Sam commited on
Commit
cfe0f9b
·
1 Parent(s): 03a9af9

Update README, chainlit, and data files

Browse files
Files changed (4) hide show
  1. .DS_Store +0 -0
  2. .env.sample +0 -5
  3. README.md +8 -6
  4. chainlit.md +8 -16
.DS_Store ADDED
Binary file (6.15 kB). View file
 
.env.sample DELETED
@@ -1,5 +0,0 @@
1
- # !!! DO NOT UPDATE THIS FILE DIRECTLY. MAKE A COPY AND RENAME IT `.env` TO PROCEED !!! #
2
- HF_LLM_ENDPOINT="YOUR_LLM_ENDPOINT_URL_HERE"
3
- HF_EMBED_ENDPOINT="YOUR_EMBED_MODEL_ENDPOINT_URL_HERE"
4
- HF_TOKEN="YOUR_HF_TOKEN_HERE"
5
- # !!! DO NOT UPDATE THIS FILE DIRECTLY. MAKE A COPY AND RENAME IT `.env` TO PROCEED !!! #
 
 
 
 
 
 
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- title: Midterm App
3
  emoji: 🏠
4
  colorFrom: blue
5
  colorTo: purple
@@ -8,9 +8,11 @@ app_file: app.py
8
  pinned: false
9
  ---
10
 
11
- # Midterm App
12
 
13
- This is the Midterm App, a project developed for the AI Engineering course. The application leverages Chainlit, LangChain, OpenAI, and Qdrant to perform retrieval-augmented generation (RAG) on a PDF document.
 
 
14
 
15
  ## Features
16
 
@@ -45,8 +47,8 @@ Run the application with:
45
 
46
  Once the application is running, you can access it in your browser at http://localhost:7860.
47
 
48
- ## Contributing
49
- Contributions are welcome! Please feel free to submit a Pull Request.
50
 
51
  ## License
52
- This project is licensed under the MIT License.
 
1
  ---
2
+ title: Compass FSS Advisor
3
  emoji: 🏠
4
  colorFrom: blue
5
  colorTo: purple
 
8
  pinned: false
9
  ---
10
 
11
+ # Compass FSS Advisor
12
 
13
+ Compass Working Capital is committed to enhancing the support provided to organizations adopting the Family Self-Sufficiency (FSS) program model. To achieve this, Compass has partnered with Ascend Impact Advisors (www.ascendimpactadvisors.com) to develop and test prototypes of custom AI Agents capable of efficiently and accurately respond to queries related to the FSS program, encompassing HUD rules and regulations, and Compass’s evidence-based program model. It is intended for use by Compass staff and Compass FSS Link members under the guidance of trained Compass program staff.
14
+
15
+ The application leverages Chainlit, LangChain, OpenAI, and Qdrant to perform retrieval-augmented generation (RAG) on its knowledge base.
16
 
17
  ## Features
18
 
 
47
 
48
  Once the application is running, you can access it in your browser at http://localhost:7860.
49
 
50
+ ## Disclaimer
51
+ The beta software, tool, product, feature and services (“Beta”) licensed hereunder is still in the testing phase and is provided on an “as is” and “as available” basis and may contain defects, inaccuracies and limited security protections. The primary purpose of this beta testing is to obtain feedback on the Beta software’s performance, services and the identification of defects. You are advised to safeguard important data, to use caution and not to rely in any way on the correct functioning or performance of the Beta and/or accompanying materials. Do not enter any sensitive or confidential information into the Beta. Ascend Impact Advisors expressly disclaims any responsibility for the security of any user information that you enter into the Beta. Any downloading or uploading of material to the Beta is done at your own risk and you will be solely responsible for any damage to any computer system or loss of data that results from such activities. Ascend Impact Advisors may modify or discontinue the Beta or any parts thereof at any time in its sole discretion. Neither Ascend Impact Advisors nor its respective officers, directors, members, employees or agents will have any liability for any harm or damage arising out of or in connection with limiting or removing your access to or use of the Beta or any parts thereof.
52
 
53
  ## License
54
+ Contact Compass Working Capital for details.
chainlit.md CHANGED
@@ -1,23 +1,15 @@
1
- Welcome to the AirBnB 10k filing QnA Bot!
2
 
3
- This bot answers questions from Airbnb's Q1 2024 10-K filings to demonstrate the power of AI to process complex financial documents and provide precise insights. It's the midterm assignment for the AI Makerspace AI Engineering Bootcamp.
4
 
5
- My mind is buzzing with the potential to harness this kind of application to drive social impact, and I can't wait to use what I'm learning co-create solutions with nonprofits, social enterprises, and government agencies across the US.
6
 
7
- Here's a bit more on the assignment for those who are interested:
8
 
9
- Build 🏗️
10
 
11
- Data: Airbnb 10-k Filings from Q1, 2024
12
- LLM: You decide! (I picked OpenAI.)
13
- Embedding Model: You decide! (I picked OpenAI.)
14
  Infrastructure: LangChain
15
  Vector Store: QDrant
16
- Deployment: Chainlit, Hugging Face
17
-
18
- Ship 🚢
19
-
20
- Evaluate your answers to the following questions
21
- Q1 "What is Airbnb's 'Description of Business'?"
22
- Q2 "What was the total value of 'Cash and cash equivalents' as of December 31, 2023?"
23
- Q3 "What is the 'maximum number of shares to be sold under the 10b5-1 Trading plan' by Brian Chesky?"
 
 
1
 
2
+ Welcome to Compass Working Capital's AI-Powered FSS Advisor (beta)!
3
 
4
+ This bot is designed to enhance support for organizations adopting the Compass Working Capital Family Self-Sufficiency (FSS) program model by efficiently and accurately responding to queries related to FSS. In collaboration with Ascend Impact Advisors (www.ascendimpactadvisors.com), Compass has developed and tested three prototypes of AI Agents, each using a different set of technologies (two leveraging low code solutions and one leveraging code). These agents are capable of addressing questions about HUD rules and regulations as well as Compass’s evidence-based program model, seeking to streamline the support process for Compass staff and FSS Link members.
5
 
6
+ Here's a bit more on the details of this FSS Advisor prototype (beta) for those who are interested:
7
 
8
+ About This Build 🏗️
9
 
10
+ Data: CFR parts 887 and 984, FSS Final Rule, and the FSS Program Guidebook
11
+ LLM: OpenAI GPT-4o
12
+ Embedding Model: OpenAI text-embedding-3-small
13
  Infrastructure: LangChain
14
  Vector Store: QDrant
15
+ Deployment: Chainlit, Hugging Face