Create prompts.py

prompts.py

@@ -0,0 +1,217 @@
+PREFIX = """You are an Internet Search Scraper.
+Your duty is to use the provided search tools to scrape text from websites, and then sort through the search results in the observation to find information that fits the user's requirements.
+
+You have access to the following tools:
+- action: UPDATE-TASK action_input=NEW_TASK
+- action: SEARCH_ENGINE action_input=SEARCH_QUERY
+- action: SCRAPE_WEBSITE action_input=WEBSITE_URL
+- action: COMPLETE
+
+Search Purpose:
+{purpose}
+"""
+
+FINDER = """
+
+Instructions
+- Use your search engine tool to find a website to scrape
+- Use your scrape website tool to scrape the text from the website url
+- Find the pertinent information in the text that you scrape
+- When you are finished, return with  action: COMPLETE
+
+Use the following format:
+task: the input task you must complete
+action: the action to take (should be one of [UPDATE-TASK, SEARCH, COMPLETE]) action_input=XXX
+observation: the result of the action
+action: SEARCH action_input=''
+action: COMPLETE
+
+Example:
+***************************
+User command: Find me the breaking news from today
+action: SEARCH_ENGINE action_input=https://www.google.com/search?q=todays+breaking+news
+observation: the data that is returned including urls to websites
+action: SCRAPE_WEBSITE action_input=https://www.news-website.com
+observation: the data that is returned
+
+Response:
+Assistant: I found the the following news articles.....
+action: COMPLETE
+***************************
+You are attempting to complete the task
+task: {task}
+{history}"""
+
+MODEL_FINDER_PRE = """
+You have access to the following tools:
+- action: UPDATE-TASK action_input=NEW_TASK
+- action: SEARCH action_input=SEARCH_QUERY
+- action: COMPLETE
+Instructions
+- Generate a search query for the requested model from these options: 
+>{TASKS}
+- Return the search query using the search tool
+- Wait for the search to return a result
+- After observing the search result, choose a model
+- Return the name of the repo and model ("repo/model")
+- When you are finished, return with  action: COMPLETE
+Use the following format:
+task: the input task you must complete
+thought: you should always think about what to do
+action: the action to take (should be one of [UPDATE-TASK, SEARCH, COMPLETE]) action_input=XXX
+observation: the result of the action
+thought: you should always think after an observation
+action: SEARCH action_input='text-generation'
+... (thought/action/observation/thought can repeat N times)
+Example:
+***************************
+User command: Find me a text generation model with less than 50M parameters.
+thought: I will use the option 'text-generation'
+action: SEARCH action_input=text-generation
+--- pause and wait for data to be returned ---
+Response:
+Assistant: I found the 'distilgpt2' model which has around 82M parameters. It is a distilled version of the GPT-2 model from OpenAI, trained by Hugging Face. Here's how to load it:
+action: COMPLETE
+***************************
+You are attempting to complete the task
+task: {task}
+{history}"""
+
+
+ACTION_PROMPT = """
+You have access to the following tools:
+- action: UPDATE-TASK action_input=NEW_TASK
+- action: SEARCH action_input=SEARCH_QUERY
+- action: COMPLETE
+Instructions
+- Generate a search query for the requested model
+- Return the search query using the search tool
+- Wait for the search to return a result
+- After observing the search result, choose a model
+- Return the name of the repo and model ("repo/model")
+Use the following format:
+task: the input task you must complete
+action: the action to take (should be one of [UPDATE-TASK, SEARCH, COMPLETE]) action_input=XXX
+observation: the result of the action
+action: SEARCH action_input='text generation'
+You are attempting to complete the task
+task: {task}
+{history}"""
+
+ACTION_PROMPT_PRE = """
+You have access to the following tools:
+- action: UPDATE-TASK action_input=NEW_TASK
+- action: SEARCH action_input=SEARCH_QUERY
+- action: COMPLETE
+Instructions
+- Generate a search query for the requested model
+- Return the search query using the search tool
+- Wait for the search to return a result
+- After observing the search result, choose a model
+- Return the name of the repo and model ("repo/model")
+Use the following format:
+task: the input task you must complete
+thought: you should always think about what to do
+action: the action to take (should be one of [UPDATE-TASK, SEARCH, COMPLETE]) action_input=XXX
+observation: the result of the action
+thought: you should always think after an observation
+action: SEARCH action_input='text generation'
+... (thought/action/observation/thought can repeat N times)
+You are attempting to complete the task
+task: {task}
+{history}"""
+
+TASK_PROMPT = """
+You are attempting to complete the task
+task: {task}
+Progress:
+{history}
+Tasks should be small, isolated, and independent
+To start a search use the format:
+action: SEARCH_ENGINE action_input=URL/?q='SEARCH_QUERY'
+What should the task be for us to achieve the purpose?
+task: """
+
+
+COMPRESS_DATA_PROMPT_SMALL = """
+You are attempting to complete the task
+task: {task}
+Current data:
+{knowledge}
+New data:
+{history}
+Compress the data above into a concise data presentation of relevant data
+Include datapoints that will provide greater accuracy in completing the task
+Return the data in JSON format to save space
+"""
+
+
+
+
+COMPRESS_DATA_PROMPT = """
+You are attempting to complete the task
+task: {task}
+Current data:
+{knowledge}
+New data:
+{history}
+Compress the data above into a concise data presentation of relevant data
+Include datapoints that will provide greater accuracy in completing the task
+"""
+
+COMPRESS_HISTORY_PROMPT = """
+You are attempting to complete the task
+task: {task}
+Progress:
+{history}
+Compress the timeline of progress above into a single summary (as a paragraph)
+Include all important milestones, the current challenges, and implementation details necessary to proceed
+"""
+
+LOG_PROMPT = """
+PROMPT
+**************************************
+{}
+**************************************
+"""
+
+LOG_RESPONSE = """
+RESPONSE
+**************************************
+{}
+**************************************
+"""
+
+
+FINDER1 = """
+Example Response 1:
+User command: Find me a text generation model with less than 50M parameters.
+Query: text generation
+--- pause and wait for data to be returned ---
+Assistant: I found the 'distilgpt2' model which has around 82M parameters. It is a distilled version of the GPT-2 model from OpenAI, trained by Hugging Face. Here's how to load it:
+```python
+from transformers import AutoTokenizer, AutoModelForMaskedLM
+tokenizer = AutoTokenizer.from_pretrained("distilgpt2")
+model = AutoModelForMaskedLM.from_pretrained("distilgpt2")
+```
+Example Response 2:
+User command: Help me locate a multilingual Named Entity Recognition model.
+Query: named entity recognition
+--- pause and wait for data to be returned ---
+Assistant: I discovered the 'dbmdz/bert-base-multilingual-cased' model, which supports named entity recognition across multiple languages. Here's how to load it:
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification
+tokenizer = AutoTokenizer.from_pretrained("dbmdz/bert-base-multilingual-cased")
+model = AutoModelForTokenClassification.from_pretrained("dbmdz/bert-base-multilingual-cased")
+```
+Example Response 3:
+User command: Search for a question-answering model fine-tuned on the SQuAD v2 dataset with more than 90% accuracy.
+action: SEARCH action_input=named entity recognition
+--- pause and wait for data to be returned ---
+Assistant: I found the 'pranavkv/roberta-base-squad2' model, which was fine-tuned on the SQuAD v2 dataset and achieves approximately 91% accuracy. Below is the way to load it:
+```python
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering
+tokenizer = AutoTokenizer.from_pretrained("pranavkv/roberta-base-squad2")
+model = AutoModelForQuestionAnswering.from_pretrained("pranavkv/roberta-base-squad2")
+```
+"""