chatflock.use_cases.bshr¶

Module Contents¶

class chatflock.use_cases.bshr.BHSRState¶

Bases: pydantic.BaseModel

information_need: str | None = None¶

queries_to_run: List[str] | None = None¶

answers_to_queries: Dict[str, str] | None = None¶

current_hypothesis: str | None = None¶

proposed_hypothesis: str | None = None¶

feedback: str | None = None¶

is_satisficed: bool | None = None¶

chatflock.use_cases.bshr.save_state(state, state_file)¶

Parameters:

state (BHSRState)
state_file (Optional[str])

Return type:

None

chatflock.use_cases.bshr.load_state(state_file)¶

Parameters:: state_file (Optional[str])
Return type:: Optional[BHSRState]

class chatflock.use_cases.bshr.QueryGenerationResult¶

Bases: pydantic.BaseModel

information_need: str¶

queries: List[str]¶

class chatflock.use_cases.bshr.HypothesisGenerationResult¶

Bases: pydantic.BaseModel

hypothesis: str¶

class chatflock.use_cases.bshr.SatisficationCheckResult¶

Bases: pydantic.BaseModel

feedback: str¶

is_satisficed: bool¶

chatflock.use_cases.bshr.generate_queries(state, chat_model, interactive_user=True, max_queries=10, shared_sections=None, web_search_tool=None, spinner=None)¶

Parameters:

state (BHSRState)
chat_model (langchain.chat_models.base.BaseChatModel)
interactive_user (bool)
max_queries (int)
shared_sections (Optional[List[chatflock.structured_string.Section]])
web_search_tool (Optional[langchain.tools.BaseTool])
spinner (Optional[halo.Halo])

Return type:

None

chatflock.use_cases.bshr.search_queries(state, web_search, n_search_results=3, spinner=None)¶

Parameters:

state (BHSRState)
web_search (chatflock.web_research.WebSearch)
n_search_results (int)
spinner (Optional[halo.Halo])

Return type:

Generator[BHSRState, None, None]

chatflock.use_cases.bshr.generate_hypothesis(state, chat_model, shared_sections=None, spinner=None)¶

Parameters:

state (BHSRState)
chat_model (langchain.chat_models.base.BaseChatModel)
shared_sections (Optional[List[chatflock.structured_string.Section]])
spinner (Optional[halo.Halo])

Return type:

None

chatflock.use_cases.bshr.check_satisficing(state, chat_model, shared_sections=None, spinner=None)¶

Parameters:

state (BHSRState)
chat_model (langchain.chat_models.base.BaseChatModel)
shared_sections (Optional[List[chatflock.structured_string.Section]])
spinner (Optional[halo.Halo])

Return type:

None

chatflock.use_cases.bshr.brainstorm_search_hypothesize_refine(web_search, chat_model, initial_state=None, n_search_results=3, state_file=None, spinner=None)¶

Parameters:

web_search (chatflock.web_research.WebSearch)
chat_model (langchain.chat_models.base.BaseChatModel)
initial_state (Optional[BHSRState])
n_search_results (int)
state_file (Optional[str])
spinner (Optional[halo.Halo])

Return type:

BHSRState

chatflock.use_cases.bshr.run_brainstorm_search_hypothesize_refine_loop(web_search, chat_model, n_search_results=3, initial_state=None, state_file=None, confirm_satisficed=False, spinner=None)¶

Parameters:

web_search (chatflock.web_research.WebSearch)
chat_model (langchain.chat_models.base.BaseChatModel)
n_search_results (int)
initial_state (Optional[BHSRState])
state_file (Optional[str])
confirm_satisficed (bool)
spinner (Optional[halo.Halo])

Return type:

str

class chatflock.use_cases.bshr.BrainstormSearchHypothesizeRefineToolArgs¶

Bases: pydantic.BaseModel

query: str¶

chatflock.use_cases.bshr.TArgSchema¶

class chatflock.use_cases.bshr.BrainstormSearchHypothesizeRefineTool¶

Bases: langchain.tools.BaseTool, Generic[TArgSchema]

Abstract base class for generic types.

A generic type is typically declared by inheriting from this class parameterized with one or more type variables. For example, a generic mapping type might be defined as:

class Mapping(Generic[KT, VT]):
    def __getitem__(self, key: KT) -> VT:
        ...
    # Etc.

This class can then be used as follows:

def lookup_name(mapping: Mapping[KT, VT], key: KT, default: VT) -> VT:
    try:
        return mapping[key]
    except KeyError:
        return default

web_search: chatflock.web_research.WebSearch¶

chat_model: langchain.chat_models.base.BaseChatModel¶

n_results: int = 3¶

state_file: str | None = None¶

spinner: halo.Halo | None = None¶

name: str = 'web_research'¶

description: str = "Research the web using a Brainstorm-Search-Hypothesize-Refine approach. Use that to get a very...¶

args_schema: Type[TArgSchema]¶

progress_text: str = 'Researching the topic (this may take a while)...'¶

_run(query, run_manager=None, **kwargs)¶

Parameters:

query (str)
run_manager (Optional[langchain.callbacks.manager.CallbackManagerForToolRun])
kwargs (Any)

Return type:

Any