This notebook demonstrates how to use the Arcee class for generating text using Arcee's Domain Adapted Language Models (DALMs).
%pip install -qU langchain-community
Before using Arcee, make sure the Arcee API key is set as ARCEE_API_KEY environment variable. You can also pass the api key as a named parameter.
from langchain_community.llms import Arcee
arcee = Arcee(
model="DALM-PubMed",
)
You can also configure Arcee's parameters such as arcee_api_url, arcee_app_url, and model_kwargs as needed. Setting the model_kwargs at the object initialization uses the parameters as default for all the subsequent calls to the generate response.
arcee = Arcee(
model="DALM-Patent",
arcee_api_url="https://custom-api.arcee.ai",
arcee_app_url="https://custom-app.arcee.ai",
model_kwargs={
"size": 5,
"filters": [
{
"field_name": "document",
"filter_type": "fuzzy_search",
"value": "Einstein",
}
],
},
)
You can generate text from Arcee by providing a prompt. Here's an example:
prompt = "Can AI-driven music therapy contribute to the rehabilitation of patients with disorders of consciousness?"
response = arcee(prompt)
Arcee allows you to apply filters and set the size (in terms of count) of retrieved document(s) to aid text generation. Filters help narrow down the results. Here's how to use these parameters:
filters = [
{"field_name": "document", "filter_type": "fuzzy_search", "value": "Einstein"},
{"field_name": "year", "filter_type": "strict_search", "value": "1905"},
]
response = arcee(prompt, size=5, filters=filters)
RetroSearch is an open source project built by @garambo | Open a GitHub Issue
Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo
HTML:
3.2
| Encoding:
UTF-8
| Version:
0.7.4