Skip to main content

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
from cognite.client import CogniteClient

client = CogniteClient()
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 2.2.15. 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.client import CogniteClient
from cognite.ai import load_pandasai

client = CogniteClient()
SmartDataframe, SmartDatalake, Agent = 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)

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)

Pandas AI agent

We can also

from cognite.client import CogniteClient
from cognite.ai import load_pandasai

client = CogniteClient()
SmartDataframe, SmartDatalake, Agent = await load_pandasai()

# Create example data
sales_by_country_df = pd.DataFrame({
    "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],
    "revenue": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000]
})

agent = Agent(sales_by_country_df, cognite_client=client)

print(agent.chat("Which are the top 5 countries by sales?"))

Metadata

Release files for andeplane-ai 0.5.2

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

Source distribution (sdist)

Source distribution for andeplane-ai 0.5.2
File Size Uploaded Provenance Actions
andeplane_ai-0.5.2.tar.gz 6.7 kB Without provenance Details for andeplane_ai-0.5.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for andeplane-ai 0.5.2
File Interpreter ABI Platform Actions
andeplane_ai-0.5.2-py3-none-any.whl Python 3 none any Details for andeplane_ai-0.5.2-py3-none-any.whl

Total release size: 15.1 kB

Release files / andeplane_ai-0.5.2.tar.gz

Download URL andeplane_ai-0.5.2.tar.gz
Size 6.7 kB
Tags Source
SHA-256 checksum
How to use checksums
ea2b18950e49c39b0cdb4a18ead64122e608d59ad5ac6dfe69c982b6587bace8
BLAKE2b-256 checksum
How to use checksums
ed61826e55770cc325735473ea760cf938c2976a4b4ce623bcb853de5b97a8f1
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.10

Release files / andeplane_ai-0.5.2-py3-none-any.whl

Download URL andeplane_ai-0.5.2-py3-none-any.whl
Size 8.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
6ab51bedde26197800d264062fed8209ac41ddc106fe10fc10c544b4ea860825
BLAKE2b-256 checksum
How to use checksums
ad577ee891cf57b6baa6ae7b8613e0fda19a9f150b7b46aa2ef7d8c7bfb7d4fa
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.11.10

Security for andeplane-ai 0.5.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page