cognite-ai

A set of AI tools for working with CDF in Python.

MemoryVectorStore

Store and query vector embeddings created from CDF. This can enable a bunch of use cases where the number of vectors aren't that big.

Install the package

%pip install cognite-ai

Then you can create vectors from text (both multiple lines or a list of strings) like this

from cognite.ai import MemoryVectorStore
vector_store = MemoryVectorStore(client)

vector_store.store_text("Hi, I am a software engineer working for Cognite.")
vector_store.store_text("The moon is orbiting the earth, which is orbiting the sun.")
vector_store.store_text("Coffee can be a great way to stay awake.")

vector_store.query_text("I am tired, what can I do?")

Smart data frames

Chat with your data using LLMs. Built on top of PandasAI version 1.5.8. If you have loaded data into a Pandas dataframe, you can run

Install the package

%pip install cognite-ai

Chat with your data

from cognite.ai import load_pandasai
SmartDataframe, SmartDatalake = await load_pandasai()

workorders_df = client.raw.rows.retrieve_dataframe("tutorial_apm", "workorders", limit=-1)
workitems_df = client.raw.rows.retrieve_dataframe("tutorial_apm", "workitems", limit=-1)
workorder2items_df = client.raw.rows.retrieve_dataframe("tutorial_apm", "workorder2items", limit=-1)
workorder2assets_df = client.raw.rows.retrieve_dataframe("tutorial_apm", "workorder2assets", limit=-1)
assets_df = client.raw.rows.retrieve_dataframe("tutorial_apm", "assets", limit=-1)

from cognite.client import CogniteClient
client = CogniteClient()

smart_lake_df = SmartDatalake([workorders_df, workitems_df, assets_df, workorder2items_df, workorder2assets_df], cognite_client=client)
smart_lake_df.chat("Which workorders are the longest, and what work items do they have?")


s_workorders_df = SmartDataframe(workorders_df, cognite_client=client)
s_workorders_df.chat('Which 5 work orders are the longest?')

Configure LLM parameters

params = {
    "model": "gpt-35-turbo",
    "temperature": 0.5
}

s_workorders_df = SmartDataframe(workorders_df, cognite_client=client, params=params)

Release files for cognite-ai 0.4.3

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for cognite-ai 0.4.3
File	Size	Uploaded
cognite_ai-0.4.3.tar.gz	5.8 kB	Dec 14, 2023	Details

Built distribution (wheel)

Table of built distributions (wheels) for cognite-ai 0.4.3
File	Interpreter	ABI	Platform	Reset
cognite_ai-0.4.3-py3-none-any.whl 7.3 kB Dec 14, 2023	Python 3	none	any	Details

Total release size: 13.0 kB

Release files / cognite_ai-0.4.3.tar.gz

Download URL	cognite_ai-0.4.3.tar.gz
Size	5.8 kB
Tags	Source
SHA-256 checksum How to use checksums	`99c58b837e5b2419225087d244ccdc3612348910546ea17c9773970c0717f905`
BLAKE2b-256 checksum How to use checksums	`10cd5c409c984615e9c95eebe4cccda5a364ce3c22670a0517f4a5313f3fac5b`
Upload date	Dec 14, 2023
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.9.18`

Release files / cognite_ai-0.4.3-py3-none-any.whl

Download URL	cognite_ai-0.4.3-py3-none-any.whl
Size	7.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`fe58ea48f14039c956ed702491ed9ca2e9525dad3600955709f790f7bb23ba9d`
BLAKE2b-256 checksum How to use checksums	`3683cce5bc57832b7c62f56320f72075db7013265a5bf6790a0c246ff8bc9de9`
Upload date	Dec 14, 2023
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/4.0.2 CPython/3.9.18`