cleanup (#1274)

docs/modules/document_loaders/examples/notebook.ipynb

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -12,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -21,15 +20,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = NotebookLoader(\"example_data/notebook.ipynb\")"
+    "loader = NotebookLoader(\"example_data/notebook.ipynb\", include_outputs=True, max_output_length=20, remove_newline=True)"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -43,19 +41,37 @@
     "* `traceback` (bool): whether to include full traceback (default is False)."
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='\\'markdown\\' cell: \\'[\\'# Notebook\\', \\'\\', \\'This notebook covers how to load data from an .ipynb notebook into a format suitable by LangChain.\\']\\'\\n\\n \\'code\\' cell: \\'[\\'from langchain.document_loaders import NotebookLoader\\']\\'\\n\\n \\'code\\' cell: \\'[\\'loader = NotebookLoader(\"example_data/notebook.ipynb\")\\']\\'\\n\\n \\'markdown\\' cell: \\'[\\'`NotebookLoader.load()` loads the `.ipynb` notebook file into a `Document` object.\\', \\'\\', \\'**Parameters**:\\', \\'\\', \\'* `include_outputs` (bool): whether to include cell outputs in the resulting document (default is False).\\', \\'* `max_output_length` (int): the maximum number of characters to include from each cell output (default is 10).\\', \\'* `remove_newline` (bool): whether to remove newline characters from the cell sources and outputs (default is False).\\', \\'* `traceback` (bool): whether to include full traceback (default is False).\\']\\'\\n\\n \\'code\\' cell: \\'[\\'loader.load(include_outputs=True, max_output_length=20, remove_newline=True)\\']\\'\\n\\n', lookup_str='', metadata={'source': 'example_data/notebook.ipynb'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader.load()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": [
-    "loader.load(include_outputs=True, max_output_length=20, remove_newline=True)"
-   ]
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -69,9 +85,8 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.1"
+   "version": "3.9.1"
   },
-  "orig_nbformat": 4,
   "vscode": {
    "interpreter": {
     "hash": "981b6680a42bdb5eb22187741e1607b3aae2cf73db800d1af1f268d1de6a1f70"

langchain/document_loaders/notebook.py

@@ -61,16 +61,23 @@ def remove_newlines(x: Any) -> Any:
 class NotebookLoader(BaseLoader):
     """Loader that loads .ipynb notebook files."""
 
-    def __init__(self, path: str):
-        """Initialize with path."""
-        self.file_path = path
-
-    def load(
+    def __init__(
         self,
+        path: str,
         include_outputs: bool = False,
         max_output_length: int = 10,
         remove_newline: bool = False,
         traceback: bool = False,
+    ):
+        """Initialize with path."""
+        self.file_path = path
+        self.include_outputs = include_outputs
+        self.max_output_length = max_output_length
+        self.remove_newline = remove_newline
+        self.traceback = traceback
+
+    def load(
+        self,
     ) -> List[Document]:
         """Load documents."""
         try:
@@ -87,12 +94,12 @@ class NotebookLoader(BaseLoader):
 
         data = pd.json_normalize(d["cells"])
         filtered_data = data[["cell_type", "source", "outputs"]]
-        if remove_newline:
+        if self.remove_newline:
             filtered_data = filtered_data.applymap(remove_newlines)
 
         text = filtered_data.apply(
             lambda x: concatenate_cells(
-                x, include_outputs, max_output_length, traceback
+                x, self.include_outputs, self.max_output_length, self.traceback
             ),
             axis=1,
         ).str.cat(sep=" ")

langchain/llms/anthropic.py

@@ -18,7 +18,7 @@ class Anthropic(LLM, BaseModel):
     Example:
         .. code-block:: python
             import anthropic
-            from langchain import Anthropic
+            from langchain.llms import Anthropic
             model = Anthropic(model="<model_name>", anthropic_api_key="my-api-key")
 
             # Simplest invocation, automatically wrapped with HUMAN_PROMPT

langchain/llms/bananadev.py

@@ -22,8 +22,8 @@ class Banana(LLM, BaseModel):
 
     Example:
         .. code-block:: python
-            from langchain import Banana
-            cerebrium = Banana(model_key="")
+            from langchain.llms import Banana
+            banana = Banana(model_key="")
     """
 
     model_key: str = ""

langchain/llms/cerebriumai.py

@@ -22,7 +22,7 @@ class CerebriumAI(LLM, BaseModel):
 
     Example:
         .. code-block:: python
-            from langchain import CerebriumAI
+            from langchain.llms import CerebriumAI
             cerebrium = CerebriumAI(endpoint_url="")
 
     """

langchain/llms/cohere.py

@@ -21,7 +21,7 @@ class Cohere(LLM, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import Cohere
+            from langchain.llms import Cohere
             cohere = Cohere(model="gptd-instruct-tft", cohere_api_key="my-api-key")
     """
 

langchain/llms/deepinfra.py

@@ -23,7 +23,7 @@ class DeepInfra(LLM, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import DeepInfra
+            from langchain.llms import DeepInfra
             di = DeepInfra(model_id="google/flan-t5-xl",
                                 deepinfra_api_token="my-api-key")
     """

langchain/llms/forefrontai.py

@@ -18,7 +18,7 @@ class ForefrontAI(LLM, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import ForefrontAI
+            from langchain.llms import ForefrontAI
             forefrontai = ForefrontAI(endpoint_url="")
     """
 

langchain/llms/gooseai.py

@@ -21,7 +21,7 @@ class GooseAI(LLM, BaseModel):
 
     Example:
         .. code-block:: python
-            from langchain import GooseAI
+            from langchain.llms import GooseAI
             gooseai = GooseAI(model_name="gpt-neo-20b")
 
     """

langchain/llms/huggingface_hub.py

@@ -23,7 +23,7 @@ class HuggingFaceHub(LLM, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import HuggingFaceHub
+            from langchain.llms import HuggingFaceHub
             hf = HuggingFaceHub(repo_id="gpt2", huggingfacehub_api_token="my-api-key")
     """
 

langchain/llms/huggingface_pipeline.py

@@ -25,14 +25,14 @@ class HuggingFacePipeline(LLM, BaseModel):
     Example using from_model_id:
         .. code-block:: python
 
-            from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+            from langchain.llms import HuggingFacePipeline
             hf = HuggingFacePipeline.from_model_id(
                 model_id="gpt2", task="text-generation"
             )
     Example passing pipeline in directly:
         .. code-block:: python
 
-            from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+            from langchain.llms import HuggingFacePipeline
             from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
             model_id = "gpt2"

langchain/llms/modal.py

@@ -21,7 +21,7 @@ class Modal(LLM, BaseModel):
 
     Example:
         .. code-block:: python
-            from langchain import Modal
+            from langchain.llms import Modal
             modal = Modal(endpoint_url="")
 
     """

langchain/llms/nlpcloud.py

@@ -16,7 +16,7 @@ class NLPCloud(LLM, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import NLPCloud
+            from langchain.llms import NLPCloud
             nlpcloud = NLPCloud(model="gpt-neox-20b")
     """
 

langchain/llms/openai.py

@@ -75,7 +75,7 @@ class BaseOpenAI(BaseLLM, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import OpenAI
+            from langchain.llms import OpenAI
             openai = OpenAI(model_name="text-davinci-003")
     """
 

langchain/llms/petals.py

@@ -22,7 +22,7 @@ class Petals(LLM, BaseModel):
 
     Example:
         .. code-block:: python
-            from langchain import petals
+            from langchain.llms import petals
             petals = Petals()
 
     """

langchain/llms/promptlayer_openai.py

@@ -23,7 +23,7 @@ class PromptLayerOpenAI(OpenAI, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import OpenAI
+            from langchain.llms import OpenAI
             openai = OpenAI(model_name="text-davinci-003")
     """
 

langchain/llms/stochasticai.py

@@ -22,8 +22,8 @@ class StochasticAI(LLM, BaseModel):
     Example:
         .. code-block:: python
 
-            from langchain import StochasticAI
-            forefrontai = StochasticAI(api_url="")
+            from langchain.llms import StochasticAI
+            stochasticai = StochasticAI(api_url="")
     """
 
     api_url: str = ""