Harrison/improve data augmented generation docs (#390)

Co-authored-by: cameronccohen <cameron.c.cohen@gmail.com>
Co-authored-by: Cameron Cohen <cameron.cohen@quantco.com>

docs/examples/chains.rst

@@ -6,14 +6,11 @@ A chain is made up of links, which can be either primitives or other chains.
 
 The following primitives exist as options to use for links:
 
-#. `LLM: <../modules/llms.rst>`_ A language model takes text as input and outputs text.
-#. `PromptTemplate: <../modules/prompt.rst>`_ A prompt template takes arbitrary string inputs and returns a final formatted string.
-#. `TextSplitter: <../modules/text_splitter.rst>`_ A text splitter takes a longer document and splits it into smaller chunks.
-#. `Python REPL: <../modules/python.rst>`_ A Python REPL takes a string representing a Python command to run, runs that command, and then returns anything that was printed during that run.
-#. `SQL Database: <../modules/sql_database.rst>`_ A SQL database takes a string representing a SQL command as input and executes that command against the database. If any rows are returned, then those are cast to a string and returned.
-#. `Search: <../modules/serpapi.rst>`_ A search object takes a string as input and executes that against a search object, returning any results.
-#. `Docstore: <../modules/docstore.rst>`_ A docstore object can be used to lookup a document in a database by exact match.
-#. `Vectorstore: <../modules/vectorstore.rst>`_ A vectorstore object uses embeddings stored in a vector database to take in an input string and return documents similar to that string.
+#. `LLM: <../reference/modules/llms.rst>`_ A language model takes text as input and outputs text.
+#. `PromptTemplate: <../reference/modules/prompt.rst>`_ A prompt template takes arbitrary string inputs and returns a final formatted string.
+#. `Python REPL: <../reference/modules/python.rst>`_ A Python REPL takes a string representing a Python command to run, runs that command, and then returns anything that was printed during that run.
+#. `SQL Database: <../reference/modules/sql_database.rst>`_ A SQL database takes a string representing a SQL command as input and executes that command against the database. If any rows are returned, then those are cast to a string and returned.
+#. `Search: <../reference/modules/serpapi.rst>`_ A search object takes a string as input and executes that against a search object, returning any results.
 
 With these primitives in mind, the following chains exist:
 
@@ -42,37 +39,6 @@ With these primitives in mind, the following chains exist:
 - **Notes**: This chain takes user input (a question), uses a first LLM chain to construct a SQL query to run against the SQL database, and then uses another LLMChain to take the results of that query and use it to answer the original question.
 - `Example Notebook <chains/sqlite.ipynb>`_
 
-
-**Vector Database Question-Answering**
-
-- **Links Used**: Vectorstore, LLMChain
-- **Notes**: This chain takes user input (a question), uses the Vectorstore and semantic search to find relevant documents, and then passes the documents plus the original question to another LLM to generate a final answer.
-- `Example Notebook <chains/vector_db_qa.ipynb>`_
-
-**Vector Database Question-Answering With Sources**
-
-- **Links Used**: Vectorstore, LLMChain
-- **Notes**: This chain takes user input (a question), uses the Vectorstore and semantic search to find relevant documents, and then passes the documents plus the original question to another LLM to generate a final answer with sources.
-- `Example Notebook <chains/vector_db_qa_with_sources.ipynb>`_
-
-**Question-Answering With Sources**
-
-- **Links Used**: LLMChain
-- **Notes**: These types of chains take a question and multiple documents as input, and return an answer plus sources for where that answer came from. There are multiple underlying types of chains to do this, for more information see `here <../explanation/combine_docs.md>`_.
-- `Example Notebook <chains/qa_with_sources.ipynb>`_
-
-**Question-Answering**
-
-- **Links Used**: LLMChain
-- **Notes**: These types of chains take a question and multiple documents as input, and return an answer. There are multiple underlying types of chains to do this, for more information see `here <../explanation/combine_docs.md>`_.
-- `Example Notebook <chains/question_answering.ipynb>`_
-
-**Summarization**
-
-- **Links Used**: LLMChain
-- **Notes**: These types of chains take multiple documents as input, and return a summary of all documents. There are multiple underlying types of chains to do this, for more information see `here <../explanation/combine_docs.md>`_.
-- `Example Notebook <chains/summarize.ipynb>`_
-
 .. toctree::
    :maxdepth: 1
    :glob:

docs/examples/data_augmented_generation.rst

@@ -0,0 +1,32 @@
+Data Augmented Generation
+=========================
+
+The walkthroughs here are related to data augmented generation.
+They cover either how to work with the components of data augmented generation (documents, embeddings, and vectorstores), or are end-to-end examples for using these components.
+
+**Components**
+
+`Text Splitters <data_augmented_generation/textsplitter.ipynb>`_: A walkthrough of how to split large documents up into smaller, more manageable pieces of text.
+
+`Embeddings & VectorStores <data_augmented_generation/embeddings.ipynb>`_: A walkthrough of the different embedding and vectorstore functionalies that LangChain supports.
+
+
+**Examples**
+
+`Question Answering <data_augmented_generation/question_answering.ipynb>`_: A walkthrough of how to use LangChain for question answering over specific documents.
+
+`Question Answering with Sources <data_augmented_generation/qa_with_sources.ipynb>`_: A walkthrough of how to use LangChain for question answering (with sources) over specific documents.
+
+`Summarization <data_augmented_generation/summarize.ipynb>`_: A walkthrough of how to use LangChain for summarization over specific documents.
+
+`Vector DB Question Answering <data_augmented_generation/vector_db_qa.ipynb>`_: A walkthrough of how to use LangChain for question answering over a vector database.
+
+`Vector DB Question Answering with Sources <data_augmented_generation/vector_db_qa_with_sources.ipynb>`_: A walkthrough of how to use LangChain for question answering (with sources) over a vector database.
+
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+   :hidden:
+
+   data_augmented_generation/*

docs/examples/data_augmented_generation/embeddings.ipynb

@@ -0,0 +1,374 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7ef4d402-6662-4a26-b612-35b542066487",
+   "metadata": {
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   },
+   "source": [
+    "#  Embeddings & VectorStores\n",
+    "\n",
+    "This notebook show cases how to use embeddings to create a VectorStore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "965eecee",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores import ElasticVectorSearch, Pinecone, Weaviate, FAISS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "68481687",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "with open('../state_of_the_union.txt') as f:\n",
+    "    state_of_the_union = f.read()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_text(state_of_the_union)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "015f4ff5",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "docsearch = FAISS.from_texts(texts, embeddings)\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "67baf32e",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
+      "\n",
+      "We cannot let this happen. \n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eea6e627",
+   "metadata": {},
+   "source": [
+    "## Requires having ElasticSearch setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4906b8a3",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "docsearch = ElasticVectorSearch.from_texts(texts, embeddings, elasticsearch_url=\"http://localhost:9200\")\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "95f9eee9",
+   "metadata": {
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n",
+      "\n",
+      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
+      "\n",
+      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7f9cb9e7",
+   "metadata": {},
+   "source": [
+    "## Weaviate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "1037a85e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import weaviate\n",
+    "import os\n",
+    "\n",
+    "WEAVIATE_URL = \"\"\n",
+    "client = weaviate.Client(\n",
+    "    url=WEAVIATE_URL,\n",
+    "    additional_headers={\n",
+    "        'X-OpenAI-Api-Key': os.environ[\"OPENAI_API_KEY\"]\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "b9043766",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "client.schema.delete_all()\n",
+    "client.schema.get()\n",
+    "schema = {\n",
+    "    \"classes\": [\n",
+    "        {\n",
+    "            \"class\": \"Paragraph\",\n",
+    "            \"description\": \"A written paragraph\",\n",
+    "            \"vectorizer\": \"text2vec-openai\",\n",
+    "              \"moduleConfig\": {\n",
+    "                \"text2vec-openai\": {\n",
+    "                  \"model\": \"babbage\",\n",
+    "                  \"type\": \"text\"\n",
+    "                }\n",
+    "              },\n",
+    "            \"properties\": [\n",
+    "                {\n",
+    "                    \"dataType\": [\"text\"],\n",
+    "                    \"description\": \"The content of the paragraph\",\n",
+    "                    \"moduleConfig\": {\n",
+    "                        \"text2vec-openai\": {\n",
+    "                          \"skip\": False,\n",
+    "                          \"vectorizePropertyName\": False\n",
+    "                        }\n",
+    "                      },\n",
+    "                    \"name\": \"content\",\n",
+    "                },\n",
+    "            ],\n",
+    "        },\n",
+    "    ]\n",
+    "}\n",
+    "\n",
+    "client.schema.create(schema)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "ac20d99c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with client.batch as batch:\n",
+    "    for text in texts:\n",
+    "        batch.add_data_object({\"content\": text}, \"Paragraph\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "01645d61",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.vectorstores.weaviate import Weaviate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "bdd97d29",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorstore = Weaviate(client, \"Paragraph\", \"content\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "b70c0f98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = vectorstore.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "07533e40",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
+      "\n",
+      "We cannot let this happen. \n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "007f3102",
+   "metadata": {},
+   "source": [
+    "## Pinecone"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7f6047e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pinecone \n",
+    "\n",
+    "# initialize pinecone\n",
+    "pinecone.init(api_key=\"\", environment=\"us-west1-gcp\")\n",
+    "\n",
+    "index_name = \"langchain-demo\"\n",
+    "\n",
+    "docsearch = Pinecone.from_texts(texts, embeddings, index_name=index_name)\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "8e81f1f0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders. ', lookup_str='', metadata={}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e7d74bd2",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/examples/data_augmented_generation/textsplitter.ipynb

@@ -19,7 +19,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "e82c4685",
    "metadata": {},
    "outputs": [],
@@ -42,7 +42,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "79ff6737",
    "metadata": {},
    "outputs": [],
@@ -57,17 +57,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "38547666",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \\n\\nLast year COVID-19 kept us apart. This year we are finally together again. \\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \\n\\nWith a duty to one another to the American people to the Constitution. \\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \\n\\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \\n\\nHe met the Ukrainian people. \\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. \\n\\nGroups of citizens blocking tanks with their bodies. Everyone from students to retirees teachers turned soldiers defending their homeland. '"
+       "'Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \\n\\nLast year COVID-19 kept us apart. This year we are finally together again. \\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \\n\\nWith a duty to one another to the American people to the Constitution. \\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \\n\\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \\n\\nHe met the Ukrainian people. \\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. '"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -77,6 +77,70 @@
     "texts[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "87a71115",
+   "metadata": {},
+   "source": [
+    "## Document creation\n",
+    "We can also use the text splitter to create \"Documents\" directly. Documents a way of bundling pieces of text with associated metadata so that chains can interact with them. We can also create documents with empty metadata though!\n",
+    "\n",
+    "In the below example, we pass two pieces of text to get split up (we pass two just to show off the interface of splitting multiple pieces of text)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4cd16222",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \\n\\nLast year COVID-19 kept us apart. This year we are finally together again. \\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \\n\\nWith a duty to one another to the American people to the Constitution. \\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \\n\\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \\n\\nHe met the Ukrainian people. \\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. ', lookup_str='', metadata={}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "documents = text_splitter.create_documents([state_of_the_union, state_of_the_union])\n",
+    "documents[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2cede1b1",
+   "metadata": {},
+   "source": [
+    "Here's an example of passing metadata along with the documents, notice that it is split along with the documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4a47515a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.  \\n\\nLast year COVID-19 kept us apart. This year we are finally together again. \\n\\nTonight, we meet as Democrats Republicans and Independents. But most importantly as Americans. \\n\\nWith a duty to one another to the American people to the Constitution. \\n\\nAnd with an unwavering resolve that freedom will always triumph over tyranny. \\n\\nSix days ago, Russia’s Vladimir Putin sought to shake the foundations of the free world thinking he could make it bend to his menacing ways. But he badly miscalculated. \\n\\nHe thought he could roll into Ukraine and the world would roll over. Instead he met a wall of strength he never imagined. \\n\\nHe met the Ukrainian people. \\n\\nFrom President Zelenskyy to every Ukrainian, their fearlessness, their courage, their determination, inspires the world. ', lookup_str='', metadata={'document': 1}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "metadatas = [{\"document\": 1}, {\"document\": 2}]\n",
+    "documents = text_splitter.create_documents([state_of_the_union, state_of_the_union], metadatas=metadatas)\n",
+    "documents[0]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "13dc0983",

docs/examples/integrations.rst

@@ -1,10 +0,0 @@
-Integrations
-============
-
-The examples here all highlight a specific type of integration.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   integrations/*

docs/examples/integrations/embeddings.ipynb

@@ -1,177 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "7ef4d402-6662-4a26-b612-35b542066487",
-   "metadata": {
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
-   "source": [
-    "#  Embeddings & VectorStores\n",
-    "\n",
-    "This notebook show cases how to use embeddings to create a VectorStore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "965eecee",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
-    "from langchain.vectorstores.faiss import FAISS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "68481687",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "with open('../state_of_the_union.txt') as f:\n",
-    "    state_of_the_union = f.read()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "texts = text_splitter.split_text(state_of_the_union)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "015f4ff5",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "docsearch = FAISS.from_texts(texts, embeddings)\n",
-    "\n",
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "67baf32e",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n",
-      "\n",
-      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
-      "\n",
-      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n"
-     ]
-    }
-   ],
-   "source": [
-    "print(docs[0].page_content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "eea6e627",
-   "metadata": {},
-   "source": [
-    "## Requires having ElasticSearch setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "4906b8a3",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "docsearch = ElasticVectorSearch.from_texts(texts, embeddings, elasticsearch_url=\"http://localhost:9200\")\n",
-    "\n",
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "95f9eee9",
-   "metadata": {
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n",
-      "\n",
-      "A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
-      "\n",
-      "And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n"
-     ]
-    }
-   ],
-   "source": [
-    "print(docs[0].page_content)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.7"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/explanation/combine_docs.md

@@ -61,7 +61,7 @@ small enough chunks.
 LangChain provides some utilities to help with splitting up larger pieces of data. This comes in the form of the TextSplitter class.
 The class takes in a document and splits it up into chunks, with several parameters that control the
 size of the chunks as well as the overlap in the chunks (important for maintaining context).
-See [this walkthrough](../examples/integrations/textsplitter.ipynb) for more information.
+See [this walkthrough](../examples/data_augmented_generation/textsplitter.ipynb) for more information.
 
 ### Relevant Documents
 A second large issue related fetching data is to make sure you are not fetching too many documents, and are only fetching
@@ -123,6 +123,6 @@ It is important to note that a large part of these implementations is the prompt
 that are used. We provide default prompts for all three use cases, but these can be configured.
 This is in case you discover a prompt that works better for your specific application.
 
-- [Question-Answering With Sources](../examples/chains/qa_with_sources.ipynb)
-- [Question-Answering](../examples/chains/question_answering.ipynb)
-- [Summarization](../examples/chains/summarize.ipynb)
+- [Question-Answering With Sources](../examples/data_augmented_generation/qa_with_sources.ipynb)
+- [Question-Answering](../examples/data_augmented_generation/question_answering.ipynb)
+- [Summarization](../examples/data_augmented_generation/summarize.ipynb)

docs/getting_started/data_augmented_generation.ipynb

@@ -0,0 +1,216 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7ba0decc",
+   "metadata": {},
+   "source": [
+    "# Data Augmented Generation\n",
+    "\n",
+    "This notebook covers getting started with some key concepts of data augmented generation, specifically Documents, Embeddings, and Vectorstores.\n",
+    "\n",
+    "After that, we will cover how to use these concepts to do question/answering over select documents.\n",
+    "\n",
+    "For a more conceptual explanation of what Data Augmented Generation is, see [this](../explanation/combine_docs.md) documentation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b37c3e1e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
+    "from langchain.vectorstores.faiss import FAISS"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a8c13318",
+   "metadata": {},
+   "source": [
+    "First, let's load in our private data that we want to use in conjunction with an LLM."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "91d307ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('../examples/state_of_the_union.txt') as f:\n",
+    "    state_of_the_union = f.read()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12f8bc8f",
+   "metadata": {},
+   "source": [
+    "Now, we need to create smaller chunks of text from this one large document. We want to do this because we cannot (and do not want to) pass this whole large text into the language model in one go - rather, we want to split it up, select the relevant parts, and then pass those into the language model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "10a93bf9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_text(state_of_the_union)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c2f8c006",
+   "metadata": {},
+   "source": [
+    "We could work with ALL these documents directly, but often we only want to find only the most relevant ones. One common way to do that is create embeddings for each document, store them in a vector database, and then query that database with an incoming query to select the most relevant documents for that query.\n",
+    "\n",
+    "In this example, we use OpenAI embeddings, and a FAISS vector store."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "fa0f3066",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = OpenAIEmbeddings()\n",
+    "docsearch = FAISS.from_texts(texts, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2c6ce83f",
+   "metadata": {},
+   "source": [
+    "Now let's give it a go!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8465b4b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs = docsearch.similarity_search(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "611be801",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
+      "\n",
+      "We cannot let this happen. \n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence. \n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0b6a48e5",
+   "metadata": {},
+   "source": [
+    "So we now have a way of selecting the most relevant documents - now what? We can plug this vectorstore into a chain, where we first select these documents, and then send them (along with the original question) to get a final answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "b6255b02",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI, VectorDBQA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ec4eacad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa = VectorDBQA.from_llm(llm=OpenAI(), vectorstore=docsearch)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "59c7508d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" The president said that Ketanji Brown Jackson is one of our nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. The president also said that Ketanji Brown Jackson is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "qa.run(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b192c91c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/index.rst

@@ -9,13 +9,14 @@ combine them with other sources of computation or knowledge.
 
 This library is aimed at assisting in the development of those types of applications.
 
-There are four main areas that LangChain is designed to help with.
+There are five main areas that LangChain is designed to help with.
 These are, in increasing order of complexity:
 
 1. LLM and Prompts
 2. Chains
-3. Agents
-4. Memory
+3. Data Augmented Generation
+4. Agents
+5. Memory
 
 Let's go through these categories and for each one identify key concepts (to clarify terminology) as well as the problems in this area LangChain helps solve.
 
@@ -51,7 +52,25 @@ LangChain provides several parts to help with that.
 - Standard interface for working with Chains
 - Easy way to construct chains of LLMs
 - Lots of integrations with other tools that you may want to use in conjunction with LLMs
-- End-to-end chains for common workflows (database question/answer, recursive summarization, etc)
+- End-to-end chains for common workflows (database question/answer, api calling, etc)
+
+**📚 Data Augmented Generation**
+
+LLMs have access to all the data they were trained on, but there are still large chunks of data they were not trained on.
+Data Augmented Generation covers how to use LLMs to generate text conditioning on data outside of what the LLM was trained on.
+
+*Key Concepts*
+
+- Documents: A document is a piece of text, along with some associated metadata, that can be inserted into the context of a query to condition generation on that text.
+- Embeddings: A vector representation of text (or other unstructured data). Useful for being able to numerically compare pieces of text.
+- Vectorstore: A database which stores embeddings and can be searched over.
+
+*Problems Solved*
+
+- Standard interface for working with Documents, Embeddings, and Vectorstores
+- Lots of integrations with common embedding providers and vectorstores
+- End-to-end chains for common workflows (recursive summarization, question answering over documents, etc)
+
 
 **🤖 Agents**
 
@@ -102,7 +121,8 @@ The documentation is structured into the following sections:
    getting_started/environment.md
    getting_started/llm.md
    getting_started/llm_chain.md
-   getting_started/sequential_chains.md
+   getting_started/sequential_chains.ipynb
+   getting_started/data_augmented_generation.ipynb
    getting_started/agents.ipynb
    getting_started/memory.ipynb
 
@@ -117,8 +137,8 @@ Start here if you haven't used LangChain before.
    :name: examples
 
    examples/prompts.rst
-   examples/integrations.rst
    examples/chains.rst
+   examples/data_augmented_generation.rst
    examples/agents.rst
    examples/memory.rst
    examples/model_laboratory.ipynb
@@ -134,19 +154,12 @@ common tasks or cool demos.
    :caption: Reference
    :name: reference
 
-   installation.md
-   integrations.md
-   modules/prompt
-   modules/example_selector
-   modules/llms
-   modules/embeddings
-   modules/text_splitter
-   modules/python.rst
-   modules/serpapi.rst
-   modules/docstore.rst
-   modules/vectorstore
-   modules/chains
-   modules/agents
+   reference/installation.md
+   reference/integrations.md
+   reference/prompts.rst
+   reference/chains.rst
+   reference/data_augmented_generation.rst
+   reference/modules/agents
 
 
 Full API documentation. This is the place to look if you want to

docs/reference/chains.rst

@@ -0,0 +1,21 @@
+Chains
+==============
+
+One big part of chains is all the utilities that can be used as part of them.
+Here is some reference documentation for the utilities natively supported by LangChain.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+
+   modules/python
+   modules/serpapi
+
+
+With those utilities in mind, here are the reference docs for all the chains in LangChain.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+
+   modules/chains

docs/reference/data_augmented_generation.rst

@@ -0,0 +1,13 @@
+Data Augmented Generation
+=========================
+
+The reference guides here all relate to components necessary for data augmented generation.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+
+   modules/text_splitter
+   modules/docstore
+   modules/embeddings
+   modules/vectorstore

docs/reference/prompts.rst

@@ -0,0 +1,12 @@
+LLMs & Prompts
+==============
+
+The reference guides here all relate to objects for working with LLMs and Prompts.
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+
+   modules/prompt
+   modules/example_selector
+   modules/llms