chore: remove deprecated 'generate' and 'run_prompt' (#28)

* chore: remove deprecated 'generate' and 'run_prompt'

* lint

docs/examples.md

@@ -4,8 +4,6 @@
 - [Create a summarizer prompt](#create-a-summarizer-prompt)
 - [Lemmatize text while processing a template](#lemmatize-text-while-processing-a-template)
 - [Use a LLM to generate a text while rendering a prompt](#use-a-llm-to-generate-a-text-while-rendering-a-prompt)
-- [Go meta: create a prompt and `generate` its response](#go-meta-create-a-prompt-and-generate-its-response)
-- [Go meta(meta): process a LLM response](#go-metameta-process-a-llm-response)
 - [Render a prompt template as chat messages](#render-a-prompt-template-as-chat-messages)
 - [Use prompt caching from Anthropic](#use-prompt-caching-from-anthropic)
 - [Reuse templates from registries](#reuse-templates-from-registries)
@@ -184,75 +182,6 @@ Examples:
 > Banks uses a cache to avoid generating text again for the same template with the same context. By default
 > the cache is in-memory but it can be customized.
 
-## Go meta: create a prompt and `generate` its response
-
-We can leverage Jinja's macro system to generate a prompt, send the result to OpenAI and get a response.
-Let's bring back the blog writing example:
-
-```py
-from banks import Prompt
-
-prompt_template = """
-{% from "banks_macros.jinja" import run_prompt with context %}
-
-{%- call run_prompt() -%}
-Write a 500-word blog post on {{ topic }}
-
-Blog post:
-{%- endcall -%}
-"""
-
-p = Prompt(prompt_template)
-print(p.text({"topic": "climate change"}))
-```
-
-The snippet above won't print the prompt, instead will generate the prompt text
-
-```
-Write a 500-word blog post on climate change
-
-Blog post:
-```
-
-and will send it to OpenAI using the `generate` extension, eventually returning its response:
-
-```
-Climate change is a phenomenon that has been gaining attention in recent years...
-...
-```
-
-## Go meta(meta): process a LLM response
-
-When generating a response from a prompt template, we can take a step further and
-post-process the LLM response by assinging it to a variable and applying filters
-to it:
-
-```py
-from banks import Prompt
-
-prompt_template = """
-{% from "banks_macros.jinja" import run_prompt with context %}
-
-{%- set prompt_result %}
-{%- call run_prompt() -%}
-Write a 500-word blog post on {{ topic }}
-
-Blog post:
-{%- endcall -%}
-{%- endset %}
-
-{# nothing is returned at this point: the variable 'prompt_result' contains the result #}
-
-{# let's use the prompt_result variable now #}
-{{ prompt_result | upper }}
-"""
-
-p = Prompt(prompt_template)
-print(p.text({"topic": "climate change"}))
-```
-
-The final answer from the LLM will be printed, this time all in uppercase.
-
 ## Render a prompt template as chat messages
 
 You'll find yourself feeding an LLM a list of chat messages instead of plain text

docs/prompt.md

@@ -93,20 +93,3 @@ Macros are a way to implement complex logic in the template itself, think about
 code instead of Python. Banks provides a set of macros out of the box that are useful in prompt engineering,
 for example to generate a prompt and call OpenAI on-the-fly, during the template rendering.
 Before using Banks' macros, you have to import them in your templates, see the examples below.
-
-### `run_prompt`
-
-Similar to `generate`, `run_prompt` will call OpenAI passing the whole block content as the input. The block
-content can in turn contain Jinja tags, which makes this macro very powerful. In the example below, during
-the template rendering the value of `{{ topic }}` will be processed before sending the resulting block to
-`run_prompt`.
-
-```jinja
-{% from "banks_macros.jinja" import run_prompt with context %}
-
-{% call run_prompt() %}
-Write a 500-word blog post on {{ topic }}
-{% endcall %}
-```
-
-When the rendering is done, the entire `call` block will be replaced with OpenAI's response.

docs/python.md

@@ -16,47 +16,3 @@
 ::: banks.registries.redis.RedisPromptRegistry
     options:
       inherited_members: true
-
-## Default macros
-
-Banks' package comes with default template macros you can use in your prompts.
-
-
-### `run_prompt`
-
-
-We can use `run_prompt` in our templates to generate a prompt, send the result to the LLM and get a response.
-Take this prompt for example:
-
-```py
-from banks import Prompt
-
-prompt_template = """
-{% from "banks_macros.jinja" import run_prompt with context %}
-
-{%- call run_prompt() -%}
-Write a 500-word blog post on {{ topic }}
-
-Blog post:
-{%- endcall -%}
-"""
-
-p = Prompt(prompt_template)
-print(p.text({"topic": "climate change"}))
-```
-
-In this case, Banks will generate internally the prompt text
-
-```
-Write a 500-word blog post on climate change
-
-Blog post:
-```
-
-but instead of returning it, will send it to the LLM using the `generate` extension under the hood, eventually
-returning the final response:
-
-```
-Climate change is a phenomenon that has been gaining attention in recent years...
-...
-```

src/banks/env.py

@@ -1,7 +1,7 @@
 # SPDX-FileCopyrightText: 2023-present Massimiliano Pippi <[email protected]>
 #
 # SPDX-License-Identifier: MIT
-from jinja2 import Environment, PackageLoader, select_autoescape
+from jinja2 import Environment, select_autoescape
 
 from .config import config
 from .filters import cache_control, image, lemmatize, tool
@@ -15,16 +15,13 @@ def _add_extensions(_env):
     """
     from .extensions.chat import ChatExtension  # pylint: disable=import-outside-toplevel
     from .extensions.completion import CompletionExtension  # pylint: disable=import-outside-toplevel
-    from .extensions.generate import GenerateExtension  # pylint: disable=import-outside-toplevel
 
     _env.add_extension(ChatExtension)
     _env.add_extension(CompletionExtension)
-    _env.add_extension(GenerateExtension)
 
 
 # Init the Jinja env
 env = Environment(
-    loader=PackageLoader("banks", "internal"),
     autoescape=select_autoescape(
         enabled_extensions=("html", "xml"),
         default_for_string=False,

src/banks/extensions/docs.py

@@ -1,5 +1,4 @@
 # This module exists for documentation purpose only
-from deprecated import deprecated
 
 
 def chat(role: str):  # pylint: disable=W0613
@@ -38,19 +37,3 @@ def completion(model_name: str):  # pylint: disable=W0613
         {{ response }}
         ```
     """
-
-
-@deprecated(version="1.3.0", reason="This extension is deprecated, use {% completion %} instead.")
-def generate(model_name: str):  # pylint: disable=W0613
-    """
-    `generate` can be used to call the LiteLLM API passing the tag text as a prompt and get back some content.
-
-    Deprecated:
-        This extension is deprecated, use `{% completion %}` instead.
-
-    Example:
-        ```jinja
-        {% generate "write a tweet with positive sentiment" "gpt-3.5-turbo" %}
-        Feeling grateful for all the opportunities that come my way! #positivity #productivity
-        ```
-    """

src/banks/prompt.py

@@ -177,12 +177,6 @@ class AsyncPrompt(BasePrompt):
 
     prompt_template = \"\"\"
     Generate a tweet about the topic '{{ topic }}' with a positive sentiment.
-
-    Examples:
-    - {% generate "write a tweet with a positive sentiment", "gpt-3.5-turbo" %}
-    - {% generate "write a tweet with a sad sentiment", "gpt-3.5-turbo" %}
-    - {% generate "write a tweet with a neutral sentiment", "gpt-3.5-turbo" %}
-
     \"\"\"
 
     async def task(task_id: int, sleep_time: int):