prebuilt.essay_grading¶

Essay Grading - TODO: Add brief description.

TODO: Add detailed description of module functionality

Examples

Basic usage:

from haive.essay_grading import module_function

# TODO: Add example

Submodules¶

Attributes¶

`action_pipeline`
`action_prompt`
`fact_checking_pipeline`
`fact_checking_prompt`
`grammar_and_bias_review`
`llm`
`quote_extraction_pipeline`
`quote_extraction_prompt`
`review_prompt`
`routes`
`structured_output_llm`
`tone_analysis_prompt`
`tone_pipeline`
`user_actions`
`user_inputs`

Classes¶

`BaseLLMConfig`	Placeholder for base LLM configuration.
`FactCheckResult`	dict() -> new empty dictionary
`JournamlsimReviewAgent`	Agent for reviewing the grammar and bias of an article.
`State`	dict() -> new empty dictionary
`SystemAction`	dict() -> new empty dictionary

Functions¶

`categorize_user_input`(→ State)	This node handles the categorization of the user input to identify the intended actions.
`chunk_large_text`(→ List[str])	Split large text into manageable chunks.
`fact_check_article`(article_text[, chunks])	Fact-check the given text by identifying factual inaccuracies, misleading information, unsupported claims, or vague language.
`fact_checking_node`(→ State)	Fact Checking Node.
`get_or_create_chunks`(state)	This function gets the article text from the state and splits it into manageable chunks.
`get_user_actions`(→ List[str])	Identify the user's intended actions based on their input.
`grammar_and_bias_review_node`(→ State)	Grammar And Bias Review Node.
`grammary_and_bias_analysis_article`(article_text[, chunks])	Review the given article text for grammar, spelling, punctuation, and bias.
`quote_extraction_article`(article_text[, chunks])	Extract direct quotes from the given article text.
`quote_extraction_node`(→ State)	Quote Extraction Node.
`route`(→ str)	Route.
`search_and_summarize`(→ str)	Search for keyword and summarize results.
`summarization_node`(state)	This node generates a summary of the article text.
`summarize_article`(→ str)	Summarize the article.
`tone_analysis_article`(article_text[, chunks])	Analyze the tones of the given article text.
`tone_analysis_node`(→ State)	Tone Analysis Node.

Package Contents¶

class prebuilt.essay_grading.BaseLLMConfig¶: Placeholder for base LLM configuration.

class prebuilt.essay_grading.FactCheckResult¶

Bases: TypedDict

dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object’s

(key, value) pairs

dict(iterable) -> new dictionary initialized as if via:: d = {} for k, v in iterable:

d[k] = v
dict(**kwargs) -> new dictionary initialized with the name=value pairs: in the keyword argument list. For example: dict(one=1, two=2)

result: List[dict]¶

class prebuilt.essay_grading.JournamlsimReviewAgent(llm: BaseLLMConfig)¶

Bases: haive.agents.base.agent.Agent

Agent for reviewing the grammar and bias of an article.

setup_workflow()¶: Setup Workflow.

graph = None¶

class prebuilt.essay_grading.State¶

Bases: TypedDict

dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object’s

(key, value) pairs

dict(iterable) -> new dictionary initialized as if via:: d = {} for k, v in iterable:

d[k] = v
dict(**kwargs) -> new dictionary initialized with the name=value pairs: in the keyword argument list. For example: dict(one=1, two=2)

actions: List[str]¶

article_text: str¶

chunks: List[str]¶

current_query: str¶

fact_check_result: List[dict]¶

grammar_and_bias_review_result: List[str]¶

quote_extraction_result: List[str]¶

summary_result: str¶

tone_analysis_result: List[str]¶

class prebuilt.essay_grading.SystemAction¶

Bases: TypedDict

dict() -> new empty dictionary dict(mapping) -> new dictionary initialized from a mapping object’s

(key, value) pairs

dict(iterable) -> new dictionary initialized as if via:: d = {} for k, v in iterable:

d[k] = v
dict(**kwargs) -> new dictionary initialized with the name=value pairs: in the keyword argument list. For example: dict(one=1, two=2)

actions: List[str]¶

prebuilt.essay_grading.categorize_user_input(state: State) → State¶: This node handles the categorization of the user input to identify the intended actions.

prebuilt.essay_grading.chunk_large_text(text: str) → List[str]¶: Split large text into manageable chunks.

prebuilt.essay_grading.fact_check_article(article_text: str, chunks=None)¶: Fact-check the given text by identifying factual inaccuracies, misleading information, unsupported claims, or vague language.

prebuilt.essay_grading.fact_checking_node(state: State) → State¶

Fact Checking Node.

Parameters:: state – [TODO: Add description]
Returns:: Add return description]
Return type:: [TODO

prebuilt.essay_grading.get_or_create_chunks(state: State)¶: This function gets the article text from the state and splits it into manageable chunks. The chunks are stored in the state to avoid recomputing them multiple times.

prebuilt.essay_grading.get_user_actions(input_text: str) → List[str]¶: Identify the user’s intended actions based on their input.

prebuilt.essay_grading.grammar_and_bias_review_node(state: State) → State¶

Grammar And Bias Review Node.

Parameters:: state – [TODO: Add description]
Returns:: Add return description]
Return type:: [TODO

prebuilt.essay_grading.grammary_and_bias_analysis_article(article_text: str, chunks=None)¶: Review the given article text for grammar, spelling, punctuation, and bias.

prebuilt.essay_grading.quote_extraction_article(article_text: str, chunks=None)¶: Extract direct quotes from the given article text.

prebuilt.essay_grading.quote_extraction_node(state: State) → State¶

Quote Extraction Node.

Parameters:: state – [TODO: Add description]
Returns:: Add return description]
Return type:: [TODO

prebuilt.essay_grading.route(state: State) → str¶

Route.

Parameters:: state – [TODO: Add description]
Returns:: Add return description]
Return type:: [TODO

prebuilt.essay_grading.search_and_summarize(keyword: str) → str¶: Search for keyword and summarize results.

prebuilt.essay_grading.summarization_node(state)¶: This node generates a summary of the article text.

prebuilt.essay_grading.summarize_article(article_text: str, chunks: List[str]) → str¶: Summarize the article.

prebuilt.essay_grading.tone_analysis_article(article_text: str, chunks=None)¶: Analyze the tones of the given article text.

prebuilt.essay_grading.tone_analysis_node(state: State) → State¶

Tone Analysis Node.

Parameters:: state – [TODO: Add description]
Returns:: Add return description]
Return type:: [TODO

prebuilt.essay_grading.action_pipeline¶

prebuilt.essay_grading.action_prompt¶

prebuilt.essay_grading.fact_checking_pipeline¶

prebuilt.essay_grading.fact_checking_prompt¶

prebuilt.essay_grading.grammar_and_bias_review¶

prebuilt.essay_grading.llm = None¶

prebuilt.essay_grading.quote_extraction_pipeline¶

prebuilt.essay_grading.quote_extraction_prompt¶

prebuilt.essay_grading.review_prompt¶

prebuilt.essay_grading.routes¶

prebuilt.essay_grading.structured_output_llm¶

prebuilt.essay_grading.tone_analysis_prompt¶

prebuilt.essay_grading.tone_pipeline¶

prebuilt.essay_grading.user_actions¶

prebuilt.essay_grading.user_inputs = ['Can you summarize this article for me?', "I'm not sure about the accuracy of this article. Can...¶