klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-06 05:39:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Upgrade default cross-encoder to mixedbread ai's mxbai-rerank-xsmall

Browse Source 
Previous cross-encoder model was a few years old, newer models should
have improved in quality. Model size increases by 50% compared to
previous for better performance, at least on benchmarks
This commit is contained in:
Debanjum Singh Solanky
2024-04-24 09:13:14 +05:30
parent 7eaf9367fe
commit ec41482324
4 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/khoj/database/models/__init__.py
View File

@@ -185,7 +185,7 @@ class SearchModelConfig(BaseModel):
bi_encoder_model_config = models.JSONField(default=dict)
bi_encoder_query_encode_config = models.JSONField(default=dict)
bi_encoder_docs_encode_config = models.JSONField(default=dict)
cross_encoder = models.CharField(max_length=200, default="cross-encoder/ms-marco-MiniLM-L-6-v2")
cross_encoder = models.CharField(max_length=200, default="mixedbread-ai/mxbai-rerank-xsmall-v1")
embeddings_inference_endpoint = models.CharField(max_length=200, default=None, null=True, blank=True)
embeddings_inference_endpoint_api_key = models.CharField(max_length=200, default=None, null=True, blank=True)
cross_encoder_inference_endpoint = models.CharField(max_length=200, default=None, null=True, blank=True)

2
src/khoj/processor/embeddings.py
View File

@@ -92,7 +92,7 @@ class EmbeddingsModel:
class CrossEncoderModel:
def __init__(
self,
model_name: str = "cross-encoder/ms-marco-MiniLM-L-6-v2",
model_name: str = "mixedbread-ai/mxbai-rerank-xsmall-v1",
cross_encoder_inference_endpoint: str = None,
cross_encoder_inference_endpoint_api_key: str = None,
):