Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Update README.md
Browse files
README.md
CHANGED
@@ -1,82 +1,10 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
``````
|
12 |
-
|
13 |
-
#### Install pre-commit hooks
|
14 |
-
|
15 |
-
```bash
|
16 |
-
pre-commit install
|
17 |
-
pre-commit
|
18 |
-
``````
|
19 |
-
|
20 |
-
|
21 |
-
#### Start app
|
22 |
-
|
23 |
-
- excute the following command with the respective version
|
24 |
-
|
25 |
-
```bash
|
26 |
-
streamlit run src/app/v1/app.py
|
27 |
-
``````
|
28 |
-
|
29 |
-
## Data Overview
|
30 |
-
|
31 |
-
- taxonomy_related data
|
32 |
-
- ```data/authors_taxonomy.json```: raw countries taxonomy
|
33 |
-
- ```data/draft_cat_taxonomy.json```: draft cat taxonomy.json
|
34 |
-
- ```data/authors_filter.json```: processed taxonomy for frontend filtering
|
35 |
-
- ```data/draftcat_taxonomy_filter.json```: processed taxonomy for frontend filtering
|
36 |
-
- ```data/inc_df_v6_small.csv```: processed data of scraping
|
37 |
-
- ```data/inc_df.csv```: data for document Storage
|
38 |
-
- ```data/taxonomies.txt```: raw taxonomies collection
|
39 |
-
- application related data
|
40 |
-
- ```database/document_store.pkl```: Document Store
|
41 |
-
- ```database/document_store.pkl```: Meta data of the document store with countries and draft labs as columns
|
42 |
-
|
43 |
-
## Code Structure
|
44 |
-
|
45 |
-
### Data Preprocessing
|
46 |
-
|
47 |
-
- ```src/data_processing/document_store_data.py```: Generates the data for the document store with last processing steps
|
48 |
-
- ```src/data_processing/get_meta_data_filter.py```: Generates the meta data from document store for the filtering in the frontend
|
49 |
-
- ```src/data_processing/taxonomy_processing.py```: Transforms the taxonomies for the filters in the frontend.
|
50 |
-
|
51 |
-
### Frontend
|
52 |
-
|
53 |
-
- ```src/app/```: versions of app
|
54 |
-
- ```src/utils```: The utils folder contains functions used in the frontend application. Please check the imports to see which functions are used.
|
55 |
-
- ```styles```: css styles for apps
|
56 |
-
- ```.streamlit```: Basic Theme of Frontend
|
57 |
-
- Some Settings and Changes related to the Spaces App have to be done directly in the respective Streamlit App.
|
58 |
-
|
59 |
-
### Backend
|
60 |
-
|
61 |
-
- ```src/document_store/document_store.py```: Generates the document store
|
62 |
-
- ```src/rag/pipeline.py```: RAG Pipeline
|
63 |
-
- ```src/rag/prompt/prompt_template.yaml```: Prompt Template for RAG
|
64 |
-
|
65 |
-
## Changes Document Storage
|
66 |
-
|
67 |
-
- **Step 1**: Delete the ```database/document_store.pkl``` and the ```database/meta_data.csv``` files or give them a new name if you want to keep them until a successful change of the document storage.
|
68 |
-
- **Step 2**: Run the script ```data_processing/document_store_data.py```. This changes update the ```data/inc_df.csv``` data. If you need to make changes in the ```data/inc_df_small_v6.csv```, they have to made either manually or you have to implement a new script with the changes.
|
69 |
-
- **Step 3***: Run the script ```data_processing/get_meta_data_filter.py```. This will save a new document store and the meta_data from the document store.
|
70 |
-
- **Step 4**: If the changes affect also the taxonomy then you need to update the taxonomies as well. To do so, first update manually ```data/authors_taxonomy.json``` and ```data/draftcat_taxonomy.json```. Then run the script ```src/data_processing/taxonomy_processing.py```.
|
71 |
-
- Frequent Bugs after changes of the data:
|
72 |
-
- new country or draft lab category or changes in the naming. Solution: Check the taxonomy files and update the ```src/data_processing/taxonomy_processing.py```
|
73 |
-
- countries with special characters. Solution: Check ```data/inc_df_small_v6.csv``` if the ```data_processing/document_store_data.py``` fails. Check the ```database/meta_data.py```if the frontend application fails after changes and the taxonomies + filters.
|
74 |
-
|
75 |
-
## Changes App
|
76 |
-
|
77 |
-
- Please always check changes in the app locally before pushing to the respective Spaces App.
|
78 |
-
- To check the Spaces App locally you can clone it like Git Repositories. Do avoid making changes directly in the interface of the Spaces App.
|
79 |
-
- Also if you copy changes from git to Spaces only copy the files where you have made changes. You need to make some adjustment before you copy the files:
|
80 |
-
- Please remove all OPENAI_KEYS from the app.py file and the the pipeline.py files.
|
81 |
-
- Make sure you added the following at the ```OPENAI_API_KEY = os.environ.get("OPEN_API_KEY")``` in the pipeline.py file
|
82 |
-
- Remove from app.py and pipeline.py ```src``` from imports. Otherwise you will get a ModuleNotFoundError.
|
|
|
1 |
+
---
|
2 |
+
title: "NegotiateAI"
|
3 |
+
emoji: "🤖"
|
4 |
+
colorFrom: "blue"
|
5 |
+
colorTo: "green"
|
6 |
+
sdk: "gradio" # or "streamlit" if you are using Streamlit
|
7 |
+
sdk_version: "3.0.0" # Change this to the correct version of the SDK you are using
|
8 |
+
app_file: app.py # Change this to your app's main file (could be "streamlit_app.py" if you use Streamlit)
|
9 |
+
pinned: false
|
10 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|