test

.gitignore

@@ -0,0 +1,2 @@
+__pycache__
+*.sqlite

app.py

@@ -7,11 +7,12 @@ embeddings = SentenceTransformerEmbeddings(model_name="multi-qa-MiniLM-L6-cos-v1
 db = FAISS.load_local('faiss_qa', embeddings)
 
 def main(query):
+    query = query.lower()
     result_docs = db.similarity_search_with_score(query, k=20)
     sentences = [doc[0].page_content for doc in result_docs]
-    # print('----------------------------------------------------------------')
-    # for doc in result_docs:
-    #     print(doc[0].metadata['articleId'], ' | ', doc[0].page_content, ' | ', doc[0].metadata['answer'])
+    #print('----------------------------------------------------------------')
+    #for doc in result_docs:
+    #    print(doc[0].metadata['articleId'], ' | ', doc[0].page_content, ' | ', doc[0].metadata['answer'])
     score, index = reranking.search(query, sentences)
     return result_docs[index][0].metadata['answer'], score, result_docs[index][0].page_content
 

faiss_qa/index.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8971a7f31e9824d0bd025ec6d4098ffc20bae88ab6faa972b074959661f3fecf
+oid sha256:654deaa1266f3e8eab26b2506d37383b8a29231daf1af292638c0e4821c45c5f
 size 263215

test.ipynb

@@ -22,18 +22,18 @@
     "      for res in results:\n",
     "        \n",
     "        questions = json.loads(res['questions'])\n",
-    "        questions_copy = questions.copy()\n",
+    "        # questions_copy = questions.copy()\n",
     "        \n",
     "        for q in questions:\n",
-    "          q['query'] = \" \".join(res['section'].split() + res['title'].split() + q['question'].split())\n",
+    "          q['query'] = \" \".join(res['section'].split() + res['title'].split() + q['question'].split()).lower()\n",
     "          q['articleId'] = res['articleId']\n",
     "          \n",
-    "        for q in questions_copy:\n",
-    "          q['query'] = q['question']\n",
-    "          q['articleId'] = res['articleId']\n",
+    "        # for q in questions_copy:\n",
+    "        #   q['query'] = q['question']\n",
+    "        #   q['articleId'] = res['articleId']\n",
     "\n",
     "        all_questions += questions\n",
-    "        all_questions += questions_copy\n",
+    "        # all_questions += questions_copy\n",
     "  return all_questions\n",
     "\n",
     "questions = load_questions(\"omnidesk-ai-chatgpt-questions.sqlite\")"