highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-06-14 18:10:58 +02:00
Code Issues Packages Projects Releases Wiki Activity

Minor Tuning for Filters (#753)

Browse Source
This commit is contained in:
Yuhong Sun 2023-11-21 15:47:58 -08:00 committed by GitHub
parent 1225c663eb
commit c0c8ae6c08
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
backend/danswer/secondary_llm_flows/source_filter.py
View File

@ -155,7 +155,7 @@ def extract_source_filter(
messages = _get_source_filter_messages(query=query, valid_sources=valid_sources) messages = _get_source_filter_messages(query=query, valid_sources=valid_sources)
filled_llm_prompt = dict_based_prompt_to_langchain_prompt(messages) filled_llm_prompt = dict_based_prompt_to_langchain_prompt(messages)
model_output = get_default_llm(use_fast_llm=True).invoke(filled_llm_prompt) model_output = get_default_llm().invoke(filled_llm_prompt)
logger.debug(model_output) logger.debug(model_output)
return _extract_source_filters_from_llm_out(model_output) return _extract_source_filters_from_llm_out(model_output)

10
backend/danswer/secondary_llm_flows/time_filter.py
View File

@ -110,7 +110,9 @@ def extract_time_filter(query: str) -> tuple[datetime | None, bool]:
if "date" in model_json: if "date" in model_json:
extracted_time = best_match_time(model_json["date"]) extracted_time = best_match_time(model_json["date"])
if extracted_time is not None: if extracted_time is not None:
return extracted_time, favor_recent # LLM struggles to understand the concept of not sensitive within a time range
# So if a time is extracted, just go with that alone
return extracted_time, False
time_diff = None time_diff = None
multiplier = 1.0 multiplier = 1.0
@ -138,7 +140,9 @@ def extract_time_filter(query: str) -> tuple[datetime | None, bool]:
if time_diff is not None: if time_diff is not None:
current = datetime.now(timezone.utc) current = datetime.now(timezone.utc)
return current - time_diff, favor_recent # LLM struggles to understand the concept of not sensitive within a time range
# So if a time is extracted, just go with that alone
return current - time_diff, False
# If we failed to extract a hard filter, just pass back the value of favor recent # If we failed to extract a hard filter, just pass back the value of favor recent
return None, favor_recent return None, favor_recent
@ -147,7 +151,7 @@ def extract_time_filter(query: str) -> tuple[datetime | None, bool]:
messages = _get_time_filter_messages(query) messages = _get_time_filter_messages(query)
filled_llm_prompt = dict_based_prompt_to_langchain_prompt(messages) filled_llm_prompt = dict_based_prompt_to_langchain_prompt(messages)
model_output = get_default_llm(use_fast_llm=True).invoke(filled_llm_prompt) model_output = get_default_llm().invoke(filled_llm_prompt)
logger.debug(model_output) logger.debug(model_output)
return _extract_time_filter_from_llm_out(model_output) return _extract_time_filter_from_llm_out(model_output)