Spaces:
Runtime error
Runtime error
Merge remote-tracking branch 'origin/main'
Browse files
README.md
CHANGED
@@ -14,6 +14,37 @@ license: cc-by-sa-4.0
|
|
14 |
|
15 |
This project is a demonstration playground for the LLM-enabled architectures built as a submission for the Online MSc in Artificial Intelligence through the University of Bath. The purpose of the project is to explore "LLM-enabled architectures" where an LLM is used in conjunction with some store of private data. The goal is to provide decision support information to technical managers on the _how_ of using LLMs with their organisational data. Specifically by comparing technical architectures and assessing the organisational implications of the technical choices.
|
16 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
# Demonstration environment
|
18 |
|
19 |
The project is available as a demonstration running [here on Hugging Face Spaces](https://huggingface.co/spaces/alfraser/llm-arch). This should be the preferred method to interact with the project.
|
|
|
14 |
|
15 |
This project is a demonstration playground for the LLM-enabled architectures built as a submission for the Online MSc in Artificial Intelligence through the University of Bath. The purpose of the project is to explore "LLM-enabled architectures" where an LLM is used in conjunction with some store of private data. The goal is to provide decision support information to technical managers on the _how_ of using LLMs with their organisational data. Specifically by comparing technical architectures and assessing the organisational implications of the technical choices.
|
16 |
|
17 |
+
# File Structure
|
18 |
+
|
19 |
+
<pre>
|
20 |
+
llm-arch
|
21 |
+
βββ config
|
22 |
+
β βββ architectures.json <i>(configuration for the architectures under test and displayed in the UI)</i>
|
23 |
+
βββ data
|
24 |
+
β βββ fine_tuning <i>(data and scripts related to fine-tuning LLMs)</i>
|
25 |
+
β βββ json <i>(raw json files containing the synthetic private data built for the project)</i>
|
26 |
+
β βββ sqlite
|
27 |
+
β β βββ 01_all_products_dataset.db <i>(sqlite db containing all products generated)</i>
|
28 |
+
β β βββ 02_baseline_dataset.db <i>(sqlite db containing the subset of data selected to be the baseline)</i>
|
29 |
+
β β βββ test_records.db <i>(sqlite database containing the peristed test results)</i>
|
30 |
+
β βββ vector_stores <i>(chromadb files containing the document embeddings for the RAG architectures)</i>
|
31 |
+
βββ img
|
32 |
+
βββ pages
|
33 |
+
βββ src
|
34 |
+
β βββ data_synthesis <i>(python code related to generating, selecting and loading the private dataset used for the project)</i>
|
35 |
+
β βββ training <i>(python code related to training the architectures - not used at runtime)</i>
|
36 |
+
β βββ architectures.py <i>(the core architecture pipeline code including components, and trace)</i>
|
37 |
+
β βββ common.py <i>(utilities for common functions, e.g. security token access, data type manipulations)</i>
|
38 |
+
β βββ datatypes.py <i>(object oriented representation of the test data and single point for runtime access of the product DB)</i>
|
39 |
+
β βββ st_helpers.py <i>(helpers specific to streamlit)</i>
|
40 |
+
β βββ testing.py <i>(functionality relating to running, recording and reporting on batches of tests)</i>
|
41 |
+
βββ Home.py <i>(main entry point for streamlit - first page in the streamlit app)</i>
|
42 |
+
βββ local_env.yml <i>(conda environment for running project locally)</i>
|
43 |
+
βββ README.md <i>(readme - this file)</i>
|
44 |
+
βββ requirements.txt <i>(requirements file for additional requirements in the HF spaces environment - do not use for local running of the project)</i>
|
45 |
+
</pre>
|
46 |
+
|
47 |
+
|
48 |
# Demonstration environment
|
49 |
|
50 |
The project is available as a demonstration running [here on Hugging Face Spaces](https://huggingface.co/spaces/alfraser/llm-arch). This should be the preferred method to interact with the project.
|