"Please help me predict the three most likely questions that human would ask, "
"and keeping each question under 20 characters.\n"
"MAKE SURE your output is the SAME language as the Assistant's latest response(if the main response is written in Chinese, then the language of your output must be using Chinese.)!\n"
"MAKE SURE your output is the SAME language as the Assistant's latest response"
"(if the main response is written in Chinese, then the language of your output must be using Chinese.)!\n"
"The output must be an array in JSON format following the specified schema:\n"
'["question1","question2","question3"]\n'
)
GENERATOR_QA_PROMPT=(
"<Task> The user will send a long text. Generate a Question and Answer pairs only using the knowledge in the long text. Please think step by step."
"<Task> The user will send a long text. Generate a Question and Answer pairs only using the knowledge"
" in the long text. Please think step by step."
"Step 1: Understand and summarize the main content of this text.\n"
"Step 2: What key information or concepts are mentioned in this text?\n"
"Step 3: Decompose or combine multiple pieces of information and concepts.\n"
"Step 4: Generate questions and answers based on these key information and concepts.\n"
"<Constraints> The questions should be clear and detailed, and the answers should be detailed and complete. "
"You must answer in {language}, in a style that is clear and detailed in {language}. No language other than {language} should be used. \n"
"You must answer in {language}, in a style that is clear and detailed in {language}."
" No language other than {language} should be used. \n"
"<Format> Use the following format: Q1:\nA1:\nQ2:\nA2:...\n"
"<QA Pairs>"
)
@ -94,7 +97,7 @@ Based on task description, please create a well-structured prompt template that
"en_US":"Controls randomness. Lower temperature results in less random completions. As the temperature approaches zero, the model will become deterministic and repetitive. Higher temperature results in more random completions.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
en_US="If specified, model will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.",
CONTEXT="Use the following context as your learned knowledge, inside <context></context> XML tags.\n\n<context>\n{{#context#}}\n</context>\n\nWhen answer to user:\n- If you don't know, just say that you don't know.\n- If you don't know when you are not sure, ask for clarification.\nAvoid mentioning that you obtained the information from the context.\nAnd answer according to the language of the user's question.\n"
CONTEXT="Use the following context as your learned knowledge, inside <context></context> XML tags.\n\n<context>\n{{#context#}}\n</context>\n\nWhen answer to user:\n- If you don't know, just say that you don't know.\n- If you don't know when you are not sure, ask for clarification.\nAvoid mentioning that you obtained the information from the context.\nAnd answer according to the language of the user's question.\n"# noqa: E501
"text":"{{#pre_prompt#}}\nHere is the chat histories between human and assistant, inside <histories></histories> XML tags.\n\n<histories>\n{{#histories#}}\n</histories>\n\n\nHuman: {{#query#}}\n\nAssistant: "
"text":"{{#pre_prompt#}}\nHere is the chat histories between human and assistant, inside <histories></histories> XML tags.\n\n<histories>\n{{#histories#}}\n</histories>\n\n\nHuman: {{#query#}}\n\nAssistant: "# noqa: E501
@ -14,7 +14,7 @@ from core.workflow.nodes.llm.llm_node import LLMNode
PREFIX="""Respond to the human as helpfully and accurately as possible. You have access to the following tools:"""
SUFFIX="""Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.
Thought:"""
Thought:""" # noqa: E501
FORMAT_INSTRUCTIONS="""Use a json blob to specify a tool by providing an action key (tool name) and an action_input key (tool input).
f"{tool.name}: {tool.description}, args: {{'query': {{'title': 'Query', 'description': 'Query for the dataset to be used to retrieve the dataset.', 'type': 'string'}}}}"
f"'description': 'Query for the dataset to be used to retrieve the dataset.', 'type': 'string'}}}}"
)
formatted_tools="\n".join(tool_strings)
unique_tool_names={tool.namefortoolintools}
@ -236,7 +237,7 @@ class ReactMultiDatasetRouter:
suffix="""Begin! Reminder to ALWAYS respond with a valid json blob of a single action. Use tools if necessary. Respond directly if appropriate. Format is Action:```$JSON_BLOB```then Observation:.
@ -310,7 +310,8 @@ class StableDiffusionTool(BuiltinTool):
),
type=ToolParameter.ToolParameterType.STRING,
form=ToolParameter.ToolParameterForm.LLM,
llm_description="Image prompt of Stable Diffusion, you should describe the image you want to generate as a list of words as possible as detailed, the prompt must be written in English.",
llm_description="Image prompt of Stable Diffusion, you should describe the image you want to generate"
" as a list of words as possible as detailed, the prompt must be written in English.",
required=True,
),
]
@ -320,12 +321,14 @@ class StableDiffusionTool(BuiltinTool):
en_US="Image id of the image you want to generate based on, if you want to generate image based on the default image, you can leave this field empty.",
en_US="Image id of the image you want to generate based on, if you want to generate image based"
" on the default image, you can leave this field empty.",
Toillustrate,ifthetaskinvolvesextractingauser's name and their request, your function call might look like this: Ensure your output follows a similar structure to examples.
FUNCTION_CALLING_EXTRACTOR_USER_TEMPLATE=f"""extract structured information from context inside <context></context> XML tags by calling the function {FUNCTION_CALLING_EXTRACTOR_NAME} with the correct parameters with structure inside <structure></structure> XML tags.
<context>
@ -33,7 +33,7 @@ FUNCTION_CALLING_EXTRACTOR_USER_TEMPLATE = f"""extract structured information fr
Bowen Liang
1 year ago
committed by
GitHub