Add application file

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +0,0 @@
----
-title: LegalSearchApp
-emoji: 👀
-colorFrom: purple
-colorTo: yellow
-sdk: streamlit
-sdk_version: 1.29.0
-app_file: app.py
-pinned: false
-license: cc-by-nc-sa-4.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,60 @@
+# coding=utf-8
+import streamlit as st
+import json
+from search import TFIDF, GenClient
+
+
+def display_search_results(results, page_number, results_per_page):
+    st.title("Search Results")
+    start_idx = (page_number - 1) * results_per_page
+    end_idx = start_idx + results_per_page
+
+    for i, result in enumerate(results[start_idx:end_idx]):
+        if start_idx + i > 10:
+            st.write(f"{start_idx + i + 1}. [link](https://www.vlaanderen.be{result['link']}):\n PDPPDP \n {result['text']}")
+        else:
+            st.write(f"{start_idx + i + 1}. [{result['Nummer']}](https://www.vlaanderen.be{result['link']}):")
+            first_index = result['summary'].find('{')
+            last_index = result['summary'].rfind('}')
+            print(first_index, last_index)
+            summary = result['summary'][first_index:last_index+1]
+            print(summary)
+            summary = json.loads(summary)
+            print(summary)
+            if summary['relevancy'] == 'YES':
+                st.write(f"{summary['answer']}")
+
+        # st.write(f"{result['text']}")
+        relevant = st.checkbox(f"Is this document {start_idx + i} relevant?")
+
+
+# Function to annotate documents
+def main():
+    st.title("Legal Search Engine")
+    query = st.text_input("Enter your search query:")
+    model = TFIDF()
+    gen = GenClient()
+    if st.button("Search"):
+        results = model.search_all([query], top_k=5)[0]
+        for r in results:
+            r['summary'] = gen.respond(query, r['text'])
+
+            # for
+        #  gen.respond()
+        st.session_state.results = results
+
+    if "results" in st.session_state:
+        results = st.session_state.results
+        st.write("Search Results:")
+        results_per_page = st.slider("Results per Page", min_value=1, max_value=len(results), value=5)
+        page_number = st.number_input("Page Number", min_value=1, max_value=len(results), value=1)
+
+        # Display search results for the selected page
+        display_search_results(results, page_number, results_per_page)
+
+
+# Press the green button in the gutter to run the script.
+if __name__ == '__main__':
+    # Sample data (replace with your own dataset)
+    main()
+    # display_all_documents()