ingestr 0.13.94__tar.gz → 0.14.0__tar.gz

{ingestr-0.13.94 → ingestr-0.14.0}/.github/workflows/tests.yml

@@ -58,6 +58,7 @@ jobs:
         uses: astral-sh/setup-uv@v3
       - name: Install pip dependencies
         run: make deps-ci
+
       - name: run tests (macOS)
         if: matrix.os == 'macos-13'
         run: make test-ci

{ingestr-0.13.94 → ingestr-0.14.0}/Makefile

@@ -31,11 +31,14 @@ test-specific: venv lock-deps
 	. venv/bin/activate; set -a; source test.env; set +a; TESTCONTAINERS_RYUK_DISABLED=true pytest -n auto  -rP -vv --tb=short --capture=no -k $(test)
 
 lint-ci:
-	ruff format ingestr && ruff check ingestr --fix
-	mypy --config-file pyproject.toml --explicit-package-bases ingestr
+	@ruff format --diff ingestr && ruff check ingestr && mypy --config-file pyproject.toml --explicit-package-bases ingestr
+
+format:
+	@ruff format ingestr && ruff check ingestr --fix
+	@mypy --config-file pyproject.toml --explicit-package-bases ingestr
 
 lint: venv lock-deps
-	. venv/bin/activate; $(MAKE) lint-ci
+	. venv/bin/activate; $(MAKE) format
 
 lint-docs:
 	vale docs --glob='!**/.vitepress/**'

{ingestr-0.13.94 → ingestr-0.14.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ingestr
-Version: 0.13.94
+Version: 0.14.0
 Summary: ingestr is a command-line application that ingests data from various sources and stores them in any database.
 Project-URL: Homepage, https://github.com/bruin-data/ingestr
 Project-URL: Issues, https://github.com/bruin-data/ingestr/issues
@@ -48,7 +48,7 @@ Requires-Dist: dataclasses-json==0.6.7
 Requires-Dist: decorator==5.2.1
 Requires-Dist: deprecation==2.1.0
 Requires-Dist: dlt-cratedb==0.0.2
-Requires-Dist: dlt==1.11.0
+Requires-Dist: dlt==1.16.0
 Requires-Dist: dnspython==2.7.0
 Requires-Dist: duckdb-engine==0.17.0
 Requires-Dist: duckdb==1.2.1
@@ -104,7 +104,6 @@ Requires-Dist: jsonpath-ng==1.7.0
 Requires-Dist: leb128==1.0.8
 Requires-Dist: lxml==5.3.1
 Requires-Dist: lz4==4.4.3
-Requires-Dist: makefun==1.15.6
 Requires-Dist: mako==1.3.9
 Requires-Dist: markdown-it-py==3.0.0
 Requires-Dist: markupsafe==3.0.2
@@ -118,7 +117,7 @@ Requires-Dist: mysql-connector-python==9.2.0
 Requires-Dist: numpy==2.2.3
 Requires-Dist: oauthlib==3.2.2
 Requires-Dist: openpyxl==3.1.5
-Requires-Dist: orjson==3.10.15
+Requires-Dist: orjson==3.11.3
 Requires-Dist: packaging==24.2
 Requires-Dist: pandas==2.2.3
 Requires-Dist: paramiko==3.5.1
@@ -161,7 +160,7 @@ Requires-Dist: reactivex==4.0.4
 Requires-Dist: requests-file==2.1.0
 Requires-Dist: requests-oauthlib==1.3.1
 Requires-Dist: requests-toolbelt==1.0.0
-Requires-Dist: requests==2.32.3
+Requires-Dist: requests==2.32.5
 Requires-Dist: requirements-parser==0.11.0
 Requires-Dist: rich-argparse==1.7.0
 Requires-Dist: rich==13.9.4
@@ -195,6 +194,7 @@ Requires-Dist: thrift==0.16.0
 Requires-Dist: time-machine==2.16.0
 Requires-Dist: tomlkit==0.13.2
 Requires-Dist: tqdm==4.67.1
+Requires-Dist: trino==0.336.0
 Requires-Dist: typer==0.13.1
 Requires-Dist: types-requests==2.32.0.20240907
 Requires-Dist: types-setuptools==75.8.2.20250305
@@ -333,7 +333,7 @@ Pull requests are welcome. However, please open an issue first to discuss what y
     <tr>
         <td>Elasticsearch</td>
         <td>✅</td>
-        <td>-</td>
+        <td>✅</td>
     </tr>
      <tr>
         <td>GCP Spanner</td>
@@ -353,7 +353,7 @@ Pull requests are welcome. However, please open an issue first to discuss what y
     <tr>
         <td>MongoDB</td>
         <td>✅</td>
-        <td>❌</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td>MotherDuck</td>
@@ -395,6 +395,11 @@ Pull requests are welcome. However, please open an issue first to discuss what y
         <td>✅</td>
         <td>❌</td>
     </tr>
+    <tr>
+        <td>Trino</td>
+        <td>✅</td>
+        <td>✅</td>
+    </tr>
     <tr>
         <td colspan="3" style='text-align:center;'><strong>Platforms</strong></td>
     </tr>

{ingestr-0.13.94 → ingestr-0.14.0}/README.md

@@ -115,7 +115,7 @@ Pull requests are welcome. However, please open an issue first to discuss what y
     <tr>
         <td>Elasticsearch</td>
         <td>✅</td>
-        <td>-</td>
+        <td>✅</td>
     </tr>
      <tr>
         <td>GCP Spanner</td>
@@ -135,7 +135,7 @@ Pull requests are welcome. However, please open an issue first to discuss what y
     <tr>
         <td>MongoDB</td>
         <td>✅</td>
-        <td>❌</td>
+        <td>✅</td>
     </tr>
     <tr>
         <td>MotherDuck</td>
@@ -177,6 +177,11 @@ Pull requests are welcome. However, please open an issue first to discuss what y
         <td>✅</td>
         <td>❌</td>
     </tr>
+    <tr>
+        <td>Trino</td>
+        <td>✅</td>
+        <td>✅</td>
+    </tr>
     <tr>
         <td colspan="3" style='text-align:center;'><strong>Platforms</strong></td>
     </tr>

{ingestr-0.13.94 → ingestr-0.14.0}/docs/.vitepress/config.mjs

@@ -114,6 +114,7 @@ export default defineConfig({
               { text: "Adjust", link: "/supported-sources/adjust.md" },
               { text: "Airtable", link: "/supported-sources/airtable.md" },
               { text: "Amazon Kinesis", link: "/supported-sources/kinesis.md" },
+              { text: "Anthropic", link: "/supported-sources/anthropic.md" },
               { text: "AppsFlyer", link: "/supported-sources/appsflyer.md" },
               { text: "Apple App Store", link: "/supported-sources/appstore.md"},
               { text: "Applovin", link: "/supported-sources/applovin.md"},
@@ -130,6 +131,7 @@ export default defineConfig({
               { text: "Fluxx", link: "/supported-sources/fluxx.md" },
               { text: "Frankfurter", link: "/supported-sources/frankfurter.md" },
               { text: "Freshdesk", link: "/supported-sources/freshdesk.md" },
+              { text: "FundraiseUp", link: "/supported-sources/fundraiseup.md" },
               { text: "Trustpilot", link: "/supported-sources/trustpilot.md" },
               { text: "Google Cloud Storage (GCS)", link: "/supported-sources/gcs.md" },
               { text: "Google Analytics", link: "/supported-sources/google_analytics.md" },

ingestr-0.14.0/docs/supported-sources/anthropic.md

@@ -0,0 +1,356 @@
+# Anthropic
+
+[Anthropic](https://www.anthropic.com/) is an AI safety company that builds Claude, a family of large language models. This source enables you to extract comprehensive data from the Anthropic Admin API, including Claude Code usage metrics, API usage reports, cost data, and organization management information.
+
+## URI Format
+
+The URI format for Anthropic is:
+
+```plaintext
+anthropic://?api_key=<admin_api_key>
+```
+
+### URI Parameters:
+
+- `api_key` (required): Your Anthropic Admin API key (must start with `sk-ant-admin...`)
+
+::: warning Admin API Key Required
+This source requires an **Admin API key** which is different from standard API keys. Only organization members with the admin role can provision Admin API keys through the [Anthropic Console](https://console.anthropic.com/settings/admin-keys).
+
+The Admin API is unavailable for individual accounts. To use this source, you must have an organization set up in Console → Settings → Organization.
+:::
+
+## Available Tables
+
+### claude_code_usage
+
+The `claude_code_usage` table contains daily aggregated usage metrics for Claude Code users in your organization. This data helps you analyze developer productivity and monitor Claude Code adoption.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `date` | `string` | Date in RFC 3339 format (UTC timestamp) |
+| `actor_type` | `string` | Type of actor (`user_actor` or `api_actor`) |
+| `actor_id` | `string` | Email address for users or API key name for API actors |
+| `organization_id` | `string` | Organization UUID |
+| `customer_type` | `string` | Type of customer account (`api` or `subscription`) |
+| `terminal_type` | `string` | Terminal/environment where Claude Code was used (e.g., `vscode`, `iTerm.app`) |
+| `num_sessions` | `integer` | Number of distinct Claude Code sessions |
+| `lines_added` | `integer` | Total lines of code added across all files |
+| `lines_removed` | `integer` | Total lines of code removed across all files |
+| `commits_by_claude_code` | `integer` | Number of git commits created through Claude Code |
+| `pull_requests_by_claude_code` | `integer` | Number of pull requests created through Claude Code |
+| `edit_tool_accepted` | `integer` | Number of Edit tool proposals accepted |
+| `edit_tool_rejected` | `integer` | Number of Edit tool proposals rejected |
+| `multi_edit_tool_accepted` | `integer` | Number of MultiEdit tool proposals accepted |
+| `multi_edit_tool_rejected` | `integer` | Number of MultiEdit tool proposals rejected |
+| `write_tool_accepted` | `integer` | Number of Write tool proposals accepted |
+| `write_tool_rejected` | `integer` | Number of Write tool proposals rejected |
+| `notebook_edit_tool_accepted` | `integer` | Number of NotebookEdit tool proposals accepted |
+| `notebook_edit_tool_rejected` | `integer` | Number of NotebookEdit tool proposals rejected |
+| `total_input_tokens` | `integer` | Total input tokens across all models |
+| `total_output_tokens` | `integer` | Total output tokens across all models |
+| `total_cache_read_tokens` | `integer` | Total cache read tokens across all models |
+| `total_cache_creation_tokens` | `integer` | Total cache creation tokens across all models |
+| `total_estimated_cost_cents` | `integer` | Total estimated cost in cents USD |
+| `models_used` | `string` | Comma-separated list of Claude models used |
+
+### usage_report
+
+The `usage_report` table contains detailed token usage metrics from the Messages API, aggregated by time bucket, workspace, API key, model, and service tier.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `bucket` | `string` | Time bucket in ISO 8601 format |
+| `api_key_id` | `string` | API key identifier |
+| `workspace_id` | `string` | Workspace identifier |
+| `model` | `string` | Claude model used |
+| `service_tier` | `string` | Service tier (scale or default) |
+| `input_tokens` | `integer` | Number of input tokens |
+| `output_tokens` | `integer` | Number of output tokens |
+| `input_cached_tokens` | `integer` | Number of cached input tokens |
+| `api_first_response_latency_ms_p50` | `float` | 50th percentile first response latency in milliseconds |
+| `api_first_response_latency_ms_p95` | `float` | 95th percentile first response latency in milliseconds |
+| `api_first_response_latency_ms_p99` | `float` | 99th percentile first response latency in milliseconds |
+| `api_total_latency_ms_p50` | `float` | 50th percentile total latency in milliseconds |
+| `api_total_latency_ms_p95` | `float` | 95th percentile total latency in milliseconds |
+| `api_total_latency_ms_p99` | `float` | 99th percentile total latency in milliseconds |
+| `api_request_count` | `integer` | Number of API requests |
+| `server_tool_search_count` | `integer` | Number of server tool searches |
+| `server_tool_result_count` | `integer` | Number of server tool results |
+
+### cost_report
+
+The `cost_report` table contains aggregated cost data broken down by workspace and cost description.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `bucket` | `string` | Time bucket in ISO 8601 format |
+| `workspace_id` | `string` | Workspace identifier |
+| `description` | `string` | Cost description (e.g., "Usage - claude-3-5-sonnet-20241022") |
+| `amount_cents` | `integer` | Cost amount in cents USD |
+
+### organization
+
+The `organization` table contains information about your Anthropic organization.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `id` | `string` | Organization UUID |
+| `name` | `string` | Organization name |
+| `settings` | `object` | Organization settings (JSON) |
+| `created_at` | `string` | Creation timestamp |
+
+### workspaces
+
+The `workspaces` table contains all workspaces in your organization.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `id` | `string` | Workspace UUID |
+| `name` | `string` | Workspace name |
+| `type` | `string` | Workspace type (default or custom) |
+| `created_at` | `string` | Creation timestamp |
+
+### api_keys
+
+The `api_keys` table contains all API keys in your organization.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `id` | `string` | API key UUID |
+| `name` | `string` | API key name |
+| `status` | `string` | API key status (active or disabled) |
+| `created_at` | `string` | Creation timestamp |
+| `workspace_id` | `string` | Associated workspace UUID |
+| `created_by_user_id` | `string` | User who created the key |
+| `last_used_at` | `string` | Last usage timestamp |
+
+### invites
+
+The `invites` table contains all pending organization invites.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `id` | `string` | Invite UUID |
+| `email` | `string` | Invitee email address |
+| `role` | `string` | Invited role (admin or member) |
+| `expires_at` | `string` | Expiration timestamp |
+| `workspace_ids` | `array` | List of workspace UUIDs |
+| `created_at` | `string` | Creation timestamp |
+| `created_by_user_id` | `string` | User who created the invite |
+
+### users
+
+The `users` table contains all users in your organization.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `id` | `string` | User UUID |
+| `email` | `string` | User email address |
+| `name` | `string` | User full name |
+| `role` | `string` | User role (admin or member) |
+| `created_at` | `string` | Creation timestamp |
+| `last_login_at` | `string` | Last login timestamp |
+
+### workspace_members
+
+The `workspace_members` table contains workspace membership information.
+
+#### Schema
+
+| Column | Type | Description |
+|--------|------|-------------|
+| `workspace_id` | `string` | Workspace UUID |
+| `user_id` | `string` | User UUID |
+| `role` | `string` | Role in workspace |
+| `added_at` | `string` | When user was added to workspace |
+
+## Examples
+
+### Basic Usage
+
+Load all Claude Code usage data to a DuckDB database:
+
+```bash
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "claude_code_usage" \
+    --dest-uri "duckdb:///anthropic_data.db" \
+    --dest-table "claude_code_usage"
+```
+
+### Incremental Loading
+
+Load data incrementally starting from a specific date:
+
+```bash
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "claude_code_usage" \
+    --dest-uri "postgresql://user:password@localhost:5432/analytics" \
+    --dest-table "claude_code_usage" \
+    --interval-start "2024-01-01" \
+    --interval-end "2024-12-31"
+```
+
+### Load to BigQuery
+
+```bash
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "claude_code_usage" \
+    --dest-uri "bigquery://project-id.dataset" \
+    --dest-table "claude_code_usage"
+```
+
+### Load Organization Data
+
+```bash
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "organization" \
+    --dest-uri "duckdb:///anthropic_data.db" \
+    --dest-table "organization"
+```
+
+### Load Usage Report
+
+```bash
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "usage_report" \
+    --dest-uri "postgresql://user:password@localhost:5432/analytics" \
+    --dest-table "api_usage" \
+    --interval-start "2024-01-01" \
+    --interval-end "2024-12-31"
+```
+
+### Load Cost Report
+
+```bash
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "cost_report" \
+    --dest-uri "duckdb:///costs.db" \
+    --dest-table "anthropic_costs"
+```
+
+### Load All Users and Workspaces
+
+```bash
+# Load users
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "users" \
+    --dest-uri "duckdb:///org_data.db" \
+    --dest-table "users"
+
+# Load workspaces
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "workspaces" \
+    --dest-uri "duckdb:///org_data.db" \
+    --dest-table "workspaces"
+
+# Load workspace members
+ingestr ingest \
+    --source-uri "anthropic://?api_key=sk-ant-admin-..." \
+    --source-table "workspace_members" \
+    --dest-uri "duckdb:///org_data.db" \
+    --dest-table "workspace_members"
+```
+
+## Incremental Loading
+
+The following tables support incremental loading:
+- `claude_code_usage` - incremental based on the `date` field
+- `usage_report` - supports date range filtering with `--interval-start` and `--interval-end`
+- `cost_report` - supports date range filtering with `--interval-start` and `--interval-end`
+
+Other tables (`organization`, `workspaces`, `api_keys`, `invites`, `users`, `workspace_members`) use full refresh mode as they represent current state data.
+
+When running incremental loads:
+- The source tracks the last loaded date for `claude_code_usage`
+- Subsequent runs will only fetch new data
+- Use `--interval-start` and `--interval-end` to specify a custom date range
+- Default start date is January 1, 2023
+
+## Use Cases
+
+### Developer Productivity Analysis
+
+Track how your team uses Claude Code:
+- Monitor adoption rates across different teams
+- Analyze code generation patterns
+- Track tool acceptance rates
+
+### Cost Monitoring
+
+Monitor Claude Code costs:
+- Track token usage by user and model
+- Analyze spending patterns
+- Allocate costs by team or project
+
+### Executive Dashboards
+
+Create reports showing:
+- Claude Code impact on development velocity
+- Lines of code generated vs. manual coding
+- Commit and PR creation metrics
+- API usage patterns across workspaces
+- Cost allocation by team and project
+
+### Organization Management
+
+Monitor and audit your organization:
+- Track user access and permissions
+- Monitor API key usage and lifecycle
+- Audit workspace memberships
+- Track pending invites and onboarding
+
+## Data Freshness
+
+Claude Code analytics data typically appears within 1 hour of user activity completion. The API provides daily aggregated metrics only.
+
+## Rate Limits
+
+The Anthropic Admin API has rate limits in place. The source handles pagination automatically and respects these limits.
+
+## Notes
+
+- This source only tracks Claude Code usage on the Anthropic API (1st party)
+- Usage on Amazon Bedrock, Google Vertex AI, or other third-party platforms is not included
+- All dates and timestamps are in UTC
+- The source requires organization-level access (not available for individual accounts)
+
+## Available Tables Summary
+
+| Table | Incremental | Primary Key | Description |
+|-------|-------------|-------------|-------------|
+| `claude_code_usage` | ✅ | date, actor_type, actor_id, terminal_type | Daily Claude Code usage metrics |
+| `usage_report` | Date Range | bucket, api_key_id, workspace_id, model, service_tier | API usage and latency metrics |
+| `cost_report` | Date Range | bucket, workspace_id, description | Cost breakdown by workspace |
+| `organization` | ❌ | - | Organization information |
+| `workspaces` | ❌ | id | Workspace list |
+| `api_keys` | ❌ | id | API key management |
+| `invites` | ❌ | id | Pending invitations |
+| `users` | ❌ | id | User list |
+| `workspace_members` | ❌ | workspace_id, user_id | Workspace memberships |
+
+For feature requests or issues, please create a GitHub issue at https://github.com/bruin-data/ingestr

ingestr-0.14.0/docs/supported-sources/fundraiseup.md

@@ -0,0 +1,83 @@
+# FundraiseUp
+
+[FundraiseUp](https://fundraiseup.com/) is a modern donation platform that helps non-profits increase their online fundraising revenue.
+
+ingestr supports FundraiseUp as a source.
+
+## URI format
+
+The URI format for FundraiseUp is:
+
+```
+fundraiseup://?api_key=<api_key>
+```
+
+URI parameters:
+- `api_key`: Your FundraiseUp API key (required).
+
+## Example usage
+
+Assuming your API key is `your_api_key`, you can ingest donations into DuckDB using:
+
+```bash
+ingestr ingest \
+    --source-uri 'fundraiseup://?api_key=your_api_key' \
+    --source-table 'donations' \
+    --dest-uri duckdb:///fundraiseup.duckdb \
+    --dest-table 'main.donations'
+```
+
+## Tables
+
+The FundraiseUp source supports the following tables:
+
+| Table           | PK | Inc Key | Inc Strategy | Details                                                                                                                                        |
+| --------------- | ----------- | --------------- | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
+| `donations`       | id | - | replace               | All donation records including amounts, supporters, and payment details |
+| `events`       | id | - | replace               | Audit log events for tracking changes and activities |
+| `fundraisers`       | id | - | replace               | Fundraiser campaigns (requires appropriate API permissions) |
+| `recurring_plans`       | id | - | replace               | Recurring donation plans and subscription details |
+| `supporters`       | id | - | replace               | Donor/supporter information including contact details |
+
+Use one of these as the `--source-table` parameter in the `ingestr ingest` command.
+
+## Notes
+
+- **Authentication**: The FundraiseUp API uses Bearer token authentication. Make sure your API key has the necessary permissions for the resources you want to access.
+- **Incremental Loading**: The FundraiseUp source does not support incremental loading. All data is fetched with a full refresh (replace strategy).
+- **Date Filtering**: The API does not support date filtering for any of the endpoints.
+- **Permissions**: The `fundraisers` endpoint may return a 403 Forbidden error if your API key doesn't have the required permissions. Contact FundraiseUp support to enable access if needed.
+
+## Example: Ingesting all available data
+
+To ingest all available data from FundraiseUp:
+
+```bash
+# Ingest donations
+ingestr ingest \
+    --source-uri 'fundraiseup://?api_key=your_api_key' \
+    --source-table 'donations' \
+    --dest-uri duckdb:///fundraiseup.db \
+    --dest-table 'main.donations'
+
+# Ingest events
+ingestr ingest \
+    --source-uri 'fundraiseup://?api_key=your_api_key' \
+    --source-table 'events' \
+    --dest-uri duckdb:///fundraiseup.db \
+    --dest-table 'main.events'
+
+# Ingest recurring plans
+ingestr ingest \
+    --source-uri 'fundraiseup://?api_key=your_api_key' \
+    --source-table 'recurring_plans' \
+    --dest-uri duckdb:///fundraiseup.db \
+    --dest-table 'main.recurring_plans'
+
+# Ingest supporters
+ingestr ingest \
+    --source-uri 'fundraiseup://?api_key=your_api_key' \
+    --source-table 'supporters' \
+    --dest-uri duckdb:///fundraiseup.db \
+    --dest-table 'main.supporters'
+```

ingestr-0.14.0/docs/supported-sources/trino.md

@@ -0,0 +1,96 @@
+# Trino
+Trino (formerly PrestoSQL) is a distributed SQL query engine designed for fast analytics on large datasets across multiple data sources.
+
+ingestr supports Trino as both a source and destination.
+
+> [!WARNING]
+> Trino is currently supported as a beta platform, which means that some features might not work as expected.
+
+## URI format
+The URI format for Trino is as follows:
+
+```plaintext
+trino://<username>:<password>@<host>:<port>/<catalog>
+```
+
+URI parameters:
+- `username`: your Trino username (required)
+- `password`: your Trino password (optional, depending on authentication)
+- `host`: the Trino server hostname or IP address
+- `port`: the Trino server port (default: 8080)
+- `catalog`: the Trino catalog to connect to
+
+The same URI structure can be used both for sources and destinations. You can read more about SQLAlchemy's Trino dialect [here](https://github.com/trinodb/trino-python-client).
+
+### Authentication methods
+Trino supports various authentication methods:
+
+1. **No Authentication**: For development/testing environments
+   ```
+   trino://user@localhost:8080/catalog
+   ```
+
+2. **Basic Authentication**: Username and password
+   ```
+   trino://user:password@localhost:8080/catalog
+   ```
+
+3. **Other Methods**: For Kerberos, JWT, or certificate-based authentication, consult your Trino administrator for the appropriate connection parameters.
+
+## Table naming
+When specifying tables for Trino (both source and destination), use the format:
+
+```plaintext
+schema.table_name
+```
+
+For example:
+- `default.users` - accesses the `users` table in the `default` schema
+- `analytics.events` - accesses the `events` table in the `analytics` schema
+
+The catalog is specified in the connection URI, not in the table name.
+
+## Examples
+
+### Using Trino as a source
+```bash
+ingestr ingest \
+    --source-uri 'trino://admin@localhost:8080/iceberg' \
+    --source-table 'default.source_table' \
+    --dest-uri 'duckdb:///output.db' \
+    --dest-table 'main.destination_table'
+```
+
+### Using Trino as a destination
+```bash
+ingestr ingest \
+    --source-uri 'postgresql://user:pass@localhost:5432/sourcedb' \
+    --source-table 'public.customers' \
+    --dest-uri 'trino://admin@localhost:8080/hive' \
+    --dest-table 'default.customers'
+```
+
+### With authentication
+```bash
+ingestr ingest \
+    --source-uri 'mysql://user:pass@localhost:3306/sourcedb' \
+    --source-table 'orders' \
+    --dest-uri 'trino://user:password@trino-server:8443/iceberg' \
+    --dest-table 'sales.orders'
+```
+
+## Supported write dispositions
+When using Trino as a destination, all the existing write dispositions are supported.
+
+## Data type handling
+Trino automatically handles most SQL data type conversions. When used as a destination:
+- JSON types are converted to TEXT/VARCHAR
+- Binary types are converted to TEXT/VARCHAR
+- All integer types are mapped to BIGINT for compatibility
+
+## Limitations
+
+### As a destination
+- Case-sensitive identifiers (table and column names preserve case)
+- JSON and Binary types are converted to STRING
+- Memory catalog does not support DELETE and UPDATE operations (affects merge/scd2 in test environments)