Merge pull request #78 from dataforgoodfr/readme_demo_extract

Video demonstration of the streamlit app for extraction on the readme
dataforgoodfr · Apr 24, 2024 · 0063e2c · 0063e2c
2 parents bc132ee + 373b800
commit 0063e2c
Show file tree

Hide file tree

Showing 2 changed files with 13 additions and 0 deletions.
diff --git a/README.md b/README.md
@@ -61,6 +61,19 @@ This config file uses:
 - LangChain with GPT-4-turbo-preview for requesting the parsed tables to extract
   and re-order the necessary informations
 
+## Running the pipeline with the streamlit app
+
+You can also interact with the pipeline with a streamlit app :
+
+```
+streamlit run app/index.py
+```
+
+Below is an example of the pipeline running on one of the reports, parsing the tables with LlamaParse and Unstructured.
+
+[PipelineDemonstration.webm](https://github.com/dataforgoodfr/12_taxobservatory/assets/1128418/f9c64e83-9c15-4de2-a512-4f4b25f2f3ae)
+
+
 # Avaiable blocks
 
 ## Page filter

diff --git a/media/extraction_demo_bhp.webm b/media/extraction_demo_bhp.webm