lightspeed-core · tisnik · Aug 12, 2025 · Aug 12, 2025
diff --git a/.github/workflows/e2e_tests.yaml b/.github/workflows/e2e_tests.yaml
@@ -87,14 +87,7 @@ jobs:
               feedback_storage: "/tmp/data/feedback"
               transcripts_disabled: false
               transcripts_storage: "/tmp/data/transcripts"
-              data_collector:
-                enabled: false
-                ingress_server_url: null
-                ingress_server_auth_token: null
-                ingress_content_service_name: null
-                collection_interval: 7200  # 2 hours in seconds
-                cleanup_after_send: true
-                connection_timeout_seconds: 30
+
             authentication:
               module: "noop"
 

diff --git a/Makefile b/Makefile
@@ -8,8 +8,7 @@ PYTHON_REGISTRY = pypi
 run: ## Run the service locally
 	uv run src/lightspeed_stack.py
 
-run-data-collector: ## Run the data collector service locally
-	uv run src/lightspeed_stack.py --data-collector
+
 
 test-unit: ## Run the unit tests
 	@echo "Running unit tests..."

diff --git a/README.md b/README.md
@@ -42,10 +42,7 @@ Lightspeed Core Stack (LCS) is an AI-powered assistant that provides answers to
     * [Utility to generate OpenAPI schema](#utility-to-generate-openapi-schema)
         * [Path](#path)
         * [Usage](#usage-1)
-    * [Data Collector Service](#data-collector-service)
-        * [Features](#features)
-        * [Configuration](#configuration-1)
-        * [Running the Service](#running-the-service)
+
 
 <!-- vim-markdown-toc -->
 
@@ -253,7 +250,6 @@ Usage: make <OPTIONS> ... <TARGETS>
 Available targets are:
 
 run                               Run the service locally
-run-data-collector                Run the data collector service
 test-unit                         Run the unit tests
 test-integration                  Run integration tests tests
 test-e2e                          Run BDD tests for the service
@@ -421,50 +417,6 @@ This script re-generated OpenAPI schema for the Lightspeed Service REST API.
 make schema
 ```
 
-## Data Collector Service
-
-The data collector service is a standalone service that runs separately from the main web service. It is responsible for collecting and sending user data including feedback and transcripts to an ingress server for analysis and archival.
-
-### Features
-
-- **Periodic Collection**: Runs at configurable intervals
-- **Data Packaging**: Packages feedback and transcript files into compressed tar.gz archives
-- **Secure Transmission**: Sends data to a configured ingress server with optional authentication
-- **File Cleanup**: Optionally removes local files after successful transmission
-- **Error Handling**: Includes retry logic and comprehensive error handling
-
-### Configuration
-
-The data collector service is configured through the `user_data_collection.data_collector` section in your configuration file:
-
-```yaml
-user_data_collection:
-  feedback_enabled: true
-  feedback_storage: "/tmp/data/feedback"
-  transcripts_enabled: true
-  transcripts_storage: "/tmp/data/transcripts"
-  data_collector:
-    enabled: true
-    ingress_server_url: "https://your-ingress-server.com"
-    ingress_server_auth_token: "your-auth-token"
-    ingress_content_service_name: "lightspeed-team"
-    collection_interval: 7200  # 2 hours in seconds
-    cleanup_after_send: true
-    connection_timeout: 30
-```
-
-### Running the Service
-
-To run the data collector service:
-
-```bash
-# Using Python directly
-uv run src/lightspeed_stack.py --data-collector
-
-# Using Make target
-make run-data-collector
-```
-
 
 
 # Project structure

diff --git a/docs/config.puml b/docs/config.puml
@@ -26,16 +26,7 @@ class "Customization" as src.models.config.Customization {
   system_prompt_path : Optional[FilePath]
   check_customization_model() -> Self
 }
-class "DataCollectorConfiguration" as src.models.config.DataCollectorConfiguration {
-  cleanup_after_send : bool
-  collection_interval : Annotated
-  connection_timeout : Annotated
-  enabled : bool
-  ingress_content_service_name : Optional[str]
-  ingress_server_auth_token : Optional[str]
-  ingress_server_url : Optional[str]
-  check_data_collector_configuration() -> Self
-}
+
 class "InferenceConfiguration" as src.models.config.InferenceConfiguration {
   default_model : Optional[str]
   default_provider : Optional[str]
@@ -78,14 +69,13 @@ class "TLSConfiguration" as src.models.config.TLSConfiguration {
   check_tls_configuration() -> Self
 }
 class "UserDataCollection" as src.models.config.UserDataCollection {
-  data_collector
   feedback_enabled : bool
   feedback_storage : Optional[str]
   transcripts_enabled : bool
   transcripts_storage : Optional[str]
   check_storage_location_is_set_when_needed() -> Self
 }
-src.models.config.DataCollectorConfiguration --* src.models.config.UserDataCollection : data_collector
+
 src.models.config.InferenceConfiguration --* src.models.config.Configuration : inference
 src.models.config.JwtConfiguration --* src.models.config.JwkConfiguration : jwt_configuration
 src.models.config.LlamaStackConfiguration --* src.models.config.Configuration : llama_stack

diff --git a/docs/deployment_guide.md b/docs/deployment_guide.md
@@ -1099,14 +1099,7 @@ user_data_collection:
   feedback_storage: "/tmp/data/feedback"
   transcripts_enabled: true
   transcripts_storage: "/tmp/data/transcripts"
-  data_collector:
-    enabled: false
-    ingress_server_url: null
-    ingress_server_auth_token: null
-    ingress_content_service_name: null
-    collection_interval: 7200  # 2 hours in seconds
-    cleanup_after_send: true
-    connection_timeout_seconds: 30
+
 authentication:
   module: "noop"
 ```
@@ -1261,14 +1254,7 @@ user_data_collection:
   feedback_storage: "/tmp/data/feedback"
   transcripts_enabled: true
   transcripts_storage: "/tmp/data/transcripts"
-  data_collector:
-    enabled: false
-    ingress_server_url: null
-    ingress_server_auth_token: null
-    ingress_content_service_name: null
-    collection_interval: 7200  # 2 hours in seconds
-    cleanup_after_send: true
-    connection_timeout_seconds: 30
+
 authentication:
   module: "noop"
 ```

diff --git a/docs/getting_started.md b/docs/getting_started.md
@@ -264,14 +264,7 @@ user_data_collection:
   feedback_storage: "/tmp/data/feedback"
   transcripts_enabled: true
   transcripts_storage: "/tmp/data/transcripts"
-  data_collector:
-    enabled: false
-    ingress_server_url: null
-    ingress_server_auth_token: null
-    ingress_content_service_name: null
-    collection_interval: 7200  # 2 hours in seconds
-    cleanup_after_send: true
-    connection_timeout_seconds: 30
+
 authentication:
   module: "noop"
 ```

diff --git a/docs/openapi.json b/docs/openapi.json
@@ -1101,67 +1101,32 @@
                 "title": "Customization",
                 "description": "Service customization."
             },
-            "DataCollectorConfiguration": {
+            "DatabaseConfiguration": {
                 "properties": {
-                    "enabled": {
-                        "type": "boolean",
-                        "title": "Enabled",
-                        "default": false
-                    },
-                    "ingress_server_url": {
-                        "anyOf": [
-                            {
-                                "type": "string"
-                            },
-                            {
-                                "type": "null"
-                            }
-                        ],
-                        "title": "Ingress Server Url"
-                    },
-                    "ingress_server_auth_token": {
+                    "sqlite": {
                         "anyOf": [
                             {
-                                "type": "string"
+                                "$ref": "#/components/schemas/SQLiteDatabaseConfiguration"
                             },
                             {
                                 "type": "null"
                             }
-                        ],
-                        "title": "Ingress Server Auth Token"
+                        ]
                     },
-                    "ingress_content_service_name": {
+                    "postgres": {
                         "anyOf": [
                             {
-                                "type": "string"
+                                "$ref": "#/components/schemas/PostgreSQLDatabaseConfiguration"
                             },
                             {
                                 "type": "null"
                             }
-                        ],
-                        "title": "Ingress Content Service Name"
-                    },
-                    "collection_interval": {
-                        "type": "integer",
-                        "exclusiveMinimum": 0.0,
-                        "title": "Collection Interval",
-                        "default": 7200
-                    },
-                    "cleanup_after_send": {
-                        "type": "boolean",
-                        "title": "Cleanup After Send",
-                        "default": true
-                    },
-                    "connection_timeout": {
-                        "type": "integer",
-                        "exclusiveMinimum": 0.0,
-                        "title": "Connection Timeout",
-                        "default": 30
+                        ]
                     }
                 },
                 "type": "object",
-                "title": "DataCollectorConfiguration",
-                "description": "Data collector configuration for sending data to ingress server."
+                "title": "DatabaseConfiguration",
+                "description": "Database configuration."
             },
             "DatabaseConfiguration": {
                 "properties": {
@@ -2122,15 +2087,6 @@
                             }
                         ],
                         "title": "Transcripts Storage"
-                    },
-                    "data_collector": {
-                        "$ref": "#/components/schemas/DataCollectorConfiguration",
-                        "default": {
-                            "enabled": false,
-                            "collection_interval": 7200,
-                            "cleanup_after_send": true,
-                            "connection_timeout": 30
-                        }
                     }
                 },
                 "type": "object",

diff --git a/docs/openapi.md b/docs/openapi.md
@@ -577,21 +577,6 @@ Service customization.
 | system_prompt |  |  |
 
 
-## DataCollectorConfiguration
-
-
-Data collector configuration for sending data to ingress server.
-
-
-| Field | Type | Description |
-|-------|------|-------------|
-| enabled | boolean |  |
-| ingress_server_url |  |  |
-| ingress_server_auth_token |  |  |
-| ingress_content_service_name |  |  |
-| collection_interval | integer |  |
-| cleanup_after_send | boolean |  |
-| connection_timeout | integer |  |
 
 
 ## DatabaseConfiguration
@@ -1026,7 +1011,6 @@ User data collection configuration.
 | feedback_storage |  |  |
 | transcripts_enabled | boolean |  |
 | transcripts_storage |  |  |
-| data_collector |  |  |
 
 
 ## ValidationError

diff --git a/docs/output.md b/docs/output.md
@@ -577,22 +577,6 @@ Service customization.
 | system_prompt |  |  |
 
 
-## DataCollectorConfiguration
-
-
-Data collector configuration for sending data to ingress server.
-
-
-| Field | Type | Description |
-|-------|------|-------------|
-| enabled | boolean |  |
-| ingress_server_url |  |  |
-| ingress_server_auth_token |  |  |
-| ingress_content_service_name |  |  |
-| collection_interval | integer |  |
-| cleanup_after_send | boolean |  |
-| connection_timeout | integer |  |
-
 
 ## DatabaseConfiguration
 
@@ -1016,7 +1000,6 @@ User data collection configuration.
 | feedback_storage |  |  |
 | transcripts_enabled | boolean |  |
 | transcripts_storage |  |  |
-| data_collector |  |  |
 
 
 ## ValidationError

diff --git a/docs/testing.md b/docs/testing.md
@@ -105,11 +105,9 @@ As specified in Definition of Done, new changes need to be covered by tests.
 │   ├── test_requests.py
 │   └── test_responses.py
 ├── runners
-│   ├── __init__.py
-│   ├── test_data_collector_runner.py
-│   └── test_uvicorn_runner.py
+│   ├── __init__.py
+│   └── test_uvicorn_runner.py
 ├── services
-│   └── test_data_collector.py
 ├── test_client.py
 ├── test_configuration.py
 ├── test_lightspeed_stack.py

diff --git a/lightspeed-stack.yaml b/lightspeed-stack.yaml
@@ -20,13 +20,6 @@ user_data_collection:
   feedback_storage: "/tmp/data/feedback"
   transcripts_enabled: true
   transcripts_storage: "/tmp/data/transcripts"
-  data_collector:
-    enabled: false
-    ingress_server_url: null
-    ingress_server_auth_token: null
-    ingress_content_service_name: null
-    collection_interval: 7200  # 2 hours in seconds
-    cleanup_after_send: true
-    connection_timeout_seconds: 30
+
 authentication:
   module: "noop"
diff --git a/src/constants.py b/src/constants.py
@@ -47,10 +47,6 @@
 DEFAULT_JWT_UID_CLAIM = "user_id"
 DEFAULT_JWT_USER_NAME_CLAIM = "username"
 
-# Data collector constants
-DATA_COLLECTOR_COLLECTION_INTERVAL = 7200  # 2 hours in seconds
-DATA_COLLECTOR_CONNECTION_TIMEOUT = 30
-DATA_COLLECTOR_RETRY_INTERVAL = 300  # 5 minutes in seconds
 
 # PostgreSQL connection constants
 # See: https://www.postgresql.org/docs/current/libpq-connect.html#LIBPQ-CONNECT-SSLMODE