add oai v1 cookbook (#12961)

docs/docs/integrations/llms/huggingface_pipelines.ipynb

@@ -84,9 +84,7 @@
     "model_id = \"gpt2\"\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
     "model = AutoModelForCausalLM.from_pretrained(model_id)\n",
-    "pipe = pipeline(\n",
-    "    \"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=10\n",
-    ")\n",
+    "pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=10)\n",
     "hf = HuggingFacePipeline(pipeline=pipe)"
    ]
   },

docs/docs/integrations/text_embedding/open_clip.ipynb

@@ -39,8 +39,8 @@
     "from langchain.embeddings import OpenCLIPEmbeddings\n",
     "\n",
     "# Images\n",
-    "img_path_dog='/Users/rlm/Desktop/Papers/LLaVA/dog.jpeg'\n",
-    "img_path_house='/Users/rlm/Desktop/Papers/LLaVA/house.jpeg'\n",
+    "img_path_dog = \"/Users/rlm/Desktop/Papers/LLaVA/dog.jpeg\"\n",
+    "img_path_house = \"/Users/rlm/Desktop/Papers/LLaVA/house.jpeg\"\n",
     "\n",
     "# Load images and convert to numpy arrays\n",
     "image_np_dog = np.array(_PILImage.open(img_path_dog).convert(\"RGB\"))\n",
@@ -106,18 +106,26 @@
     "text_feat_house_np = np.array(text_feat_house[0])\n",
     "\n",
     "# Compute similarity\n",
-    "similarities = np.array([\n",
-    "    [text_feat_dog_np @ img_feat_dog_np.T][0][0], \n",
-    "    [text_feat_dog_np @ img_feat_house_np.T][0][0],\n",
-    "    [text_feat_house_np @ img_feat_dog_np.T][0][0], \n",
-    "    [text_feat_house_np @ img_feat_house_np.T][0][0]\n",
-    "]).reshape(2, 2)\n",
+    "similarities = np.array(\n",
+    "    [\n",
+    "        [text_feat_dog_np @ img_feat_dog_np.T][0][0],\n",
+    "        [text_feat_dog_np @ img_feat_house_np.T][0][0],\n",
+    "        [text_feat_house_np @ img_feat_dog_np.T][0][0],\n",
+    "        [text_feat_house_np @ img_feat_house_np.T][0][0],\n",
+    "    ]\n",
+    ").reshape(2, 2)\n",
     "\n",
     "# Ensure similarities is of shape (2, 2)\n",
     "print(similarities.shape)  # Expected: (2, 2)\n",
     "\n",
     "# Plot heatmap\n",
-    "sns.heatmap(similarities, annot=True, cmap='viridis', xticklabels=['dog image', 'house image'], yticklabels=['dog text', 'house text'])\n"
+    "sns.heatmap(\n",
+    "    similarities,\n",
+    "    annot=True,\n",
+    "    cmap=\"viridis\",\n",
+    "    xticklabels=[\"dog image\", \"house image\"],\n",
+    "    yticklabels=[\"dog text\", \"house text\"],\n",
+    ")"
    ]
   }
  ],

docs/docs/integrations/vectorstores/baiducloud_vector_search.ipynb

@@ -59,8 +59,8 @@
     "import os\n",
     "import getpass\n",
     "\n",
-    "os.environ['QIANFAN_AK'] = getpass.getpass(\"Your Qianfan AK:\")\n",
-    "os.environ['QIANFAN_SK'] = getpass.getpass(\"Your Qianfan SK:\")"
+    "os.environ[\"QIANFAN_AK\"] = getpass.getpass(\"Your Qianfan AK:\")\n",
+    "os.environ[\"QIANFAN_SK\"] = getpass.getpass(\"Your Qianfan SK:\")"
    ]
   },
   {
@@ -85,6 +85,7 @@
     "docs = text_splitter.split_documents(documents)\n",
     "\n",
     "from langchain.embeddings import QianfanEmbeddingsEndpoint\n",
+    "\n",
     "embeddings = QianfanEmbeddingsEndpoint()"
    ]
   },
@@ -104,8 +105,12 @@
    "source": [
     "# Create a bes instance and index docs.\n",
     "from langchain.vectorstores import BESVectorStore\n",
+    "\n",
     "bes = BESVectorStore.from_documents(\n",
-    "    documents=docs, embedding=embeddings, bes_url=\"your bes cluster url\", index_name=\"your vector index\"\n",
+    "    documents=docs,\n",
+    "    embedding=embeddings,\n",
+    "    bes_url=\"your bes cluster url\",\n",
+    "    index_name=\"your vector index\",\n",
     ")\n",
     "bes.client.indices.refresh(index=\"your vector index\")"
    ]

docs/docs/integrations/vectorstores/dingo.ipynb

@@ -108,7 +108,10 @@
     "\n",
     "dingo_client = DingoDB(user=\"\", password=\"\", host=[\"127.0.0.1:13000\"])\n",
     "# First, check if our index already exists. If it doesn't, we create it\n",
-    "if index_name not in dingo_client.get_index() and index_name.upper() not in dingo_client.get_index():\n",
+    "if (\n",
+    "    index_name not in dingo_client.get_index()\n",
+    "    and index_name.upper() not in dingo_client.get_index()\n",
+    "):\n",
     "    # we create a new index, modify to your own\n",
     "    dingo_client.create_index(\n",
     "        index_name=index_name, dimension=1536, metric_type=\"cosine\", auto_id=False\n",