Skip to content

armgit / dspy

Public Imported from GitHub
0

DSPy: The framework for programming—not prompting—language models

Python

fix: moved faiss_rm to dspy.logger

KCaverly1181d803d27e
diff --git a/dspy/retrieve/faiss_rm.py b/dspy/retrieve/faiss_rm.py
index 8cd98466f..c551eacde 100755
--- a/dspy/retrieve/faiss_rm.py
+++ b/dspy/retrieve/faiss_rm.py
@@ -2,7 +2,6 @@
Author: Jagane Sundar: https://github.com/jagane.
"""
-import logging
from typing import Optional, Union
import numpy as np
@@ -81,7 +80,7 @@ class FaissRM(dspy.Retrieve):
embeddings = self._vectorizer(document_chunks)
xb = np.array(embeddings)
d = len(xb[0])
- logging.info(f"FaissRM: embedding size={d}")
+ dspy.logger.info(f"FaissRM: embedding size={d}")
if len(xb) < 100:
self._faiss_index = faiss.IndexFlatL2(d)
self._faiss_index.add(xb)
@@ -93,7 +92,7 @@ class FaissRM(dspy.Retrieve):
self._faiss_index.train(xb)
self._faiss_index.add(xb)
- logging.info(f"{self._faiss_index.ntotal} vectors in faiss index")
+ dspy.logger.info(f"{self._faiss_index.ntotal} vectors in faiss index")
self._document_chunks = document_chunks # save the input document chunks
super().__init__(k=k)
@@ -102,12 +101,12 @@ class FaissRM(dspy.Retrieve):
for i in range(len(queries)):
indices = index_list[i]
distances = distance_list[i]
- logging.debug(f"Query: {queries[i]}")
+ dspy.logger.debug(f"Query: {queries[i]}")
for j in range(len(indices)):
- logging.debug(f" Hit {j} = {indices[j]}/{distances[j]}: {self._document_chunks[indices[j]]}")
+ dspy.logger.debug(f" Hit {j} = {indices[j]}/{distances[j]}: {self._document_chunks[indices[j]]}")
return
- def forward(self, query_or_queries: Union[str, list[str]], k: Optional[int] = None,**kwargs) -> dspy.Prediction:
+ def forward(self, query_or_queries: Union[str, list[str]], k: Optional[int] = None, **kwargs) -> dspy.Prediction:
"""Search the faiss index for k or self.k top passages for query.
Args:
@@ -127,7 +126,7 @@ class FaissRM(dspy.Retrieve):
passages = [(self._document_chunks[ind], ind) for ind in index_list[0]]
return [dotdict({"long_text": passage[0], "index": passage[1]}) for passage in passages]
- distance_list, index_list = self._faiss_index.search(emb_npa, (k or self.k) * 3,**kwargs)
+ distance_list, index_list = self._faiss_index.search(emb_npa, (k or self.k) * 3, **kwargs)
# self._dump_raw_results(queries, index_list, distance_list)
passage_scores = {}
for emb in range(len(embeddings)):
@@ -146,5 +145,10 @@ class FaissRM(dspy.Retrieve):
# first degree sort: number of queries that got a hit with any particular document chunk. More
# is a better match. This is len(queries)-len(x[1])
# second degree sort: sum of the distances of each hit returned by faiss. Smaller distance is a better match
- sorted_passages = sorted(passage_scores.items(), key=lambda x: (len(queries) - len(x[1]), sum(x[1])))[: k or self.k]
- return [ dotdict({"long_text": self._document_chunks[passage_index], "index": passage_index}) for passage_index, _ in sorted_passages ]
+ sorted_passages = sorted(passage_scores.items(), key=lambda x: (len(queries) - len(x[1]), sum(x[1])))[
+ : k or self.k
+ ]
+ return [
+ dotdict({"long_text": self._document_chunks[passage_index], "index": passage_index})
+ for passage_index, _ in sorted_passages
+ ]