make similarity gradio app

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,20 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N806" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="nextcord.ui.view.View.*" />
+          <option value="typing.Coroutine.__getitem__" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (ns_issue_search)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ns_issue_search.iml" filepath="$PROJECT_DIR$/.idea/ns_issue_search.iml" />
+    </modules>
+  </component>
+</project>

.idea/ns_issue_search.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

app.py

@@ -1,62 +1,44 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from FlagEmbedding import BGEM3FlagModel
+import numpy as np
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+model = BGEM3FlagModel('BAAI/bge-m3',
+                       use_fp16=True) # Setting use_fp16 to True speeds up computation with a slight performance degradation
+issue_embeddings = np.load('ns_issues_dense_bge-m3.npy')
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def get_similarity(search_term):
+    search_embedding = model.encode([search_term])['dense_vecs']
+    similarity = search_embedding @ issue_embeddings.T
+    return similarity
 
-    messages.append({"role": "user", "content": message})
 
-    response = ""
+def get_similarity_rankings(search_term):
+    similarity = get_similarity(search_term)
+    search_sentence = [search_term]
+    results = []
+    for i, search_query_similarities in enumerate(similarity):
+        indexed_similarities = []
+        for issue_index, sim_score in enumerate(search_query_similarities):
+            indexed_similarities.append((issue_index, sim_score))
+        sorted_similarities = sorted(indexed_similarities, key=lambda item: item[1], reverse=True)
+        results.append(sorted_similarities)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    similarity_text = ""
+    for i, search_query_result in enumerate(results):
+        similarity_text += f"Search Query: {search_sentence[i]}"
+        for index, sim_score in search_query_result[:20]:
+            similarity_text += f"\nIssue {index}, Similarity: {sim_score:.4f}"
 
-        response += token
-        yield response
+    return similarity_text
 
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
 """
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+demo = gr.Interface(
+    get_similarity_rankings,
+    inputs=["text"],
+    outputs=["text"],
 )
 
 

ns_issues_dense_bge-m3.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f1b40ff8445d9b7ce7c4018094b8480bfde110741d67111bbd5a3e990c8da62
+size 3399808

requirements.txt

@@ -1 +1,3 @@
-huggingface_hub==0.25.2
+huggingface_hub==0.25.2
+FlagEmbedding
+gradio