first commit

app.py

@@ -0,0 +1,153 @@
+import os
+
+import streamlit as st
+import streamlit.components.v1 as components
+from datasets import load_dataset
+
+
+st.set_page_config(page_title="Gaia Search", layout="wide")
+
+os.makedirs(os.path.join(os.getcwd(), ".streamlit"), exist_ok=True)
+with open(os.path.join(os.getcwd(), ".streamlit/config.toml"), "w") as file:
+    file.write('[theme]\nbase="light"')
+
+
+st.sidebar.markdown(
+    """
+<style>
+.aligncenter {
+    text-align: center;
+    font-weight: bold;
+    font-size: 50px;
+}
+</style>
+<p class="aligncenter">Gaia Search 🌖🌏</p>
+<p style="text-align: center;"> A search engine for the LAION large scale image caption corpora</p>
+""",
+    unsafe_allow_html=True,
+)
+
+st.sidebar.markdown(
+    """
+<style>
+.aligncenter {
+    text-align: center;
+}
+</style>
+<p style='text-align: center'>
+<a href="" >GitHub</a> | <a href="" >Project Report</a>
+</p>
+<p class="aligncenter">
+  <a href="" target="_blank"> 
+        <img src="https://colab.research.google.com/assets/colab-badge.svg"/>
+    </a>
+</p>
+""",
+    unsafe_allow_html=True,
+)
+
+query = st.sidebar.text_input(label="Search query", value="")
+
+footer = """<style>
+.footer {
+position: fixed;
+left: 0;
+bottom: 0;
+width: 100%;
+background-color: white;
+color: black;
+text-align: center;
+}
+</style>
+<div class="footer">
+<p>Powered by <a href="https://huggingface.co/" >HuggingFace 🤗</a> and <a href="https://github.com/castorini/pyserini" >Pyserini 🦆</a></p>
+</div>
+"""
+st.sidebar.markdown(footer, unsafe_allow_html=True)
+
+
+searcher = LuceneSearcher("index")
+ds = load_dataset("imdb", split="train")
+
+
+def search(query):
+    hits = searcher.search(query, k=10)
+    results = ds.select([int(hit.docid) for hit in hits])
+    return results + "<br><br>"
+
+
+if st.sidebar.button("Search"):
+    results = search(query)
+    rendered_results = f"""
+            <div id="searchresultsarea">
+                <br>
+                {results}
+            </div>
+                        """
+    st.markdown(
+        """
+                <link href="https://cdn.jsdelivr.net/npm/bootstrap@5.0.2/dist/css/bootstrap.min.css" rel="stylesheet" 
+                    integrity="sha384-EVSTQN3/azprG1Anm3QDgpJLIm9Nao0Yz1ztcQTwFspd3yD65VohhpuuCOmLASjC" crossorigin="anonymous">
+                """,
+        unsafe_allow_html=True,
+    )
+    st.markdown(
+        """
+        <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.0.0/css/all.min.css">                                  
+        """,
+        unsafe_allow_html=True,
+    )
+    st.markdown(
+        f"""
+        <div class="row no-gutters mt-3 align-items-center">
+            Gaia Search 🌖🌏
+            <div class="col col-md-4">
+                <input class="form-control border-secondary rounded-pill pr-5" type="search" value="{query}" id="example-search-input2">
+            </div>
+            <div class="col-auto">
+                <button class="btn btn-outline-light text-dark border-0 rounded-pill ml-n5" type="button">
+                    <i class="fa fa-search"></i>
+                </button>
+            </div>
+        </div> 
+        """,
+        unsafe_allow_html=True,
+    )
+    components.html(
+        """
+        <style>
+        #searchresultsarea {
+            font-family: 'Arial';
+        }
+        
+        #searchresultsnumber {
+            font-size: 0.8rem;
+            color: gray;
+        }
+        
+        .searchresult h2 {
+            font-size: 19px;
+            line-height: 18px;
+            font-weight: normal;
+            color: rgb(7, 111, 222);
+            margin-bottom: 0px;
+            margin-top: 25px;
+        }
+        
+        .searchresult a {
+            font-size: 12px;
+            line-height: 12px;
+            color: green;
+            margin-bottom: 0px;
+        }
+    
+        .dark-mode {
+          color: white;
+        }
+        </style>
+        <button onclick="myFunction()">Toggle dark mode</button>
+        """
+        + rendered_results,
+        height=800,
+        scrolling=True,
+    )

index/_c_Lucene90_0.pos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ac8c1c910a978617aa54300a6c2421ab1295ad8fd3a28da9eca9ffec36948d
+size 1240149

index/_d_Lucene90_0.pos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1185b23dfe7d554487554e5b731375c22821508fcf8781aec15d0899984efa
+size 1262499

index/_e_Lucene90_0.pos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccaee5e5633b5c35ba7045c5e12e692587380d32c3020b81bac24a28da69ca2
+size 1238216