unstructured, community, initialize langchain-unstructured package

cookbook/self_query_hotel_search.ipynb

@@ -355,15 +355,15 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-2][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
-    ")\n",
-    "attribute_info[3][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
-    ")\n",
-    "attribute_info[-3][\"description\"] += (\n",
-    "    f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\"\n",
-    ")"
+    "attribute_info[-2][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
+    "attribute_info[3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\""
    ]
   },
   {
@@ -688,9 +688,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "attribute_info[-3][\"description\"] += (\n",
-    "    \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
-    ")\n",
+    "attribute_info[-3][\n",
+    "    \"description\"\n",
+    "] += \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
     "chain = load_query_constructor_runnable(\n",
     "    ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
     "    doc_contents,\n",

docs/docs/integrations/providers/unstructured.mdx

@@ -8,10 +8,15 @@ ecosystem within LangChain.
 
 ## Installation and Setup
 
-If you are using a loader that runs locally, use the following steps to get `unstructured` and
-its dependencies running locally.
+If you are using a loader that runs locally, use the following steps to get `unstructured` and its
+dependencies running.
 
-- Install the Python SDK with `pip install unstructured`.
+- For the smallest installation footprint and to take advantage of features not available in the
+  open-source `unstructured package`, install the Python SDK with `pip install unstructured-client`.
+    - Unstructured's documentation for the sdk can be found here:
+      https://docs.unstructured.io/api-reference/api-services/sdk
+
+- Install the open-source python package with `pip install unstructured`.
     - You can install document specific dependencies with extras, i.e. `pip install "unstructured[docx]"`.
     - To install the dependencies for all document types, use `pip install "unstructured[all-docs]"`.
 - Install the following system dependencies if they are not already available on your system.
@@ -22,11 +27,6 @@ its dependencies running locally.
     - `libreoffice` (MS Office docs)
     - `pandoc` (EPUBs)
 
-If you want to get up and running with less set up, you can
-simply run `pip install unstructured` and use `UnstructuredAPIFileLoader` or
-`UnstructuredAPIFileIOLoader`. That will process your document using the hosted Unstructured API.
-
-
 The `Unstructured API` requires API keys to make requests.
 You can request an API key [here](https://unstructured.io/api-key-hosted) and start using it today!
 Checkout the README [here](https://github.com/Unstructured-IO/unstructured-api) here to get started making API calls.

docs/docs/integrations/vectorstores/azure_cosmos_db.ipynb

@@ -92,13 +92,13 @@
     "# Set up the OpenAI Environment Variables\n",
     "os.environ[\"OPENAI_API_TYPE\"] = \"azure\"\n",
     "os.environ[\"OPENAI_API_VERSION\"] = \"2023-05-15\"\n",
-    "os.environ[\"OPENAI_API_BASE\"] = (\n",
-    "    \"YOUR_OPEN_AI_ENDPOINT\"  # https://example.openai.azure.com/\n",
-    ")\n",
+    "os.environ[\n",
+    "    \"OPENAI_API_BASE\"\n",
+    "] = \"YOUR_OPEN_AI_ENDPOINT\"  # https://example.openai.azure.com/\n",
     "os.environ[\"OPENAI_API_KEY\"] = \"YOUR_OPENAI_API_KEY\"\n",
-    "os.environ[\"OPENAI_EMBEDDINGS_DEPLOYMENT\"] = (\n",
-    "    \"smart-agent-embedding-ada\"  # the deployment name for the embedding model\n",
-    ")\n",
+    "os.environ[\n",
+    "    \"OPENAI_EMBEDDINGS_DEPLOYMENT\"\n",
+    "] = \"smart-agent-embedding-ada\"  # the deployment name for the embedding model\n",
     "os.environ[\"OPENAI_EMBEDDINGS_MODEL_NAME\"] = \"text-embedding-ada-002\"  # the model name"
    ]
   },

docs/docs/integrations/vectorstores/documentdb.ipynb

@@ -105,9 +105,9 @@
     "\n",
     "# Set up the OpenAI Environment Variables\n",
     "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
-    "os.environ[\"OPENAI_EMBEDDINGS_DEPLOYMENT\"] = (\n",
-    "    \"smart-agent-embedding-ada\"  # the deployment name for the embedding model\n",
-    ")\n",
+    "os.environ[\n",
+    "    \"OPENAI_EMBEDDINGS_DEPLOYMENT\"\n",
+    "] = \"smart-agent-embedding-ada\"  # the deployment name for the embedding model\n",
     "os.environ[\"OPENAI_EMBEDDINGS_MODEL_NAME\"] = \"text-embedding-ada-002\"  # the model name"
    ]
   },

docs/scripts/arxiv_references.py

@@ -176,9 +176,9 @@ def search_code_for_arxiv_references(code_dir: Path) -> dict[str, set[str]]:
             else:
                 module_name_and_member_reduced.add(module_name_and_member)
         if module_name_and_member_reduced:
-            arxiv_id2module_name_and_members_reduced[arxiv_id] = (
-                module_name_and_member_reduced
-            )
+            arxiv_id2module_name_and_members_reduced[
+                arxiv_id
+            ] = module_name_and_member_reduced
         if removed_modules:
             logger.warning(
                 f"{arxiv_id}: Removed the following modules with 2+ -part namespaces: {removed_modules}."