feat: rag

2026-05-06 11:35:10 +08:00
commit a17c65c4bc
75 changed files with 5196 additions and 0 deletions
@@ -0,0 +1,64 @@
+# 完整流程
+
+from chromadb import PersistentClient
+
+# 创建持久化客户端
+client = PersistentClient(path="./chromadb_store")
+
+# 获取或者创建集合
+collection = client.get_or_create_collection(name="example")
+
+# 准备说明文档
+documents = [
+    "机器学习包含监督学习和无监督学习",
+    "Python 拥有丰富的数据科学生态",
+    "数据库可以持久化结构化或非结构化数据",
+]
+# 创建元数据
+metadatas = [
+    {"topic": "ml", "level": "intro"},
+    {"topic": "python", "level": "beginner"},
+    {"topic": "database", "level": "intro"},
+]
+
+# ids
+ids = ["doc1", "doc2", "dic3"]
+
+# 写入数据
+collection.add(documents=documents, metadatas=metadatas, ids=ids)
+
+abc = collection.get(ids=["doc2"])
+print(abc)
+
+# 查询
+result = collection.query(query_texts=["如何入门机器学习"], n_results=2)
+
+# print(result)
+# {
+#     "ids": [["doc1", "doc2"]],
+#     "embeddings": None,
+#     "documents": [
+#         ["机器学习包含监督学习和无监督学习", "Python 拥有丰富的数据科学生态"]
+#     ],
+#     "uris": None,
+#     "included": ["metadatas", "documents", "distances"],
+#     "data": None,
+#     "metadatas": [
+#         [{"topic": "ml", "level": "intro"}, {"topic": "python", "level": "beginner"}]
+#     ],
+#     "distances": [[0.24633410573005676, 0.8512163758277893]],
+# }
+# for index, (id, doc, metadata, distance) in enumerate(
+#     zip(
+#         result["ids"][0],
+#         result["documents"][0],
+#         result["metadatas"][0],
+#         result["distances"][0],
+#     ),
+#     1,
+# ):
+#     print(f"匹配结果 {index}:")
+#     print(f"  文档：{doc}")
+#     print(f"  元数据：{metadata}")
+#     print(f"  距离：{distance:.4f}")
+#     print()