tumblrbot 1.3.0__tar.gz → 1.3.2__tar.gz

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tumblrbot
-Version: 1.3.0
+Version: 1.3.2
 Summary: An updated bot that posts to Tumblr, based on your very own blog!
 Requires-Python: >= 3.13
 Description-Content-Type: text/markdown
@@ -12,6 +12,7 @@ Requires-Dist: pydantic-settings
 Requires-Dist: requests
 Requires-Dist: requests-oauthlib
 Requires-Dist: rich
+Requires-Dist: tenacity
 Requires-Dist: tiktoken
 Requires-Dist: tomlkit
 Project-URL: Source, https://github.com/MaidThatPrograms/tumblrbot
@@ -57,7 +58,6 @@ Features:
       - Filters out posts that contain more than just text data.
       - Filters out any posts flagged by the [OpenAI] [Moderation API] (optional).
          - Shows progress and previews the current post.
-      - Formats asks as the user message and the responses as the assistant response.
       - Adds custom user messages and assistant responses to the dataset from the [configured][config] file.
    1. Provides cost estimates if the currently saved examples are used to fine-tune the [configured][config] model.
    1. [Uploads examples][Fine-Tune] to [OpenAI] and begins the fine-tuning process.
@@ -90,11 +90,14 @@ Features:
 Run `tumblrbot` from anywhere. Run `tumblrbot --help` for command-line options. Every command-line option corresponds to a value from the [config](#configuration).
 
 ## Obtaining Tokens
-- The [OpenAI] API token can be created [here](https://platform.openai.com/settings/organization/api-keys).
+### OpenAI
+API token can be created [here](https://platform.openai.com/settings/organization/api-keys).
    1. Leave everything at the defaults and set `Project` to `Default Project`.
    1. Press `Create secret key`.
    1. Press `Copy` to copy the API token to your clipboard.
-- The [Tumblr] API tokens can be created [here](https://tumblr.com/oauth/apps).
+
+### Tumblr
+API tokens can be created [here](https://tumblr.com/oauth/apps).
    1. Press `+ Register Application`.
    1. Enter anything for `Application Name` and `Application Description`.
    1. Enter any URL for `Application Website` and `Default callback URL`, like `https://example.com`.

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/README.md

@@ -39,7 +39,6 @@ Features:
       - Filters out posts that contain more than just text data.
       - Filters out any posts flagged by the [OpenAI] [Moderation API] (optional).
          - Shows progress and previews the current post.
-      - Formats asks as the user message and the responses as the assistant response.
       - Adds custom user messages and assistant responses to the dataset from the [configured][config] file.
    1. Provides cost estimates if the currently saved examples are used to fine-tune the [configured][config] model.
    1. [Uploads examples][Fine-Tune] to [OpenAI] and begins the fine-tuning process.
@@ -72,11 +71,14 @@ Features:
 Run `tumblrbot` from anywhere. Run `tumblrbot --help` for command-line options. Every command-line option corresponds to a value from the [config](#configuration).
 
 ## Obtaining Tokens
-- The [OpenAI] API token can be created [here](https://platform.openai.com/settings/organization/api-keys).
+### OpenAI
+API token can be created [here](https://platform.openai.com/settings/organization/api-keys).
    1. Leave everything at the defaults and set `Project` to `Default Project`.
    1. Press `Create secret key`.
    1. Press `Copy` to copy the API token to your clipboard.
-- The [Tumblr] API tokens can be created [here](https://tumblr.com/oauth/apps).
+
+### Tumblr
+API tokens can be created [here](https://tumblr.com/oauth/apps).
    1. Press `+ Register Application`.
    1. Enter anything for `Application Name` and `Application Description`.
    1. Enter any URL for `Application Website` and `Default callback URL`, like `https://example.com`.

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tumblrbot"
-version = "1.3.0"
+version = "1.3.2"
 description = "An updated bot that posts to Tumblr, based on your very own blog!"
 readme = "README.md"
 requires-python = ">= 3.13"
@@ -13,6 +13,7 @@ dependencies = [
   "requests",
   "requests-oauthlib",
   "rich",
+  "tenacity",
   "tiktoken",
   "tomlkit",
 ]

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/src/tumblrbot/flow/examples.py

@@ -53,7 +53,7 @@ class ExamplesWriter(FlowClass):
             with data_path.open(encoding="utf_8") as fp:
                 for line in fp:
                     post = Post.model_validate_json(line)
-                    if not (post.is_submission or post.trail) and post.only_text_blocks() and post.get_response_content():
+                    if not (post.is_submission or post.trail) and post.only_text_blocks() and post.get_content_text():
                         yield post
 
     def get_filtered_posts(self) -> Generator[Post]:
@@ -68,7 +68,7 @@ class ExamplesWriter(FlowClass):
                     ceil(len(posts) / chunk_size),
                     description="Removing flagged posts...",
                 ):
-                    response = self.openai.moderations.create(input=["\n".join(post.get_text_content()) for post in chunk])
+                    response = self.openai.moderations.create(input=list(map(Post.get_content_text, chunk)))
                     for post, moderation in zip(chunk, response.results, strict=True):
                         if moderation.flagged:
                             removed += 1
@@ -89,11 +89,9 @@ class ExamplesWriter(FlowClass):
 
         with self.config.examples_file.open("w", encoding="utf_8") as fp:
             for post in self.get_filtered_posts():
-                ask_content, response_content = post.get_text_content()
-
                 self.write_example(
-                    ask_content or self.config.user_message,
-                    response_content,
+                    self.config.user_message,
+                    post.get_content_text(),
                     fp,
                 )
 

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/src/tumblrbot/flow/fine_tune.py

@@ -4,7 +4,10 @@ from textwrap import dedent
 from time import sleep
 
 import rich
+from openai import BadRequestError
+from openai.types import FileObject
 from openai.types.fine_tuning import FineTuningJob
+from tenacity import retry, retry_if_exception_type, stop_after_attempt, wait_fixed, wait_random
 
 from tumblrbot.utils.common import FlowClass, PreviewLive
 
@@ -46,35 +49,46 @@ class FineTuner(FlowClass):
 
         return job
 
-    def create_job(self) -> FineTuningJob:
-        if self.config.job_id:
-            return self.poll_job_status()
-
-        file = self.openai.files.create(
-            file=self.config.examples_file,
-            purpose="fine-tune",
-        )
-        job = self.openai.fine_tuning.jobs.create(
+    @retry(
+        stop=stop_after_attempt(5),
+        wait=wait_fixed(1.5) + wait_random(),
+        retry=retry_if_exception_type(BadRequestError),
+        reraise=True,
+    )
+    def attempt_submit_job(self, file: FileObject) -> FineTuningJob:
+        return self.openai.fine_tuning.jobs.create(
             model=self.config.base_model,
             training_file=file.id,
         )
 
+    def create_job(self, live: PreviewLive) -> FineTuningJob:
+        if self.config.job_id:
+            return self.poll_job_status()
+
+        with live.progress.open(self.config.examples_file, "rb", description=f"Uploading {self.config.examples_file}...") as fp:
+            file = self.openai.files.create(
+                file=fp,
+                purpose="fine-tune",
+            )
+
+        job = self.attempt_submit_job(file)
+
         self.config.job_id = job.id
         return job
 
     def fine_tune(self) -> None:
-        job = self.create_job()
+        with PreviewLive() as live:
+            job = self.create_job(live)
 
-        self.dedent_print(f"""
-            [bold]Fine-tuning is starting...[/]
-            View it online at: https://platform.openai.com/finetune/{job.id}
-                Created at: {datetime.fromtimestamp(job.created_at)}
-                Base Model: {job.model}
+            self.dedent_print(f"""
+                [bold]Fine-tuning is starting...[/]
+                View it online at: https://platform.openai.com/finetune/{job.id}
+                    Created at: {datetime.fromtimestamp(job.created_at)}
+                    Base Model: {job.model}
 
-            [italic dim]Closing this terminal will not stop the fine-tuning. This will take a while...
-        """)  # noqa: DTZ006
+                [italic dim]Closing this terminal will not stop the fine-tuning. This will take a while...
+            """)  # noqa: DTZ006
 
-        with PreviewLive() as live:
             task_id = live.progress.add_task("", total=None)
 
             while job.status not in {"succeeded", "failed", "cancelled"}:
@@ -82,6 +96,7 @@ class FineTuner(FlowClass):
 
                 live.progress.update(
                     task_id,
+                    total=job.estimated_finish,
                     description=f"Fine-tuning: [italic]{job.status.replace('_', ' ').title()}[/]...",
                 )
 

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/src/tumblrbot/flow/generate.py

@@ -10,10 +10,10 @@ class DraftGenerator(FlowClass):
     def generate_tags(self, content: Post.Block) -> Post | None:
         if random() < self.config.tags_chance:  # noqa: S311
             return self.openai.responses.parse(
-                input=content.text,
+                input=f"Extract the most important subjects from the following text:\n\n{content.text}",
                 model=self.config.base_model,
                 text_format=Post,
-                instructions="You are an advanced text summarization tool. Extract the most important subjects.",
+                instructions="You are an advanced text summarization tool. You return the requested data to the user as a list of comma-separated strings.",
                 temperature=0.5,
             ).output_parsed
 

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/src/tumblrbot/utils/config.py

@@ -5,7 +5,7 @@ from typing import TYPE_CHECKING, Self, override
 import rich
 import tomlkit
 from openai.types import ChatModel
-from pydantic import Field, PositiveFloat, PositiveInt, Secret, model_validator
+from pydantic import Field, NonNegativeFloat, PositiveFloat, PositiveInt, Secret, model_validator
 from pydantic_settings import BaseSettings, PydanticBaseSettingsSource, SettingsConfigDict, TomlConfigSettingsSource
 from rich.prompt import Prompt
 from tomlkit import comment, document
@@ -32,7 +32,7 @@ class Config(BaseSettings):
         description="The identifier of the blog which generated drafts will be uploaded to. This must be a blog associated with the same account as the configured Tumblr secret tokens.",
     )
     draft_count: PositiveInt = Field(150, description="The number of drafts to process. This will affect the number of tokens used with OpenAI")
-    tags_chance: float = Field(0.1, description="The chance to generate tags for any given post. This will incur extra calls to OpenAI.")
+    tags_chance: NonNegativeFloat = Field(0.1, description="The chance to generate tags for any given post. This will incur extra calls to OpenAI.")
 
     download_blog_identifiers: list[str] = Field(
         [],
@@ -43,9 +43,9 @@ class Config(BaseSettings):
     examples_file: Path = Field(Path("examples.jsonl"), description="Where to output the examples that will be used to fine-tune the model.")
     job_id: str = Field("", description="The fine-tuning job ID that will be polled on next run.")
     expected_epochs: PositiveInt = Field(3, description="The expected number of epochs fine-tuning will be run for. This will be updated during fine-tuning.")
-    token_price: PositiveFloat = Field(1.50, description="The expected price in USD per million tokens during fine-tuning for the current model.")
+    token_price: PositiveFloat = Field(3, description="The expected price in USD per million tokens during fine-tuning for the current model.")
 
-    base_model: ChatModel = Field("gpt-4.1-nano-2025-04-14", description="The name of the model that will be fine-tuned by the generated training data.")
+    base_model: ChatModel = Field("gpt-4o-mini-2024-07-18", description="The name of the model that will be fine-tuned by the generated training data.")
     developer_message: str = Field("You are a Tumblr post bot. Please generate a Tumblr post in accordance with the user's request.", description="The developer message used by the OpenAI API to generate drafts.")
     user_message: str = Field("Please write a comical Tumblr post.", description="The user input used by the OpenAI API to generate drafts.")
 

{tumblrbot-1.3.0 → tumblrbot-1.3.2}/src/tumblrbot/utils/models.py

@@ -102,24 +102,16 @@ class Post(FullyValidatedModel):
 
     def __rich__(self) -> Panel:
         return Panel(
-            self.get_text_content(),
+            self.get_content_text(),
             title="Preview",
             subtitle=" ".join(f"#{tag}" for tag in self.tags),
             subtitle_align="left",
         )
 
-    @override
-    def model_post_init(self, context: object) -> None:
-        super().model_post_init(context)
-
-        indices: set[int] = set()
-        for block in self.layout:
-            if block.type == "ask":
-                indices.update(block.blocks)
-
-        self.content = [block for i, block in enumerate(self.content) if i not in indices and block.type == "text"]
+    def only_text_blocks(self) -> bool:
+        return all(block.type == "text" for block in self.content) and not any(block.type == "ask" for block in self.layout)
 
-    def get_text_content(self) -> str:
+    def get_content_text(self) -> str:
         return "\n\n".join(block.text for block in self.content)