ted-at-openai/update-embedding-examples (#67)

* updates embeddings examples

* updates README with new example notebook using embeddings for recommendation

Author: ted-at-openai

README.md

@@ -100,6 +100,7 @@ Examples of how to use embeddings are shared in the following Jupyter notebooks:
 - [Semantic text search using embeddings](https://github.com/openai/openai-python/blob/main/examples/embeddings/Semantic_text_search_using_embeddings.ipynb)
 - [User and product embeddings](https://github.com/openai/openai-python/blob/main/examples/embeddings/User_and_product_embeddings.ipynb)
 - [Zero-shot classification using embeddings](https://github.com/openai/openai-python/blob/main/examples/embeddings/Zero-shot_classification.ipynb)
+- [Recommendation using embeddings](https://github.com/openai/openai-python/blob/main/examples/embeddings/Recommendation.ipynb)
 
 For more information on embeddings and the types of embeddings OpenAI offers, read the [embeddings guide](https://beta.openai.com/docs/guides/embeddings) in the OpenAI documentation.
 

examples/embeddings/Clustering.ipynb

@@ -31,7 +31,7 @@
     "\n",
     "\n",
     "df = pd.read_csv('output/embedded_1k_reviews.csv')\n",
-    "df['babbage_similarity'] = df.babbage_similarity.apply(eval).apply(np.array)\n",
+    "df['text-similarity-babbage-001'] = df.babbage_similarity.apply(eval).apply(np.array)\n",
     "matrix = np.vstack(df.babbage_similarity.values)\n",
     "matrix.shape"
    ]
@@ -253,7 +253,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.9.9"
   },
   "orig_nbformat": 4
  },

examples/embeddings/Code_search.ipynb

@@ -81,7 +81,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "For code search models we use babbage-code-search-code to obtain embeddings for code snippets, and code-search-text to embed natural language queries."
+    "For code search models we use code-search-{model}-code to obtain embeddings for code snippets, and code-search-{model}-text to embed natural language queries."
    ]
   },
   {
@@ -188,7 +188,7 @@
     "from openai.embeddings_utils import get_embedding\n",
     "\n",
     "df = pd.DataFrame(all_funcs)\n",
-    "df['code_embedding'] = df['code'].apply(lambda x: get_embedding(x, engine='babbage-code-search-code'))\n",
+    "df['code_embedding'] = df['code'].apply(lambda x: get_embedding(x, engine='code-search-babbage-code-001'))\n",
     "df['filepath'] = df['filepath'].apply(lambda x: x.replace(code_root, \"\"))\n",
     "df.to_csv(\"output/code_search_openai-python.csv\", index=False)\n",
     "df.head()"
@@ -234,7 +234,7 @@
     "from openai.embeddings_utils import cosine_similarity\n",
     "\n",
     "def search_functions(df, code_query, n=3, pprint=True, n_lines=7):\n",
-    "    embedding = get_embedding(code_query, engine='babbage-code-search-text')\n",
+    "    embedding = get_embedding(code_query, engine='code-search-babbage-text-001')\n",
     "    df['similarities'] = df.code_embedding.apply(lambda x: cosine_similarity(x, embedding))\n",
     "\n",
     "    res = df.sort_values('similarities', ascending=False).head(n)\n",

examples/embeddings/Get_embeddings.ipynb

@@ -50,13 +50,12 @@
     "from tenacity import retry, wait_random_exponential, stop_after_attempt\n",
     "\n",
     "@retry(wait=wait_random_exponential(min=1, max=20), stop=stop_after_attempt(6))\n",
-    "def get_embedding(text, engine=\"text-similarity-davinci-001\"):\n",
-    "\n",
+    "def get_embedding(text: str, engine=\"text-similarity-davinci-001\") -> List[float]:\n",
     "\n",
     "    # replace newlines, which can negatively affect performance.\n",
     "    text = text.replace(\"\\n\", \" \")\n",
     "\n",
-    "    return openai.Embedding.create(input=[text], engine=engine)['data'][0]['embedding']\n",
+    "    return openai.Embedding.create(input=[text], engine=engine)[\"data\"][0][\"embedding\"]\n",
     "\n",
     "embedding = get_embedding(\"Sample query text goes here\", engine=\"text-search-ada-query-001\")\n",
     "print(len(embedding))"

examples/embeddings/Obtain_dataset.ipynb

@@ -159,8 +159,8 @@
     "from openai.embeddings_utils import get_embedding\n",
     "\n",
     "# This will take just under 10 minutes\n",
-    "df['babbage_similarity'] = df.combined.apply(lambda x: get_embedding(x, engine='babbage-similarity'))\n",
-    "df['babbage_search'] = df.combined.apply(lambda x: get_embedding(x, engine='babbage-search-document'))\n",
+    "df['babbage_similarity'] = df.combined.apply(lambda x: get_embedding(x, engine='text-similarity-babbage-001'))\n",
+    "df['babbage_search'] = df.combined.apply(lambda x: get_embedding(x, engine='text-search-babbage-doc-001'))\n",
     "df.to_csv('output/embedded_1k_reviews.csv')"
    ]
   }
@@ -183,7 +183,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.9.9"
   },
   "orig_nbformat": 4
  },