Merge branch 'main' of https://github.com/continuedev/continue

7 files changed, 222 insertions, 1 deletions

diff --git a/continuedev/src/continuedev/core/policy.py b/continuedev/src/continuedev/core/policy.py
index a4c8d60f..667b4546 100644
--- a/continuedev/src/continuedev/core/policy.py
+++ b/continuedev/src/continuedev/core/policy.py
@@ -11,6 +11,7 @@ from ..steps.main import EditHighlightedCodeStep, SolveTracebackStep, RunCodeSte
 from ..recipes.WritePytestsRecipe.main import WritePytestsRecipe
 from ..recipes.ContinueRecipeRecipe.main import ContinueStepStep
 from ..steps.comment_code import CommentCodeStep
+from ..recipes.DDtoBQRecipe.main import DDtoBQRecipeRecipe
 from ..steps.core.core import MessageStep
 
 
@@ -33,6 +34,8 @@ class DemoPolicy(Policy):
                 return WritePytestsRecipe(instructions=observation.user_input)
             elif "/dlt" in observation.user_input.lower():
                 return CreatePipelineRecipe()
+            elif "/ddtobq" in observation.user_input.lower():
+                return DDtoBQRecipeRecipe()
             elif "/airflow" in observation.user_input.lower():
                 return DeployPipelineAirflowRecipe()
             elif "/transform" in observation.user_input.lower():
diff --git a/continuedev/src/continuedev/recipes/DDtoBQRecipe/README.md b/continuedev/src/continuedev/recipes/DDtoBQRecipe/README.md
new file mode 100644
index 00000000..c4981e56
--- /dev/null
+++ b/continuedev/src/continuedev/recipes/DDtoBQRecipe/README.md
@@ -0,0 +1,3 @@
+# DDtoBQRecipe
+
+Move from using DuckDB to Google BigQuery as the destination for your `dlt` pipeline
\ No newline at end of file
diff --git a/continuedev/src/continuedev/recipes/DDtoBQRecipe/dlt_duckdb_to_bigquery_docs.md b/continuedev/src/continuedev/recipes/DDtoBQRecipe/dlt_duckdb_to_bigquery_docs.md
new file mode 100644
index 00000000..eb68e117
--- /dev/null
+++ b/continuedev/src/continuedev/recipes/DDtoBQRecipe/dlt_duckdb_to_bigquery_docs.md
@@ -0,0 +1,85 @@
+### Credentials Missing: ConfigFieldMissingException
+
+You'll see this exception if `dlt` cannot find your bigquery credentials. In the exception below all of them ('project_id', 'private_key', 'client_email') are missing. The exception gives you also the list of all lookups for configuration performed - [here we explain how to read such list](run-a-pipeline.md#missing-secret-or-configuration-values).
+
+```
+dlt.common.configuration.exceptions.ConfigFieldMissingException: Following fields are missing: ['project_id', 'private_key', 'client_email'] in configuration with spec GcpServiceAccountCredentials
+        for field "project_id" config providers and keys were tried in following order:
+                In Environment Variables key WEATHERAPI__DESTINATION__BIGQUERY__CREDENTIALS__PROJECT_ID was not found.
+                In Environment Variables key WEATHERAPI__DESTINATION__CREDENTIALS__PROJECT_ID was not found.
+```
+
+The most common cases for the exception:
+
+1. The secrets are not in `secrets.toml` at all
+2. The are placed in wrong section. For example the fragment below will not work:
+
+```toml
+[destination.bigquery]
+project_id = "project_id" # please set me up!
+```
+
+3. You run the pipeline script from the **different** folder from which it is saved. For example `python weatherapi_demo/weatherapi.py` will run the script from `weatherapi_demo` folder but the current working directory is folder above. This prevents `dlt` from finding `weatherapi_demo/.dlt/secrets.toml` and filling-in credentials.
+
+### Placeholders still in secrets.toml
+
+Here BigQuery complain that the format of the `private_key` is incorrect. Practically this most often happens if you forgot to replace the placeholders in `secrets.toml` with real values
+
+```
+<class 'dlt.destinations.exceptions.DestinationConnectionError'>
+Connection with BigQuerySqlClient to dataset name weatherapi_data failed. Please check if you configured the credentials at all and provided the right credentials values. You can be also denied access or your internet connection may be down. The actual reason given is: No key could be detected.
+```
+
+### Bigquery not enabled
+
+[You must enable Bigquery API.](https://console.cloud.google.com/apis/dashboard)
+
+```
+<class 'google.api_core.exceptions.Forbidden'>
+403 POST https://bigquery.googleapis.com/bigquery/v2/projects/bq-walkthrough/jobs?prettyPrint=false: BigQuery API has not been used in project 364286133232 before or it is disabled. Enable it by visiting https://console.developers.google.com/apis/api/bigquery.googleapis.com/overview?project=364286133232 then retry. If you enabled this API recently, wait a few minutes for the action to propagate to our systems and retry.
+
+Location: EU
+Job ID: a5f84253-3c10-428b-b2c8-1a09b22af9b2
+ [{'@type': 'type.googleapis.com/google.rpc.Help', 'links': [{'description': 'Google developers console API activation', 'url': 'https://console.developers.google.com/apis/api/bigquery.googleapis.com/overview?project=364286133232'}]}, {'@type': 'type.googleapis.com/google.rpc.ErrorInfo', 'reason': 'SERVICE_DISABLED', 'domain': 'googleapis.com', 'metadata': {'service': 'bigquery.googleapis.com', 'consumer': 'projects/364286133232'}}]
+```
+
+### Lack of permissions to create jobs
+
+Add `BigQuery Job User` as described in the [destination page](../destinations/bigquery.md).
+
+```
+<class 'google.api_core.exceptions.Forbidden'>
+403 POST https://bigquery.googleapis.com/bigquery/v2/projects/bq-walkthrough/jobs?prettyPrint=false: Access Denied: Project bq-walkthrough: User does not have bigquery.jobs.create permission in project bq-walkthrough.
+
+Location: EU
+Job ID: c1476d2c-883c-43f7-a5fe-73db195e7bcd
+```
+
+### Lack of permissions to query/write data
+
+Add `BigQuery Data Editor` as described in the [destination page](../destinations/bigquery.md).
+
+```
+<class 'dlt.destinations.exceptions.DatabaseTransientException'>
+403 Access Denied: Table bq-walkthrough:weatherapi_data._dlt_loads: User does not have permission to query table bq-walkthrough:weatherapi_data._dlt_loads, or perhaps it does not exist in location EU.
+
+Location: EU
+Job ID: 299a92a3-7761-45dd-a433-79fdeb0c1a46
+```
+
+### Lack of billing / BigQuery in sandbox mode
+
+`dlt` does not support BigQuery when project has no billing enabled. If you see a stack trace where following warning appears:
+
+```
+<class 'dlt.destinations.exceptions.DatabaseTransientException'>
+403 Billing has not been enabled for this project. Enable billing at https://console.cloud.google.com/billing. DML queries are not allowed in the free tier. Set up a billing account to remove this restriction.
+```
+
+or
+
+```
+2023-06-08 16:16:26,769|[WARNING              ]|8096|dlt|load.py|complete_jobs:198|Job for weatherapi_resource_83b8ac9e98_4_jsonl retried in load 1686233775.932288 with message {"error_result":{"reason":"billingNotEnabled","message":"Billing has not been enabled for this project. Enable billing at https://console.cloud.google.com/billing. Table expiration time must be less than 60 days while in sandbox mode."},"errors":[{"reason":"billingNotEnabled","message":"Billing has not been enabled for this project. Enable billing at https://console.cloud.google.com/billing. Table expiration time must be less than 60 days while in sandbox mode."}],"job_start":"2023-06-08T14:16:26.850000Z","job_end":"2023-06-08T14:16:26.850000Z","job_id":"weatherapi_resource_83b8ac9e98_4_jsonl"}
+```
+
+you must enable the billing.
diff --git a/continuedev/src/continuedev/recipes/DDtoBQRecipe/main.py b/continuedev/src/continuedev/recipes/DDtoBQRecipe/main.py
new file mode 100644
index 00000000..cd1ff1b9
--- /dev/null
+++ b/continuedev/src/continuedev/recipes/DDtoBQRecipe/main.py
@@ -0,0 +1,27 @@
+from textwrap import dedent
+
+from ...core.main import Step
+from ...core.sdk import ContinueSDK
+from ...steps.core.core import WaitForUserInputStep
+from ...steps.main import MessageStep
+from .steps import SetUpChessPipelineStep, SwitchDestinationStep, LoadDataStep
+
+# Based on the following guide:
+# https://github.com/dlt-hub/dlt/pull/392
+
+
+class DDtoBQRecipeRecipe(Step):
+    hide: bool = True
+
+    async def run(self, sdk: ContinueSDK):
+        await sdk.run_step(
+            MessageStep(name="Move from using DuckDB to Google BigQuery as the destination", message=dedent("""\
+                This recipe will walk you through the process of moving from using DuckDB to Google BigQuery as the destination for your dlt pipeline. With the help of Continue, you will:
+                - Set up a dlt pipeline for the chess.com API
+                - Switch destination from DuckDB to Google BigQuery
+                - Add BigQuery credentials to your secrets.toml file
+                - Run the pipeline again to load data to BigQuery""")) >>
+            SetUpChessPipelineStep() >>
+            SwitchDestinationStep() >>
+            LoadDataStep()
+        )
diff --git a/continuedev/src/continuedev/recipes/DDtoBQRecipe/steps.py b/continuedev/src/continuedev/recipes/DDtoBQRecipe/steps.py
new file mode 100644
index 00000000..c7e5d095
--- /dev/null
+++ b/continuedev/src/continuedev/recipes/DDtoBQRecipe/steps.py
@@ -0,0 +1,100 @@
+import os
+import subprocess
+from textwrap import dedent
+import time
+
+from ...steps.find_and_replace import FindAndReplaceStep
+from ...models.main import Range
+from ...models.filesystem import RangeInFile
+from ...steps.main import MessageStep
+from ...core.sdk import Models
+from ...core.observation import DictObservation, InternalErrorObservation
+from ...models.filesystem_edit import AddFile, FileEdit
+from ...core.main import Step
+from ...core.sdk import ContinueSDK
+
+AI_ASSISTED_STRING = "(✨ AI-Assisted ✨)"
+
+
+class SetUpChessPipelineStep(Step):
+    hide: bool = True
+    name: str = "Setup Chess.com API dlt Pipeline"
+
+    async def describe(self, models: Models):
+        return "This step will create a new dlt pipeline that loads data from the chess.com API."
+
+    async def run(self, sdk: ContinueSDK):
+
+        # running commands to get started when creating a new dlt pipeline
+        await sdk.run([
+            'python3 -m venv env',
+            'source env/bin/activate',
+            'pip install dlt',
+            'dlt --non-interactive init chess duckdb',
+            'pip install -r requirements.txt',
+        ], name="Set up Python environment", description=dedent(f"""\
+            Running the following commands:
+            - `python3 -m venv env`: Create a Python virtual environment
+            - `source env/bin/activate`: Activate the virtual environment
+            - `pip install dlt`: Install dlt
+            - `dlt init chess duckdb`: Create a new dlt pipeline called "chess" that loads data into a local DuckDB instance
+            - `pip install -r requirements.txt`: Install the Python dependencies for the pipeline"""))
+
+
+class SwitchDestinationStep(Step):
+    hide: bool = True
+
+    async def run(self, sdk: ContinueSDK):
+
+        # Switch destination from DuckDB to Google BigQuery
+        filepath = os.path.join(
+            sdk.ide.workspace_directory, 'chess_pipeline.py')
+        await sdk.run_step(FindAndReplaceStep(filepath=filepath, pattern="destination='duckdb'", replacement="destination='bigquery'"))
+
+        # Add BigQuery credentials to your secrets.toml file
+        template = dedent(f"""\
+            [destination.bigquery.credentials]
+            location = "US"  # change the location of the data
+            project_id = "project_id" # please set me up!
+            private_key = "private_key" # please set me up!
+            client_email = "client_email" # please set me up!""")
+
+        # wait for user to put API key in secrets.toml
+        secrets_path = os.path.join(
+            sdk.ide.workspace_directory, ".dlt/secrets.toml")
+        await sdk.ide.setFileOpen(secrets_path)
+        await sdk.append_to_file(secrets_path, template)
+
+        # append template to bottom of secrets.toml
+        await sdk.wait_for_user_confirmation("Please add your GCP credentials to `secrets.toml` file and then press `Continue`")
+
+
+class LoadDataStep(Step):
+    name: str = "Load data to BigQuery"
+    hide: bool = True
+
+    async def run(self, sdk: ContinueSDK):
+        # Run the pipeline again to load data to BigQuery
+        output = await sdk.run('env/bin/python3 chess_pipeline.py', name="Load data to BigQuery", description="Running `env/bin/python3 chess_pipeline.py` to load data to Google BigQuery")
+
+        if "Traceback" in output or "SyntaxError" in output:
+            with open(os.path.join(os.path.dirname(__file__), "dlt_duckdb_to_bigquery_docs.md"), "r") as f:
+                docs = f.read()
+
+            output = "Traceback" + output.split("Traceback")[-1]
+            suggestion = sdk.models.gpt35.complete(dedent(f"""\
+                When trying to load data into BigQuery, the following error occurred:
+
+                ```ascii
+                {output}
+                ```
+
+                Here is documentation describing common errors and their causes/solutions:
+
+                {docs}
+
+                This is a brief summary of the error followed by a suggestion on how it can be fixed:"""))
+
+            sdk.raise_exception(
+                title="Error while running query", message=output, with_step=MessageStep(name=f"Suggestion to solve error {AI_ASSISTED_STRING}", message=suggestion)
+            )
diff --git a/continuedev/src/continuedev/steps/find_and_replace.py b/continuedev/src/continuedev/steps/find_and_replace.py
index 78511b27..c9654867 100644
--- a/continuedev/src/continuedev/steps/find_and_replace.py
+++ b/continuedev/src/continuedev/steps/find_and_replace.py
@@ -19,7 +19,8 @@ class FindAndReplaceStep(Step):
             end_index = start_index + len(self.pattern)
             await sdk.ide.applyFileSystemEdit(FileEdit(
                 filepath=self.filepath,
-                range=Range.from_indices(file_content, start_index, end_index),
+                range=Range.from_indices(
+                    file_content, start_index, end_index - 1),
                 replacement=self.replacement
             ))
             file_content = file_content[:start_index] + \
diff --git a/continuedev/src/continuedev/steps/steps_on_startup.py b/continuedev/src/continuedev/steps/steps_on_startup.py
index 2586eb03..80a57f76 100644
--- a/continuedev/src/continuedev/steps/steps_on_startup.py
+++ b/continuedev/src/continuedev/steps/steps_on_startup.py
@@ -1,6 +1,7 @@
 from ..core.main import ContinueSDK, Models, Step
 from .main import UserInputStep
 from ..recipes.CreatePipelineRecipe.main import CreatePipelineRecipe
+from ..recipes.DDtoBQRecipe.main import DDtoBQRecipeRecipe
 from ..recipes.DeployPipelineAirflowRecipe.main import DeployPipelineAirflowRecipe
 from ..recipes.DDtoBQRecipe.main import DDtoBQRecipe
 from ..recipes.AddTransformRecipe.main import AddTransformRecipe
@@ -8,6 +9,7 @@ from ..recipes.AddTransformRecipe.main import AddTransformRecipe
 step_name_to_step_class = {
     "UserInputStep": UserInputStep,
     "CreatePipelineRecipe": CreatePipelineRecipe,
+    "DDtoBQRecipeRecipe": DDtoBQRecipeRecipe,
     "DeployPipelineAirflowRecipe": DeployPipelineAirflowRecipe,
     "AddTransformRecipe": AddTransformRecipe,
     "DDtoBQRecipe": DDtoBQRecipe