IMPROVEMENT format notebooks

cookbook/multi_modal_RAG_chroma.ipynb

@@ -115,7 +115,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Folder with pdf and extracted images \n",
+    "# Folder with pdf and extracted images\n",
     "path = \"/Users/rlm/Desktop/photos/\""
    ]
   },
@@ -128,9 +128,10 @@
    "source": [
     "# Extract images, tables, and chunk text\n",
     "from unstructured.partition.pdf import partition_pdf\n",
+    "\n",
     "raw_pdf_elements = partition_pdf(\n",
     "    filename=path + \"photos.pdf\",\n",
-    "    extract_images_in_pdf=True, \n",
+    "    extract_images_in_pdf=True,\n",
     "    infer_table_structure=True,\n",
     "    chunking_strategy=\"by_title\",\n",
     "    max_characters=4000,\n",
@@ -191,14 +192,17 @@
     "\n",
     "# Create chroma\n",
     "vectorstore = Chroma(\n",
-    "    collection_name=\"mm_rag_clip_photos\",\n",
-    "    embedding_function=OpenCLIPEmbeddings()\n",
+    "    collection_name=\"mm_rag_clip_photos\", embedding_function=OpenCLIPEmbeddings()\n",
     ")\n",
     "\n",
     "# Get image URIs with .jpg extension only\n",
-    "image_uris = sorted([os.path.join(path, image_name) \n",
-    "                     for image_name in os.listdir(path) \n",
-    "                     if image_name.endswith('.jpg')])\n",
+    "image_uris = sorted(\n",
+    "    [\n",
+    "        os.path.join(path, image_name)\n",
+    "        for image_name in os.listdir(path)\n",
+    "        if image_name.endswith(\".jpg\")\n",
+    "    ]\n",
+    ")\n",
     "\n",
     "# Add images\n",
     "vectorstore.add_images(uris=image_uris)\n",
@@ -206,7 +210,7 @@
     "# Add documents\n",
     "vectorstore.add_texts(texts=texts)\n",
     "\n",
-    "# Make retriever \n",
+    "# Make retriever\n",
     "retriever = vectorstore.as_retriever()"
    ]
   },
@@ -235,6 +239,7 @@
     "from io import BytesIO\n",
     "from PIL import Image\n",
     "\n",
+    "\n",
     "def resize_base64_image(base64_string, size=(128, 128)):\n",
     "    \"\"\"\n",
     "    Resize an image encoded as a Base64 string.\n",
@@ -258,30 +263,31 @@
     "    resized_img.save(buffered, format=img.format)\n",
     "\n",
     "    # Encode the resized image to Base64\n",
-    "    return base64.b64encode(buffered.getvalue()).decode('utf-8')\n",
+    "    return base64.b64encode(buffered.getvalue()).decode(\"utf-8\")\n",
+    "\n",
     "\n",
     "def is_base64(s):\n",
-    "    ''' Check if a string is Base64 encoded '''\n",
+    "    \"\"\"Check if a string is Base64 encoded\"\"\"\n",
     "    try:\n",
     "        return base64.b64encode(base64.b64decode(s)) == s.encode()\n",
     "    except Exception:\n",
     "        return False\n",
-    "        \n",
+    "\n",
+    "\n",
     "def split_image_text_types(docs):\n",
-    "    ''' Split numpy array images and texts '''\n",
+    "    \"\"\"Split numpy array images and texts\"\"\"\n",
     "    images = []\n",
     "    text = []\n",
     "    for doc in docs:\n",
-    "        doc = doc.page_content # Extract Document contents \n",
+    "        doc = doc.page_content  # Extract Document contents\n",
     "        if is_base64(doc):\n",
     "            # Resize image to avoid OAI server error\n",
-    "            images.append(resize_base64_image(doc, size=(250, 250)))  # base64 encoded str \n",
+    "            images.append(\n",
+    "                resize_base64_image(doc, size=(250, 250))\n",
+    "            )  # base64 encoded str\n",
     "        else:\n",
-    "            text.append(doc) \n",
-    "    return {\n",
-    "        \"images\": images,\n",
-    "        \"texts\": text\n",
-    "    }"
+    "            text.append(doc)\n",
+    "    return {\"images\": images, \"texts\": text}"
    ]
   },
   {
@@ -311,6 +317,7 @@
     "from langchain.schema.runnable import RunnablePassthrough, RunnableLambda\n",
     "from langchain.schema.messages import HumanMessage, SystemMessage\n",
     "\n",
+    "\n",
     "def prompt_func(data_dict):\n",
     "    # Joining the context texts into a single string\n",
     "    formatted_texts = \"\\n\".join(data_dict[\"context\"][\"texts\"])\n",
@@ -322,7 +329,7 @@
     "            \"type\": \"image_url\",\n",
     "            \"image_url\": {\n",
     "                \"url\": f\"data:image/jpeg;base64,{data_dict['context']['images'][0]}\"\n",
-    "            }\n",
+    "            },\n",
     "        }\n",
     "        messages.append(image_message)\n",
     "\n",
@@ -342,17 +349,21 @@
     "            f\"User-provided keywords: {data_dict['question']}\\n\\n\"\n",
     "            \"Text and / or tables:\\n\"\n",
     "            f\"{formatted_texts}\"\n",
-    "        )\n",
+    "        ),\n",
     "    }\n",
     "    messages.append(text_message)\n",
     "\n",
     "    return [HumanMessage(content=messages)]\n",
-    "    \n",
+    "\n",
+    "\n",
     "model = ChatOpenAI(temperature=0, model=\"gpt-4-vision-preview\", max_tokens=1024)\n",
     "\n",
     "# RAG pipeline\n",
     "chain = (\n",
-    "    {\"context\": retriever | RunnableLambda(split_image_text_types), \"question\": RunnablePassthrough()}\n",
+    "    {\n",
+    "        \"context\": retriever | RunnableLambda(split_image_text_types),\n",
+    "        \"question\": RunnablePassthrough(),\n",
+    "    }\n",
     "    | RunnableLambda(prompt_func)\n",
     "    | model\n",
     "    | StrOutputParser()\n",
@@ -410,7 +421,7 @@
     }
    ],
    "source": [
-    "docs = retriever.get_relevant_documents(\"Woman with children\",k=10)\n",
+    "docs = retriever.get_relevant_documents(\"Woman with children\", k=10)\n",
     "for doc in docs:\n",
     "    if is_base64(doc.page_content):\n",
     "        plt_img_base64(doc.page_content)\n",
@@ -436,9 +447,7 @@
     }
    ],
    "source": [
-    "chain.invoke(\n",
-    "    \"Woman with children\"\n",
-    ")"
+    "chain.invoke(\"Woman with children\")"
    ]
   },
   {

docs/docs/integrations/document_loaders/docusaurus.ipynb

@@ -118,7 +118,9 @@
    "source": [
     "loader = DocusaurusLoader(\n",
     "    \"https://python.langchain.com\",\n",
-    "    filter_urls=[\"https://python.langchain.com/docs/integrations/document_loaders/sitemap\"],\n",
+    "    filter_urls=[\n",
+    "        \"https://python.langchain.com/docs/integrations/document_loaders/sitemap\"\n",
+    "    ],\n",
     ")\n",
     "documents = loader.load()"
    ]
@@ -162,9 +164,11 @@
    "source": [
     "loader = DocusaurusLoader(\n",
     "    \"https://python.langchain.com\",\n",
-    "    filter_urls=[\"https://python.langchain.com/docs/integrations/document_loaders/sitemap\"],\n",
+    "    filter_urls=[\n",
+    "        \"https://python.langchain.com/docs/integrations/document_loaders/sitemap\"\n",
+    "    ],\n",
     "    # This will only include the content that matches these tags, otherwise they will be removed\n",
-    "    custom_html_tags=[\"#content\", \".main\"]\n",
+    "    custom_html_tags=[\"#content\", \".main\"],\n",
     ")"
    ]
   },
@@ -213,7 +217,9 @@
    "source": [
     "loader = DocusaurusLoader(\n",
     "    \"https://python.langchain.com\",\n",
-    "    filter_urls=[\"https://python.langchain.com/docs/integrations/document_loaders/sitemap\"],\n",
+    "    filter_urls=[\n",
+    "        \"https://python.langchain.com/docs/integrations/document_loaders/sitemap\"\n",
+    "    ],\n",
     "    parsing_function=remove_nav_and_header_elements,\n",
     ")"
    ]

docs/docs/integrations/memory/neo4j_chat_message_history.ipynb

@@ -25,7 +25,7 @@
     "    url=\"bolt://localhost:7687\",\n",
     "    username=\"neo4j\",\n",
     "    password=\"password\",\n",
-    "    session_id=\"session_id_1\"\n",
+    "    session_id=\"session_id_1\",\n",
     ")\n",
     "\n",
     "history.add_user_message(\"hi!\")\n",

docs/docs/integrations/text_embedding/fastembed.ipynb

@@ -110,7 +110,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "document_embeddings = embeddings.embed_documents([\"This is a document\", \"This is some other document\"])"
+    "document_embeddings = embeddings.embed_documents(\n",
+    "    [\"This is a document\", \"This is some other document\"]\n",
+    ")"
    ]
   },
   {

docs/docs/integrations/text_embedding/open_clip.ipynb

@@ -48,6 +48,7 @@
    "outputs": [],
    "source": [
     "import open_clip\n",
+    "\n",
     "open_clip.list_pretrained()"
    ]
   },
@@ -147,8 +148,8 @@
     "    \"rocket\": \"a rocket standing on a launchpad\",\n",
     "    \"motorcycle_right\": \"a red motorcycle standing in a garage\",\n",
     "    \"camera\": \"a person looking at a camera on a tripod\",\n",
-    "    \"horse\": \"a black-and-white silhouette of a horse\", \n",
-    "    \"coffee\": \"a cup of coffee on a saucer\"\n",
+    "    \"horse\": \"a black-and-white silhouette of a horse\",\n",
+    "    \"coffee\": \"a cup of coffee on a saucer\",\n",
     "}\n",
     "\n",
     "original_images = []\n",
@@ -158,14 +159,18 @@
     "plt.figure(figsize=(16, 5))\n",
     "\n",
     "# Loop to display and prepare images and assemble URIs\n",
-    "for filename in [filename for filename in os.listdir(skimage.data_dir) if filename.endswith(\".png\") or filename.endswith(\".jpg\")]:\n",
+    "for filename in [\n",
+    "    filename\n",
+    "    for filename in os.listdir(skimage.data_dir)\n",
+    "    if filename.endswith(\".png\") or filename.endswith(\".jpg\")\n",
+    "]:\n",
     "    name = os.path.splitext(filename)[0]\n",
     "    if name not in descriptions:\n",
     "        continue\n",
     "\n",
     "    image_path = os.path.join(skimage.data_dir, filename)\n",
     "    image = Image.open(image_path).convert(\"RGB\")\n",
-    "  \n",
+    "\n",
     "    plt.subplot(2, 4, len(images) + 1)\n",
     "    plt.imshow(image)\n",
     "    plt.title(f\"{filename}\\n{descriptions[name]}\")\n",
@@ -173,7 +178,7 @@
     "    plt.yticks([])\n",
     "\n",
     "    original_images.append(image)\n",
-    "    images.append(image) # Origional code does preprocessing here\n",
+    "    images.append(image)  # Origional code does preprocessing here\n",
     "    texts.append(descriptions[name])\n",
     "    image_uris.append(image_path)  # Add the image URI to the list\n",
     "\n",
@@ -216,7 +221,7 @@
     "# Instantiate your model\n",
     "clip_embd = OpenCLIPEmbeddings()\n",
     "\n",
-    "# Embed images and text \n",
+    "# Embed images and text\n",
     "img_features = clip_embd.embed_image(image_uris)\n",
     "text_features = clip_embd.embed_documents([\"This is \" + desc for desc in texts])\n",
     "\n",
@@ -241,7 +246,7 @@
     "        plt.text(x, y, f\"{similarity[y, x]:.2f}\", ha=\"center\", va=\"center\", size=12)\n",
     "\n",
     "for side in [\"left\", \"top\", \"right\", \"bottom\"]:\n",
-    "  plt.gca().spines[side].set_visible(False)\n",
+    "    plt.gca().spines[side].set_visible(False)\n",
     "\n",
     "plt.xlim([-0.5, count - 0.5])\n",
     "plt.ylim([count + 0.5, -2])\n",

docs/docs/integrations/vectorstores/weaviate.ipynb

@@ -149,12 +149,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "db = Weaviate.from_documents(\n",
-    "    docs, \n",
-    "    embeddings, \n",
-    "    weaviate_url=WEAVIATE_URL, \n",
-    "    by_text=False\n",
-    ")"
+    "db = Weaviate.from_documents(docs, embeddings, weaviate_url=WEAVIATE_URL, by_text=False)"
    ]
   },
   {
@@ -227,8 +222,7 @@
     "import weaviate\n",
     "\n",
     "client = weaviate.Client(\n",
-    "    url=WEAVIATE_URL, \n",
-    "    auth_client_secret=weaviate.AuthApiKey(WEAVIATE_API_KEY)\n",
+    "    url=WEAVIATE_URL, auth_client_secret=weaviate.AuthApiKey(WEAVIATE_API_KEY)\n",
     ")\n",
     "\n",
     "# client = weaviate.Client(\n",
@@ -240,10 +234,7 @@
     "# )\n",
     "\n",
     "vectorstore = Weaviate.from_documents(\n",
-    "    documents, \n",
-    "    embeddings, \n",
-    "    client=client, \n",
-    "    by_text=False\n",
+    "    documents, embeddings, client=client, by_text=False\n",
     ")"
    ]
   },
@@ -378,6 +369,7 @@
    ],
    "source": [
     "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
     "llm = ChatOpenAI(model_name=\"gpt-3.5-turbo\", temperature=0)\n",
     "llm.predict(\"What did the president say about Justice Breyer\")"
    ]
@@ -575,10 +567,10 @@
     "from langchain.schema.output_parser import StrOutputParser\n",
     "\n",
     "rag_chain = (\n",
-    "    {\"context\": retriever,  \"question\": RunnablePassthrough()} \n",
-    "    | prompt \n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
     "    | llm\n",
-    "    | StrOutputParser() \n",
+    "    | StrOutputParser()\n",
     ")\n",
     "\n",
     "rag_chain.invoke(\"What did the president say about Justice Breyer\")"

docs/docs/modules/agents/index.ipynb

@@ -198,6 +198,7 @@
    "source": [
     "from langchain.agents import tool\n",
     "\n",
+    "\n",
     "@tool\n",
     "def get_word_length(word: str) -> int:\n",
     "    \"\"\"Returns the length of a word.\"\"\"\n",
@@ -606,10 +607,12 @@
    "source": [
     "input1 = \"how many letters in the word educa?\"\n",
     "result = agent_executor.invoke({\"input\": input1, \"chat_history\": chat_history})\n",
-    "chat_history.extend([\n",
-    "    HumanMessage(content=input1),\n",
-    "    AIMessage(content=result[\"output\"]),\n",
-    "])\n",
+    "chat_history.extend(\n",
+    "    [\n",
+    "        HumanMessage(content=input1),\n",
+    "        AIMessage(content=result[\"output\"]),\n",
+    "    ]\n",
+    ")\n",
     "agent_executor.invoke({\"input\": \"is that a real word?\", \"chat_history\": chat_history})"
    ]
   },

docs/scripts/copy_templates.py

@@ -1,16 +1,15 @@
 import glob
 import os
-from pathlib import Path
 import re
 import shutil
-
+from pathlib import Path
 
 TEMPLATES_DIR = Path(os.path.abspath(__file__)).parents[2] / "templates"
 DOCS_TEMPLATES_DIR = Path(os.path.abspath(__file__)).parents[1] / "docs" / "templates"
 
 
 readmes = list(glob.glob(str(TEMPLATES_DIR) + "/*/README.md"))
-destinations = [readme[len(str(TEMPLATES_DIR)) + 1:-10] + ".md" for readme in readmes]
+destinations = [readme[len(str(TEMPLATES_DIR)) + 1 : -10] + ".md" for readme in readmes]
 for source, destination in zip(readmes, destinations):
     full_destination = DOCS_TEMPLATES_DIR / destination
     shutil.copyfile(source, full_destination)
@@ -33,4 +32,3 @@ with open(TEMPLATES_INDEX_DESTINATION, "r") as f:
 content = re.sub("\]\(\.\.\/", "](/docs/templates/", content)
 with open(TEMPLATES_INDEX_DESTINATION, "w") as f:
     f.write(sidebar_hidden + content)
-

templates/rag-timescale-conversation/rag_conversation.ipynb

@@ -79,7 +79,6 @@
     }
    ],
    "source": [
-    "\n",
     "answer = rag_app.invoke(\n",
     "    {\n",
     "        \"question\": \"What commits did the person with my name make?\",\n",
@@ -125,7 +124,7 @@
     "        \"end_date\": \"2016-01-01 00:00:00\",\n",
     "    }\n",
     ")\n",
-    "answer\n"
+    "answer"
    ]
   },
   {