airbytehq · flash1293 · Nov 14, 2023 · Nov 9, 2023 · Nov 9, 2023 · Nov 9, 2023
@@ -41,5 +41,5 @@ COPY destination_chroma ./destination_chroma
 ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
 ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
 
-LABEL io.airbyte.version=0.0.5
+LABEL io.airbyte.version=0.0.6
 LABEL io.airbyte.name=airbyte/destination-chroma
@@ -7,7 +7,7 @@ data:
   connectorSubtype: vectorstore
   connectorType: destination
   definitionId: 0b75218b-f702-4a28-85ac-34d3d84c0fc2
-  dockerImageTag: 0.0.5
+  dockerImageTag: 0.0.6
   dockerRepository: airbyte/destination-chroma
   githubIssueLabel: destination-chroma
   icon: chroma.svg

@@ -6,7 +6,7 @@
 from setuptools import find_packages, setup
 
 MAIN_REQUIREMENTS = [
-    "airbyte-cdk[vector-db-based]==0.51.41",
+    "airbyte-cdk[vector-db-based]==0.53.3",
     "chromadb",
 ]
 

@@ -14,6 +14,7 @@
     OpenAIEmbeddingConfigModel,
     ProcessingConfigModel,
 )
+from airbyte_cdk.utils.oneof_option_config import OneOfOptionConfig
 from airbyte_cdk.utils.spec_schema_transformations import resolve_refs
 from pydantic import BaseModel, Field
 
@@ -23,28 +24,29 @@ class UsernamePasswordAuth(BaseModel):
     username: str = Field(..., title="Username", description="Username for the Milvus instance", order=1)
     password: str = Field(..., title="Password", description="Password for the Milvus instance", airbyte_secret=True, order=2)
 
-    class Config:
+    class Config(OneOfOptionConfig):
         title = "Username/Password"
-        schema_extra = {"description": "Authenticate using username and password (suitable for self-managed Milvus clusters)"}
+        description = "Authenticate using username and password (suitable for self-managed Milvus clusters)"
+        discriminator = "mode"
 
 
 class NoAuth(BaseModel):
     mode: Literal["no_auth"] = Field("no_auth", const=True)
 
-    class Config:
+    class Config(OneOfOptionConfig):
         title = "No auth"
-        schema_extra = {
-            "description": "Do not authenticate (suitable for locally running test clusters, do not use for clusters with public IP addresses)"
-        }
+        description = "Do not authenticate (suitable for locally running test clusters, do not use for clusters with public IP addresses)"
+        discriminator = "mode"
 
 
 class TokenAuth(BaseModel):
     mode: Literal["token"] = Field("token", const=True)
     token: str = Field(..., title="API Token", description="API Token for the Milvus instance", airbyte_secret=True)
 
-    class Config:
+    class Config(OneOfOptionConfig):
         title = "API Token"
-        schema_extra = {"description": "Authenticate using an API token (suitable for Zilliz Cloud)"}
+        description = "Authenticate using an API token (suitable for Zilliz Cloud)"
+        discriminator = "mode"
 
 
 class MilvusIndexingConfigModel(BaseModel):

@@ -11,6 +11,7 @@
           "chunk_size": {
             "title": "Chunk size",
             "description": "Size of chunks in tokens to store in vector store (make sure it is not too big for the context if your LLM)",
+            "minimum": 1,
             "maximum": 8191,
             "type": "integer"
           },
@@ -91,6 +92,7 @@
                     "type": "boolean"
                   }
                 },
+                "required": ["mode"],
                 "description": "Split the text by the list of separators until the chunk size is reached, using the earlier mentioned separators where possible. This is useful for splitting text fields by paragraphs, sentences, words, etc."
               },
               {
@@ -113,6 +115,7 @@
                     "type": "integer"
                   }
                 },
+                "required": ["mode"],
                 "description": "Split the text by Markdown headers down to the specified header level. If the chunk size fits multiple sections, they will be combined into a single chunk."
               },
               {
@@ -150,7 +153,7 @@
                     "type": "string"
                   }
                 },
-                "required": ["language"],
+                "required": ["language", "mode"],
                 "description": "Split the text by suitable delimiters based on the programming language. This is useful for splitting code into chunks."
               }
             ]
@@ -182,7 +185,7 @@
                 "type": "string"
               }
             },
-            "required": ["openai_key"],
+            "required": ["openai_key", "mode"],
             "description": "Use the OpenAI API to embed text. This option is using the text-embedding-ada-002 model with 1536 embedding dimensions."
           },
           {
@@ -202,7 +205,7 @@
                 "type": "string"
               }
             },
-            "required": ["cohere_key"],
+            "required": ["cohere_key", "mode"],
             "description": "Use the Cohere API to embed text."
           },
           {
@@ -217,6 +220,7 @@
                 "type": "string"
               }
             },
+            "required": ["mode"],
             "description": "Use a fake embedding made out of random vectors with 1536 embedding dimensions. This is useful for testing the data pipeline without incurring any costs."
           },
           {
@@ -243,7 +247,7 @@
                 "type": "integer"
               }
             },
-            "required": ["field_name", "dimensions"],
+            "required": ["field_name", "dimensions", "mode"],
             "description": "Use a field in the record as the embedding. This is useful if you already have an embedding for your data and want to store it in the vector store."
           },
           {
@@ -276,7 +280,7 @@
                 "type": "string"
               }
             },
-            "required": ["openai_key", "api_base", "deployment"],
+            "required": ["openai_key", "api_base", "deployment", "mode"],
             "description": "Use the Azure-hosted OpenAI API to embed text. This option is using the text-embedding-ada-002 model with 1536 embedding dimensions."
           },
           {
@@ -316,7 +320,7 @@
                 "type": "integer"
               }
             },
-            "required": ["base_url", "dimensions"],
+            "required": ["base_url", "dimensions", "mode"],
             "description": "Use a service that's compatible with the OpenAI API to embed text."
           }
         ]
@@ -372,7 +376,7 @@
                     "type": "string"
                   }
                 },
-                "required": ["token"],
+                "required": ["token", "mode"],
                 "description": "Authenticate using an API token (suitable for Zilliz Cloud)"
               },
               {
@@ -400,7 +404,7 @@
                     "type": "string"
                   }
                 },
-                "required": ["username", "password"],
+                "required": ["username", "password", "mode"],
                 "description": "Authenticate using username and password (suitable for self-managed Milvus clusters)"
               },
               {
@@ -415,7 +419,8 @@
                     "type": "string"
                   }
                 },
-                "description": "Do not authenticate (suitable for locally running test clusters, do not use for clusters with public IP addresses)"
+                "description": "Do not authenticate (suitable for locally running test clusters, do not use for clusters with public IP addresses)",
+                "required": ["mode"]
               }
             ]
           },

@@ -22,7 +22,7 @@ data:
   connectorSubtype: vectorstore
   connectorType: destination
   definitionId: 65de8962-48c9-11ee-be56-0242ac120002
-  dockerImageTag: 0.0.8
+  dockerImageTag: 0.0.9
   dockerRepository: airbyte/destination-milvus
   githubIssueLabel: destination-milvus
   icon: milvus.svg

@@ -5,7 +5,7 @@
 
 from setuptools import find_packages, setup
 
-MAIN_REQUIREMENTS = ["airbyte-cdk[vector-db-based]==0.51.41", "pymilvus==2.3.0"]
+MAIN_REQUIREMENTS = ["airbyte-cdk[vector-db-based]==0.53.3", "pymilvus==2.3.0"]
 
 TEST_REQUIREMENTS = ["pytest~=6.2"]
 

@@ -62,7 +62,7 @@ class Config:
     @staticmethod
     def remove_discriminator(schema: dict) -> None:
         """pydantic adds "discriminator" to the schema for oneOfs, which is not treated right by the platform as we inline all references"""
-        dpath.util.delete(schema, "properties/*/discriminator")
+        dpath.util.delete(schema, "properties/**/discriminator")
 
     @classmethod
     def schema(cls):

@@ -53,7 +53,7 @@
                 "type": "string"
               }
             },
-            "required": ["openai_key"],
+            "required": ["openai_key", "mode"],
             "description": "Use the OpenAI API to embed text. This option is using the text-embedding-ada-002 model with 1536 embedding dimensions."
           },
           {
@@ -73,7 +73,7 @@
                 "type": "string"
               }
             },
-            "required": ["cohere_key"],
+            "required": ["cohere_key", "mode"],
             "description": "Use the Cohere API to embed text."
           },
           {
@@ -88,6 +88,7 @@
                 "type": "string"
               }
             },
+            "required": ["mode"],
             "description": "Use a fake embedding made out of random vectors with 1536 embedding dimensions. This is useful for testing the data pipeline without incurring any costs."
           },
           {
@@ -120,7 +121,7 @@
                 "type": "string"
               }
             },
-            "required": ["openai_key", "api_base", "deployment"],
+            "required": ["openai_key", "api_base", "deployment", "mode"],
             "description": "Use the Azure-hosted OpenAI API to embed text. This option is using the text-embedding-ada-002 model with 1536 embedding dimensions."
           },
           {
@@ -160,7 +161,7 @@
                 "type": "integer"
               }
             },
-            "required": ["base_url", "dimensions"],
+            "required": ["base_url", "dimensions", "mode"],
             "description": "Use a service that's compatible with the OpenAI API to embed text."
           }
         ]
@@ -172,6 +173,7 @@
           "chunk_size": {
             "title": "Chunk size",
             "description": "Size of chunks in tokens to store in vector store (make sure it is not too big for the context if your LLM)",
+            "minimum": 1,
             "maximum": 8191,
             "type": "integer"
           },
@@ -226,14 +228,6 @@
             "title": "Text splitter",
             "description": "Split text fields into chunks based on the specified method.",
             "type": "object",
-            "discriminator": {
-              "propertyName": "mode",
-              "mapping": {
-                "separator": "#/definitions/SeparatorSplitterConfigModel",
-                "markdown": "#/definitions/MarkdownHeaderSplitterConfigModel",
-                "code": "#/definitions/CodeSplitterConfigModel"
-              }
-            },
             "oneOf": [
               {
                 "title": "By Separator",
@@ -260,6 +254,7 @@
                     "type": "boolean"
                   }
                 },
+                "required": ["mode"],
                 "description": "Split the text by the list of separators until the chunk size is reached, using the earlier mentioned separators where possible. This is useful for splitting text fields by paragraphs, sentences, words, etc."
               },
               {
@@ -282,6 +277,7 @@
                     "type": "integer"
                   }
                 },
+                "required": ["mode"],
                 "description": "Split the text by Markdown headers down to the specified header level. If the chunk size fits multiple sections, they will be combined into a single chunk."
               },
               {
@@ -319,7 +315,7 @@
                     "type": "string"
                   }
                 },
-                "required": ["language"],
+                "required": ["language", "mode"],
                 "description": "Split the text by suitable delimiters based on the programming language. This is useful for splitting code into chunks."
               }
             ]

@@ -13,7 +13,7 @@ data:
   connectorSubtype: vectorstore
   connectorType: destination
   definitionId: 3d2b6f84-7f0d-4e3f-a5e5-7c7d4b50eabd
-  dockerImageTag: 0.0.19
+  dockerImageTag: 0.0.20
   dockerRepository: airbyte/destination-pinecone
   documentationUrl: https://docs.airbyte.com/integrations/destinations/pinecone
   githubIssueLabel: destination-pinecone

@@ -6,7 +6,7 @@
 from setuptools import find_packages, setup
 
 MAIN_REQUIREMENTS = [
-    "airbyte-cdk[vector-db-based]==0.51.41",
+    "airbyte-cdk[vector-db-based]==0.53.3",
     "pinecone-client[grpc]",
 ]
 

@@ -41,5 +41,5 @@ COPY destination_qdrant ./destination_qdrant
 ENV AIRBYTE_ENTRYPOINT "python /airbyte/integration_code/main.py"
 ENTRYPOINT ["python", "/airbyte/integration_code/main.py"]
 
-LABEL io.airbyte.version=0.0.6
+LABEL io.airbyte.version=0.0.7
 LABEL io.airbyte.name=airbyte/destination-qdrant
@@ -20,7 +20,7 @@ data:
   connectorSubtype: vectorstore
   connectorType: destination
   definitionId: 6eb1198a-6d38-43e5-aaaa-dccd8f71db2b
-  dockerImageTag: 0.0.6
+  dockerImageTag: 0.0.7
   dockerRepository: airbyte/destination-qdrant
   githubIssueLabel: destination-qdrant
   icon: qdrant.svg

@@ -5,7 +5,7 @@
 
 from setuptools import find_packages, setup
 
-MAIN_REQUIREMENTS = ["airbyte-cdk[vector-db-based]==0.51.41", "qdrant-client", "fastembed"]
+MAIN_REQUIREMENTS = ["airbyte-cdk[vector-db-based]==0.53.3", "qdrant-client", "fastembed"]
 
 TEST_REQUIREMENTS = ["pytest~=6.2"]