test

.gitattributes

@@ -32,4 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

app.py

@@ -21,8 +21,8 @@ def decrypt_file(input_path, key):
 
 llm = llama_cpp.Llama.from_pretrained(repo_id="mradermacher/bge-large-zh-v1.5-GGUF", filename="bge-large-zh-v1.5.Q4_K_M.gguf", embedding=True)
 
-embedding_1 = llm.create_embedding("Hello, world!")
-embedding_2 = llm.create_embedding("你好, 世界!") # type(embedding_1['data'][0]['embedding']) list
+# embedding_1 = llm.create_embedding("Hello, world!")
+# embedding_2 = llm.create_embedding("你好, 世界!") # type(embedding_1['data'][0]['embedding']) list
 
 from pymilvus import MilvusClient
 client = MilvusClient("./books.db")
@@ -40,6 +40,10 @@ raw_jsons = json.loads(decrypted_content)
 docs = []
 metas = []
 
+with open('embeddings.json', mode='w+') as embedding_file:
+    all_embs = json.load(embedding_file)
+
+
 for vhjx_index, vhjx_item in enumerate(raw_jsons):
     chapter = vhjx_item[0]
     for jvvi_item in vhjx_item[1:]:
@@ -56,7 +60,7 @@ for vhjx_index, vhjx_item in enumerate(raw_jsons):
     # 一个章节一次
     # 批量生成 embeddings（每个为 list[float]）
     emb_result = llm.create_embedding(docs)
-    embeddings = [item["embedding"] for item in emb_result["data"]]  # List[List[float]]
+    embeddings = all_embs[vhjx_index]  # List[List[float]]
 
     # 准备数据
     milvus_data = []

embeddings.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfd6c4db5126d998144279518e6f0d134c7c84cbe07d5a8531711a1ec949602
+size 119355981