_llm_doc.document_id} not in display_doc_order_dict. Used LLM citation number instead."
|
||||
)
|
||||
|
||||
# Skip consecutive citations of the same work
|
||||
if final_citation_num in self.current_citations:
|
||||
start, end = citation.span()
|
||||
real_start = length_to_add + start
|
||||
diff = end - start
|
||||
self.curr_segment = (
|
||||
self.curr_segment[: length_to_add + start]
|
||||
+ self.curr_segment[real_start + diff :]
|
||||
)
|
||||
length_to_add -= diff
|
||||
continue
|
||||
|
||||
# Handle edge case where LLM outputs citation itself
|
||||
if self.curr_segment.startswith("[["):
|
||||
match = re.match(r"\[\[(\d+)\]\]", self.curr_segment)
|
||||
if match:
|
||||
try:
|
||||
doc_id = int(match.group(1))
|
||||
context_llm_doc = self.context_docs[doc_id - 1]
|
||||
yield CitationInfo(
|
||||
# citation_num is now the number post initial ranking, i.e. as displayed to user
|
||||
citation_num=displayed_citation_num,
|
||||
document_id=context_llm_doc.document_id,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
f"Manual LLM citation didn't properly cite documents {e}"
|
||||
)
|
||||
else:
|
||||
logger.warning(
|
||||
"Manual LLM citation wasn't able to close brackets"
|
||||
)
|
||||
continue
|
||||
|
||||
link = context_llm_doc.link
|
||||
|
||||
self.past_cite_count = len(self.llm_out)
|
||||
self.current_citations.append(final_citation_num)
|
||||
|
||||
if citation_order_idx not in self.cited_inds:
|
||||
self.cited_inds.add(citation_order_idx)
|
||||
yield CitationInfo(
|
||||
# citation number is now the one that was displayed to user
|
||||
citation_num=displayed_citation_num,
|
||||
document_id=context_llm_doc.document_id,
|
||||
)
|
||||
|
||||
# Skip consecutive citations of the same work
|
||||
if final_citation_num in self.current_citations:
|
||||
start, end = citation.span()
|
||||
if link:
|
||||
prev_length = len(self.curr_segment)
|
||||
self.curr_segment = (
|
||||
self.curr_segment[: start + length_to_add]
|
||||
+ f"[[{displayed_citation_num}]]({link})" # use the value that was displayed to user
|
||||
+ self.curr_segment[end + length_to_add :]
|
||||
)
|
||||
length_to_add += len(self.curr_segment) - prev_length
|
||||
else:
|
||||
prev_length = len(self.curr_segment)
|
||||
self.curr_segment = (
|
||||
self.curr_segment[: start + length_to_add]
|
||||
+ f"[[{displayed_citation_num}]]()" # use the value that was displayed to user
|
||||
+ self.curr_segment[end + length_to_add :]
|
||||
)
|
||||
length_to_add += len(self.curr_segment) - prev_length
|
||||
real_start = length_to_add + start
|
||||
diff = end - start
|
||||
self.curr_segment = (
|
||||
self.curr_segment[: length_to_add + start]
|
||||
+ self.curr_segment[real_start + diff :]
|
||||
)
|
||||
length_to_add -= diff
|
||||
continue
|
||||
|
||||
last_citation_end = end + length_to_add
|
||||
# Handle edge case where LLM outputs citation itself
|
||||
if self.curr_segment.startswith("[["):
|
||||
match = re.match(r"\[\[(\d+)\]\]", self.curr_segment)
|
||||
if match:
|
||||
try:
|
||||
doc_id = int(match.group(1))
|
||||
context_llm_doc = self.context_docs[doc_id - 1]
|
||||
yield CitationInfo(
|
||||
# citation_num is now the number post initial ranking, i.e. as displayed to user
|
||||
citation_num=displayed_citation_num,
|
||||
document_id=context_llm_doc.document_id,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.warning(
|
||||
f"Manual LLM citation didn't properly cite documents {e}"
|
||||
)
|
||||
else:
|
||||
logger.warning(
|
||||
"Manual LLM citation wasn't able to close brackets"
|
||||
)
|
||||
continue
|
||||
|
||||
link = context_llm_doc.link
|
||||
|
||||
self.past_cite_count = len(self.llm_out)
|
||||
self.current_citations.append(final_citation_num)
|
||||
|
||||
if citation_order_idx not in self.cited_inds:
|
||||
self.cited_inds.add(citation_order_idx)
|
||||
yield CitationInfo(
|
||||
# citation number is now the one that was displayed to user
|
||||
citation_num=displayed_citation_num,
|
||||
document_id=context_llm_doc.document_id,
|
||||
)
|
||||
|
||||
start, end = citation.span()
|
||||
if link:
|
||||
prev_length = len(self.curr_segment)
|
||||
self.curr_segment = (
|
||||
self.curr_segment[: start + length_to_add]
|
||||
+ f"[[{displayed_citation_num}]]({link})" # use the value that was displayed to user
|
||||
+ self.curr_segment[end + length_to_add :]
|
||||
)
|
||||
length_to_add += len(self.curr_segment) - prev_length
|
||||
else:
|
||||
prev_length = len(self.curr_segment)
|
||||
self.curr_segment = (
|
||||
self.curr_segment[: start + length_to_add]
|
||||
+ f"[[{displayed_citation_num}]]()" # use the value that was displayed to user
|
||||
+ self.curr_segment[end + length_to_add :]
|
||||
)
|
||||
length_to_add += len(self.curr_segment) - prev_length
|
||||
|
||||
last_citation_end = end + length_to_add
|
||||
|
||||
if last_citation_end > 0:
|
||||
result += self.curr_segment[:last_citation_end]
|
||||
|
||||
Reference in New Issue
Block a user