From 980d88a0f2635d6d33070619f202ebe2874b21ab Mon Sep 17 00:00:00 2001 From: Branden Chan <33759007+brandenchan@users.noreply.github.com> Date: Wed, 1 Sep 2021 18:39:06 +0200 Subject: [PATCH] Update faq model (#1401) --- tutorials/Tutorial4_FAQ_style_QA.ipynb | 4 ++-- tutorials/Tutorial4_FAQ_style_QA.py | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tutorials/Tutorial4_FAQ_style_QA.ipynb b/tutorials/Tutorial4_FAQ_style_QA.ipynb index 20b89bc1b..c3f529a04 100644 --- a/tutorials/Tutorial4_FAQ_style_QA.ipynb +++ b/tutorials/Tutorial4_FAQ_style_QA.ipynb @@ -162,7 +162,7 @@ "document_store = ElasticsearchDocumentStore(host=\"localhost\", username=\"\", password=\"\",\n", " index=\"document\",\n", " embedding_field=\"question_emb\",\n", - " embedding_dim=768,\n", + " embedding_dim=384,\n", " excluded_meta_data=[\"question_emb\"])" ] }, @@ -182,7 +182,7 @@ "execution_count": null, "outputs": [], "source": [ - "retriever = EmbeddingRetriever(document_store=document_store, embedding_model=\"deepset/sentence_bert\", use_gpu=True)" + "retriever = EmbeddingRetriever(document_store=document_store, embedding_model=\"sentence-transformers/all-MiniLM-L6-v2\", use_gpu=True)" ], "metadata": { "collapsed": false, diff --git a/tutorials/Tutorial4_FAQ_style_QA.py b/tutorials/Tutorial4_FAQ_style_QA.py index 7edab6736..f82f29091 100755 --- a/tutorials/Tutorial4_FAQ_style_QA.py +++ b/tutorials/Tutorial4_FAQ_style_QA.py @@ -35,7 +35,7 @@ def tutorial4_faq_style_qa(): document_store = ElasticsearchDocumentStore(host="localhost", username="", password="", index="document", embedding_field="question_emb", - embedding_dim=768, + embedding_dim=384, excluded_meta_data=["question_emb"], similarity="cosine") @@ -43,7 +43,7 @@ def tutorial4_faq_style_qa(): # Instead of retrieving via Elasticsearch's plain BM25, we want to use vector similarity of the questions (user question vs. FAQ ones). # We can use the `EmbeddingRetriever` for this purpose and specify a model that we use for the embeddings. # - retriever = EmbeddingRetriever(document_store=document_store, embedding_model="deepset/sentence_bert", use_gpu=True) + retriever = EmbeddingRetriever(document_store=document_store, embedding_model="sentence-transformers/all-MiniLM-L6-v2", use_gpu=True) # Download a csv containing some FAQ data # Here: Some question-answer pairs related to COVID-19