Functions — github.com/SqueezeAILab/TinyAgent

hub / github.com/SqueezeAILab/TinyAgent / functions

Functions338 in github.com/SqueezeAILab/TinyAgent

⨍ Functions 338◇ Types & classes 74 ↳ Endpoints 4

↓ 23 callersMethodjoin

( self, input_query: str, agent_scratchpad: str, is_final: bool )

src/llm_compiler/llm_compiler.py:210

↓ 17 callersFunctionlog

Print the given string only if logging is enabled.

src/utils/logger_utils.py:75

↓ 14 callersFunction_is_valid_config_field

(config: dict[str, Any], field: str)

src/tiny_agent/config.py:223

↓ 12 callersFunctionrun_applescript

Runs the given AppleScript using osascript and returns the result.

src/tiny_agent/run_apple_script.py:4

↓ 8 callersFunctionensure_email_formatting

( email_addresses: Sequence[str], computer: Computer )

src/tiny_agent/tiny_agent_tools.py:44

↓ 8 callersMethodrun

Convenience method for executing chain. The main difference between this method and `Chain.__call__` is that this method expects inpu

src/chains/chain.py:443

↓ 8 callersFunctionrun_applescript_capture

Runs the given AppleScript using osascript, captures the output and error, and returns them.

src/tiny_agent/run_apple_script.py:12

↓ 7 callersMethodparse

Parse text into agent action/finish.

src/agents/agent.py:36

↓ 6 callersMethodopen

Does Spotlight Search and opens the first thing that matches the name. If no exact match, performs fuzzy search. Additionally

src/tiny_agent/tools/spotlight_search.py:13

↓ 6 callersMethodtool_run_logging_kwargs

(self)

src/agents/agent.py:284

↓ 5 callersMethod_format_email_addresses

(emails: list[str])

src/tiny_agent/tools/mail.py:186

↓ 4 callersMethod_areturn

( self, output: AgentFinish, intermediate_steps: list, run_manager: Optional[A

src/executors/agent_executor.py:223

↓ 4 callersMethodacall

Asynchronously execute the chain. Args: inputs: Dictionary of inputs, or single input if chain expects only one p

src/chains/chain.py:307

↓ 4 callersMethodapredict

Format prompt with kwargs and pass to LLM. Args: callbacks: Callbacks to pass to LLMChain **kwargs: Keys to pass to p

src/chains/llm_chain.py:306

↓ 4 callersMethodarun

Convenience method for executing chain. The main difference between this method and `Chain.__call__` is that this method expects inpu

src/chains/chain.py:513

↓ 4 callersMethodcreate_outputs

Create outputs from response.

src/chains/llm_chain.py:267

↓ 4 callersMethodon_chain_error

( self, error: BaseException, *, run_id: UUID, parent_run_id: Optional

src/llm_compiler/planner.py:238

↓ 4 callersMethodpredict

Format prompt with kwargs and pass to LLM. Args: callbacks: Callbacks to pass to LLMChain **kwargs: Keys to pass to p

src/chains/llm_chain.py:289

↓ 4 callersMethodserialize

(self)

src/utils/data_utils.py:98

↓ 3 callersMethod_format_attachments

(attachments: list[str])

src/tiny_agent/tools/mail.py:190

↓ 3 callersMethod_get_folder_line

(self, folder: str | None)

src/tiny_agent/tools/notes.py:186

↓ 3 callersFunction_make_with_name

(tool_name: str)

src/tools/base.py:412

↓ 3 callersMethod_return

( self, output: AgentFinish, intermediate_steps: list, run_manager: Optional[C

src/executors/agent_executor.py:210

↓ 3 callersMethodcheck_context_length

Checks if the final length of the messages is greater than the context length, and if so, removes the excess tokens from the context.

src/tiny_agent/sub_agents/sub_agent.py:38

↓ 3 callersFunctionensure_file_paths

(file_paths: Sequence[str], computer: Computer)

src/tiny_agent/tiny_agent_tools.py:53

↓ 3 callersFunctiongenerate_llm_compiler_prompt

( tools: Sequence[Union[Tool, StructuredTool]], example_prompt: str, custom_instructions: str | No

src/llm_compiler/planner.py:37

↓ 3 callersFunctionget_datetime

(date: str | None)

src/tiny_agent/tiny_agent_tools.py:21

↓ 3 callersFunctionget_model

( model_type, model_name, api_key, vllm_port, stream, temperature=0, azure_endpoin

src/utils/model_utils.py:12

↓ 3 callersFunctionget_model_config

( config: dict[str, Any], provider: str, agent_type: AgentType, )

src/tiny_agent/config.py:49

↓ 3 callersFunctioninstantiate_task

( tools: Sequence[Union[Tool, StructuredTool]], idx: int, tool_name: str, args: str, thoug

src/llm_compiler/output_parser.py:111

↓ 3 callersMethodreturn_stopped_response

Return response when agent has been stopped due to max iterations.

src/agents/agent.py:242

↓ 3 callersFunctionrun_command

Executes a shell command and returns the output.

src/tiny_agent/run_apple_script.py:22

↓ 2 callersMethod_acall

Asynchronously execute the chain. This is a private method that is not user-facing. It is only called within `Chain.acall`, which

src/chains/chain.py:215

↓ 2 callersMethod_all_tasks_done

(self)

src/llm_compiler/task_fetching_unit.py:97

↓ 2 callersMethod_call

Execute the chain. This is a private method that is not user-facing. It is only called within `Chain.__call__`, which is the user

src/chains/chain.py:192

↓ 2 callersMethod_convert_note_to_text

Converts an HTML note content to plain text.

src/tiny_agent/tools/notes.py:232

↓ 2 callersMethod_do_fuzzy_matching

(self, name: str)

src/tiny_agent/tools/notes.py:191

↓ 2 callersMethod_get_all_executable_tasks

(self)

src/llm_compiler/task_fetching_unit.py:100

↓ 2 callersMethod_get_first_calendar

(self)

src/tiny_agent/tools/calendar.py:89

↓ 2 callersMethod_get_in_context_examples_prompt

(embeddings: list[PickledEmbedding])

src/tiny_agent/tool_rag/base_tool_rag.py:125

↓ 2 callersMethod_get_tool_return

Check if the tool is a returning tool.

src/executors/agent_executor.py:547

↓ 2 callersMethod_load_filtered_embeddings

Loads the embeddings.pkl file that contains a list of PickledEmbedding objects and returns the filtered results based on the availabl

src/tiny_agent/tool_rag/base_tool_rag.py:105

↓ 2 callersMethod_match_buffer_and_generate_task

Runs every time "\n" is encountered in the input stream or at the end of the stream. Matches the buffer against the regex patterns and generat

src/llm_compiler/planner.py:101

↓ 2 callersMethod_parse_generation

( self, generation: List[Dict[str, str]] )

src/chains/llm_chain.py:362

↓ 2 callersMethod_prepare_intermediate_steps

( self, intermediate_steps: List[Tuple[AgentAction, str]] )

src/executors/agent_executor.py:562

↓ 2 callersMethod_retrieve_top_k_embeddings

Computes the cosine similarity of each example and retrieves the closest top_k examples. If there are already less than top_k example

src/tiny_agent/tool_rag/base_tool_rag.py:77

↓ 2 callersMethod_run_task

(self, task: Task)

src/llm_compiler/task_fetching_unit.py:117

↓ 2 callersMethod_should_continue

(self, iterations: int, time_elapsed: float)

src/executors/agent_executor.py:199

↓ 2 callersFunctionadd_new_dependency_edge

( *, node_name: str, dependency: str, )

src/utils/graph_utils.py:22

↓ 2 callersMethodagenerate

Generate LLM result from inputs.

src/chains/llm_chain.py:137

↓ 2 callersFunctioncall_compose_email_agent

( compose_email_agent: ComposeEmailAgent, context: str, email_thread: str = "", mode: ComposeE

src/tiny_agent/tiny_agent_tools.py:230

↓ 2 callersFunctioncheck_for_dependency

(item: str)

src/utils/graph_utils.py:11

↓ 2 callersMethodgenerate

Generate LLM result from inputs.

src/chains/llm_chain.py:102

↓ 2 callersMethodget_email_address

Returns the email address of a contact by name.

src/tiny_agent/tools/contacts.py:37

↓ 2 callersMethodget_full_inputs

Create the full inputs for the LLMChain from intermediate steps.

src/agents/agent.py:161

↓ 2 callersMethodget_full_names_from_first_name

Returns a list of full names of contacts that contain the first name provided.

src/tiny_agent/tools/contacts.py:64

↓ 2 callersMethodget_phone_number

Returns the phone number of a contact by name.

src/tiny_agent/tools/contacts.py:10

↓ 2 callersFunctionget_planner_custom_instructions_prompt

( tools: Sequence[Tool | StructuredTool], custom_instructions: str | None )

src/tiny_agent/prompts.py:86

↓ 2 callersMethodget_stats

(self)

src/callbacks/callbacks.py:35

↓ 2 callersMethodget_though_action_observation

( self, include_action=True, include_thought=True, include_action_idx=False )

src/llm_compiler/task_fetching_unit.py:59

↓ 2 callersFunctionget_tiny_agent_config

(config_path: str)

src/tiny_agent/config.py:147

↓ 2 callersFunctionget_tiny_agent_tools

( computer: Computer, compose_email_agent: ComposeEmailAgent, pdf_summarizer_agent: PDFSummarizerA

src/tiny_agent/tiny_agent_tools.py:714

↓ 2 callersMethodopen_note

Opens an existing note by its name and optionally returns its content. If no exact match is found, attempts fuzzy matching to suggest

src/tiny_agent/tools/notes.py:53

↓ 2 callersMethodprep_inputs

Validate and prepare chain inputs, including adding inputs from memory. Args: inputs: Dictionary of raw inputs, or single input i

src/chains/chain.py:402

↓ 2 callersMethodprep_outputs

Validate and prepare chain outputs, and save info about this run to memory. Args: inputs: Dictionary of chain inputs, including a

src/chains/chain.py:376

↓ 2 callersMethodreset

(self)

src/callbacks/callbacks.py:29

↓ 2 callersMethodrun_llm

Run the LLM.

src/llm_compiler/planner.py:279

↓ 2 callersMethodset_tasks

(self, tasks: dict[str, Any])

src/llm_compiler/task_fetching_unit.py:92

↓ 1 callersMethod__init__

(self)

src/callbacks/callbacks.py:11

↓ 1 callersMethod_atake_next_step

Take a single step in the thought-action-observation loop. Override this to take control of how the agent makes and acts on choices.

src/executors/agent_executor.py:334

↓ 1 callersFunction_check_azure_config

(config: dict[str, Any], agent_prefix: str)

src/tiny_agent/config.py:227

↓ 1 callersMethod_check_folder_exists

(self, folder: str)

src/tiny_agent/tools/notes.py:208

↓ 1 callersFunction_check_local_config

(config: dict[str, Any], agent_prefix: str)

src/tiny_agent/config.py:261

↓ 1 callersFunction_check_openai_config

(config: dict[str, Any], agent_prefix: str)

src/tiny_agent/config.py:247

↓ 1 callersMethod_classify_tools

Retrieves the best tools for the given query by classification.

src/tiny_agent/tool_rag/classifier_tool_rag.py:92

↓ 1 callersMethod_construct_scratchpad

Construct the scratchpad that lets the agent continue its thought process.

src/agents/agent.py:89

↓ 1 callersFunction_create_subset_model

Create a pydantic model with only a subset of model's fields.

src/tools/base.py:29

↓ 1 callersFunction_default_stringify_rule_for_arguments

(args)

src/llm_compiler/task_fetching_unit.py:12

↓ 1 callersMethod_extract_text_from_pdf

(pdf_path: str)

src/tiny_agent/sub_agents/pdf_summarizer_agent.py:69

↓ 1 callersFunction_find_tool

Find a tool by name. Args: tool_name: Name of the tool to find. Returns: Tool or StructuredTool.

src/llm_compiler/output_parser.py:80

↓ 1 callersMethod_format_contexts

contexts is a list of context each context is formatted as the description of _generate_context_for_replanner

src/llm_compiler/llm_compiler.py:200

↓ 1 callersMethod_generate_context_for_replanner

Formatted like this: ``` 1. action 1 Observation: xxx 2. action 2 Observation: yyy ... Thought

src/llm_compiler/llm_compiler.py:174

↓ 1 callersMethod_get_accuracy

(self, key: str)

src/utils/logger_utils.py:36

↓ 1 callersMethod_get_default_output_parser

Get default output parser for this class.

src/agents/agent.py:213

↓ 1 callersMethod_get_default_output_parser

( cls, llm: Optional[BaseLanguageModel] = None, **kwargs: Any )

src/agents/structured_chat_agent.py:64

↓ 1 callersFunction_get_dependencies_from_graph

Get dependencies from a graph.

src/llm_compiler/output_parser.py:97

↓ 1 callersFunction_get_filtered_args

Get the arguments from a function's signature.

src/tools/base.py:40

↓ 1 callersMethod_get_mean_latency

(self, key: str)

src/utils/logger_utils.py:32

↓ 1 callersFunction_get_verbosity

()

src/chains/chain.py:33

↓ 1 callersMethod_parse_joinner_output

We expect the joinner output format to be: ``` Thought: xxx Action: Finish/Replan(yyy) ``` Returns:

src/llm_compiler/llm_compiler.py:147

↓ 1 callersFunction_parse_llm_compiler_action_args

Parse arguments from a string.

src/utils/plan_utils.py:13

↓ 1 callersFunction_parse_llm_compiler_action_args

Parse arguments from a string.

src/llm_compiler/output_parser.py:64

↓ 1 callersMethod_preprocess_args

Replace dependency placeholders, i.e. ${1}, in task.args with the actual observation.

src/llm_compiler/task_fetching_unit.py:109

↓ 1 callersFunction_replace_arg_mask_with_real_value

( args, dependencies: List[int], tasks: Dict[str, Task] )

src/llm_compiler/task_fetching_unit.py:19

↓ 1 callersMethod_take_next_step

Take a single step in the thought-action-observation loop. Override this to take control of how the agent makes and acts on choices.

src/executors/agent_executor.py:238

↓ 1 callersMethod_validate_inputs

Check that all inputs are present.

src/chains/chain.py:180

↓ 1 callersMethod_validate_outputs

(self, outputs: Dict[str, Any])

src/chains/chain.py:186

↓ 1 callersMethod_validate_tools

Validate that appropriate tools are passed in.

src/agents/agent.py:207

↓ 1 callersMethod_validate_tools

(cls, tools: Sequence[BaseTool])

src/agents/structured_chat_agent.py:60

↓ 1 callersMethodaapply

Utilize the LLM generate method for speed gains.

src/chains/llm_chain.py:243

next →1–100 of 338, ranked by callers