flashrag-dev 0.1.3.dev20241110__tar.gz → 0.1.3.dev20241112__tar.gz

{flashrag-dev-0.1.3.dev20241110/flashrag_dev.egg-info → flashrag-dev-0.1.3.dev20241112}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flashrag-dev
-Version: 0.1.3.dev20241110
+Version: 0.1.3.dev20241112
 Summary: A library for efficient Retrieval-Augmented Generation research
 Home-page: https://github.com/RUC-NLPIR/FlashRAG
 Author: Jiajie Jin, Yutao Zhu, Chenghao Zhang, Xinyu Yang, Zhicheng Dou

{flashrag-dev-0.1.3.dev20241110 → flashrag-dev-0.1.3.dev20241112}/flashrag/config/basic_config.yaml

@@ -2,7 +2,7 @@
 # Paths to various models
 model2path:
   e5: "intfloat/e5-base-v2"
-  bge: "intfloat/e5-base-v2"
+  bge: "BAAI/bge-base-en-v1.5"
   contriever: "facebook/contriever"
   llama2-7B-chat: "meta-llama/Llama-2-7b-chat-hf"
   llama2-7B: "meta-llama/Llama-2-7b-hf"

{flashrag-dev-0.1.3.dev20241110 → flashrag-dev-0.1.3.dev20241112}/flashrag/config/config.py

@@ -131,7 +131,8 @@ class Config:
                 print("Index is empty!!")
                 assert False
 
-        self.final_config["retrieval_model_path"] = model2path.get(retrieval_method, retrieval_method)
+        if self.final_config.get("retrieval_model_path") is None:
+            self.final_config["retrieval_model_path"] = model2path.get(retrieval_method, retrieval_method)
         # TODO: not support when `retrieval_model` is path
 
         def set_pooling_method(method, model2pooling):

{flashrag-dev-0.1.3.dev20241110 → flashrag-dev-0.1.3.dev20241112}/flashrag/dataset/dataset.py

@@ -4,7 +4,6 @@ import random
 import warnings
 from typing import List, Dict, Any, Optional, Generator
 import numpy as np
-from flashrag.dataset.utils import convert_numpy
 
 
 class Item:
@@ -53,6 +52,7 @@ class Item:
         """Convert all information within the data sample into a dict. Information generated
         during the inference will be saved into output field.
         """
+        from flashrag.dataset.utils import convert_numpy
 
         output = {
             "id": self.id,
@@ -85,7 +85,7 @@ class Dataset:
     ) -> None:
         if config is not None:
             self.config = config
-            dataset_name = config.get("dataset_name", "default_dataset")
+            dataset_name = config['dataset_name'] if 'dataset_name' in config else 'defalut_dataset'
         else:
             self.config = None
             warnings.warn("dataset_name is not in config, set it as default.")
@@ -100,8 +100,11 @@ class Dataset:
             self.data = self._load_data(self.dataset_name, self.dataset_path)
         else:
             print("Load data from provided data")
-            assert isinstance(data[0], dict)
-            self.data = [Item(item_dict) for item_dict in data]
+            if isinstance(data[0], dict):
+                self.data = [Item(item_dict) for item_dict in data]
+            else:
+                assert isinstance(data[0], Item)
+                self.data = data
 
     def _load_data(self, dataset_name: str, dataset_path: str) -> List[Item]:
         """Load data from the provided dataset_path or directly download the file(TODO)."""

flashrag-dev-0.1.3.dev20241112/flashrag/version.py

@@ -0,0 +1 @@
+__version__ = "0.1.3dev20241112"

{flashrag-dev-0.1.3.dev20241110 → flashrag-dev-0.1.3.dev20241112/flashrag_dev.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flashrag-dev
-Version: 0.1.3.dev20241110
+Version: 0.1.3.dev20241112
 Summary: A library for efficient Retrieval-Augmented Generation research
 Home-page: https://github.com/RUC-NLPIR/FlashRAG
 Author: Jiajie Jin, Yutao Zhu, Chenghao Zhang, Xinyu Yang, Zhicheng Dou

flashrag-dev-0.1.3.dev20241110/flashrag/version.py

@@ -1 +0,0 @@
-__version__ = "0.1.3dev20241110"