Upload with huggingface_hub

.gitattributes

@@ -1,34 +1,2 @@
-*.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
-*.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
+index/**/* filter=lfs diff=lfs merge=lfs -text
+data/data-00000-of-00001.arrow filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,13 @@
 ---
-title: Imdb Search Pagination
-emoji: 🔥
+title: IMDB search
+emoji: 🐠
 colorFrom: blue
-colorTo: green
+colorTo: blue
 sdk: gradio
-sdk_version: 3.18.0
+sdk_version: 3.12.0
 app_file: app.py
 pinned: false
+license: apache-2.0
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,85 @@
+import gradio as gr
+from datasets import load_from_disk
+from pyserini.search.lucene import LuceneSearcher
+
+searcher = LuceneSearcher("index")
+ds = load_from_disk("data")
+NUM_PAGES = 10 # STATIC. THIS CAN'T CHANGE BECAUSE GRADIO CAN'T DYNAMICALLY CREATE COMPONENTS. 
+RESULTS_PER_PAGE = 5 
+
+TEXT_FIELD = "text"
+METADATA_FIELD = "docid"
+
+def result_html(result, meta):
+    return (
+    f"<div style=\"color:#2a5cb3;font-weight: 500\"><u>{meta}</u></div><br>"
+    f"<div><details><summary>{result[:250]}...</summary><p>{result[250:]}</p></details></div><br><hr><br>"
+    )
+
+def format_results(results):
+    return "\n".join([result_html(result, meta) for result,meta in zip(results[TEXT_FIELD], results[METADATA_FIELD])])
+    
+def page_0(query):
+    hits = searcher.search(query, k=NUM_PAGES*RESULTS_PER_PAGE)
+    ix = [int(hit.docid) for hit in hits]
+    results = ds.select(ix).shard(num_shards=NUM_PAGES, index=0, contiguous=True) # no need to shard. split ix in batches instead. (would make sense if results was cacheable)
+    results = format_results(results)
+    return results, [ix], gr.update(visible=True)
+
+def page_i(i, ix):
+    ix = ix[0]
+    results = ds.select(ix).shard(num_shards=NUM_PAGES, index=i, contiguous=True)
+    results = format_results(results)
+    return results, [ix]
+    
+with gr.Blocks(css="#b {min-width:15px;background:transparent;border:white;box-shadow:none;}") as demo: #
+    with gr.Row():
+        gr.Markdown(value="""## <p style="text-align: center;"> IMDB search </p>""")  
+    with gr.Row():
+        with gr.Column(scale=1):
+            result_list = gr.Dataframe(type="array", visible=False, col_count=1)      
+        with gr.Column(scale=13):
+            query = gr.Textbox(lines=1, max_lines=1, placeholder="Search…", label="")
+        with gr.Column(scale=1):
+            with gr.Row(scale=1):
+                pass
+            with gr.Row(scale=1):    
+                submit_btn = gr.Button("🔍", elem_id="b").style(full_width=False)
+            with gr.Row(scale=1):
+                pass
+                
+    with gr.Row():
+        with gr.Column(scale=1):
+            pass
+        with gr.Column(scale=13):
+            c = gr.HTML(label="Results")
+            with gr.Row(visible=False) as pagination:
+                # left = gr.Button(value="◀", elem_id="b", visible=False).style(full_width=True)
+                page_1 = gr.Button(value="1", elem_id="b").style(full_width=True)
+                page_2 = gr.Button(value="2", elem_id="b").style(full_width=True)
+                page_3 = gr.Button(value="3", elem_id="b").style(full_width=True)
+                page_4 = gr.Button(value="4", elem_id="b").style(full_width=True)
+                page_5 = gr.Button(value="5", elem_id="b").style(full_width=True)
+                page_6 = gr.Button(value="6", elem_id="b").style(full_width=True)
+                page_7 = gr.Button(value="7", elem_id="b").style(full_width=True)
+                page_8 = gr.Button(value="8", elem_id="b").style(full_width=True)
+                page_9 = gr.Button(value="9", elem_id="b").style(full_width=True)
+                page_10 = gr.Button(value="10", elem_id="b").style(full_width=True)
+                # right = gr.Button(value="▶", elem_id="b", visible=False).style(full_width=True)
+        with gr.Column(scale=1):
+            pass
+    query.submit(fn=page_0, inputs=[query], outputs=[c, result_list, pagination])
+    submit_btn.click(page_0, inputs=[query], outputs=[c, result_list, pagination])
+    with gr.Box(visible=False):
+        nums = [gr.Number(i, visible=False, precision=0) for i in range(NUM_PAGES)]
+    page_1.click(fn=page_i, inputs=[nums[0], result_list], outputs=[c, result_list])
+    page_2.click(fn=page_i, inputs=[nums[1], result_list], outputs=[c, result_list])
+    page_3.click(fn=page_i, inputs=[nums[2], result_list], outputs=[c, result_list])
+    page_4.click(fn=page_i, inputs=[nums[3], result_list], outputs=[c, result_list])
+    page_5.click(fn=page_i, inputs=[nums[4], result_list], outputs=[c, result_list])
+    page_6.click(fn=page_i, inputs=[nums[5], result_list], outputs=[c, result_list])
+    page_7.click(fn=page_i, inputs=[nums[6], result_list], outputs=[c, result_list])
+    page_8.click(fn=page_i, inputs=[nums[7], result_list], outputs=[c, result_list])
+    page_9.click(fn=page_i, inputs=[nums[8], result_list], outputs=[c, result_list])
+    page_10.click(fn=page_i, inputs=[nums[9], result_list], outputs=[c, result_list])
+demo.launch(enable_queue=True, debug=True)

data/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfaf51061c059feb91bd8f72f373869d655db66d82de94796c0b68ef8221921
+size 33438680

data/dataset_info.json

@@ -0,0 +1,55 @@
+{
+  "builder_name": "imdb",
+  "citation": "@InProceedings{maas-EtAl:2011:ACL-HLT2011,\n  author    = {Maas, Andrew L.  and  Daly, Raymond E.  and  Pham, Peter T.  and  Huang, Dan  and  Ng, Andrew Y.  and  Potts, Christopher},\n  title     = {Learning Word Vectors for Sentiment Analysis},\n  booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},\n  month     = {June},\n  year      = {2011},\n  address   = {Portland, Oregon, USA},\n  publisher = {Association for Computational Linguistics},\n  pages     = {142--150},\n  url       = {http://www.aclweb.org/anthology/P11-1015}\n}\n",
+  "config_name": "plain_text",
+  "dataset_size": 133190302,
+  "description": "Large Movie Review Dataset.\nThis is a dataset for binary sentiment classification containing substantially more data than previous benchmark datasets. We provide a set of 25,000 highly polar movie reviews for training, and 25,000 for testing. There is additional unlabeled data for use as well.",
+  "download_checksums": {
+    "http://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz": {
+      "num_bytes": 84125825,
+      "checksum": "c40f74a18d3b61f90feba1e17730e0d38e8b97c05fde7008942e91923d1658fe"
+    }
+  },
+  "download_size": 84125825,
+  "features": {
+    "text": {
+      "dtype": "string",
+      "_type": "Value"
+    },
+    "docid": {
+      "dtype": "int64",
+      "_type": "Value"
+    }
+  },
+  "homepage": "http://ai.stanford.edu/~amaas/data/sentiment/",
+  "license": "",
+  "size_in_bytes": 217316127,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 33432823,
+      "num_examples": 25000,
+      "dataset_name": "imdb"
+    },
+    "test": {
+      "name": "test",
+      "num_bytes": 32650685,
+      "num_examples": 25000,
+      "dataset_name": "imdb"
+    },
+    "unsupervised": {
+      "name": "unsupervised",
+      "num_bytes": 67106794,
+      "num_examples": 50000,
+      "dataset_name": "imdb"
+    }
+  },
+  "task_templates": [],
+  "version": {
+    "version_str": "1.0.0",
+    "description": "",
+    "major": 1,
+    "minor": 0,
+    "patch": 0
+  }
+}

data/state.json

@@ -0,0 +1,13 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "1d74567875c58748",
+  "_format_columns": null,
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": "train"
+}

index/_0_Lucene90_0.pos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dbe681b0efdc4898bbe577bbd385d79444e4292c27ee4e2969fd9cbcd353d14
+size 1282325

index/_1_Lucene90_0.pos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dba719a2c87ca74bdc184de9bc594834e11a1c467d10f42c47466df685308ccb
+size 1285669

index/_2_Lucene90_0.pos

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0e985ae3cba265a28c9e284ad3b8862d2611aa51b2447a14c9ad2053374fb47
+size 1220422