tumblrbot 1.4.7__py3-none-any.whl → 1.6.0__py3-none-any.whl

tumblrbot/__main__.py

@@ -19,8 +19,12 @@ def main() -> None:
         if Confirm.ask("Download latest posts?", default=False):
             PostDownloader(openai=openai, tumblr=tumblr).main()
 
+        examples_writer = ExamplesWriter(openai=openai, tumblr=tumblr)
         if Confirm.ask("Create training data?", default=False):
-            ExamplesWriter(openai=openai, tumblr=tumblr).main()
+            examples_writer.main()
+
+        if Confirm.ask("Remove training data flagged by the OpenAI moderation? [bold]This can sometimes resolve errors with fine-tuning validation, but is slow.", default=False):
+            examples_writer.filter_examples()
 
         fine_tuner = FineTuner(openai=openai, tumblr=tumblr)
         fine_tuner.print_estimates()

tumblrbot/flow/download.py

@@ -36,18 +36,18 @@ class PostDownloader(FlowClass):
         task_id = live.progress.add_task(f"Downloading posts from '{blog_identifier}'...", total=None, completed=completed)
 
         while True:
-            response = self.tumblr.retrieve_published_posts(blog_identifier, after=after).json()["response"]
-            live.progress.update(task_id, total=response["blog"]["posts"], completed=completed)
+            response = self.tumblr.retrieve_published_posts(blog_identifier, after=after)
+            live.progress.update(task_id, total=response.response.blog.posts, completed=completed)
 
-            if posts := response["posts"]:
-                for post in posts:
-                    dump(post, fp)
-                    fp.write("\n")
+            if not response.response.posts:
+                return
 
-                    model = Post.model_validate(post)
-                    after = model.timestamp
-                    live.custom_update(model)
+            for post in response.response.posts:
+                dump(post, fp)
+                fp.write("\n")
 
-                completed += len(posts)
-            else:
-                return
+                model = Post.model_validate(post)
+                after = model.timestamp
+                live.custom_update(model)
+
+            completed += len(response.response.posts)

tumblrbot/flow/examples.py

@@ -7,7 +7,6 @@ from typing import IO, override
 
 import rich
 from openai import BadRequestError
-from rich.prompt import Confirm
 
 from tumblrbot.utils.common import FlowClass, PreviewLive
 from tumblrbot.utils.models import Example, Post
@@ -26,7 +25,7 @@ class ExamplesWriter(FlowClass):
                     fp,
                 )
 
-            for post in self.get_filtered_posts():
+            for post in self.get_valid_posts():
                 self.write_example(
                     self.config.user_message,
                     post.get_content_text(),
@@ -54,38 +53,33 @@ class ExamplesWriter(FlowClass):
                 data: dict[str, str] = loads(line)
                 yield from data.items()
 
-    def get_filtered_posts(self) -> Generator[Post]:
-        posts = self.get_valid_posts()
+    def get_valid_posts(self) -> Generator[Post]:
+        for data_path in self.get_data_paths():
+            with data_path.open("rb") as fp:
+                for line in fp:
+                    post = Post.model_validate_json(line)
+                    if post.valid_text_post():
+                        yield post
 
-        if Confirm.ask("[gray62]Remove posts flagged by the OpenAI moderation? This can sometimes resolve errors with fine-tuning validation, but is slow.", default=False):
+    def filter_examples(self) -> None:
+        examples = self.config.examples_file.read_text("utf_8").splitlines()
+        with self.config.examples_file.open("w", encoding="utf_8") as fp:
             batch_size = self.get_moderation_batch_size()
-            posts = list(posts)
             removed = 0
 
             with PreviewLive() as live:
                 for batch in live.progress.track(
-                    batched(posts, batch_size, strict=False),
-                    ceil(len(posts) / batch_size),
+                    batched(examples, batch_size, strict=False),
+                    ceil(len(examples) / batch_size),
                     description="Removing flagged posts...",
                 ):
-                    response = self.openai.moderations.create(input=list(map(Post.get_content_text, batch)))
-                    for post, moderation in zip(batch, response.results, strict=True):
+                    response = self.openai.moderations.create(input=list(batch))
+                    for example, moderation in zip(batch, response.results, strict=True):
                         if moderation.flagged:
                             removed += 1
-                            live.custom_update(post)
                         else:
-                            yield post
+                            fp.write(f"{example}\n")
             rich.print(f"[red]Removed {removed} posts.\n")
-        else:
-            yield from posts
-
-    def get_valid_posts(self) -> Generator[Post]:
-        for data_path in self.get_data_paths():
-            with data_path.open("rb") as fp:
-                for line in fp:
-                    post = Post.model_validate_json(line)
-                    if post.valid_text_post():
-                        yield post
 
     def get_moderation_batch_size(self) -> int:
         try:

tumblrbot/flow/generate.py

@@ -1,4 +1,4 @@
-from random import random
+from random import random, randrange
 from typing import override
 
 import rich
@@ -28,28 +28,47 @@ class DraftGenerator(FlowClass):
         rich.print(f":chart_increasing: [bold green]Generated {self.config.draft_count} draft(s).[/] {message}")
 
     def generate_post(self) -> Post:
-        content = self.generate_content()
-        post = Post(content=[content])
-        if tags := self.generate_tags(content):
-            post.tags = tags.tags
-        return post
-
-    def generate_content(self) -> Post.Block:
-        content = self.openai.responses.create(
-            input=self.config.user_message,
+        if random() < self.config.reblog_chance:  # noqa: S311
+            original = self.get_random_post()
+            user_message = f"{self.config.reblog_user_message}\n\n{original.get_content_text()}"
+        else:
+            original = Post()
+            user_message = self.config.user_message
+
+        text = self.generate_text(user_message)
+        if tags := self.generate_tags(text):
+            tags = tags.tags
+        return Post(
+            content=[Post.Block(type="text", text=text)],
+            tags=tags or [],
+            state="draft",
+            parent_tumblelog_uuid=original.blog.uuid,
+            parent_post_id=original.id,
+            reblog_key=original.reblog_key,
+        )
+
+    def generate_text(self, user_message: str) -> str:
+        return self.openai.responses.create(
+            input=user_message,
             instructions=self.config.developer_message,
             model=self.config.fine_tuned_model,
         ).output_text
 
-        return Post.Block(text=content)
-
-    def generate_tags(self, content: Post.Block) -> Post | None:
+    def generate_tags(self, text: str) -> Post | None:
         if random() < self.config.tags_chance:  # noqa: S311
             return self.openai.responses.parse(
                 text_format=Post,
-                input=content.text,
+                input=text,
                 instructions=self.config.tags_developer_message,
                 model=self.config.base_model,
             ).output_parsed
 
         return None
+
+    def get_random_post(self) -> Post:
+        total = self.tumblr.retrieve_blog_info(self.config.upload_blog_identifier).response.blog.posts
+        post = self.tumblr.retrieve_published_posts(
+            self.config.upload_blog_identifier,
+            offset=randrange(total),  # noqa: S311
+        ).response.posts[0]
+        return Post.model_validate(post)

tumblrbot/utils/models.py

@@ -74,6 +74,8 @@ class Config(FileSyncSettings):
     draft_count: PositiveInt = Field(150, description="The number of drafts to process. This will affect the number of tokens used with OpenAI")
     tags_chance: NonNegativeFloat = Field(0.1, description="The chance to generate tags for any given post. This will incur extra calls to OpenAI.")
     tags_developer_message: str = Field("You will be provided with a block of text, and your task is to extract a very short list of the most important subjects from it.", description="The developer message used to generate tags.")
+    reblog_chance: NonNegativeFloat = Field(0.05, description="The chance to generate a reblog of a random post.")
+    reblog_user_message: str = Field("Please write a comical Tumblr post in response to the following Tumblr post:", description="The prefix for the user message used to reblog posts.")
 
     @classmethod
     @override
@@ -100,7 +102,7 @@ class Config(FileSyncSettings):
 
             toml_table[name] = value
 
-        Path(self.toml_file).write_text(tomlkit.dumps(toml_table), encoding="utf_8")
+        self.toml_file.write_text(tomlkit.dumps(toml_table), encoding="utf_8")
 
         return self
 
@@ -170,15 +172,34 @@ class Tokens(FileSyncSettings):
         return self
 
 
+class Blog(FullyValidatedModel):
+    posts: int = 0
+    uuid: str = ""
+
+
+class ResponseModel(FullyValidatedModel):
+    class Response(FullyValidatedModel):
+        blog: Blog = Blog()
+        posts: list[Any] = []
+
+    response: Response
+
+
 class Post(FullyValidatedModel):
     class Block(FullyValidatedModel):
-        type: str = "text"
+        type: str = ""
         text: str = ""
         blocks: list[int] = []
 
+    blog: SkipJsonSchema[Blog] = Blog()
+    id: SkipJsonSchema[int] = 0
+    parent_tumblelog_uuid: SkipJsonSchema[str] = ""
+    parent_post_id: SkipJsonSchema[int] = 0
+    reblog_key: SkipJsonSchema[str] = ""
+
     timestamp: SkipJsonSchema[int] = 0
     tags: Annotated[list[str], PlainSerializer(",".join)] = []
-    state: SkipJsonSchema[Literal["published", "queued", "draft", "private", "unapproved"]] = "draft"
+    state: SkipJsonSchema[Literal["published", "queued", "draft", "private", "unapproved"]] = "published"
 
     content: SkipJsonSchema[list[Block]] = []
     layout: SkipJsonSchema[list[Block]] = []

tumblrbot/utils/tumblr.py

@@ -3,7 +3,7 @@ from typing import Self
 from requests import HTTPError, Response
 from requests_oauthlib import OAuth1Session
 
-from tumblrbot.utils.models import Post, Tokens
+from tumblrbot.utils.models import Post, ResponseModel, Tokens
 
 
 class TumblrSession(OAuth1Session):
@@ -22,18 +22,25 @@ class TumblrSession(OAuth1Session):
             error.add_note(response.text)
             raise
 
-    def retrieve_published_posts(self, blog_identifier: str, after: int) -> Response:
-        return self.get(
+    def retrieve_blog_info(self, blog_identifier: str) -> ResponseModel:
+        response = self.get(f"https://api.tumblr.com/v2/blog/{blog_identifier}/info")
+        return ResponseModel.model_validate_json(response.text)
+
+    def retrieve_published_posts(self, blog_identifier: str, offset: int | None = None, after: int | None = None) -> ResponseModel:
+        response = self.get(
             f"https://api.tumblr.com/v2/blog/{blog_identifier}/posts",
             params={
+                "offset": offset,
                 "after": after,
                 "sort": "asc",
                 "npf": True,
             },
         )
+        return ResponseModel.model_validate_json(response.text)
 
-    def create_post(self, blog_identifier: str, post: Post) -> Response:
-        return self.post(
+    def create_post(self, blog_identifier: str, post: Post) -> ResponseModel:
+        response = self.post(
             f"https://api.tumblr.com/v2/blog/{blog_identifier}/posts",
             json=post.model_dump(),
         )
+        return ResponseModel.model_validate_json(response.text)

{tumblrbot-1.4.7.dist-info → tumblrbot-1.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tumblrbot
-Version: 1.4.7
+Version: 1.6.0
 Summary: An updated bot that posts to Tumblr, based on your very own blog!
 Requires-Python: >= 3.13
 Description-Content-Type: text/markdown
@@ -13,6 +13,7 @@ Requires-Dist: requests-oauthlib
 Requires-Dist: rich
 Requires-Dist: tiktoken
 Requires-Dist: tomlkit
+Project-URL: Funding, https://ko-fi.com/maidscientistizutsumimarin
 Project-URL: Source, https://github.com/MaidScientistIzutsumiMarin/tumblrbot
 
 # tumblrbot
@@ -30,8 +31,8 @@ Project-URL: Source, https://github.com/MaidScientistIzutsumiMarin/tumblrbot
 [OpenAI]: https://pypi.org/project/openai
 [OpenAI Pricing]: https://platform.openai.com/docs/pricing#fine-tuning
 [OpenAI Tokens]: https://platform.openai.com/settings/organization/api-keys
+[OpenAI Moderation API]: https://platform.openai.com/docs/guides/moderation
 [Fine-Tuning Portal]: https://platform.openai.com/finetune
-[Moderation API]: https://platform.openai.com/docs/api-reference/moderations
 
 [Tumblr]: https://tumblr.com
 [Tumblr Tokens]: https://tumblr.com/oauth/apps
@@ -62,9 +63,8 @@ Features:
       - Shows progress and previews the current post.
    1. [Creates examples][Examples] to fine-tune the model from your posts.
       - 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.
       - Adds custom user messages and assistant responses to the dataset from the [configured][config] file.
+   1. Filters out any posts flagged by the [OpenAI Moderation API].
    1. [Uploads examples][Fine-Tune] to [OpenAI] and begins the fine-tuning process.
       - Provides cost estimates if the currently saved examples are used to fine-tune the [configured][config] model.
       - Resumes monitoring the same fine-tuning process when restarted.
@@ -73,13 +73,14 @@ Features:
    1. [Generates and uploads posts][Generate] to the [configured][config] [Tumblr] blog using the [configured][config] fine-tuned model.
       - Creates tags by extracting keywords at the [configured][config] frequency using the [configured][config] model.
       - Uploads posts as drafts to the [configured][config] [Tumblr] blog.
+      - Reblog posts at the [configured][config] frequency.
       - Shows progress and previews the current post.
 - Colorful output, progress bars, and post previews using [rich].
 - Automatically keeps the [config] file up-to-date and recreates it if missing.
 
 **To-Do:**
 
-- Add code documentation.
+- ...
 
 **Known Issues:**
 

tumblrbot-1.6.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+tumblrbot/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tumblrbot/__main__.py,sha256=XWSbOmI_y2MJVU9xpkgA-0zaF3HNwR5uF6_BZqtCQWY,1719
+tumblrbot/flow/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tumblrbot/flow/download.py,sha256=PUs7eM-1kGOb2RKijy3lW0zyvfFDwbxzTGhVghrWIhc,2012
+tumblrbot/flow/examples.py,sha256=MlukrVdzpIwk_-37PpRsBGV5eX-lLlNUUYvuozXC_vw,3726
+tumblrbot/flow/fine_tune.py,sha256=YDukEwZNw3GveEAH4ORv6oylka5MQNLK_4iSmuAVPtg,5387
+tumblrbot/flow/generate.py,sha256=GPWd2dBFQa8t1vH9C3gDs8d8mGvLkKuFjDlYC7s0PnM,3001
+tumblrbot/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tumblrbot/utils/common.py,sha256=RvICPORtBSqsN7VWADgStogJ8w4owzBfR1E2XbCQrfA,1795
+tumblrbot/utils/models.py,sha256=8A7gd4L0TZQwHJmD6YutV0WaIU_jkl39SRzO8OMrays,10429
+tumblrbot/utils/tumblr.py,sha256=NP_qRaB4A5cKcQdOErYhTqyQQcO3ffytULvQpQTtlM8,1725
+tumblrbot-1.6.0.dist-info/entry_points.txt,sha256=lTiN7PxAbyGY1fpCWApEw6NUIUgobfcOKhvn6cu3IQA,53
+tumblrbot-1.6.0.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
+tumblrbot-1.6.0.dist-info/METADATA,sha256=0QHZRZ8KNja_rCMmE4zflOHDjykl_JVkI6KZzSlulkM,10138
+tumblrbot-1.6.0.dist-info/RECORD,,

tumblrbot-1.4.7.dist-info/RECORD

@@ -1,15 +0,0 @@
-tumblrbot/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tumblrbot/__main__.py,sha256=BenjVNlVZDy-ZlSWukEIguGLa6qXvZjhYSSWMqa8-0Q,1447
-tumblrbot/flow/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tumblrbot/flow/download.py,sha256=wdXmtCnnArn8Zw7D2Hoa_KhH-k61j9w3cbYztgBkUlY,2036
-tumblrbot/flow/examples.py,sha256=Th6vgiu3D2VloOx7otZlk164h3ifkJEwDk21YHMEYP0,3976
-tumblrbot/flow/fine_tune.py,sha256=YDukEwZNw3GveEAH4ORv6oylka5MQNLK_4iSmuAVPtg,5387
-tumblrbot/flow/generate.py,sha256=Q6nUtmoj28-rGUCs4V0fuovJshvFMlmipyu9GGqnmzM,2147
-tumblrbot/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tumblrbot/utils/common.py,sha256=RvICPORtBSqsN7VWADgStogJ8w4owzBfR1E2XbCQrfA,1795
-tumblrbot/utils/models.py,sha256=Z0k16qJsZEO8tfmPp7X3edz-RgGCDLRSm7HrSDLGh1Y,9663
-tumblrbot/utils/tumblr.py,sha256=6V9AjT-dyR2vuUkfqgqs52Ua5irhQJzhgQhV54xKyGM,1258
-tumblrbot-1.4.7.dist-info/entry_points.txt,sha256=lTiN7PxAbyGY1fpCWApEw6NUIUgobfcOKhvn6cu3IQA,53
-tumblrbot-1.4.7.dist-info/WHEEL,sha256=G2gURzTEtmeR8nrdXUJfNiB3VYVxigPQ-bEQujpNiNs,82
-tumblrbot-1.4.7.dist-info/METADATA,sha256=q_PH1oU-d0PRdXDuL5Bjh-Y8gccZJVvLCCho2E_CLvc,10104
-tumblrbot-1.4.7.dist-info/RECORD,,