Skip to content

Commit 357a2ae

Browse files
committed
add genai docs
modified: docs/genai/01_getting_started/01_intro.mdx deleted: docs/genai/02_external_llms/01_llm_access.md new file: docs/genai/02_external_llms/01_llm_access.mdx modified: docs/genai/02_external_llms/02_catalogue.md modified: docs/genai/02_external_llms/03_playground.md new file: docs/genai/02_external_llms/static/portkey_arch.png modified: docs/genai/04_vector_databases/01_intro.md
1 parent 5052308 commit 357a2ae

File tree

7 files changed

+63
-11
lines changed

7 files changed

+63
-11
lines changed
Lines changed: 10 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,14 @@
1-
# Pythia, the Generative AI platform for Research workflows
1+
# Pythia
22

3-
:::tip[Non-research workflows]
3+
:::warning[Non-research workflows]
44
If you're looking to harness Generative AI for administrative or classroom use, please reach out to [email protected]
55
:::
66

7-
Welcome to Pythia, the generative AI platform for research workflows.
7+
Welcome to Pythia, the generative AI platform for research workflows. As part of the Pythia platform, the following capabilities are offered:
8+
- [Access to externally hosted LLMs](../02_external_llms/01_llm_access.mdx)
9+
- [HPC resources for fine tuning LLMs](../03_llm_fine_tuning/01_intro.md)
10+
- [Milvus vector database](../04_vector_databases/01_intro.md)
11+
12+
:::tip[Personal use]
13+
If you want to access NYU provided LLMs for personal use, proceed to https://gemini.google.com/app with your NYU credentials.
14+
:::

docs/genai/02_external_llms/01_llm_access.md

Lines changed: 0 additions & 5 deletions
This file was deleted.
Lines changed: 50 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,50 @@
1+
# Portkey
2+
3+
[Portkey](https://portkey.ai/docs/introduction/what-is-portkey) is an enterprise-grade LLM gateway running on-prem:
4+
5+
![Portkey Architecture](./static/portkey_arch.png)
6+
7+
Broadly it facilitates:
8+
- **Route requests** via configurations that can allow for fallbacks, load balance, etc
9+
- **Observability** via the control pane that displays your usage statistics and logs. You can retrive your logs via an API.
10+
- **Prompt management** via the prompt playground. You can compare the respone for a prompt across multiple LLMs, collaborate with your team and export your prompts.
11+
- **Guardrails** usage by allowing you to define them or integrate with third party guardrails.
12+
- **Agentic workflows** by integrating with various agentic frameworks like langchain, llamaindex, etc.
13+
- **Security & Governance** by allowing you to set budget and rate limits on the API keys created for your workspace
14+
15+
:::tip[Gateway URL]
16+
Whenever you instantiate a Portkey client, the `base_url` must be set to `base_url="https://ai-gateway.apps.cloud.rt.nyu.edu/v1/"`. If you miss this parameter you would be connecting to the vendor's SaaS platform and NYU provisioned virtual keys will not work.
17+
:::
18+
19+
## Onboarding
20+
Send an email to `[email protected]` to start the onboarding process.
21+
22+
## Getting started with Portkey
23+
As part of the onboarding process, you would have received an invite which gives you access to a workspace. We will also add virtual keys for LLMs to your workspace as part of the onboarding process. Once you've accepted it, head over to `https://app.portkey.ai/` and select the sign-in with Single Sign-On option and proceed with your NYU email address.
24+
25+
:::danger[Access to Portkey is only permitted via NYU VPN]
26+
You need to be connected to the NYU VPN to access the Portkey LLM gateway. If you are not, your requests will timeout and result in connection errors.
27+
:::
28+
29+
You will now be able to create an API key for yourself by access the `API Keys` item on the left sidebar. With an API key and a virtual key at your disposal, you can now run the following script:
30+
```python
31+
from portkey_ai import Portkey
32+
33+
portkey = Portkey(
34+
base_url="https://ai-gateway.apps.cloud.rt.nyu.edu/v1/",
35+
api_key="", # Replace with your Portkey API key
36+
virtual_key="", # Replace with your virtual key for Google
37+
)
38+
39+
completion = portkey.chat.completions.create(
40+
messages=[
41+
{"role": "system", "content": "You are not a helpful assistant"},
42+
{"role": "user", "content": "Say this is a test"},
43+
],
44+
model="gemini-2.0-flash-lite-preview-02-05",
45+
)
46+
47+
print(completion)
48+
```
49+
50+
Once the script is executed, you can head back to `app.portkey.ai` to view the logs for the call!

docs/genai/02_external_llms/02_catalogue.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
# External models listed by provider
22

3+
We currently facilitate access to the following externally hosted LLMs:
4+
35
## OpenAI
46
- gpt-4o-mini
57
- o3-mini
Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,3 @@
11
# OpenWebUI
22

3-
Provided as a way to access all external LLMs via a GUI.
3+
We are working on providing an NYU hosted instance of [OpenWebUI](https://docs.openwebui.com/). More details about this will be provided soon.
868 KB
Loading
Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,3 @@
11
# Vector Databases
22

33
What is it? How is it different from a regular database?
4-
5-
Milvus at NYU.

0 commit comments

Comments
 (0)