hjxdl 0.1.67__py3-none-any.whl → 0.1.69__py3-none-any.whl

hdl/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.67'
-__version_tuple__ = version_tuple = (0, 1, 67)
+__version__ = version = '0.1.69'
+__version_tuple__ = version_tuple = (0, 1, 69)

hdl/utils/llm/vis.py

@@ -9,6 +9,8 @@ from PIL import Image
 # from transformers import ChineseCLIPProcessor, ChineseCLIPModel
 import open_clip
 import natsort
+from redis.commands.search.field import VectorField
+from redis.commands.search.indexDefinition import IndexDefinition, IndexType
 
 from ..database_tools.connect import conn_redis
 
@@ -254,7 +256,7 @@ class ImgHandler:
         """
         sorted_imgs = natsort.natsorted(images)
         img_feats = self.get_img_features(sorted_imgs, to_numpy=True)
-        pipeline = self.ih.db_conn.pipeline()
+        pipeline = self.db_conn.pipeline()
         for img_file, emb in zip(sorted_imgs, img_feats):
             # 初始化 Redis，先使用 img 文件名作为 Key 和 Value，后续再更新为图片特征向量
             # pipeline.json().set(img_file, "$", img_file)
@@ -263,8 +265,47 @@ class ImgHandler:
                 "emb": emb,
                 "data": imgfile_to_base64(img_file)
             }
-            pipeline.json().set(img_file, "$", emb_json)
+            pipeline.json().set(f"pic-{img_file}", "$", emb_json)
             res = pipeline.execute()
-            print('redis set:', res)
+            # print('redis set:', res)
+
+        schema = (
+            VectorField(
+                "$.emb",  # 这是 JSON 中存储向量的路径
+                "FLAT",  # 使用 FLAT 索引类型
+                {
+                    "TYPE": "FLOAT32",  # 向量类型
+                    "DIM": self.num_vec_dim,  # 向量维度，必须与实际数据的维度一致
+                    "DISTANCE_METRIC": "COSINE",  # 余弦相似度作为距离度量
+                },
+                as_name="vector",  # 给这个字段定义一个别名，后续可以使用
+            ),
+        )
+        vector_idx_name = "idx:pic_idx"
+        definition = IndexDefinition(
+            prefix=["pic-"],
+            index_type=IndexType.JSON
+        )
+        res = self.db_conn.ft(
+            vector_idx_name
+        ).create_index(
+            fields=schema,
+            definition=definition
+        )
+        print("create_index:", res)
+
+    @property
+    def pic_idx_info(self):
+        res = self.db_conn.ping()
+        print("redis connected:", res)
+
+        vector_idx_name = "idx:pic_idx"
+
+        # 从 Redis 数据库中读取索引状态
+        info = self.db_conn.ft(vector_idx_name).info()
+        # 获取索引状态中的 num_docs 和 hash_indexing_failures
+        num_docs = info["num_docs"]
+        indexing_failures = info["hash_indexing_failures"]
+        print(f"{num_docs} documents indexed with {indexing_failures} failures")
 
 

{hjxdl-0.1.67.dist-info → hjxdl-0.1.69.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hjxdl
-Version: 0.1.67
+Version: 0.1.69
 Summary: A collection of functions for Jupyter notebooks
 Home-page: https://github.com/huluxiaohuowa/hdl
 Author: Jianxing Hu

{hjxdl-0.1.67.dist-info → hjxdl-0.1.69.dist-info}/RECORD

@@ -1,5 +1,5 @@
 hdl/__init__.py,sha256=GffnD0jLJdhkd-vo989v40N90sQbofkayRBwxc6TVhQ,72
-hdl/_version.py,sha256=FcaV_ACOb2e682h3wmnM4BoU2t4Y9YegpmtQ5bKxxNg,413
+hdl/_version.py,sha256=lVXaDORAcShTMS0Ix_T7zlcXAGst1lAMus_P8nq4GD4,413
 hdl/args/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/args/loss_args.py,sha256=s7YzSdd7IjD24rZvvOrxLLFqMZQb9YylxKeyelSdrTk,70
 hdl/controllers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -131,12 +131,12 @@ hdl/utils/llm/chat.py,sha256=sk7Lw5Oa30k-l2fnJknkMmTc5zkBeEKsR981aeFhH5s,11907
 hdl/utils/llm/embs.py,sha256=Tf0FOYrOFZp7qQpEPiSCXzlgyHH0X9HVTUtsup74a9E,7174
 hdl/utils/llm/extract.py,sha256=2sK_WJzmYIc8iuWaM9DA6Nw3_6q1O4lJ5pKpcZo-bBA,6512
 hdl/utils/llm/llama_chat.py,sha256=watcHGOaz-bv3x-yDucYlGk5f8FiqfFhwWogrl334fk,4387
-hdl/utils/llm/vis.py,sha256=dkrSWZJcnLFy5ZmT8aDTy2EdvfzWbYOwDjUL47BbmxI,8547
+hdl/utils/llm/vis.py,sha256=BygpjORSwbe_7SmThzt_OvzsrEym7FwCk6fubGyiDDc,10097
 hdl/utils/schedulers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/utils/schedulers/norm_lr.py,sha256=bDwCmdEK-WkgxQMFBiMuchv8Mm7C0-GZJ6usm-PQk14,4461
 hdl/utils/weather/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/utils/weather/weather.py,sha256=k11o6wM15kF8b9NMlEfrg68ak-SfSYLN3nOOflFUv-I,4381
-hjxdl-0.1.67.dist-info/METADATA,sha256=dxyZsd_-4xjvQ6k6WZcaxsxYI6gJzQ38iO2CAFZf2OY,903
-hjxdl-0.1.67.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
-hjxdl-0.1.67.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
-hjxdl-0.1.67.dist-info/RECORD,,
+hjxdl-0.1.69.dist-info/METADATA,sha256=LZ8Y6-VsUCMYG1AQ5n-GBzff1lwfa-hOev1wT79OULc,903
+hjxdl-0.1.69.dist-info/WHEEL,sha256=cVxcB9AmuTcXqmwrtPhNK88dr7IR_b6qagTj0UvIEbY,91
+hjxdl-0.1.69.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
+hjxdl-0.1.69.dist-info/RECORD,,