Skip to content

Allow setting query transformers in BaseRAGQA (#67) #145

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Ch-Abhinav-Chowdary wants to merge 1 commit into
base: main
Choose a base branch
from
+23 −3
Open

Allow setting query transformers in BaseRAGQA (#67) #145

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 23 additions & 3 deletions python/pathway/xpacks/llm/question_answering.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -519,6 +519,7 @@ def __init__(
*,
default_llm_name: str | None = None,
prompt_template: str | Callable[[str, str], str] | pw.UDF = prompts.prompt_qa,
query_transformer_prompt: pw.UDF | None = None,
Copy link
Contributor

@szymondudycz szymondudycz Dec 17, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please update the docstring of this class with the description of the newly added parameter

Copy link
Author

@Ch-Abhinav-Chowdary Ch-Abhinav-Chowdary Dec 23, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Okay i will look upon it

context_processor: (
BaseContextProcessor | Callable[[list[dict] | list[Doc]], str] | pw.UDF
) = SimpleContextProcessor(),
Expand All @@ -538,6 +539,7 @@ def __init__(
self._init_schemas(default_llm_name)

self.prompt_udf = _get_RAG_prompt_udf(prompt_template)
self.query_transformer_prompt = query_transformer_prompt

if isinstance(context_processor, BaseContextProcessor):
self.docs_to_context_transformer = context_processor.as_udf()
Expand Down Expand Up @@ -641,11 +643,29 @@ def add_score_to_doc(doc: pw.Json, score: float) -> dict:
def answer_query(self, pw_ai_queries: pw.Table) -> pw.Table:
"""Answer a question based on the available information."""

pw_ai_results = pw_ai_queries + self.indexer.retrieve_query(
pw_ai_queries.select(
pw_ai_results = pw_ai_queries

if self.query_transformer_prompt is not None:
pw_ai_results += pw_ai_results.select(
_rewrite_prompt=self.query_transformer_prompt(pw.this.prompt)
)
pw_ai_results += pw_ai_results.select(
_transformed_query=self.llm(
llms.prompt_chat_single_qa(pw.this._rewrite_prompt),
model=pw.this.model,
)
)
pw_ai_results += pw_ai_results.select(
search_query=pw.this._transformed_query
)
else:
pw_ai_results += pw_ai_results.select(search_query=pw.this.prompt)

pw_ai_results += self.indexer.retrieve_query(
pw_ai_results.select(
metadata_filter=pw.this.filters,
filepath_globpattern=pw.cast(str | None, None),
query=pw.this.prompt,
query=pw.this.search_query,
k=self.search_topk,
)
).select(
Expand Down