Filtering Query
This section provides a detailed guide to the filter expression syntax, a lightweight query language for filtering data.
Simple Query
Querying the data works as follows
import os, requests
url = "https://api.activeloop.ai/chat/completions"
token = os.environ["ACTIVELOOP_TOKEN"]
headers = {'Authorization': f'Bearer {token}'}
payload = {
"model": "activeloop-l0",
"messages": [
{
"role": "user",
"content": "What is logic?",
}
]
}
response = requests.post(url, headers=headers, json=payload)
# Print the response
print(response.json())
Retrieving top K elements without Reasoning
When activeloop-l0-retrieval is used there is no reasoning or summary returned. Only top_k results.
payload = {
"model": "activeloop-l0-retrieval",
"messages": [
{
"role": "user",
"content": [
{
"type": "filter",
"top_k": 3
},
{
"type": "text",
"text": "What is logic?" # query
}
]
}
]
}
response = requests.post(url, headers=headers, json=payload)
print(response.json()["choices"]) # top k elements
Getting answer from Hegel
Now, we can filter files based on metadata, before running the query.
payload = {
"model": "activeloop-l0",
"messages": [
{
"role": "user",
"content": [
{
"type": "filter",
"filter": "metadata.author == 'hegel'"
},
{
"type": "text",
"text": "What is logic?"
}
]
}
],
}
response = requests.post(url, headers=headers, json=payload)
print(response.json())
Getting answer from other authors
payload = {
"model": "activeloop-l0",
"messages": [
{
"role": "user",
"content": [
{
"type": "filter",
"filter": "metadata.author != 'hegel'"
},
{
"type": "text",
"text": "What is logic?"
}
]
}
],
}
response = requests.post(url, headers=headers, json=payload)
print(response.json())
