chore: merge main

pilot/configs/__init__.py

@@ -0,0 +1,14 @@
+import os
+import random
+import sys
+
+from dotenv import load_dotenv
+
+if "pytest" in sys.argv or "pytest" in sys.modules or os.getenv("CI"):
+    print("Setting random seed to 42")
+    random.seed(42)
+
+# Load the users .env file into environment variables
+load_dotenv(verbose=True, override=True)
+
+del load_dotenv

pilot/configs/config.py

@@ -39,13 +39,6 @@ class Config(metaclass=Singleton):
         self.use_mac_os_tts = False
         self.use_mac_os_tts = os.getenv("USE_MAC_OS_TTS")
 
-        # milvus or zilliz cloud configuration
-        self.milvus_addr = os.getenv("MILVUS_ADDR", "localhost:19530")
-        self.milvus_username = os.getenv("MILVUS_USERNAME")
-        self.milvus_password = os.getenv("MILVUS_PASSWORD")
-        self.milvus_collection = os.getenv("MILVUS_COLLECTION", "dbgpt")
-        self.milvus_secure = os.getenv("MILVUS_SECURE") == "True"
-
         self.authorise_key = os.getenv("AUTHORISE_COMMAND_KEY", "y")
         self.exit_key = os.getenv("EXIT_KEY", "n")
         self.image_provider = os.getenv("IMAGE_PROVIDER", True)

pilot/vector_store/milvus_store.py

@@ -141,29 +141,21 @@ class MilvusStore(VectorStoreBase):
         fields.append(
             FieldSchema(text_field, DataType.VARCHAR, max_length=max_length + 1)
         )
-        # create the primary key field
+        # primary key field
         fields.append(
             FieldSchema(primary_field, DataType.INT64, is_primary=True, auto_id=True)
         )
-        # create the vector field
+        # vector field
         fields.append(FieldSchema(vector_field, DataType.FLOAT_VECTOR, dim=dim))
-        # Create the schema for the collection
+        # milvus the schema for the collection
         schema = CollectionSchema(fields)
         # Create the collection
         collection = Collection(collection_name, schema)
         self.col = collection
-        # Index parameters for the collection
+        # index parameters for the collection
         index = self.index_params
-        # Create the index
+        # milvus index
         collection.create_index(vector_field, index)
-        # Create the VectorStore
-        # milvus = cls(
-        #     embedding,
-        #     kwargs.get("connection_args", {"port": 19530}),
-        #     collection_name,
-        #     text_field,
-        # )
-        # Add the texts.
         schema = collection.schema
         for x in schema.fields:
             self.fields.append(x.name)

requirements.txt

@@ -69,6 +69,7 @@ colorama
 playsound
 distro
 pypdf
+milvus-cli==0.3.2
 
 # Testing dependencies
 pytest

tools/knowlege_init.py

@@ -1,16 +1,21 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8 -*-
 import argparse
+import os
+import sys
 
+sys.path.append(os.path.dirname(os.path.dirname(os.path.realpath(__file__))))
+
+from pilot.configs.config import Config
 from pilot.configs.model_config import (
     DATASETS_DIR,
     LLM_MODEL_CONFIG,
     VECTOR_SEARCH_TOP_K,
-    VECTOR_STORE_CONFIG,
-    VECTOR_STORE_TYPE,
 )
 from pilot.source_embedding.knowledge_embedding import KnowledgeEmbedding
 
+CFG = Config()
+
 
 class LocalKnowledgeInit:
     embeddings: object = None
@@ -47,12 +52,8 @@ if __name__ == "__main__":
     args = parser.parse_args()
     vector_name = args.vector_name
     append_mode = args.append
-    store_type = VECTOR_STORE_TYPE
-    vector_store_config = {
-        "url": VECTOR_STORE_CONFIG["url"],
-        "port": VECTOR_STORE_CONFIG["port"],
-        "vector_store_name": vector_name,
-    }
+    store_type = CFG.VECTOR_STORE_TYPE
+    vector_store_config = {"vector_store_name": vector_name}
     print(vector_store_config)
     kv = LocalKnowledgeInit(vector_store_config=vector_store_config)
     vector_store = kv.knowledge_persist(file_path=DATASETS_DIR, append_mode=append_mode)