chore: commit a fully generated provider for testing

.goreleaser.yml

@@ -1,4 +1,3 @@
-version: 2
 # Visit https://goreleaser.com for documentation on how to customize this
 # behavior.
 before:
@@ -58,4 +57,4 @@ release:
   # If you want to manually examine the release before its live, uncomment this line:
   # draft: true
 changelog:
-  disable: true
+  skip: true

.speakeasy/workflow.lock

@@ -1,18 +1,18 @@
-speakeasyVersion: 1.335.2
+speakeasyVersion: 1.321.0
 sources:
     my-source:
         sourceNamespace: my-source
-        sourceRevisionDigest: sha256:11bc6c5cce07b8124f88147cb7e73b56ed406eefd4374dce9f478c06a1fd3d7d
-        sourceBlobDigest: sha256:20143bd569af5fe53d9cc6d46c85db6b8bdfa07d2f1adfd286931ba24c8cb1a6
+        sourceRevisionDigest: sha256:3033fa2ed31f47a1508ad2e10594f824a2c68caa25670224e7d576f93c63b269
+        sourceBlobDigest: sha256:bb31cea6549192e0e90dda8d97fa05daa2cf2debac4223ee19e46b59b1c18ce3
         tags:
             - latest
             - main
 targets:
     terraform-provider-airbyte:
         source: my-source
         sourceNamespace: my-source
-        sourceRevisionDigest: sha256:11bc6c5cce07b8124f88147cb7e73b56ed406eefd4374dce9f478c06a1fd3d7d
-        sourceBlobDigest: sha256:20143bd569af5fe53d9cc6d46c85db6b8bdfa07d2f1adfd286931ba24c8cb1a6
+        sourceRevisionDigest: sha256:3033fa2ed31f47a1508ad2e10594f824a2c68caa25670224e7d576f93c63b269
+        sourceBlobDigest: sha256:bb31cea6549192e0e90dda8d97fa05daa2cf2debac4223ee19e46b59b1c18ce3
         outLocation: /github/workspace/repo
 workflow:
     workflowVersion: 1.0.0

README.md

@@ -24,7 +24,7 @@ terraform {
   required_providers {
     airbyte = {
       source  = "airbytehq/airbyte"
-      version = "0.7.1"
+      version = "0.7.0"
     }
   }
 }

RELEASES.md

@@ -28,24 +28,4 @@ Based on:
 ### Generated
 - [terraform v0.6.0] .
 ### Releases
-- [Terraform v0.6.0] https://registry.terraform.io/providers/airbytehq/airbyte/0.6.0 - .
-
-## 2024-07-03 19:55:55
-### Changes
-Based on:
-- OpenAPI Doc  
-- Speakeasy CLI 1.326.0 (2.359.0) https://github.com/speakeasy-api/speakeasy
-### Generated
-- [terraform v0.7.0] .
-### Releases
-- [Terraform v0.7.0] https://registry.terraform.io/providers/airbytehq/airbyte/0.7.0 - .
-
-## 2024-07-15 18:17:47
-### Changes
-Based on:
-- OpenAPI Doc  
-- Speakeasy CLI 1.335.2 (2.372.3) https://github.com/speakeasy-api/speakeasy
-### Generated
-- [terraform v0.7.1] .
-### Releases
-- [Terraform v0.7.1] https://registry.terraform.io/providers/airbytehq/airbyte/0.7.1 - .
+- [Terraform v0.6.0] https://registry.terraform.io/providers/airbytehq/airbyte/0.6.0 - .

docs/data-sources/destination_langchain.md

@@ -0,0 +1,35 @@
+---
+# generated by https://github.com/hashicorp/terraform-plugin-docs
+page_title: "airbyte_destination_langchain Data Source - terraform-provider-airbyte"
+subcategory: ""
+description: |-
+  DestinationLangchain DataSource
+---
+
+# airbyte_destination_langchain (Data Source)
+
+DestinationLangchain DataSource
+
+## Example Usage
+
+```terraform
+data "airbyte_destination_langchain" "my_destination_langchain" {
+  destination_id = "...my_destination_id..."
+}
+```
+
+<!-- schema generated by tfplugindocs -->
+## Schema
+
+### Required
+
+- `destination_id` (String)
+
+### Read-Only
+
+- `configuration` (String) The values required to configure the destination. Parsed as JSON.
+- `destination_type` (String)
+- `name` (String)
+- `workspace_id` (String)
+
+

docs/data-sources/source_clazar.md → docs/data-sources/source_google_analytics_v4_service_account_only.md

@@ -1,19 +1,19 @@
 ---
 # generated by https://github.com/hashicorp/terraform-plugin-docs
-page_title: "airbyte_source_clazar Data Source - terraform-provider-airbyte"
+page_title: "airbyte_source_google_analytics_v4_service_account_only Data Source - terraform-provider-airbyte"
 subcategory: ""
 description: |-
-  SourceClazar DataSource
+  SourceGoogleAnalyticsV4ServiceAccountOnly DataSource
 ---
 
-# airbyte_source_clazar (Data Source)
+# airbyte_source_google_analytics_v4_service_account_only (Data Source)
 
-SourceClazar DataSource
+SourceGoogleAnalyticsV4ServiceAccountOnly DataSource
 
 ## Example Usage
 
 ```terraform
-data "airbyte_source_clazar" "my_source_clazar" {
+data "airbyte_source_google_analytics_v4_service_account_only" "my_source_googleanalyticsv4serviceaccountonly" {
   source_id = "...my_source_id..."
 }
 ```

docs/data-sources/source_goldcast.md → docs/data-sources/source_punk_api.md

@@ -1,19 +1,19 @@
 ---
 # generated by https://github.com/hashicorp/terraform-plugin-docs
-page_title: "airbyte_source_goldcast Data Source - terraform-provider-airbyte"
+page_title: "airbyte_source_punk_api Data Source - terraform-provider-airbyte"
 subcategory: ""
 description: |-
-  SourceGoldcast DataSource
+  SourcePunkAPI DataSource
 ---
 
-# airbyte_source_goldcast (Data Source)
+# airbyte_source_punk_api (Data Source)
 
-SourceGoldcast DataSource
+SourcePunkAPI DataSource
 
 ## Example Usage
 
 ```terraform
-data "airbyte_source_goldcast" "my_source_goldcast" {
+data "airbyte_source_punk_api" "my_source_punkapi" {
   source_id = "...my_source_id..."
 }
 ```

docs/index.md

@@ -17,7 +17,7 @@ terraform {
   required_providers {
     airbyte = {
       source  = "airbytehq/airbyte"
-      version = "0.7.1"
+      version = "0.6.0"
     }
   }
 }

docs/resources/destination_langchain.md

@@ -0,0 +1,147 @@
+---
+# generated by https://github.com/hashicorp/terraform-plugin-docs
+page_title: "airbyte_destination_langchain Resource - terraform-provider-airbyte"
+subcategory: ""
+description: |-
+  DestinationLangchain Resource
+---
+
+# airbyte_destination_langchain (Resource)
+
+DestinationLangchain Resource
+
+## Example Usage
+
+```terraform
+resource "airbyte_destination_langchain" "my_destination_langchain" {
+  configuration = {
+    embedding = {
+      fake = {}
+    }
+    indexing = {
+      chroma_local_persistance = {
+        collection_name  = "...my_collection_name..."
+        destination_path = "/local/my_chroma_db"
+      }
+    }
+    processing = {
+      chunk_overlap = 7
+      chunk_size    = 3
+      text_fields = [
+        "...",
+      ]
+    }
+  }
+  definition_id = "a735a4e1-8012-43f0-976f-b78bf74fa22d"
+  name          = "Jack Christiansen"
+  workspace_id  = "1b5f134d-0007-4497-b4ae-87c30892ffb0"
+}
+```
+
+<!-- schema generated by tfplugindocs -->
+## Schema
+
+### Required
+
+- `configuration` (Attributes) (see [below for nested schema](#nestedatt--configuration))
+- `name` (String) Name of the destination e.g. dev-mysql-instance.
+- `workspace_id` (String)
+
+### Optional
+
+- `definition_id` (String) The UUID of the connector definition. One of configuration.destinationType or definitionId must be provided. Requires replacement if changed.
+
+### Read-Only
+
+- `destination_id` (String)
+- `destination_type` (String)
+
+<a id="nestedatt--configuration"></a>
+### Nested Schema for `configuration`
+
+Required:
+
+- `embedding` (Attributes) Embedding configuration (see [below for nested schema](#nestedatt--configuration--embedding))
+- `indexing` (Attributes) Indexing configuration (see [below for nested schema](#nestedatt--configuration--indexing))
+- `processing` (Attributes) (see [below for nested schema](#nestedatt--configuration--processing))
+
+<a id="nestedatt--configuration--embedding"></a>
+### Nested Schema for `configuration.embedding`
+
+Optional:
+
+- `fake` (Attributes) 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. (see [below for nested schema](#nestedatt--configuration--embedding--fake))
+- `open_ai` (Attributes) Use the OpenAI API to embed text. This option is using the text-embedding-ada-002 model with 1536 embedding dimensions. (see [below for nested schema](#nestedatt--configuration--embedding--open_ai))
+
+<a id="nestedatt--configuration--embedding--fake"></a>
+### Nested Schema for `configuration.embedding.fake`
+
+
+<a id="nestedatt--configuration--embedding--open_ai"></a>
+### Nested Schema for `configuration.embedding.open_ai`
+
+Required:
+
+- `openai_key` (String, Sensitive)
+
+
+
+<a id="nestedatt--configuration--indexing"></a>
+### Nested Schema for `configuration.indexing`
+
+Optional:
+
+- `chroma_local_persistance` (Attributes) Chroma is a popular vector store that can be used to store and retrieve embeddings. It will build its index in memory and persist it to disk by the end of the sync. (see [below for nested schema](#nestedatt--configuration--indexing--chroma_local_persistance))
+- `doc_array_hnsw_search` (Attributes) DocArrayHnswSearch is a lightweight Document Index implementation provided by Docarray that runs fully locally and is best suited for small- to medium-sized datasets. It stores vectors on disk in hnswlib, and stores all other data in SQLite. (see [below for nested schema](#nestedatt--configuration--indexing--doc_array_hnsw_search))
+- `pinecone` (Attributes) Pinecone is a popular vector store that can be used to store and retrieve embeddings. It is a managed service and can also be queried from outside of langchain. (see [below for nested schema](#nestedatt--configuration--indexing--pinecone))
+
+<a id="nestedatt--configuration--indexing--chroma_local_persistance"></a>
+### Nested Schema for `configuration.indexing.chroma_local_persistance`
+
+Required:
+
+- `destination_path` (String) Path to the directory where chroma files will be written. The files will be placed inside that local mount.
+
+Optional:
+
+- `collection_name` (String) Name of the collection to use. Default: "langchain"
+
+
+<a id="nestedatt--configuration--indexing--doc_array_hnsw_search"></a>
+### Nested Schema for `configuration.indexing.doc_array_hnsw_search`
+
+Required:
+
+- `destination_path` (String) Path to the directory where hnswlib and meta data files will be written. The files will be placed inside that local mount. All files in the specified destination directory will be deleted on each run.
+
+
+<a id="nestedatt--configuration--indexing--pinecone"></a>
+### Nested Schema for `configuration.indexing.pinecone`
+
+Required:
+
+- `index` (String) Pinecone index to use
+- `pinecone_environment` (String) Pinecone environment to use
+- `pinecone_key` (String, Sensitive)
+
+
+
+<a id="nestedatt--configuration--processing"></a>
+### Nested Schema for `configuration.processing`
+
+Required:
+
+- `chunk_size` (Number) Size of chunks in tokens to store in vector store (make sure it is not too big for the context if your LLM)
+- `text_fields` (List of String) List of fields in the record that should be used to calculate the embedding. All other fields are passed along as meta fields. The field list is applied to all streams in the same way and non-existing fields are ignored. If none are defined, all fields are considered text fields. When specifying text fields, you can access nested fields in the record by using dot notation, e.g. `user.name` will access the `name` field in the `user` object. It's also possible to use wildcards to access all fields in an object, e.g. `users.*.name` will access all `names` fields in all entries of the `users` array.
+
+Optional:
+
+- `chunk_overlap` (Number) Size of overlap between chunks in tokens to store in vector store to better capture relevant context. Default: 0
+
+## Import
+
+Import is supported using the following syntax:
+
+```shell
+terraform import airbyte_destination_langchain.my_airbyte_destination_langchain ""
+```

docs/resources/destination_milvus.md

@@ -30,14 +30,14 @@ resource "airbyte_destination_milvus" "my_destination_milvus" {
       }
       collection   = "...my_collection..."
       db           = "...my_db..."
-      host         = "tcp://host.docker.internal:19530"
+      host         = "tcp://my-local-milvus:19530"
       text_field   = "...my_text_field..."
       vector_field = "...my_vector_field..."
     }
-    omit_raw_text = true
+    omit_raw_text = false
     processing = {
-      chunk_overlap = 6
-      chunk_size    = 4
+      chunk_overlap = 1
+      chunk_size    = 10
       field_name_mappings = [
         {
           from_field = "...my_from_field..."
@@ -52,14 +52,14 @@ resource "airbyte_destination_milvus" "my_destination_milvus" {
       ]
       text_splitter = {
         by_markdown_header = {
-          split_level = 2
+          split_level = 6
         }
       }
     }
   }
-  definition_id = "5a4e1801-23f0-4d76-bb78-bf74fa22de12"
-  name          = "Jenny Braun"
-  workspace_id  = "f134d000-7497-474a-a87c-30892ffb0f41"
+  definition_id = "2248d601-2833-484b-987b-5cce36148543"
+  name          = "Sylvia Smitham"
+  workspace_id  = "3c5e509f-4525-421a-8478-78c254cd184f"
 }
 ```