diff options
32 files changed, 803 insertions, 46 deletions
diff --git a/continuedev/src/continuedev/core/abstract_sdk.py b/continuedev/src/continuedev/core/abstract_sdk.py index 1c800875..417971cd 100644 --- a/continuedev/src/continuedev/core/abstract_sdk.py +++ b/continuedev/src/continuedev/core/abstract_sdk.py @@ -1,10 +1,10 @@ -from abc import ABC, abstractmethod +from abc import ABC, abstractmethod, abstractproperty from typing import Coroutine, List, Union from .config import ContinueConfig from ..models.filesystem_edit import FileSystemEdit from .observation import Observation -from .main import History, Step +from .main import ChatMessage, History, Step, ChatMessageRole """ @@ -83,3 +83,11 @@ class AbstractContinueSDK(ABC): @abstractmethod def set_loading_message(self, message: str): pass + + @abstractmethod + def add_chat_context(self, content: str, role: ChatMessageRole = "assistent"): + pass + + @abstractproperty + def chat_context(self) -> List[ChatMessage]: + pass diff --git a/continuedev/src/continuedev/core/autopilot.py b/continuedev/src/continuedev/core/autopilot.py index b82e1fef..c979d53a 100644 --- a/continuedev/src/continuedev/core/autopilot.py +++ b/continuedev/src/continuedev/core/autopilot.py @@ -35,6 +35,7 @@ class Autopilot(ContinueBaseModel): class Config: arbitrary_types_allowed = True + keep_untouched = (cached_property,) def get_full_state(self) -> FullState: return FullState(history=self.history, active=self._active, user_input_queue=self._main_user_input_queue) diff --git a/continuedev/src/continuedev/core/main.py b/continuedev/src/continuedev/core/main.py index 37d80de3..3053e5a1 100644 --- a/continuedev/src/continuedev/core/main.py +++ b/continuedev/src/continuedev/core/main.py @@ -1,10 +1,17 @@ -from typing import Callable, Coroutine, Dict, Generator, List, Tuple, Union +from textwrap import dedent +from typing import Callable, Coroutine, Dict, Generator, List, Literal, Tuple, Union from ..models.main import ContinueBaseModel from pydantic import validator -from ..libs.llm import LLM from .observation import Observation +ChatMessageRole = Literal["assistant", "user", "system"] + + +class ChatMessage(ContinueBaseModel): + role: ChatMessageRole + content: str + class HistoryNode(ContinueBaseModel): """A point in history, a list of which make up History""" @@ -12,12 +19,24 @@ class HistoryNode(ContinueBaseModel): observation: Union[Observation, None] depth: int + def to_chat_messages(self) -> List[ChatMessage]: + if self.step.description is None: + return self.step.chat_context + return self.step.chat_context + [ChatMessage(role="assistant", content=self.step.description)] + class History(ContinueBaseModel): """A history of steps taken and their results""" timeline: List[HistoryNode] current_index: int + def to_chat_history(self) -> List[ChatMessage]: + msgs = [] + for node in self.timeline: + if not node.step.hide: + msgs += node.to_chat_messages() + return msgs + def add_node(self, node: HistoryNode): self.timeline.insert(self.current_index + 1, node) self.current_index += 1 @@ -113,6 +132,7 @@ class Step(ContinueBaseModel): description: Union[str, None] = None system_message: Union[str, None] = None + chat_context: List[ChatMessage] = [] class Config: copy_on_model_validation = False diff --git a/continuedev/src/continuedev/core/policy.py b/continuedev/src/continuedev/core/policy.py index 0b0c0fcd..6a183598 100644 --- a/continuedev/src/continuedev/core/policy.py +++ b/continuedev/src/continuedev/core/policy.py @@ -3,14 +3,18 @@ from typing import List, Tuple, Type from ..steps.chroma import AnswerQuestionChroma, EditFileChroma, CreateCodebaseIndexChroma from ..steps.steps_on_startup import StepsOnStartupStep from ..recipes.CreatePipelineRecipe.main import CreatePipelineRecipe +from ..recipes.DeployPipelineAirflowRecipe.main import DeployPipelineAirflowRecipe +from ..recipes.AddTransformRecipe.main import AddTransformRecipe from .main import Step, Validator, History, Policy from .observation import Observation, TracebackObservation, UserInputObservation -from ..steps.main import EditHighlightedCodeStep, SolveTracebackStep, RunCodeStep, FasterEditHighlightedCodeStep, StarCoderEditHighlightedCodeStep, MessageStep, EmptyStep, SetupContinueWorkspaceStep +from ..steps.main import EditHighlightedCodeStep, SolveTracebackStep, RunCodeStep, FasterEditHighlightedCodeStep, StarCoderEditHighlightedCodeStep, EmptyStep, SetupContinueWorkspaceStep from ..recipes.WritePytestsRecipe.main import WritePytestsRecipe from ..recipes.ContinueRecipeRecipe.main import ContinueStepStep from ..steps.comment_code import CommentCodeStep from ..steps.react import NLDecisionStep from ..steps.chat import SimpleChatStep +from ..recipes.DDtoBQRecipe.main import DDtoBQRecipe +from ..steps.core.core import MessageStep class DemoPolicy(Policy): @@ -34,6 +38,17 @@ class DemoPolicy(Policy): elif "/dlt" in user_input.lower() or " dlt" in user_input.lower(): return CreatePipelineRecipe() elif "/comment" in user_input.lower(): + if "/pytest" in observation.user_input.lower(): + return WritePytestsRecipe(instructions=observation.user_input) + elif "/dlt" in observation.user_input.lower(): + return CreatePipelineRecipe() + elif "/ddtobq" in observation.user_input.lower(): + return DDtoBQRecipe() + elif "/airflow" in observation.user_input.lower(): + return DeployPipelineAirflowRecipe() + elif "/transform" in observation.user_input.lower(): + return AddTransformRecipe() + elif "/comment" in observation.user_input.lower(): return CommentCodeStep() elif "/ask" in user_input: return AnswerQuestionChroma(question=" ".join(user_input.split(" ")[1:])) diff --git a/continuedev/src/continuedev/core/sdk.py b/continuedev/src/continuedev/core/sdk.py index ea90a13a..59bfc0f2 100644 --- a/continuedev/src/continuedev/core/sdk.py +++ b/continuedev/src/continuedev/core/sdk.py @@ -14,7 +14,7 @@ from ..libs.llm.hf_inference_api import HuggingFaceInferenceAPI from ..libs.llm.openai import OpenAI from .observation import Observation from ..server.ide_protocol import AbstractIdeProtocolServer -from .main import Context, ContinueCustomException, History, Step +from .main import Context, ContinueCustomException, History, Step, ChatMessage, ChatMessageRole from ..steps.core.core import * @@ -77,9 +77,9 @@ class ContinueSDK(AbstractContinueSDK): async def wait_for_user_confirmation(self, prompt: str): return await self.run_step(WaitForUserConfirmationStep(prompt=prompt)) - async def run(self, commands: Union[List[str], str], cwd: str = None, name: str = None, description: str = None) -> Coroutine[str, None, None]: + async def run(self, commands: Union[List[str], str], cwd: str = None, name: str = None, description: str = None, handle_error: bool = True) -> Coroutine[str, None, None]: commands = commands if isinstance(commands, List) else [commands] - return (await self.run_step(ShellCommandsStep(cmds=commands, cwd=cwd, description=description, **({'name': name} if name else {})))).text + return (await self.run_step(ShellCommandsStep(cmds=commands, cwd=cwd, description=description, handle_error=handle_error, **({'name': name} if name else {})))).text async def edit_file(self, filename: str, prompt: str, name: str = None, description: str = None, range: Range = None): filepath = await self._ensure_absolute_path(filename) @@ -136,3 +136,11 @@ class ContinueSDK(AbstractContinueSDK): def raise_exception(self, message: str, title: str, with_step: Union[Step, None] = None): raise ContinueCustomException(message, title, with_step) + + def add_chat_context(self, content: str, role: ChatMessageRole = "assistent"): + self.history.timeline[self.history.current_index].step.chat_context.append( + ChatMessage(content=content, role=role)) + + @property + def chat_context(self) -> List[ChatMessage]: + return self.history.to_chat_history() diff --git a/continuedev/src/continuedev/libs/llm/__init__.py b/continuedev/src/continuedev/libs/llm/__init__.py index 6bae2222..24fd34be 100644 --- a/continuedev/src/continuedev/libs/llm/__init__.py +++ b/continuedev/src/continuedev/libs/llm/__init__.py @@ -1,4 +1,6 @@ -from typing import Union +from typing import List, Union + +from ...core.main import ChatMessage from ...models.main import AbstractModel from pydantic import BaseModel @@ -6,7 +8,7 @@ from pydantic import BaseModel class LLM(BaseModel): system_message: Union[str, None] = None - def complete(self, prompt: str, **kwargs): + def complete(self, prompt: str, with_history: List[ChatMessage] = [], **kwargs): """Return the completion of the text with the given temperature.""" raise diff --git a/continuedev/src/continuedev/libs/llm/hf_inference_api.py b/continuedev/src/continuedev/libs/llm/hf_inference_api.py index 734da160..1586c620 100644 --- a/continuedev/src/continuedev/libs/llm/hf_inference_api.py +++ b/continuedev/src/continuedev/libs/llm/hf_inference_api.py @@ -1,3 +1,5 @@ +from typing import List +from ...core.main import ChatMessage from ..llm import LLM import requests @@ -9,7 +11,7 @@ class HuggingFaceInferenceAPI(LLM): api_key: str model: str = "bigcode/starcoder" - def complete(self, prompt: str, **kwargs): + def complete(self, prompt: str, with_history: List[ChatMessage] = [], **kwargs): """Return the completion of the text with the given temperature.""" API_URL = f"https://api-inference.huggingface.co/models/{self.model}" headers = { diff --git a/continuedev/src/continuedev/libs/llm/openai.py b/continuedev/src/continuedev/libs/llm/openai.py index 10801465..6a537afd 100644 --- a/continuedev/src/continuedev/libs/llm/openai.py +++ b/continuedev/src/continuedev/libs/llm/openai.py @@ -1,6 +1,7 @@ import asyncio import time from typing import Any, Dict, Generator, List, Union +from ...core.main import ChatMessage import openai import aiohttp from ..llm import LLM @@ -62,7 +63,7 @@ class OpenAI(LLM): for chunk in generator: yield chunk.choices[0].text - def complete(self, prompt: str, **kwargs) -> str: + def complete(self, prompt: str, with_history: List[ChatMessage] = [], **kwargs) -> str: t1 = time.time() self.completion_count += 1 @@ -70,15 +71,17 @@ class OpenAI(LLM): "frequency_penalty": 0, "presence_penalty": 0, "stream": False} | kwargs if args["model"] == "gpt-3.5-turbo": - messages = [{ - "role": "user", - "content": prompt - }] + messages = [] if self.system_message: - messages.insert(0, { + messages.append({ "role": "system", "content": self.system_message }) + messages += [msg.dict() for msg in with_history] + messages.append({ + "role": "user", + "content": prompt + }) resp = openai.ChatCompletion.create( messages=messages, **args, diff --git a/continuedev/src/continuedev/recipes/AddTransformRecipe/README.md b/continuedev/src/continuedev/recipes/AddTransformRecipe/README.md new file mode 100644 index 00000000..d735e0cd --- /dev/null +++ b/continuedev/src/continuedev/recipes/AddTransformRecipe/README.md @@ -0,0 +1,8 @@ +# AddTransformRecipe
+
+Uses the Chess.com API example to show how to add map and filter Python transforms to a dlt pipeline.
+
+Background
+- https://dlthub.com/docs/general-usage/resource#filter-transform-and-pivot-data
+- https://dlthub.com/docs/customizations/customizing-pipelines/renaming_columns
+- https://dlthub.com/docs/customizations/customizing-pipelines/pseudonymizing_columns
\ No newline at end of file diff --git a/continuedev/src/continuedev/recipes/AddTransformRecipe/dlt_transform_docs.md b/continuedev/src/continuedev/recipes/AddTransformRecipe/dlt_transform_docs.md new file mode 100644 index 00000000..658b285f --- /dev/null +++ b/continuedev/src/continuedev/recipes/AddTransformRecipe/dlt_transform_docs.md @@ -0,0 +1,135 @@ +# Customize resources +## Filter, transform and pivot data + +You can attach any number of transformations that are evaluated on item per item basis to your resource. The available transformation types: +- map - transform the data item (resource.add_map) +- filter - filter the data item (resource.add_filter) +- yield map - a map that returns iterator (so single row may generate many rows - resource.add_yield_map) + +Example: We have a resource that loads a list of users from an api endpoint. We want to customize it so: +- we remove users with user_id == 'me' +- we anonymize user data +Here's our resource: +```python +import dlt + +@dlt.resource(write_disposition='replace') +def users(): + ... + users = requests.get(...) + ... + yield users +``` + +Here's our script that defines transformations and loads the data. +```python +from pipedrive import users + +def anonymize_user(user_data): + user_data['user_id'] = hash_str(user_data['user_id']) + user_data['user_email'] = hash_str(user_data['user_email']) + return user_data + +# add the filter and anonymize function to users resource and enumerate +for user in users().add_filter(lambda user: user['user_id'] != 'me').add_map(anonymize_user): +print(user) +``` + +Here is a more complex example of a filter transformation: + + # Renaming columns + ## Renaming columns by replacing the special characters + + In the example below, we create a dummy source with special characters in the name. We then write a function that we intend to apply to the resource to modify its output (i.e. replacing the German umlaut): replace_umlauts_in_dict_keys. + ```python + import dlt + + # create a dummy source with umlauts (special characters) in key names (um) + @dlt.source + def dummy_source(prefix: str = None): + @dlt.resource + def dummy_data(): + for _ in range(100): + yield {f'Objekt_{_}':{'Größe':_, 'Äquivalenzprüfung':True}} + return dummy_data(), + + def replace_umlauts_in_dict_keys(d): + # Replaces umlauts in dictionary keys with standard characters. + umlaut_map = {'ä': 'ae', 'ö': 'oe', 'ü': 'ue', 'ß': 'ss', 'Ä': 'Ae', 'Ö': 'Oe', 'Ü': 'Ue'} + result = {} + for k, v in d.items(): + new_key = ''.join(umlaut_map.get(c, c) for c in k) + if isinstance(v, dict): + result[new_key] = replace_umlauts_in_dict_keys(v) + else: + result[new_key] = v + return result + + # We can add the map function to the resource + + # 1. Create an instance of the source so you can edit it. + data_source = dummy_source() + + # 2. Modify this source instance's resource + data_source = data_source.dummy_data().add_map(replace_umlauts_in_dict_keys) + + # 3. Inspect your result + for row in data_source: + print(row) + + # {'Objekt_0': {'Groesse': 0, 'Aequivalenzpruefung': True}} + # ... + ``` + +Here is a more complex example of a map transformation: + +# Pseudonymizing columns +## Pseudonymizing (or anonymizing) columns by replacing the special characters +Pseudonymization is a deterministic way to hide personally identifiable info (PII), enabling us to consistently achieve the same mapping. If instead you wish to anonymize, you can delete the data, or replace it with a constant. In the example below, we create a dummy source with a PII column called 'name', which we replace with deterministic hashes (i.e. replacing the German umlaut). + +```python +import dlt +import hashlib + +@dlt.source +def dummy_source(prefix: str = None): + @dlt.resource + def dummy_data(): + for _ in range(3): + yield {'id':_, 'name': f'Jane Washington {_}'} + return dummy_data(), + +def pseudonymize_name(doc): + Pseudonmyisation is a deterministic type of PII-obscuring + Its role is to allow identifying users by their hash, without revealing the underlying info. + + # add a constant salt to generate + salt = 'WI@N57%zZrmk#88c' + salted_string = doc['name'] + salt + sh = hashlib.sha256() + sh.update(salted_string.encode()) + hashed_string = sh.digest().hex() + doc['name'] = hashed_string + return doc + + # run it as is + for row in dummy_source().dummy_data().add_map(pseudonymize_name): + print(row) + + #{'id': 0, 'name': '96259edb2b28b48bebce8278c550e99fbdc4a3fac8189e6b90f183ecff01c442'} + #{'id': 1, 'name': '92d3972b625cbd21f28782fb5c89552ce1aa09281892a2ab32aee8feeb3544a1'} + #{'id': 2, 'name': '443679926a7cff506a3b5d5d094dc7734861352b9e0791af5d39db5a7356d11a'} + + # Or create an instance of the data source, modify the resource and run the source. + + # 1. Create an instance of the source so you can edit it. + data_source = dummy_source() + # 2. Modify this source instance's resource + data_source = data_source.dummy_data().add_map(replace_umlauts_in_dict_keys) + # 3. Inspect your result + for row in data_source: + print(row) + + pipeline = dlt.pipeline(pipeline_name='example', destination='bigquery', dataset_name='normalized_data') + load_info = pipeline.run(data_source) +```
\ No newline at end of file diff --git a/continuedev/src/continuedev/recipes/AddTransformRecipe/main.py b/continuedev/src/continuedev/recipes/AddTransformRecipe/main.py new file mode 100644 index 00000000..e9a998e3 --- /dev/null +++ b/continuedev/src/continuedev/recipes/AddTransformRecipe/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.core.core import MessageStep +from .steps import SetUpChessPipelineStep, AddTransformStep + + +class AddTransformRecipe(Step): + hide: bool = True + + async def run(self, sdk: ContinueSDK): + text_observation = await sdk.run_step( + MessageStep(message=dedent("""\ + This recipe will walk you through the process of adding a transform to a dlt pipeline that uses the chess.com API source. With the help of Continue, you will: + - Set up a dlt pipeline for the chess.com API + - Add a filter or map transform to the pipeline + - Run the pipeline and view the transformed data in a Streamlit app"""), name="Add transformation to a dlt pipeline") >> + SetUpChessPipelineStep() >> + WaitForUserInputStep( + prompt="How do you want to transform the Chess.com API data before loading it? For example, you could use the `python-chess` library to decode the moves or filter out certain games") + ) + await sdk.run_step( + AddTransformStep( + transform_description=text_observation.text) + ) diff --git a/continuedev/src/continuedev/recipes/AddTransformRecipe/steps.py b/continuedev/src/continuedev/recipes/AddTransformRecipe/steps.py new file mode 100644 index 00000000..7bb0fc23 --- /dev/null +++ b/continuedev/src/continuedev/recipes/AddTransformRecipe/steps.py @@ -0,0 +1,89 @@ +import os +from textwrap import dedent + +from ...models.main import Range +from ...models.filesystem import RangeInFile +from ...steps.core.core import MessageStep +from ...core.sdk import Models +from ...core.observation import DictObservation +from ...models.filesystem_edit import AddFile +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', + 'pip install pandas streamlit' # Needed for the pipeline show step later + ], 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 AddTransformStep(Step): + hide: bool = True + + # e.g. "Use the `python-chess` library to decode the moves in the game data" + transform_description: str + + async def run(self, sdk: ContinueSDK): + source_name = 'chess' + filename = f'{source_name}_pipeline.py' + abs_filepath = os.path.join(sdk.ide.workspace_directory, filename) + + await sdk.run_step(MessageStep(message=dedent("""\ + This step will customize your resource function with a transform of your choice: + - Add a filter or map transformation depending on your request + - Load the data into a local DuckDB instance + - Open up a Streamlit app for you to view the data"""), name="Write transformation function")) + + # Open the file and highlight the function to be edited + await sdk.ide.setFileOpen(abs_filepath) + await sdk.ide.highlightCode(range_in_file=RangeInFile( + filepath=abs_filepath, + range=Range.from_shorthand(47, 0, 51, 0) + )) + + with open(os.path.join(os.path.dirname(__file__), 'dlt_transform_docs.md')) as f: + dlt_transform_docs = f.read() + + prompt = dedent(f"""\ + Task: Write a transform function using the description below and then use `add_map` or `add_filter` from the `dlt` library to attach it a resource. + + Description: {self.transform_description} + + Here are some docs pages that will help you better understand how to use `dlt`. + + {dlt_transform_docs}""") + + # edit the pipeline to add a tranform function and attach it to a resource + await sdk.edit_file( + filename=filename, + prompt=prompt, + name=f"Writing transform function {AI_ASSISTED_STRING}" + ) + + # run the pipeline and load the data + await sdk.run(f'python3 {filename}', name="Run the pipeline", description=f"Running `python3 {filename}` to load the data into a local DuckDB instance") + + # run a streamlit app to show the data + await sdk.run(f'dlt pipeline {source_name}_pipeline show', name="Show data in a Streamlit app", description=f"Running `dlt pipeline {source_name} show` to show the data in a Streamlit app, where you can view and play with the data.") diff --git a/continuedev/src/continuedev/recipes/CreatePipelineRecipe/main.py b/continuedev/src/continuedev/recipes/CreatePipelineRecipe/main.py index 39e1ba42..818168ba 100644 --- a/continuedev/src/continuedev/recipes/CreatePipelineRecipe/main.py +++ b/continuedev/src/continuedev/recipes/CreatePipelineRecipe/main.py @@ -3,7 +3,7 @@ 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.core.core import MessageStep from .steps import SetupPipelineStep, ValidatePipelineStep, RunQueryStep diff --git a/continuedev/src/continuedev/recipes/CreatePipelineRecipe/steps.py b/continuedev/src/continuedev/recipes/CreatePipelineRecipe/steps.py index 3b9a8c85..e59cc51c 100644 --- a/continuedev/src/continuedev/recipes/CreatePipelineRecipe/steps.py +++ b/continuedev/src/continuedev/recipes/CreatePipelineRecipe/steps.py @@ -5,7 +5,7 @@ import time from ...models.main import Range from ...models.filesystem import RangeInFile -from ...steps.main import MessageStep +from ...steps.core.core import MessageStep from ...core.sdk import Models from ...core.observation import DictObservation, InternalErrorObservation from ...models.filesystem_edit import AddFile, FileEdit @@ -51,7 +51,7 @@ class SetupPipelineStep(Step): # editing the resource function to call the requested API resource_function_range = Range.from_shorthand(15, 0, 29, 0) - await sdk.ide.highlightCode(RangeInFile(filepath=os.path.join(await sdk.ide.getWorkspaceDirectory(), filename), range=resource_function_range), "#00ff0022") + await sdk.ide.highlightCode(RangeInFile(filepath=os.path.join(await sdk.ide.getWorkspaceDirectory(), filename), range=resource_function_range)) # sdk.set_loading_message("Writing code to call the API...") await sdk.edit_file( @@ -86,7 +86,7 @@ class ValidatePipelineStep(Step): # """))) # test that the API call works - output = await sdk.run(f'python3 {filename}', name="Test the pipeline", description=f"Running `python3 {filename}` to test loading data from the API") + output = await sdk.run(f'python3 {filename}', name="Test the pipeline", description=f"Running `python3 {filename}` to test loading data from the API", handle_error=False) # If it fails, return the error if "Traceback" in output or "SyntaxError" in output: @@ -157,7 +157,7 @@ class RunQueryStep(Step): hide: bool = True async def run(self, sdk: ContinueSDK): - output = await sdk.run('env/bin/python3 query.py', name="Run test query", description="Running `env/bin/python3 query.py` to test that the data was loaded into DuckDB as expected") + output = await sdk.run('env/bin/python3 query.py', name="Run test query", description="Running `env/bin/python3 query.py` to test that the data was loaded into DuckDB as expected", handle_error=False) if "Traceback" in output or "SyntaxError" in output: suggestion = sdk.models.gpt35.complete(dedent(f"""\ 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..1ae84310 --- /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.core.core import MessageStep +from .steps import SetUpChessPipelineStep, SwitchDestinationStep, LoadDataStep + +# Based on the following guide: +# https://github.com/dlt-hub/dlt/pull/392 + + +class DDtoBQRecipe(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..5cf89ccf --- /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.core.core 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/recipes/DeployPipelineAirflowRecipe/README.md b/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/README.md new file mode 100644 index 00000000..e69de29b --- /dev/null +++ b/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/README.md diff --git a/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/main.py b/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/main.py new file mode 100644 index 00000000..f3601c2d --- /dev/null +++ b/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/main.py @@ -0,0 +1,50 @@ +from textwrap import dedent + +from ...steps.input.nl_multiselect import NLMultiselectStep +from ...core.main import Step +from ...core.sdk import ContinueSDK +from ...steps.core.core import WaitForUserInputStep +from ...steps.core.core import MessageStep +from .steps import SetupPipelineStep, DeployAirflowStep + + +# https://github.com/dlt-hub/dlt-deploy-template/blob/master/airflow-composer/dag_template.py +# https://www.notion.so/dlthub/Deploy-a-pipeline-with-Airflow-245fd1058652479494307ead0b5565f3 +# 1. What verified pipeline do you want to deploy with Airflow? +# 2. Set up selected verified pipeline +# 3. Deploy selected verified pipeline with Airflow +# 4. Set up Airflow locally? + +class DeployPipelineAirflowRecipe(Step): + hide: bool = True + + async def run(self, sdk: ContinueSDK): + source_name = await sdk.run_step( + MessageStep(name="Deploying a pipeline to Airflow", message=dedent("""\ + This recipe will show you how to deploy a pipeline to Airflow. With the help of Continue, you will: + - Select a dlt-verified pipeline + - Setup the pipeline + - Deploy it to Airflow + - Optionally, setup Airflow locally""")) >> + NLMultiselectStep( + prompt=dedent("""\ + Which verified pipeline do you want to deploy with Airflow? The options are: + - Asana + - Chess.com + - GitHub + - Google Analytics + - Google Sheets + - HubSpot + - Matomo + - Pipedrive + - Shopify + - Strapi + - Zendesk"""), + options=[ + "asana_dlt", "chess", "github", "google_analytics", "google_sheets", "hubspot", "matomo", "pipedrive", "shopify_dlt", "strapi", "zendesk" + ]) + ) + await sdk.run_step( + SetupPipelineStep(source_name=source_name) >> + DeployAirflowStep(source_name=source_name) + ) diff --git a/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/steps.py b/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/steps.py new file mode 100644 index 00000000..4a128786 --- /dev/null +++ b/continuedev/src/continuedev/recipes/DeployPipelineAirflowRecipe/steps.py @@ -0,0 +1,92 @@ +import os +import subprocess +from textwrap import dedent +import time + +from ...steps.core.core import WaitForUserInputStep +from ...models.main import Range +from ...models.filesystem import RangeInFile +from ...steps.core.core 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 +from ...steps.find_and_replace import FindAndReplaceStep + +AI_ASSISTED_STRING = "(✨ AI-Assisted ✨)" + + +class SetupPipelineStep(Step): + hide: bool = True + name: str = "Setup dlt Pipeline" + + source_name: str + + async def describe(self, models: Models): + pass + + async def run(self, sdk: ContinueSDK): + await sdk.run([ + 'python3 -m venv env', + 'source env/bin/activate', + 'pip install dlt', + f'dlt --non-interactive init {self.source_name} duckdb', + 'pip install -r requirements.txt' + ], 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 {self.source_name} duckdb`: Create a new dlt pipeline called {self.source_name} that loads data into a local DuckDB instance + - `pip install -r requirements.txt`: Install the Python dependencies for the pipeline"""), name="Setup Python environment") + + +class RunPipelineStep(Step): + hide: bool = True + name: str = "Run dlt Pipeline" + + source_name: str + + async def describe(self, models: Models): + pass + + async def run(self, sdk: ContinueSDK): + await sdk.run([ + f'python3 {self.source_name}_pipeline.py', + ], description=dedent(f"""\ + Running the command `python3 {self.source_name}_pipeline.py to run the pipeline: """), name="Run dlt pipeline") + + +class DeployAirflowStep(Step): + hide: bool = True + source_name: str + + async def run(self, sdk: ContinueSDK): + + # Run dlt command to deploy pipeline to Airflow + await sdk.run([ + f'dlt --non-interactive deploy {self.source_name}_pipeline.py airflow-composer', + ], description="Running `dlt deploy airflow` to deploy the dlt pipeline to Airflow", name="Deploy dlt pipeline to Airflow") + + # Modify the DAG file + directory = await sdk.ide.getWorkspaceDirectory() + filepath = os.path.join( + directory, f"dags/dag_{self.source_name}_pipeline.py") + + # Replace the pipeline name and dataset name + await sdk.run_step(FindAndReplaceStep(filepath=filepath, pattern="'pipeline_name'", replacement=f"'{self.source_name}_pipeline'")) + await sdk.run_step(FindAndReplaceStep(filepath=filepath, pattern="'dataset_name'", replacement=f"'{self.source_name}_data'")) + await sdk.run_step(FindAndReplaceStep(filepath=filepath, pattern="pipeline_or_source_script", replacement=f"{self.source_name}_pipeline")) + + # Prompt the user for the DAG schedule + edit_dag_range = Range.from_shorthand(18, 0, 23, 0) + await sdk.ide.highlightCode(range_in_file=RangeInFile(filepath=filepath, range=edit_dag_range), color="#33993333") + response = await sdk.run_step(WaitForUserInputStep(prompt="When would you like this Airflow DAG to run? (e.g. every day, every Monday, every 1st of the month, etc.)")) + await sdk.edit_file(filepath, prompt=f"Edit the DAG so that it runs at the following schedule: '{response.text}'", + range=edit_dag_range) + + # Tell the user to check the schedule and fill in owner, email, other default_args + await sdk.run_step(MessageStep(message="Fill in the owner, email, and other default_args in the DAG file with your own personal information.", name="Fill in default_args")) + + # Run the DAG locally ?? diff --git a/continuedev/src/continuedev/server/ide.py b/continuedev/src/continuedev/server/ide.py index 5826f15f..f4ea1071 100644 --- a/continuedev/src/continuedev/server/ide.py +++ b/continuedev/src/continuedev/server/ide.py @@ -138,7 +138,7 @@ class IdeProtocolServer(AbstractIdeProtocolServer): "sessionId": session_id }) - async def highlightCode(self, range_in_file: RangeInFile, color: str): + async def highlightCode(self, range_in_file: RangeInFile, color: str = "#00ff0022"): await self._send_json("highlightCode", { "rangeInFile": range_in_file.dict(), "color": color diff --git a/continuedev/src/continuedev/steps/core/core.py b/continuedev/src/continuedev/steps/core/core.py index dfd765eb..53df65cc 100644 --- a/continuedev/src/continuedev/steps/core/core.py +++ b/continuedev/src/continuedev/steps/core/core.py @@ -1,4 +1,5 @@ # These steps are depended upon by ContinueSDK +import os import subprocess from textwrap import dedent from typing import Coroutine, List, Union @@ -23,6 +24,17 @@ class ReversibleStep(Step): raise NotImplementedError +class MessageStep(Step): + name: str = "Message" + message: str + + async def describe(self, models: Models) -> Coroutine[str, None, None]: + return self.message + + async def run(self, sdk: ContinueSDK) -> Coroutine[Observation, None, None]: + return TextObservation(text=self.message) + + class FileSystemEditStep(ReversibleStep): edit: FileSystemEdit _diff: Union[EditDiff, None] = None @@ -38,10 +50,18 @@ class FileSystemEditStep(ReversibleStep): # Where and when should file saves happen? +def output_contains_error(output: str) -> bool: + return "Traceback" in output or "SyntaxError" in output + + +AI_ASSISTED_STRING = "(✨ AI-Assisted ✨)" + + class ShellCommandsStep(Step): cmds: List[str] cwd: Union[str, None] = None name: str = "Run Shell Commands" + handle_error: bool = True _err_text: Union[str, None] = None @@ -50,13 +70,26 @@ class ShellCommandsStep(Step): return f"Error when running shell commands:\n```\n{self._err_text}\n```" cmds_str = "\n".join(self.cmds) - return (await models.gpt35()).complete(f"{cmds_str}\n\nSummarize what was done in these shell commands, using markdown bullet points:") + return models.gpt35.complete(f"{cmds_str}\n\nSummarize what was done in these shell commands, using markdown bullet points:") async def run(self, sdk: ContinueSDK) -> Coroutine[Observation, None, None]: cwd = await sdk.ide.getWorkspaceDirectory() if self.cwd is None else self.cwd for cmd in self.cmds: output = await sdk.ide.runCommand(cmd) + if self.handle_error and output is not None and output_contains_error(output): + suggestion = sdk.models.gpt35.complete(dedent(f"""\ + While running the command `{cmd}`, the following error occurred: + + ```ascii + {output} + ``` + + This is a brief summary of the error followed by a suggestion on how it can be fixed:"""), with_history=sdk.chat_context) + + sdk.raise_exception( + title="Error while running query", message=output, with_step=MessageStep(name=f"Suggestion to solve error {AI_ASSISTED_STRING}", message=suggestion) + ) return TextObservation(text=output) @@ -116,7 +149,7 @@ class Gpt35EditCodeStep(Step): _prompt_and_completion: str = "" async def describe(self, models: Models) -> Coroutine[str, None, None]: - return (await models.gpt35()).complete(f"{self._prompt_and_completion}\n\nPlease give brief a description of the changes made above using markdown bullet points:") + return models.gpt35.complete(f"{self._prompt_and_completion}\n\nPlease give brief a description of the changes made above using markdown bullet points:") async def run(self, sdk: ContinueSDK) -> Coroutine[Observation, None, None]: rif_with_contents = [] diff --git a/continuedev/src/continuedev/steps/find_and_replace.py b/continuedev/src/continuedev/steps/find_and_replace.py new file mode 100644 index 00000000..fec33997 --- /dev/null +++ b/continuedev/src/continuedev/steps/find_and_replace.py @@ -0,0 +1,28 @@ +from ..models.filesystem_edit import FileEdit, Range +from ..core.main import Models, Step +from ..core.sdk import ContinueSDK + + +class FindAndReplaceStep(Step): + name: str = "Find and replace" + filepath: str + pattern: str + replacement: str + + async def describe(self, models: Models): + return f"Replace all instances of `{self.pattern}` with `{self.replacement}` in `{self.filepath}`" + + async def run(self, sdk: ContinueSDK): + file_content = await sdk.ide.readFile(self.filepath) + while self.pattern in file_content: + start_index = file_content.index(self.pattern) + 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 - 1), + replacement=self.replacement + )) + file_content = file_content[:start_index] + \ + self.replacement + file_content[end_index:] + await sdk.ide.saveFile(self.filepath) diff --git a/continuedev/src/continuedev/steps/input/nl_multiselect.py b/continuedev/src/continuedev/steps/input/nl_multiselect.py new file mode 100644 index 00000000..c3c832f5 --- /dev/null +++ b/continuedev/src/continuedev/steps/input/nl_multiselect.py @@ -0,0 +1,27 @@ +from typing import List, Union +from ..core.core import WaitForUserInputStep +from ...core.main import Step +from ...core.sdk import ContinueSDK + + +class NLMultiselectStep(Step): + hide: bool = True + + prompt: str + options: List[str] + + async def run(self, sdk: ContinueSDK): + user_response = (await sdk.run_step(WaitForUserInputStep(prompt=self.prompt))).text + + def extract_option(text: str) -> Union[str, None]: + for option in self.options: + if option in text: + return option + return None + + first_try = extract_option(user_response.lower()) + if first_try is not None: + return first_try + + gpt_parsed = await sdk.models.gpt35.complete(f"These are the available options are: [{', '.join(self.options)}]. The user requested {user_response}. This is the exact string from the options array that they selected:") + return extract_option(gpt_parsed) or self.options[0] diff --git a/continuedev/src/continuedev/steps/main.py b/continuedev/src/continuedev/steps/main.py index 81a1e3a9..24335b4f 100644 --- a/continuedev/src/continuedev/steps/main.py +++ b/continuedev/src/continuedev/steps/main.py @@ -212,7 +212,7 @@ class StarCoderEditHighlightedCodeStep(Step): _prompt_and_completion: str = "" async def describe(self, models: Models) -> Coroutine[str, None, None]: - return (await models.gpt35()).complete(f"{self._prompt_and_completion}\n\nPlease give brief a description of the changes made above using markdown bullet points:") + return models.gpt35.complete(f"{self._prompt_and_completion}\n\nPlease give brief a description of the changes made above using markdown bullet points:") async def run(self, sdk: ContinueSDK) -> Coroutine[Observation, None, None]: range_in_files = await sdk.ide.getHighlightedCode() @@ -317,17 +317,6 @@ class SolveTracebackStep(Step): return None -class MessageStep(Step): - name: str = "Message" - message: str - - async def describe(self, models: Models) -> Coroutine[str, None, None]: - return self.message - - async def run(self, sdk: ContinueSDK) -> Coroutine[Observation, None, None]: - return TextObservation(text=self.message) - - class EmptyStep(Step): hide: bool = True diff --git a/continuedev/src/continuedev/steps/steps_on_startup.py b/continuedev/src/continuedev/steps/steps_on_startup.py index cd40ff56..eae8b558 100644 --- a/continuedev/src/continuedev/steps/steps_on_startup.py +++ b/continuedev/src/continuedev/steps/steps_on_startup.py @@ -1,11 +1,18 @@ from ..core.main import ContinueSDK, Models, Step from .main import UserInputStep from ..recipes.CreatePipelineRecipe.main import CreatePipelineRecipe - +from ..recipes.DDtoBQRecipe.main import DDtoBQRecipe +from ..recipes.DeployPipelineAirflowRecipe.main import DeployPipelineAirflowRecipe +from ..recipes.DDtoBQRecipe.main import DDtoBQRecipe +from ..recipes.AddTransformRecipe.main import AddTransformRecipe step_name_to_step_class = { "UserInputStep": UserInputStep, - "CreatePipelineRecipe": CreatePipelineRecipe + "CreatePipelineRecipe": CreatePipelineRecipe, + "DDtoBQRecipe": DDtoBQRecipe, + "DeployPipelineAirflowRecipe": DeployPipelineAirflowRecipe, + "AddTransformRecipe": AddTransformRecipe, + "DDtoBQRecipe": DDtoBQRecipe } diff --git a/docs/docs/walkthroughs/create-a-recipe.md b/docs/docs/walkthroughs/create-a-recipe.md index 60bfe9a8..3b80df8a 100644 --- a/docs/docs/walkthroughs/create-a-recipe.md +++ b/docs/docs/walkthroughs/create-a-recipe.md @@ -17,8 +17,6 @@ continue/continuedev/src/continuedev/recipes ## 1. Create a step
-
-
### a. Start by creating a subclass of Step
You should first consider what will be the parameters of your recipe. These are defined as attributes in the step, as with `input_file_path: str` below
@@ -33,7 +31,7 @@ If you'd like to override the default description of your steps, which is just t - Return a static string
- Store state in a class attribute (prepend with a double underscore, which signifies (through Pydantic) that this is not a parameter for the Step, just internal state) during the run method, and then grab this in the describe method.
-- Use state in conjunction with the `models` parameter of the describe method to autogenerate a description with a language model. For example, if you'd used an attribute called `__code_written` to store a string representing some code that was written, you could implement describe as `return (await models.gpt35()).complete(f"{self.\_\_code_written}\n\nSummarize the changes made in the above code.")`.
+- Use state in conjunction with the `models` parameter of the describe method to autogenerate a description with a language model. For example, if you'd used an attribute called `__code_written` to store a string representing some code that was written, you could implement describe as `return models.gpt35.complete(f"{self.\_\_code_written}\n\nSummarize the changes made in the above code.")`.
## 2. Compose steps together into a complete recipe
diff --git a/extension/package-lock.json b/extension/package-lock.json index 061b6342..aebd0803 100644 --- a/extension/package-lock.json +++ b/extension/package-lock.json @@ -1,12 +1,12 @@ { "name": "continue", - "version": "0.0.25", + "version": "0.0.34", "lockfileVersion": 2, "requires": true, "packages": { "": { "name": "continue", - "version": "0.0.25", + "version": "0.0.34", "license": "Apache-2.0", "dependencies": { "@electron/rebuild": "^3.2.10", diff --git a/extension/package.json b/extension/package.json index 66ade224..1d2fd995 100644 --- a/extension/package.json +++ b/extension/package.json @@ -14,7 +14,7 @@ "displayName": "Continue", "pricing": "Free", "description": "Refine code 10x faster", - "version": "0.0.25", + "version": "0.0.34", "publisher": "Continue", "engines": { "vscode": "^1.74.0" diff --git a/extension/scripts/continuedev-0.1.1-py3-none-any.whl b/extension/scripts/continuedev-0.1.1-py3-none-any.whl Binary files differindex 4c89d23e..42f3d4a3 100644 --- a/extension/scripts/continuedev-0.1.1-py3-none-any.whl +++ b/extension/scripts/continuedev-0.1.1-py3-none-any.whl diff --git a/extension/src/terminal/terminalEmulator.ts b/extension/src/terminal/terminalEmulator.ts index 67b47e2f..b3031baf 100644 --- a/extension/src/terminal/terminalEmulator.ts +++ b/extension/src/terminal/terminalEmulator.ts @@ -74,7 +74,7 @@ export class CapturedTerminal { if ( lines.length > 0 && (lines[lines.length - 1].includes("bash-") || - lines[lines.length - 1].includes("(main)")) && + lines[lines.length - 1].includes(") $ ")) && lines[lines.length - 1].includes("$") ) { resolve(this.dataBuffer); |