gpt-4

_Thank you to the LangChain team for the great project and in advance
for your review. Let me know if I can provide any other additional
information or do things differently in the future to make your lives
easier 🙏 _

@hwchase17 please let me know if you're not the right person to review 😄

This PR enables LangChain to access the Konko API via the chat_models
API wrapper.

Konko API is a fully managed API designed to help application
developers:

1. Select the right LLM(s) for their application
2. Prototype with various open-source and proprietary LLMs
3. Move to production in-line with their security, privacy, throughput,
latency SLAs without infrastructure set-up or administration using Konko
AI's SOC 2 compliant infrastructure

_Note on integration tests:_ 
We added 14 integration tests. They will all fail unless you export the
right API keys. 13 will pass with a KONKO_API_KEY provided and the other
one will pass with a OPENAI_API_KEY provided. When both are provided,
all 14 integration tests pass. If you would like to test this yourself,
please let me know and I can provide some temporary keys.

### Installation and Setup

1. **First you'll need an API key**
2. **Install Konko AI's Python SDK**
    1. Enable a Python3.8+ environment
    
    `pip install konko`
    
3.  **Set API Keys**
    
          **Option 1:** Set Environment Variables
    
    You can set environment variables for
    
    1. KONKO_API_KEY (Required)
    2. OPENAI_API_KEY (Optional)
    
    In your current shell session, use the export command:
    
    `export KONKO_API_KEY={your_KONKO_API_KEY_here}`
    `export OPENAI_API_KEY={your_OPENAI_API_KEY_here} #Optional`
    
Alternatively, you can add the above lines directly to your shell
startup script (such as .bashrc or .bash_profile for Bash shell and
.zshrc for Zsh shell) to have them set automatically every time a new
shell session starts.
    
    **Option 2:** Set API Keys Programmatically
    
If you prefer to set your API keys directly within your Python script or
Jupyter notebook, you can use the following commands:
    
    ```python
    konko.set_api_key('your_KONKO_API_KEY_here')
    konko.set_openai_api_key('your_OPENAI_API_KEY_here') # Optional
    
    ```
    

### Calling a model

Find a model on the [[Konko Introduction
page](https://docs.konko.ai/docs#available-models)](https://docs.konko.ai/docs#available-models)

For example, for this [[LLama 2
model](https://docs.konko.ai/docs/meta-llama-2-13b-chat)](https://docs.konko.ai/docs/meta-llama-2-13b-chat).
The model id would be: `"meta-llama/Llama-2-13b-chat-hf"`

Another way to find the list of models running on the Konko instance is
through this
[[endpoint](https://docs.konko.ai/reference/listmodels)](https://docs.konko.ai/reference/listmodels).

From here, we can initialize our model:

```python
chat_instance = ChatKonko(max_tokens=10, model = 'meta-llama/Llama-2-13b-chat-hf')

```

And run it:

```python
msg = HumanMessage(content="Hi")
chat_response = chat_instance([msg])

```

docs/docs_skeleton/docs/modules/data_connection/index.mdx

@@ -4,58 +4,32 @@ sidebar_position: 1
 
 # Retrieval
 
-Many LLM applications require user-specific data that is not part of the model's training set.
-The primary way of accomplishing this is through Retrieval Augmented Generation (RAG).
-In this process, external data is *retrieved* and then passed to the LLM when doing the *generation* step.
+Imagine needing to feed a Language Learning Model (LLM) with user-specific data that isn't part of its training set. Retrieval Augmented Generation (RAG) makes this possible, serving as a bridge to fetch and supply this external data to the LLM during the generation phase.
 
-LangChain provides all the building blocks for RAG applications - from simple to complex.
-This section of the documentation covers everything related to the *retrieval* step - e.g. the fetching of the data.
-Although this sounds simple, it can be subtly complex.
-This encompasses several key modules.
+LangChain provides all the necessary tools to implement RAG applications, catering to all levels of complexity. This section delves into the intricacies of the *retrieval* step. While it may seem straightforward, this process can involve sophisticated complexities and revolves around several key modules.
 
 ![data_connection_diagram](/img/data_connection.jpg)
 
-**[Document loaders](/docs/modules/data_connection/document_loaders/)**
+**[Document Loaders](/docs/modules/data_connection/document_loaders/)**
 
-Load documents from many different sources.
-LangChain provides over 100 different document loaders as well as integrations with other major providers in the space,
-like AirByte and Unstructured.
-We provide integrations to load all types of documents (HTML, PDF, code) from all types of locations (private s3 buckets, public websites).
+Document loaders act as the 'gatherers', fetching documents from a multitude of sources. For instance, LangChain's loaders can gather HTML files from private s3 buckets or PDFs from public websites. We offer over 100 different loaders and seamlessly integrate with major providers like AirByte and Unstructured.
 
-**[Document transformers](/docs/modules/data_connection/document_transformers/)**
+**[Document Transformers](/docs/modules/data_connection/document_transformers/)**
 
-A key part of retrieval is fetching only the relevant parts of documents.
-This involves several transformation steps in order to best prepare the documents for retrieval.
-One of the primary ones here is splitting (or chunking) a large document into smaller chunks.
-LangChain provides several different algorithms for doing this, as well as logic optimized for specific document types (code, markdown, etc).
+Transformers work as the 'selectors', fetching only the relevant parts of documents. For example, they can split a large code document into smaller, manageable chunks for easier processing. LangChain provides specialized algorithms and logic for this purpose.
 
-**[Text embedding models](/docs/modules/data_connection/text_embedding/)**
+**[Text Embedding Models](/docs/modules/data_connection/text_embedding/)**
 
-Another key part of retrieval has become creating embeddings for documents.
-Embeddings capture the semantic meaning of the text, allowing you to quickly and
-efficiently find other pieces of text that are similar.
-LangChain provides integrations with over 25 different embedding providers and methods,
-from open-source to proprietary API,
-allowing you to choose the one best suited for your needs.
-LangChain provides a standard interface, allowing you to easily swap between models.
+Text embeddings serve as 'capsules' capturing the semantic meaning of text, helping in finding similar text pieces efficiently. For example, they can help find documents related to 'climate change' even if the exact phrase isn't used. LangChain integrates with over 25 embedding providers, offering a standard interface for easy model swapping.
 
-**[Vector stores](/docs/modules/data_connection/vectorstores/)**
+**[Vector Stores](/docs/modules/data_connection/vectorstores/)**
 
-With the rise of embeddings, there has emerged a need for databases to support efficient storage and searching of these embeddings.
-LangChain provides integrations with over 50 different vectorstores, from open-source local ones to cloud-hosted proprietary ones,
-allowing you to choose the one best suited for your needs.
-LangChain exposes a standard interface, allowing you to easily swap between vector stores.
+Vector stores function as the 'libraries' that efficiently store and search text embeddings. LangChain integrates with over 50 vector stores, from local open-source ones to cloud-hosted proprietary ones, providing a standard interface for easy store swapping.
 
 **[Retrievers](/docs/modules/data_connection/retrievers/)**
 
-Once the data is in the database, you still need to retrieve it.
-LangChain supports many different retrieval algorithms and is one of the places where we add the most value.
-We support basic methods that are easy to get started - namely simple semantic search.
-However, we have also added a collection of algorithms on top of this to increase performance.
-These include:
-
+Retrievers act as the 'fetchers' that extract the stored data when needed. LangChain supports various retrieval algorithms, such as:
 - [Parent Document Retriever](/docs/modules/data_connection/retrievers/parent_document_retriever): This allows you to create multiple embeddings per parent document, allowing you to look up smaller chunks but return larger context.
 - [Self Query Retriever](/docs/modules/data_connection/retrievers/self_query): User questions often contain a reference to something that isn't just semantic but rather expresses some logic that can best be represented as a metadata filter. Self-query allows you to parse out the *semantic* part of a query from other *metadata filters* present in the query.
 - [Ensemble Retriever](/docs/modules/data_connection/retrievers/ensemble): Sometimes you may want to retrieve documents from multiple different sources, or using multiple different algorithms. The ensemble retriever allows you to easily do this.
-- And more!
-
+- And more!

docs/docs_skeleton/docs/modules/model_io/output_parsers/index.mdx

@@ -12,7 +12,7 @@ Output parsers are classes that help structure language model responses. There a
 
 And then one optional one:
 
-- "Parse with prompt": A method which takes in a string (assumed to be the response from a language model) and a prompt (assumed to the prompt that generated such a response) and parses it into some structure. The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.
+- "Parse with prompt": A method which takes in a string (assumed to be the response from a language model) and a prompt (assumed to be the prompt that generated such a response) and parses it into some structure. The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.
 
 ## Get started
 

docs/docs_skeleton/vercel.json

@@ -1076,6 +1076,10 @@
       "source": "/docs/modules/agents/tools/integrations/zapier",
       "destination": "/docs/integrations/tools/zapier"
     },
+    {
+      "source": "/docs/integrations/tools/sqlite",
+      "destination": "/docs/use_cases/sql/sqlite"
+    },
     {
       "source": "/en/latest/modules/callbacks/filecallbackhandler.html",
       "destination": "/docs/modules/callbacks/how_to/filecallbackhandler"
@@ -2216,6 +2220,10 @@
       "source": "/docs/modules/data_connection/text_embedding/integrations/tensorflowhub",
       "destination": "/docs/integrations/text_embedding/tensorflowhub"
     },
+    {
+      "source": "/docs/integrations/text_embedding/Awa",
+      "destination": "/docs/integrations/text_embedding/awadb"
+    },
     {
       "source": "/en/latest/modules/indexes/vectorstores/examples/analyticdb.html",
       "destination": "/docs/integrations/vectorstores/analyticdb"

docs/extras/expression_language/cookbook/code_writing.ipynb

@@ -0,0 +1,119 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f09fd305",
+   "metadata": {},
+   "source": [
+    "# Code writing\n",
+    "\n",
+    "Example of how to use LCEL to write Python code."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "bd7c259a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from langchain.utilities import PythonREPL"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "73795d2d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Write some python code to solve the user's problem. \n",
+    "\n",
+    "Return only python code in Markdown format, e.g.:\n",
+    "\n",
+    "```python\n",
+    "....\n",
+    "```\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"system\", template), (\"human\", \"{input}\")]\n",
+    ")\n",
+    "\n",
+    "model = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "42859e8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _sanitize_output(text: str):\n",
+    "    _, after = text.split(\"```python\")\n",
+    "    return after.split(\"```\")[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "5ded1a86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model | StrOutputParser() | _sanitize_output | PythonREPL().run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "208c2b75",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Python REPL can execute arbitrary code. Use with caution.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'4\\n'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"whats 2 plus 2\"})"
+   ]
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/cookbook/index.mdx

@@ -0,0 +1,11 @@
+---
+sidebar_position: 2
+---
+
+# Cookbook
+
+import DocCardList from "@theme/DocCardList";
+
+Example code for accomplishing common tasks with the LangChain Expression Language (LCEL). These examples show how to compose different Runnable (the core LCEL interface) components to achieve various tasks. If you're just getting acquainted with LCEL, the [Prompt + LLM](/docs/expression_language/cookbook/prompt_llm_parser) page is a good place to start.
+
+<DocCardList />

docs/extras/expression_language/cookbook/memory.ipynb

@@ -0,0 +1,180 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "5062941a",
+   "metadata": {},
+   "source": [
+    "# Adding memory\n",
+    "\n",
+    "This shows how to add memory to an arbitrary chain. Right now, you can use the memory classes but need to hook it up manually"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7998efd8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain.schema.runnable import RunnableMap\n",
+    "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "prompt = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"You are a helpful chatbot\"),\n",
+    "    MessagesPlaceholder(variable_name=\"history\"),\n",
+    "    (\"human\", \"{input}\")\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "fa0087f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferMemory(return_messages=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "06b531ae",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': []}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d9437af6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = RunnableMap({\n",
+    "    \"input\": lambda x: x[\"input\"],\n",
+    "    \"memory\": memory.load_memory_variables\n",
+    "}) | {\n",
+    "    \"input\": lambda x: x[\"input\"],\n",
+    "    \"history\": lambda x: x[\"memory\"][\"history\"]\n",
+    "} | prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "bed1e260",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs = {\"input\": \"hi im bob\"}\n",
+    "response = chain.invoke(inputs)\n",
+    "response"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "890475b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory.save_context(inputs, {\"output\": response.content})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "e8fcb77f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [HumanMessage(content='hi im bob', additional_kwargs={}, example=False),\n",
+       "  AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)]}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "d837d5c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Your name is Bob.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs = {\"input\": \"whats my name\"}\n",
+    "response = chain.invoke(inputs)\n",
+    "response"
+   ]
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/cookbook/moderation.ipynb

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "4927a727-b4c8-453c-8c83-bd87b4fcac14",
+   "metadata": {},
+   "source": [
+    "# Adding moderation\n",
+    "\n",
+    "This shows how to add in moderation (or other safeguards) around your LLM application."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "4f5f6449-940a-4f5c-97c0-39b71c3e2a68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import OpenAIModerationChain\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import ChatPromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fcb8312b-7e7a-424f-a3ec-76738c9a9d21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "moderate = OpenAIModerationChain()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "b24b9148-f6b0-4091-8ea8-d3fb281bd950",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = OpenAI()\n",
+    "prompt = ChatPromptTemplate.from_messages([\n",
+    "    (\"system\", \"repeat after me: {input}\")\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "1c8ed87c-9ca6-4559-bf60-d40e94a0af08",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "5256b9bd-381a-42b0-bfa8-7e6d18f853cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nYou are stupid.'"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"you are stupid\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "fe6e3b33-dc9a-49d5-b194-ba750c58a628",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "moderated_chain = chain | moderate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "d8ba0cbd-c739-4d23-be9f-6ae092bd5ffb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': '\\n\\nYou are stupid',\n",
+       " 'output': \"Text was found that violates OpenAI's content policy.\"}"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "moderated_chain.invoke({\"input\": \"you are stupid\"})"
+   ]
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/cookbook/multiple_chains.ipynb

@@ -0,0 +1,240 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "877102d1-02ea-4fa3-8ec7-a08e242b95b3",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 2\n",
+    "title: Multiple chains\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f2bf8d3",
+   "metadata": {},
+   "source": [
+    "Runnables can easily be used to string together multiple Chains"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "d65d4e9e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'El país donde se encuentra la ciudad de Honolulu, donde nació Barack Obama, el 44º Presidente de los Estados Unidos, es Estados Unidos. Honolulu se encuentra en la isla de Oahu, en el estado de Hawái.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema import StrOutputParser\n",
+    "\n",
+    "prompt1 = ChatPromptTemplate.from_template(\"what is the city {person} is from?\")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\"what country is the city {city} in? respond in {language}\")\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "\n",
+    "chain1 = prompt1 | model | StrOutputParser()\n",
+    "\n",
+    "chain2 = {\"city\": chain1, \"language\": itemgetter(\"language\")} | prompt2 | model | StrOutputParser()\n",
+    "\n",
+    "chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "878f8176",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
+    "\n",
+    "prompt1 = ChatPromptTemplate.from_template(\"generate a {attribute} color. Return the name of the color and nothing else:\")\n",
+    "prompt2 = ChatPromptTemplate.from_template(\"what is a fruit of color: {color}. Return the name of the fruit and nothing else:\")\n",
+    "prompt3 = ChatPromptTemplate.from_template(\"what is a country with a flag that has the color: {color}. Return the name of the country and nothing else:\")\n",
+    "prompt4 = ChatPromptTemplate.from_template(\"What is the color of {fruit} and the flag of {country}?\")\n",
+    "\n",
+    "model_parser = model | StrOutputParser()\n",
+    "\n",
+    "color_generator = {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
+    "color_to_fruit = prompt2 | model_parser\n",
+    "color_to_country = prompt3 | model_parser\n",
+    "question_generator = color_generator | {\"fruit\": color_to_fruit, \"country\": color_to_country} | prompt4"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d621a870",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ChatPromptValue(messages=[HumanMessage(content='What is the color of strawberry and the flag of China?', additional_kwargs={}, example=False)])"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "question_generator.invoke({\"warm\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b4a9812b-bead-4fd9-ae27-0b8be57e5dc1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The color of an apple is typically red or green. The flag of China is predominantly red with a large yellow star in the upper left corner and four smaller yellow stars surrounding it.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt = question_generator.invoke({\"warm\"})\n",
+    "model.invoke(prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d75a313-f1c8-4e94-9a17-24e0bf4a2bdc",
+   "metadata": {},
+   "source": [
+    "### Branching and Merging\n",
+    "\n",
+    "You may want the output of one component to be processed by 2 or more other components. [RunnableMaps](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.base.RunnableMap.html) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
+    "\n",
+    "```text\n",
+    "     Input\n",
+    "      / \\\n",
+    "     /   \\\n",
+    " Branch1 Branch2\n",
+    "     \\   /\n",
+    "      \\ /\n",
+    "      Combine\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "247fa0bd-4596-4063-8cb3-1d7fc119d982",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "planner = (\n",
+    "    ChatPromptTemplate.from_template(\n",
+    "        \"Generate an argument about: {input}\"\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    "    | {\"base_response\": RunnablePassthrough()}\n",
+    ")\n",
+    "\n",
+    "arguments_for = (\n",
+    "    ChatPromptTemplate.from_template(\n",
+    "        \"List the pros or positive aspects of {base_response}\"\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "arguments_against =  (\n",
+    "    ChatPromptTemplate.from_template(\n",
+    "        \"List the cons or negative aspects of {base_response}\"\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "final_responder = (\n",
+    "    ChatPromptTemplate.from_messages(\n",
+    "        [\n",
+    "            (\"ai\", \"{original_response}\"),\n",
+    "            (\"human\", \"Pros:\\n{results_1}\\n\\nCons:\\n{results_2}\"),\n",
+    "            (\"system\", \"Generate a final response given the critique\"),\n",
+    "        ]\n",
+    "    )\n",
+    "    | ChatOpenAI()\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "chain = (\n",
+    "    planner \n",
+    "    | {\n",
+    "        \"results_1\": arguments_for,\n",
+    "        \"results_2\": arguments_against,\n",
+    "        \"original_response\": itemgetter(\"base_response\"),\n",
+    "    }\n",
+    "    | final_responder\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "2564f310-0674-4bb1-9c4e-d7848ca73511",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'While Scrum has its potential cons and challenges, many organizations have successfully embraced and implemented this project management framework to great effect. The cons mentioned above can be mitigated or overcome with proper training, support, and a commitment to continuous improvement. It is also important to note that not all cons may be applicable to every organization or project.\\n\\nFor example, while Scrum may be complex initially, with proper training and guidance, teams can quickly grasp the concepts and practices. The lack of predictability can be mitigated by implementing techniques such as velocity tracking and release planning. The limited documentation can be addressed by maintaining a balance between lightweight documentation and clear communication among team members. The dependency on team collaboration can be improved through effective communication channels and regular team-building activities.\\n\\nScrum can be scaled and adapted to larger projects by using frameworks like Scrum of Scrums or LeSS (Large Scale Scrum). Concerns about speed versus quality can be addressed by incorporating quality assurance practices, such as continuous integration and automated testing, into the Scrum process. Scope creep can be managed by having a well-defined and prioritized product backlog, and a strong product owner can be developed through training and mentorship.\\n\\nResistance to change can be overcome by providing proper education and communication to stakeholders and involving them in the decision-making process. Ultimately, the cons of Scrum can be seen as opportunities for growth and improvement, and with the right mindset and support, they can be effectively managed.\\n\\nIn conclusion, while Scrum may have its challenges and potential cons, the benefits and advantages it offers in terms of collaboration, flexibility, adaptability, transparency, and customer satisfaction make it a widely adopted and successful project management framework. With proper implementation and continuous improvement, organizations can leverage Scrum to drive innovation, efficiency, and project success.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"scrum\"})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv",
+   "language": "python",
+   "name": "poetry-venv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/cookbook/prompt_llm_parser.ipynb

@@ -0,0 +1,431 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "abf7263d-3a62-4016-b5d5-b157f92f2070",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Prompt + LLM\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a434f2b-9405-468c-9dfd-254d456b57a6",
+   "metadata": {},
+   "source": [
+    "The most common and valuable composition is taking:\n",
+    "\n",
+    "``PromptTemplate`` / ``ChatPromptTemplate`` -> ``LLM`` / ``ChatModel`` -> ``OutputParser``\n",
+    "\n",
+    "Almost any other chains you build will use this building block."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93aa2c87",
+   "metadata": {},
+   "source": [
+    "## PromptTemplate + LLM\n",
+    "\n",
+    "The simplest composition is just combing a prompt and model to create a chain that takes user input, adds it to a prompt, passes it to a model, and returns the raw model input.\n",
+    "\n",
+    "Note, you can mix and match PromptTemplate/ChatPromptTemplates and LLMs/ChatModels as you like here."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "466b65b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")\n",
+    "model = ChatOpenAI()\n",
+    "chain = prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e3d0a6cd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7eb9ef50",
+   "metadata": {},
+   "source": [
+    "Often times we want to attach kwargs that'll be passed to each model call. Here's a few examples of that:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0b1d8f88",
+   "metadata": {},
+   "source": [
+    "### Attaching Stop Sequences"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "562a06bf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model.bind(stop=[\"\\n\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "43f5d04c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Why did the bear never wear shoes?', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f3eaf88a",
+   "metadata": {},
+   "source": [
+    "### Attaching Function Call information"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f94b71b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "functions = [\n",
+    "    {\n",
+    "      \"name\": \"joke\",\n",
+    "      \"description\": \"A joke\",\n",
+    "      \"parameters\": {\n",
+    "        \"type\": \"object\",\n",
+    "        \"properties\": {\n",
+    "          \"setup\": {\n",
+    "            \"type\": \"string\",\n",
+    "            \"description\": \"The setup for the joke\"\n",
+    "          },\n",
+    "          \"punchline\": {\n",
+    "            \"type\": \"string\",\n",
+    "            \"description\": \"The punchline for the joke\"\n",
+    "          }\n",
+    "        },\n",
+    "        \"required\": [\"setup\", \"punchline\"]\n",
+    "      }\n",
+    "    }\n",
+    "  ]\n",
+    "chain = prompt | model.bind(function_call= {\"name\": \"joke\"}, functions= functions)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "decf7710",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'function_call': {'name': 'joke', 'arguments': '{\\n  \"setup\": \"Why don\\'t bears wear shoes?\",\\n  \"punchline\": \"Because they have bear feet!\"\\n}'}}, example=False)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"}, config={})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9098c5ed",
+   "metadata": {},
+   "source": [
+    "## PromptTemplate + LLM + OutputParser\n",
+    "\n",
+    "We can also add in an output parser to easily trasform the raw LLM/ChatModel output into a more workable format"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cc194c78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "\n",
+    "chain = prompt | model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77acf448",
+   "metadata": {},
+   "source": [
+    "Notice that this now returns a string - a much more workable format for downstream tasks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e3d69a18",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\""
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c01864e5",
+   "metadata": {},
+   "source": [
+    "### Functions Output Parser\n",
+    "\n",
+    "When you specify the function to return, you may just want to parse that directly"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ad0dd88e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
+    "\n",
+    "chain = (\n",
+    "    prompt \n",
+    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    | JsonOutputFunctionsParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1e7aa8eb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'setup': \"Why don't bears like fast food?\",\n",
+       " 'punchline': \"Because they can't catch it!\"}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d4aa1a01",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
+    "\n",
+    "chain = (\n",
+    "    prompt \n",
+    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "8b6df9ba",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "023fbccb-ef7d-489e-a9ba-f98e17283d51",
+   "metadata": {},
+   "source": [
+    "## Simplifying input\n",
+    "\n",
+    "To make invocation even simpler, we can add a `RunnableMap` to take care of creating the prompt input dict for us:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "9601c0f0-71f9-4bd4-a672-7bd04084b018",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
+    "\n",
+    "map_ = RunnableMap({\"foo\": RunnablePassthrough()})\n",
+    "chain = (\n",
+    "    map_ \n",
+    "    | prompt\n",
+    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "7ec4f154-fda5-4847-9220-41aa902fdc33",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears wear shoes?\""
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"bears\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "def00bfe-0f83-4805-8c8f-8a53f99fa8ea",
+   "metadata": {},
+   "source": [
+    "Since we're composing our map with another Runnable, we can even use some syntactic sugar and just use a dict:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "7bf3846a-02ee-41a3-ba1b-a708827d4f3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = (\n",
+    "    {\"foo\": RunnablePassthrough()} \n",
+    "    | prompt\n",
+    "    | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
+    "    | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "e566d6a1-538d-4cb5-a210-a63e082e4c74",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Why don't bears like fast food?\""
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"bears\")"
+   ]
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/cookbook/retrieval.ipynb

@@ -0,0 +1,461 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "abe47592-909c-4844-bf44-9e55c2fb4bfa",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 1\n",
+    "title: RAG\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91c5ef3d",
+   "metadata": {},
+   "source": [
+    "Let's look at adding in a retrieval step to a prompt and LLM, which adds up to a \"retrieval-augmented generation\" chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7f25d9e9-d192-42e9-af50-5660a4bfb0d9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install langchain openai faiss-cpu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "33be32af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from langchain.schema.runnable import RunnablePassthrough\n",
+    "from langchain.vectorstores import FAISS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "bfc47ec1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorstore = FAISS.from_texts([\"harrison worked at kensho\"], embedding=OpenAIEmbeddings())\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "\n",
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "\n",
+    "model = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "eae31755",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = (\n",
+    "    {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
+    "    | prompt \n",
+    "    | model \n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f3040b0c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Harrison worked at Kensho.'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"where did harrison work?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e1d20c7c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\n",
+    "Answer in the following language: {language}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "\n",
+    "chain = {\n",
+    "    \"context\": itemgetter(\"question\") | retriever, \n",
+    "    \"question\": itemgetter(\"question\"), \n",
+    "    \"language\": itemgetter(\"language\")\n",
+    "} | prompt | model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7ee8b2d4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Harrison ha lavorato a Kensho.'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"question\": \"where did harrison work\", \"language\": \"italian\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f007669c",
+   "metadata": {},
+   "source": [
+    "## Conversational Retrieval Chain\n",
+    "\n",
+    "We can easily add in conversation history. This primarily means adding in chat_message_history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3f30c348",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.runnable import RunnableMap\n",
+    "from langchain.schema import format_document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "64ab1dbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts.prompt import PromptTemplate\n",
+    "\n",
+    "_template = \"\"\"Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n",
+    "\n",
+    "Chat History:\n",
+    "{chat_history}\n",
+    "Follow Up Input: {question}\n",
+    "Standalone question:\"\"\"\n",
+    "CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "7d628c97",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "ANSWER_PROMPT = ChatPromptTemplate.from_template(template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "f60a5d0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "DEFAULT_DOCUMENT_PROMPT = PromptTemplate.from_template(template=\"{page_content}\")\n",
+    "def _combine_documents(docs, document_prompt = DEFAULT_DOCUMENT_PROMPT, document_separator=\"\\n\\n\"):\n",
+    "    doc_strings = [format_document(doc, document_prompt) for doc in docs]\n",
+    "    return document_separator.join(doc_strings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "7d007db6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Tuple, List\n",
+    "def _format_chat_history(chat_history: List[Tuple]) -> str:\n",
+    "    buffer = \"\"\n",
+    "    for dialogue_turn in chat_history:\n",
+    "        human = \"Human: \" + dialogue_turn[0]\n",
+    "        ai = \"Assistant: \" + dialogue_turn[1]\n",
+    "        buffer += \"\\n\" + \"\\n\".join([human, ai])\n",
+    "    return buffer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "5c32cc89",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_inputs = RunnableMap(\n",
+    "    {\n",
+    "        \"standalone_question\": {\n",
+    "            \"question\": lambda x: x[\"question\"],\n",
+    "            \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
+    "        } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
+    "    }\n",
+    ")\n",
+    "_context = {\n",
+    "    \"context\": itemgetter(\"standalone_question\") | retriever | _combine_documents,\n",
+    "    \"question\": lambda x: x[\"standalone_question\"]\n",
+    "}\n",
+    "conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "135c8205",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversational_qa_chain.invoke({\n",
+    "    \"question\": \"where did harrison work?\",\n",
+    "    \"chat_history\": [],\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "424e7e7a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Harrison worked at Kensho.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversational_qa_chain.invoke({\n",
+    "    \"question\": \"where did he work?\",\n",
+    "    \"chat_history\": [(\"Who wrote this notebook?\", \"Harrison\")],\n",
+    "})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c5543183",
+   "metadata": {},
+   "source": [
+    "### With Memory and returning source documents\n",
+    "\n",
+    "This shows how to use memory with the above. For memory, we need to manage that outside at the memory. For returning the retrieved documents, we just need to pass them through all the way."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "e31dd17c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationBufferMemory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "d4bffe94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferMemory(return_messages=True, output_key=\"answer\", input_key=\"question\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "733be985",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# First we add a step to load memory\n",
+    "# This needs to be a RunnableMap because its the first input\n",
+    "loaded_memory = RunnableMap(\n",
+    "    {\n",
+    "        \"question\": itemgetter(\"question\"),\n",
+    "        \"memory\": memory.load_memory_variables,\n",
+    "    }\n",
+    ")\n",
+    "# Next we add a step to expand memory into the variables\n",
+    "expanded_memory = {\n",
+    "    \"question\": itemgetter(\"question\"),\n",
+    "    \"chat_history\": lambda x: x[\"memory\"][\"history\"]\n",
+    "}\n",
+    "\n",
+    "# Now we calculate the standalone question\n",
+    "standalone_question = {\n",
+    "    \"standalone_question\": {\n",
+    "        \"question\": lambda x: x[\"question\"],\n",
+    "        \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
+    "    } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
+    "}\n",
+    "# Now we retrieve the documents\n",
+    "retrieved_documents = {\n",
+    "    \"docs\": itemgetter(\"standalone_question\") | retriever,\n",
+    "    \"question\": lambda x: x[\"standalone_question\"]\n",
+    "}\n",
+    "# Now we construct the inputs for the final prompt\n",
+    "final_inputs = {\n",
+    "    \"context\": lambda x: _combine_documents(x[\"docs\"]),\n",
+    "    \"question\": itemgetter(\"question\")\n",
+    "}\n",
+    "# And finally, we do the part that returns the answers\n",
+    "answer = {\n",
+    "    \"answer\": final_inputs | ANSWER_PROMPT | ChatOpenAI(),\n",
+    "    \"docs\": itemgetter(\"docs\"),\n",
+    "}\n",
+    "# And now we put it all together!\n",
+    "final_chain = loaded_memory | expanded_memory | standalone_question | retrieved_documents | answer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "806e390c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'answer': AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False),\n",
+       " 'docs': [Document(page_content='harrison worked at kensho', metadata={})]}"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "inputs = {\"question\": \"where did harrison work?\"}\n",
+    "result = final_chain.invoke(inputs)\n",
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "977399fd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Note that the memory does not save automatically\n",
+    "# This will be improved in the future\n",
+    "# For now you need to save it yourself\n",
+    "memory.save_context(inputs, {\"answer\": result[\"answer\"].content})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "f94f7de4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [HumanMessage(content='where did harrison work?', additional_kwargs={}, example=False),\n",
+       "  AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)]}"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv",
+   "language": "python",
+   "name": "poetry-venv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/cookbook/sql_db.ipynb

@@ -0,0 +1,227 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "c14da114-1a4a-487d-9cff-e0e8c30ba366",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 3\n",
+    "title: Querying a SQL DB\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "506e9636",
+   "metadata": {},
+   "source": [
+    "We can replicate our SQLDatabaseChain with Runnables."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7a927516",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "\n",
+    "template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query:\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3f51f386",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.utilities import SQLDatabase"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7c3449d6-684b-416e-ba16-90a035835a88",
+   "metadata": {},
+   "source": [
+    "We'll need the Chinook sample DB for this example. There's many places to download it from, e.g. https://database.guide/2-sample-databases-sqlite/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "2ccca6fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db = SQLDatabase.from_uri(\"sqlite:///./Chinook.db\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "05ba88ee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_schema(_):\n",
+    "    return db.get_table_info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "a4eda902",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def run_query(query):\n",
+    "    return db.run(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "5046cb17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from langchain.schema.runnable import RunnableLambda, RunnableMap\n",
+    "\n",
+    "model = ChatOpenAI()\n",
+    "\n",
+    "inputs = {\n",
+    "    \"schema\": RunnableLambda(get_schema),\n",
+    "    \"question\": itemgetter(\"question\")\n",
+    "}\n",
+    "sql_response = (\n",
+    "        RunnableMap(inputs)\n",
+    "        | prompt\n",
+    "        | model.bind(stop=[\"\\nSQLResult:\"])\n",
+    "        | StrOutputParser()\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "a5552039",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'SELECT COUNT(*) FROM Employee'"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sql_response.invoke({\"question\": \"How many employees are there?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "d6fee130",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
+    "{schema}\n",
+    "\n",
+    "Question: {question}\n",
+    "SQL Query: {query}\n",
+    "SQL Response: {response}\"\"\"\n",
+    "prompt_response = ChatPromptTemplate.from_template(template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "923aa634",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "full_chain = (\n",
+    "    RunnableMap({\n",
+    "        \"question\": itemgetter(\"question\"),\n",
+    "        \"query\": sql_response,\n",
+    "    }) \n",
+    "    | {\n",
+    "        \"schema\": RunnableLambda(get_schema),\n",
+    "        \"question\": itemgetter(\"question\"),\n",
+    "        \"query\": itemgetter(\"query\"),\n",
+    "        \"response\": lambda x: db.run(x[\"query\"])    \n",
+    "    } \n",
+    "    | prompt_response \n",
+    "    | model\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "e94963d8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='There are 8 employees.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "full_chain.invoke({\"question\": \"How many employees are there?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f358d7b-a721-4db3-9f92-f06913428afc",
+   "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/cookbook/tools.ipynb

@@ -0,0 +1,122 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "29781123",
+   "metadata": {},
+   "source": [
+    "# Using tools\n",
+    "\n",
+    "You can use any Tools with Runnables easily."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a5c579dd-2e22-41b0-a789-346dfdecb5a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install duckduckgo-search"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9232d2a9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "from langchain.tools import DuckDuckGoSearchRun"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a0c64d2c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search = DuckDuckGoSearchRun()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "391969b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"turn the following user input into a search query for a search engine:\n",
+    "\n",
+    "{input}\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "\n",
+    "model = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e3d9d20d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = prompt | model | StrOutputParser() | search"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "55f2967d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'What sports games are on TV today & tonight? Watch and stream live sports on TV today, tonight, tomorrow. Today\\'s 2023 sports TV schedule includes football, basketball, baseball, hockey, motorsports, soccer and more. Watch on TV or stream online on ESPN, FOX, FS1, CBS, NBC, ABC, Peacock, Paramount+, fuboTV, local channels and many other networks. MLB Games Tonight: How to Watch on TV, Streaming & Odds - Thursday, September 7. Seattle Mariners\\' Julio Rodriguez greets teammates in the dugout after scoring against the Oakland Athletics in a ... Circle - Country Music and Lifestyle. Live coverage of all the MLB action today is available to you, with the information provided below. The Brewers will look to pick up a road win at PNC Park against the Pirates on Wednesday at 12:35 PM ET. Check out the latest odds and with BetMGM Sportsbook. Use bonus code \"GNPLAY\" for special offers! MLB Games Tonight: How to Watch on TV, Streaming & Odds - Tuesday, September 5. Houston Astros\\' Kyle Tucker runs after hitting a double during the fourth inning of a baseball game against the Los Angeles Angels, Sunday, Aug. 13, 2023, in Houston. (AP Photo/Eric Christian Smith) (APMedia) The Houston Astros versus the Texas Rangers is one of ... The second half of tonight\\'s college football schedule still has some good games remaining to watch on your television.. We\\'ve already seen an exciting one when Colorado upset TCU. And we saw some ...'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"input\": \"I'd like to figure out what games are tonight\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a16949cf-00ea-43c6-a6aa-797ad4f6918d",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv",
+   "language": "python",
+   "name": "poetry-venv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/how_to/_category_.yml

@@ -0,0 +1,2 @@
+label: 'How to'
+position: 1

docs/extras/expression_language/how_to/functions.ipynb

@@ -0,0 +1,158 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "fbc4bf6e",
+   "metadata": {},
+   "source": [
+    "# Run arbitrary functions\n",
+    "\n",
+    "You can use arbitrary functions in the pipeline\n",
+    "\n",
+    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single input and unpacks it into multiple argument."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "id": "6bb221b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.runnable import RunnableLambda\n",
+    "\n",
+    "def length_function(text):\n",
+    "    return len(text)\n",
+    "\n",
+    "def _multiple_length_function(text1, text2):\n",
+    "    return len(text1) * len(text2)\n",
+    "\n",
+    "def multiple_length_function(_dict):\n",
+    "    return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
+    "\n",
+    "chain1 = prompt | model\n",
+    "\n",
+    "chain = {\n",
+    "    \"a\": itemgetter(\"foo\") | RunnableLambda(length_function),\n",
+    "    \"b\": {\"text1\": itemgetter(\"foo\"), \"text2\": itemgetter(\"bar\")} | RunnableLambda(multiple_length_function)\n",
+    "} | prompt | model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 78,
+   "id": "5488ec85",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='3 + 9 equals 12.', additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 78,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4728ddd9-914d-42ce-ae9b-72c9ce8ec940",
+   "metadata": {},
+   "source": [
+    "## Accepting a Runnable Config\n",
+    "\n",
+    "Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.config.RunnableConfig.html?highlight=runnableconfig#langchain.schema.runnable.config.RunnableConfig), which they can use to pass callbacks, tags, and other configuration information to nested runs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 139,
+   "id": "80b3b5f6-5d58-44b9-807e-cce9a46bf49f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema.runnable import RunnableConfig"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 149,
+   "id": "ff0daf0c-49dd-4d21-9772-e5fa133c5f36",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "def parse_or_fix(text: str, config: RunnableConfig):\n",
+    "    fixing_chain = (\n",
+    "        ChatPromptTemplate.from_template(\n",
+    "            \"Fix the following text:\\n\\n```text\\n{input}\\n```\\nError: {error}\"\n",
+    "            \" Don't narrate, just respond with the fixed data.\"\n",
+    "        )\n",
+    "        | ChatOpenAI()\n",
+    "        | StrOutputParser()\n",
+    "    )\n",
+    "    for _ in range(3):\n",
+    "        try:\n",
+    "            return json.loads(text)\n",
+    "        except Exception as e:\n",
+    "            text = fixing_chain.invoke({\"input\": text, \"error\": e}, config)\n",
+    "    return \"Failed to parse\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 152,
+   "id": "1a5e709e-9d75-48c7-bb9c-503251990505",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Tokens Used: 65\n",
+      "\tPrompt Tokens: 56\n",
+      "\tCompletion Tokens: 9\n",
+      "Successful Requests: 1\n",
+      "Total Cost (USD): $0.00010200000000000001\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.callbacks import get_openai_callback\n",
+    "\n",
+    "with get_openai_callback() as cb:\n",
+    "    RunnableLambda(parse_or_fix).invoke(\"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]})\n",
+    "    print(cb)"
+   ]
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/expression_language/interface.ipynb

@@ -1,12 +1,21 @@
 {
  "cells": [
+  {
+   "cell_type": "raw",
+   "id": "366a0e68-fd67-4fe5-a292-5c33733339ea",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Interface\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "9a9acd2e",
    "metadata": {},
    "source": [
-    "# Interface\n",
-    "\n",
     "In an effort to make it as easy as possible to create custom chains, we've implemented a [\"Runnable\"](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.Runnable.html#langchain.schema.runnable.Runnable) protocol that most components implement. This is a standard interface with a few different methods, which makes it easy to define custom chains as well as making it possible to invoke them in a standard way. The standard interface exposed includes:\n",
     "\n",
     "- `stream`: stream back chunks of the response\n",
@@ -429,7 +438,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/extras/guides/privacy/presidio_data_anonymization/index.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# Data anonymization with Microsoft Presidio\n",
     "\n",
-    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization.ipynb)\n",
+    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/index.ipynb)\n",
     "\n",
     "## Use case\n",
     "\n",
@@ -439,8 +439,6 @@
    "metadata": {},
    "source": [
     "## Future works\n",
-    "\n",
-    "- **deanonymization** - add the ability to reverse anonymization. For example, the workflow could look like this: `anonymize -> LLMChain -> deanonymize`. By doing this, we will retain anonymity in requests to, for example, OpenAI, and then be able restore the original data.\n",
     "- **instance anonymization** - at this point, each occurrence of PII is treated as a separate entity and separately anonymized. Therefore, two occurrences of the name John Doe in the text will be changed to two different names. It is therefore worth introducing support for full instance detection, so that repeated occurrences are treated as a single object."
    ]
   }
@@ -461,7 +459,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/extras/guides/privacy/presidio_data_anonymization/multi_language.ipynb

@@ -0,0 +1,520 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Mutli-language data anonymization with Microsoft Presidio\n",
+    "\n",
+    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/multi_language.ipynb)\n",
+    "\n",
+    "\n",
+    "## Use case\n",
+    "\n",
+    "Multi-language support in data pseudonymization is essential due to differences in language structures and cultural contexts. Different languages may have varying formats for personal identifiers. For example, the structure of names, locations and dates can differ greatly between languages and regions. Furthermore, non-alphanumeric characters, accents, and the direction of writing can impact pseudonymization processes. Without multi-language support, data could remain identifiable or be misinterpreted, compromising data privacy and accuracy. Hence, it enables effective and precise pseudonymization suited for global operations.\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "PII detection in Microsoft Presidio relies on several components - in addition to the usual pattern matching (e.g. using regex), the analyser uses a model for Named Entity Recognition (NER) to extract entities such as:\n",
+    "- `PERSON`\n",
+    "- `LOCATION`\n",
+    "- `DATE_TIME`\n",
+    "- `NRP`\n",
+    "- `ORGANIZATION`\n",
+    "\n",
+    "[[Source]](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)\n",
+    "\n",
+    "To handle NER in specific languages, we utilize unique models from the `spaCy` library, recognized for its extensive selection covering multiple languages and sizes. However, it's not restrictive, allowing for integration of alternative frameworks such as [Stanza](https://microsoft.github.io/presidio/analyzer/nlp_engines/spacy_stanza/) or [transformers](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/) when necessary.\n",
+    "\n",
+    "\n",
+    "## Quickstart\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Install necessary packages\n",
+    "# ! pip install langchain langchain-experimental openai presidio-analyzer presidio-anonymizer spacy Faker\n",
+    "# ! python -m spacy download en_core_web_lg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_experimental.data_anonymizer import PresidioReversibleAnonymizer\n",
+    "\n",
+    "anonymizer = PresidioReversibleAnonymizer(\n",
+    "    analyzed_fields=[\"PERSON\"],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "By default, `PresidioAnonymizer` and `PresidioReversibleAnonymizer` use a model trained on English texts, so they handle other languages moderately well. \n",
+    "\n",
+    "For example, here the model did not detect the person:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Me llamo Sofía'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "anonymizer.anonymize(\"Me llamo Sofía\")  # \"My name is Sofía\" in Spanish"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "They may also take words from another language as actual entities. Here, both the word *'Yo'* (*'I'* in Spanish) and *Sofía* have been classified as `PERSON`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Bridget Kirk soy Sally Knight'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "anonymizer.anonymize(\"Yo soy Sofía\")  # \"I am Sofía\" in Spanish"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you want to anonymise texts from other languages, you need to download other models and add them to the anonymiser configuration:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Download the models for the languages you want to use\n",
+    "# ! python -m spacy download en_core_web_md\n",
+    "# ! python -m spacy download es_core_news_md"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "nlp_config = {\n",
+    "    \"nlp_engine_name\": \"spacy\",\n",
+    "    \"models\": [\n",
+    "        {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
+    "        {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
+    "    ],\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We have therefore added a Spanish language model. Note also that we have downloaded an alternative model for English as well - in this case we have replaced the large model `en_core_web_lg` (560MB) with its smaller version `en_core_web_md` (40MB) - the size is therefore reduced by 14 times! If you care about the speed of anonymisation, it is worth considering it.\n",
+    "\n",
+    "All models for the different languages can be found in the [spaCy documentation](https://spacy.io/usage/models).\n",
+    "\n",
+    "Now pass the configuration as the `languages_config` parameter to Anonymiser. As you can see, both previous examples work flawlessly:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Me llamo Michelle Smith\n",
+      "Yo soy Rachel Wright\n"
+     ]
+    }
+   ],
+   "source": [
+    "anonymizer = PresidioReversibleAnonymizer(\n",
+    "    analyzed_fields=[\"PERSON\"],\n",
+    "    languages_config=nlp_config,\n",
+    ")\n",
+    "\n",
+    "print(\n",
+    "    anonymizer.anonymize(\"Me llamo Sofía\", language=\"es\")\n",
+    ")  # \"My name is Sofía\" in Spanish\n",
+    "print(anonymizer.anonymize(\"Yo soy Sofía\", language=\"es\"))  # \"I am Sofía\" in Spanish"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "By default, the language indicated first in the configuration will be used when anonymising text (in this case English):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "My name is Ronnie Ayala\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(anonymizer.anonymize(\"My name is John\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Advanced usage\n",
+    "\n",
+    "### Custom labels in NER model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "It may be that the spaCy model has different class names than those supported by the Microsoft Presidio by default. Take Polish, for example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Text: Wiktoria, Start: 12, End: 20, Label: persName\n"
+     ]
+    }
+   ],
+   "source": [
+    "# ! python -m spacy download pl_core_news_md\n",
+    "\n",
+    "import spacy\n",
+    "\n",
+    "nlp = spacy.load(\"pl_core_news_md\")\n",
+    "doc = nlp(\"Nazywam się Wiktoria\")  # \"My name is Wiktoria\" in Polish\n",
+    "\n",
+    "for ent in doc.ents:\n",
+    "    print(\n",
+    "        f\"Text: {ent.text}, Start: {ent.start_char}, End: {ent.end_char}, Label: {ent.label_}\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The name *Victoria* was classified as `persName`, which does not correspond to the default class names `PERSON`/`PER` implemented in Microsoft Presidio (look for `CHECK_LABEL_GROUPS` in [SpacyRecognizer implementation](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)). \n",
+    "\n",
+    "You can find out more about custom labels in spaCy models (including your own, trained ones) in [this thread](https://github.com/microsoft/presidio/issues/851).\n",
+    "\n",
+    "That's why our sentence will not be anonymized:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Nazywam się Wiktoria\n"
+     ]
+    }
+   ],
+   "source": [
+    "nlp_config = {\n",
+    "    \"nlp_engine_name\": \"spacy\",\n",
+    "    \"models\": [\n",
+    "        {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
+    "        {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
+    "        {\"lang_code\": \"pl\", \"model_name\": \"pl_core_news_md\"},\n",
+    "    ],\n",
+    "}\n",
+    "\n",
+    "anonymizer = PresidioReversibleAnonymizer(\n",
+    "    analyzed_fields=[\"PERSON\", \"LOCATION\", \"DATE_TIME\"],\n",
+    "    languages_config=nlp_config,\n",
+    ")\n",
+    "\n",
+    "print(\n",
+    "    anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
+    ")  # \"My name is Wiktoria\" in Polish"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To address this, create your own `SpacyRecognizer` with your own class mapping and add it to the anonymizer:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from presidio_analyzer.predefined_recognizers import SpacyRecognizer\n",
+    "\n",
+    "polish_check_label_groups = [\n",
+    "    ({\"LOCATION\"}, {\"placeName\", \"geogName\"}),\n",
+    "    ({\"PERSON\"}, {\"persName\"}),\n",
+    "    ({\"DATE_TIME\"}, {\"date\", \"time\"}),\n",
+    "]\n",
+    "\n",
+    "spacy_recognizer = SpacyRecognizer(\n",
+    "    supported_language=\"pl\",\n",
+    "    check_label_groups=polish_check_label_groups,\n",
+    ")\n",
+    "\n",
+    "anonymizer.add_recognizer(spacy_recognizer)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now everything works smoothly:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Nazywam się Morgan Walters\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\n",
+    "    anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
+    ")  # \"My name is Wiktoria\" in Polish"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's try on more complex example:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Nazywam się Ernest Liu. New Taylorburgh to moje miasto rodzinne. Urodziłam się 1987-01-19\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\n",
+    "    anonymizer.anonymize(\n",
+    "        \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
+    "        language=\"pl\",\n",
+    "    )\n",
+    ")  # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "As you can see, thanks to class mapping, the anonymiser can cope with different types of entities. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Custom language-specific operators\n",
+    "\n",
+    "In the example above, the sentence has been anonymised correctly, but the fake data does not fit the Polish language at all. Custom operators can therefore be added, which will resolve the issue:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from faker import Faker\n",
+    "from presidio_anonymizer.entities import OperatorConfig\n",
+    "\n",
+    "fake = Faker(locale=\"pl_PL\")  # Setting faker to provide Polish data\n",
+    "\n",
+    "new_operators = {\n",
+    "    \"PERSON\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.first_name_female()}),\n",
+    "    \"LOCATION\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.city()}),\n",
+    "}\n",
+    "\n",
+    "anonymizer.add_operators(new_operators)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Nazywam się Marianna. Szczecin to moje miasto rodzinne. Urodziłam się 1976-11-16\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\n",
+    "    anonymizer.anonymize(\n",
+    "        \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
+    "        language=\"pl\",\n",
+    "    )\n",
+    ")  # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Limitations\n",
+    "\n",
+    "Remember - results are as good as your recognizers and as your NER models!\n",
+    "\n",
+    "Look at the example below - we downloaded the small model for Spanish (12MB) and it no longer performs as well as the medium version (40MB):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Model: es_core_news_sm. Result: Me llamo Sofía\n",
+      "Model: es_core_news_md. Result: Me llamo Lawrence Davis\n"
+     ]
+    }
+   ],
+   "source": [
+    "# ! python -m spacy download es_core_news_sm\n",
+    "\n",
+    "for model in [\"es_core_news_sm\", \"es_core_news_md\"]:\n",
+    "    nlp_config = {\n",
+    "        \"nlp_engine_name\": \"spacy\",\n",
+    "        \"models\": [\n",
+    "            {\"lang_code\": \"es\", \"model_name\": model},\n",
+    "        ],\n",
+    "    }\n",
+    "\n",
+    "    anonymizer = PresidioReversibleAnonymizer(\n",
+    "        analyzed_fields=[\"PERSON\"],\n",
+    "        languages_config=nlp_config,\n",
+    "    )\n",
+    "\n",
+    "    print(\n",
+    "        f\"Model: {model}. Result: {anonymizer.anonymize('Me llamo Sofía', language='es')}\"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In many cases, even the larger models from spaCy will not be sufficient - there are already other, more complex and better methods of detecting named entities, based on transformers. You can read more about this [here](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Future works\n",
+    "\n",
+    "- **automatic language detection** - instead of passing the language as a parameter in `anonymizer.anonymize`, we could detect the language/s beforehand and then use the corresponding NER model."
+   ]
+  }
+ ],
+ "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/extras/guides/privacy/presidio_data_anonymization/reversible.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# Reversible data anonymization with Microsoft Presidio\n",
     "\n",
-    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_reversible_anonymization.ipynb)\n",
+    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/reversible.ipynb)\n",
     "\n",
     "\n",
     "## Use case\n",
@@ -453,7 +453,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/extras/integrations/chat/konko.ipynb

@@ -0,0 +1,164 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Konko\n",
+    "\n",
+    ">[Konko](https://www.konko.ai/) API is a fully managed Web API designed to help application developers:\n",
+    "\n",
+    "Konko API is a fully managed API designed to help application developers:\n",
+    "\n",
+    "1. Select the right LLM(s) for their application\n",
+    "2. Prototype with various open-source and proprietary LLMs\n",
+    "3. Move to production in-line with their security, privacy, throughput, latency SLAs without infrastructure set-up or administration using Konko AI's SOC 2 compliant infrastructure\n",
+    "\n",
+    "\n",
+    "This example goes over how to use LangChain to interact with `Konko` [models](https://docs.konko.ai/docs/overview)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To run this notebook, you'll need Konko API key. You can request it by messaging support@konko.ai."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatKonko\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import AIMessage, HumanMessage, SystemMessage"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 2. Set API Keys\n",
+    "\n",
+    "<br />\n",
+    "\n",
+    "### Option 1: Set Environment Variables\n",
+    "\n",
+    "1. You can set environment variables for \n",
+    "   1. KONKO_API_KEY (Required)\n",
+    "   2. OPENAI_API_KEY (Optional)\n",
+    "2. In your current shell session, use the export command:\n",
+    "\n",
+    "```shell\n",
+    "export KONKO_API_KEY={your_KONKO_API_KEY_here}\n",
+    "export OPENAI_API_KEY={your_OPENAI_API_KEY_here} #Optional\n",
+    "```\n",
+    "\n",
+    "Alternatively, you can add the above lines directly to your shell startup script (such as .bashrc or .bash_profile for Bash shell and .zshrc for Zsh shell) to have them set automatically every time a new shell session starts.\n",
+    "\n",
+    "### Option 2: Set API Keys Programmatically\n",
+    "\n",
+    "If you prefer to set your API keys directly within your Python script or Jupyter notebook, you can use the following commands:\n",
+    "\n",
+    "```python\n",
+    "konko.set_api_key('your_KONKO_API_KEY_here')  \n",
+    "konko.set_openai_api_key('your_OPENAI_API_KEY_here') # Optional\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Calling a model\n",
+    "\n",
+    "Find a model on the [Konko overview page](https://docs.konko.ai/docs/overview)\n",
+    "\n",
+    "For example, for this [LLama 2 model](https://docs.konko.ai/docs/meta-llama-2-13b-chat). The model id would be: `\"meta-llama/Llama-2-13b-chat-hf\"`\n",
+    "\n",
+    "Another way to find the list of models running on the Konko instance is through this [endpoint](https://docs.konko.ai/reference/listmodels).\n",
+    "\n",
+    "From here, we can initialize our model:\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatKonko(max_tokens=400, model = 'meta-llama/Llama-2-13b-chat-hf')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Sure, I'd be happy to explain the Big Bang Theory briefly!\\n\\nThe Big Bang Theory is the leading explanation for the origin and evolution of the universe, based on a vast amount of observational evidence from many fields of science. In essence, the theory posits that the universe began as an infinitely hot and dense point, known as a singularity, around 13.8 billion years ago. This singularity expanded rapidly, and as it did, it cooled and formed subatomic particles, which eventually coalesced into the first atoms, and later into the stars and galaxies we see today.\\n\\nThe theory gets its name from the idea that the universe began in a state of incredibly high energy and temperature, and has been expanding and cooling ever since. This expansion is thought to have been driven by a mysterious force known as dark energy, which is thought to be responsible for the accelerating expansion of the universe.\\n\\nOne of the key predictions of the Big Bang Theory is that the universe should be homogeneous and isotropic on large scales, meaning that it should look the same in all directions and have the same properties everywhere. This prediction has been confirmed by a wealth of observational evidence, including the cosmic microwave background radiation, which is thought to be a remnant of the early universe.\\n\\nOverall, the Big Bang Theory is a well-established and widely accepted explanation for the origins of the universe, and it has been supported by a vast amount of observational evidence from many fields of science.\", additional_kwargs={}, example=False)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    SystemMessage(\n",
+    "        content=\"You are a helpful assistant.\"\n",
+    "    ),\n",
+    "    HumanMessage(\n",
+    "        content=\"Explain Big Bang Theory briefly\"\n",
+    "    ),\n",
+    "]\n",
+    "chat(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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": "3.11.3"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/extras/integrations/providers/awadb.md

@@ -9,13 +9,20 @@ pip install awadb
 ```
 
 
-## VectorStore
+## Vector Store
 
-There exists a wrapper around AwaDB vector databases, allowing you to use it as a vectorstore,
-whether for semantic search or example selection.
 
 ```python
 from langchain.vectorstores import AwaDB
 ```
 
-For a more detailed walkthrough of the AwaDB wrapper, see [here](/docs/integrations/vectorstores/awadb.html).
+See a [usage example](/docs/integrations/vectorstores/awadb).
+
+
+## Text Embedding Model
+
+```python
+from langchain.embeddings import AwaEmbeddings
+```
+
+See a [usage example](/docs/integrations/text_embedding/awadb).

docs/extras/integrations/providers/konko.mdx

@@ -0,0 +1,80 @@
+# Konko
+This page covers how to run models on Konko within LangChain.
+
+Konko API is a fully managed API designed to help application developers:
+
+Select the right LLM(s) for their application
+Prototype with various open-source and proprietary LLMs
+Move to production in-line with their security, privacy, throughput, latency SLAs without infrastructure set-up or administration using Konko AI's SOC 2 compliant infrastructure
+
+## Installation and Setup
+
+### First you'll need an API key
+You can request it by messaging [support@konko.ai](mailto:support@konko.ai) 
+
+### Install Konko AI's Python SDK
+
+#### 1. Enable a Python3.8+ environment
+
+#### 2. Set API Keys
+
+##### Option 1: Set Environment Variables
+
+1. You can set environment variables for 
+   1. KONKO_API_KEY (Required)
+   2. OPENAI_API_KEY (Optional)
+
+2. In your current shell session, use the export command:
+
+```shell
+export KONKO_API_KEY={your_KONKO_API_KEY_here}
+export OPENAI_API_KEY={your_OPENAI_API_KEY_here} #Optional
+```
+
+Alternatively, you can add the above lines directly to your shell startup script (such as .bashrc or .bash_profile for Bash shell and .zshrc for Zsh shell) to have them set automatically every time a new shell session starts.
+
+##### Option 2: Set API Keys Programmatically
+
+If you prefer to set your API keys directly within your Python script or Jupyter notebook, you can use the following commands:
+
+```python
+konko.set_api_key('your_KONKO_API_KEY_here')  
+konko.set_openai_api_key('your_OPENAI_API_KEY_here') # Optional
+```
+
+#### 3. Install the SDK
+
+
+```shell
+pip install konko
+```
+
+#### 4. Verify Installation & Authentication
+
+```python
+#Confirm konko has installed successfully
+import konko
+#Confirm API keys from Konko and OpenAI are set properly
+konko.Model.list()
+```
+
+## Calling a model
+
+Find a model on the [Konko Introduction page](https://docs.konko.ai/docs#available-models)
+
+For example, for this [LLama 2 model](https://docs.konko.ai/docs/meta-llama-2-13b-chat). The model id would be: `"meta-llama/Llama-2-13b-chat-hf"`
+
+Another way to find the list of models running on the Konko instance is through this [endpoint](https://docs.konko.ai/reference/listmodels).
+
+From here, we can initialize our model:
+
+```python
+chat_instance = ChatKonko(max_tokens=10, model = 'meta-llama/Llama-2-13b-chat-hf')
+```
+
+And run it:
+
+```python
+msg = HumanMessage(content="Hi")
+chat_response = chat_instance([msg])
+```

docs/extras/integrations/providers/modelscope.mdx

@@ -1,20 +1,24 @@
 # ModelScope
 
+>[ModelScope](https://www.modelscope.cn/home) is a big repository of the models and datasets.
+
 This page covers how to use the modelscope ecosystem within LangChain.
 It is broken into two parts: installation and setup, and then references to specific modelscope wrappers.
 
 ## Installation and Setup
 
-* Install the Python SDK with `pip install modelscope`
+Install the `modelscope` package.
+ 
+```bash
+pip install modelscope
+```
 
-## Wrappers
 
-### Embeddings
+## Text Embedding Models
 
-There exists a modelscope Embeddings wrapper, which you can access with 
 
 ```python
 from langchain.embeddings import ModelScopeEmbeddings
 ```
 
-For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/modelscope_hub.html)
+For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/modelscope_hub)

docs/extras/integrations/providers/nlpcloud.mdx

@@ -1,17 +1,31 @@
 # NLPCloud
 
-This page covers how to use the NLPCloud ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific NLPCloud wrappers.
+>[NLP Cloud](https://docs.nlpcloud.com/#introduction) is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. 
+
 
 ## Installation and Setup
-- Install the Python SDK with `pip install nlpcloud`
+
+- Install the `nlpcloud` package.
+
+```bash
+pip install nlpcloud
+```
+
 - Get an NLPCloud api key and set it as an environment variable (`NLPCLOUD_API_KEY`)
 
-## Wrappers
 
-### LLM
+## LLM
+
+See a [usage example](/docs/integrations/llms/nlpcloud).
 
-There exists an NLPCloud LLM wrapper, which you can access with 
 ```python
 from langchain.llms import NLPCloud
 ```
+
+## Text Embedding Models
+
+See a [usage example](/docs/integrations/text_embedding/nlp_cloud)
+
+```python
+from langchain.embeddings import NLPCloudEmbeddings
+```

docs/extras/integrations/providers/portkey/index.md

@@ -1,4 +1,10 @@
 # Portkey
+
+>[Portkey](https://docs.portkey.ai/overview/introduction) is a platform designed to streamline the deployment 
+> and management of Generative AI applications. 
+> It provides comprehensive features for monitoring, managing models,
+> and improving the performance of your AI applications.
+
 ## LLMOps for Langchain
 
 Portkey brings production readiness to Langchain. With Portkey, you can 

docs/extras/integrations/providers/portkey/logging_tracing_portkey.ipynb

@@ -1,19 +1,14 @@
 {
  "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Log, Trace, and Monitor Langchain LLM Calls\n",
+    "# Log, Trace, and Monitor\n",
     "\n",
     "When building apps or agents using Langchain, you end up making multiple API calls to fulfill a single user request. However, these requests are not chained when you want to analyse them. With [**Portkey**](/docs/ecosystem/integrations/portkey), all the embeddings, completion, and other requests from a single user request will get logged and traced to a common ID, enabling you to gain full visibility of user interactions.\n",
     "\n",
-    "This notebook serves as a step-by-step guide on how to integrate and use Portkey in your Langchain app."
+    "This notebook serves as a step-by-step guide on how to log, trace, and monitor Langchain LLM calls using `Portkey` in your Langchain app."
    ]
   },
   {
@@ -234,9 +229,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/providers/spacy.mdx

@@ -18,3 +18,11 @@ See a [usage example](/docs/modules/data_connection/document_transformers/text_s
 ```python
 from langchain.text_splitter import SpacyTextSplitter
 ```
+
+## Text Embedding Models
+
+See a [usage example](/docs/integrations/text_embedding/spacy_embedding)
+
+```python
+from langchain.embeddings.spacy_embeddings import SpacyEmbeddings
+```

docs/extras/integrations/providers/vectara/index.mdx

@@ -11,9 +11,10 @@ What is Vectara?
 - You can use Vectara's integration with LangChain as a Vector store or using the Retriever abstraction.
 
 ## Installation and Setup
-To use Vectara with LangChain no special installation steps are required. You just have to provide your customer_id, corpus ID, and an API key created within the Vectara console to enable indexing and searching.
+To use Vectara with LangChain no special installation steps are required. 
+To get started, follow our [quickstart](https://docs.vectara.com/docs/quickstart) guide to create an account, a corpus and an API key. 
+Once you have these, you can provide them as arguments to the Vectara vectorstore, or you can set them as environment variables.
 
-Alternatively these can be provided as environment variables
 - export `VECTARA_CUSTOMER_ID`="your_customer_id"
 - export `VECTARA_CORPUS_ID`="your_corpus_id"
 - export `VECTARA_API_KEY`="your-vectara-api-key"

docs/extras/integrations/text_embedding/awadb.ipynb

@@ -5,9 +5,11 @@
    "id": "b14a24db",
    "metadata": {},
    "source": [
-    "# AwaEmbedding\n",
+    "# AwaDB\n",
     "\n",
-    "This notebook explains how to use AwaEmbedding, which is included in [awadb](https://github.com/awa-ai/awadb), to embedding texts in langchain."
+    ">[AwaDB](https://github.com/awa-ai/awadb) is an AI Native database for the search and storage of embedding vectors used by LLM Applications.\n",
+    "\n",
+    "This notebook explains how to use `AwaEmbeddings` in LangChain."
    ]
   },
   {
@@ -101,7 +103,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/text_embedding/bedrock.ipynb

@@ -5,7 +5,9 @@
    "id": "75e378f5-55d7-44b6-8e2e-6d7b8b171ec4",
    "metadata": {},
    "source": [
-    "# Bedrock Embeddings"
+    "# Bedrock\n",
+    "\n",
+    ">[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that makes FMs from leading AI startups and Amazon available via an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case.\n"
    ]
   },
   {
@@ -91,7 +93,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/text_embedding/bge_huggingface.ipynb

@@ -5,26 +5,29 @@
    "id": "719619d3",
    "metadata": {},
    "source": [
-    "# BGE Hugging Face Embeddings\n",
+    "# BGE on Hugging Face\n",
     "\n",
-    "This notebook shows how to use BGE Embeddings through Hugging Face"
+    ">[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).\n",
+    ">BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://www.baai.ac.cn/english.html). `BAAI` is a private non-profit organization engaged in AI research and development.\n",
+    "\n",
+    "This notebook shows how to use `BGE Embeddings` through `Hugging Face`"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "id": "f7a54279",
    "metadata": {
     "scrolled": true
    },
    "outputs": [],
    "source": [
-    "# !pip install sentence_transformers"
+    "#!pip install sentence_transformers"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "9e1d5b6b",
    "metadata": {},
    "outputs": [],
@@ -43,12 +46,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "id": "e59d1a89",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "384"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "embedding = hf.embed_query(\"hi this is harrison\")"
+    "embedding = hf.embed_query(\"hi this is harrison\")\n",
+    "len(embedding)"
    ]
   },
   {
@@ -76,7 +91,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/extras/integrations/text_embedding/google_vertex_ai_palm.ipynb

@@ -1,13 +1,14 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Google Cloud Platform Vertex AI PaLM \n",
+    "# Google Vertex AI PaLM \n",
     "\n",
-    "Note: This is seperate from the Google PaLM integration, it exposes [Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) on Google Cloud. \n",
+    ">[Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) is a service on Google Cloud exposing the embedding models. \n",
+    "\n",
+    "Note: This integration is seperate from the Google PaLM integration.\n",
     "\n",
     "By default, Google Cloud [does not use](https://cloud.google.com/vertex-ai/docs/generative-ai/data-governance#foundation_model_development) Customer Data to train its foundation models as part of Google Cloud`s AI/ML Privacy Commitment. More details about how Google processes data can also be found in [Google's Customer Data Processing Addendum (CDPA)](https://cloud.google.com/terms/data-processing-addendum).\n",
     "\n",
@@ -96,7 +97,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/extras/integrations/text_embedding/modelscope_hub.ipynb

@@ -1,12 +1,13 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "# ModelScope\n",
     "\n",
+    ">[ModelScope](https://www.modelscope.cn/home) is big repository of the models and datasets.\n",
+    "\n",
     "Let's load the ModelScope Embedding class."
    ]
   },
@@ -67,16 +68,23 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "chatgpt",
+   "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",
-   "version": "3.9.15"
-  },
-  "orig_nbformat": 4
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/text_embedding/mosaicml.ipynb

@@ -1,15 +1,14 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# MosaicML embeddings\n",
+    "# MosaicML\n",
     "\n",
-    "[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
+    ">[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
     "\n",
-    "This example goes over how to use LangChain to interact with MosaicML Inference for text embedding."
+    "This example goes over how to use LangChain to interact with `MosaicML` Inference for text embedding."
    ]
   },
   {
@@ -94,6 +93,11 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
@@ -103,9 +107,10 @@
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3"
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/text_embedding/nlp_cloud.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# NLP Cloud\n",
     "\n",
-    "NLP Cloud is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. \n",
+    ">[NLP Cloud](https://docs.nlpcloud.com/#introduction) is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. \n",
     "\n",
     "The [embeddings](https://docs.nlpcloud.com/#embeddings) endpoint offers the following model:\n",
     "\n",
@@ -80,7 +80,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.11.2 64-bit",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -94,7 +94,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/extras/integrations/text_embedding/sagemaker-endpoint.ipynb

@@ -5,11 +5,13 @@
    "id": "1f83f273",
    "metadata": {},
    "source": [
-    "# SageMaker Endpoint Embeddings\n",
+    "# SageMaker\n",
     "\n",
-    "Let's load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
+    "Let's load the `SageMaker Endpoints Embeddings` class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
     "\n",
-    "For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). **Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n",
+    "For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). \n",
+    "\n",
+    "**Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n",
     "\n",
     "Change from\n",
     "\n",
@@ -143,7 +145,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/extras/integrations/text_embedding/self-hosted.ipynb

@@ -5,8 +5,8 @@
    "id": "eec4efda",
    "metadata": {},
    "source": [
-    "# Self Hosted Embeddings\n",
-    "Let's load the SelfHostedEmbeddings, SelfHostedHuggingFaceEmbeddings, and SelfHostedHuggingFaceInstructEmbeddings classes."
+    "# Self Hosted\n",
+    "Let's load the `SelfHostedEmbeddings`, `SelfHostedHuggingFaceEmbeddings`, and `SelfHostedHuggingFaceInstructEmbeddings` classes."
    ]
   },
   {
@@ -149,9 +149,7 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "fc1bfd0f",
-   "metadata": {
-    "scrolled": false
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "query_result = embeddings.embed_query(text)"
@@ -182,7 +180,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/extras/integrations/text_embedding/sentence_transformers.ipynb

@@ -1,16 +1,15 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "ed47bb62",
    "metadata": {},
    "source": [
-    "# Sentence Transformers Embeddings\n",
+    "# Sentence Transformers\n",
     "\n",
-    "[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
+    ">[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
     "\n",
-    "SentenceTransformers is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
+    "`SentenceTransformers` is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
    ]
   },
   {
@@ -109,7 +108,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.16"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/extras/integrations/text_embedding/spacy_embedding.ipynb

@@ -1,21 +1,31 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Spacy Embedding\n",
+    "# SpaCy\n",
     "\n",
-    "### Loading the Spacy embedding class to generate and query embeddings"
+    ">[spaCy](https://spacy.io/) is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython.\n",
+    " \n",
+    "\n",
+    "## Installation and Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install spacy"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Import the necessary classes"
+    "Import the necessary classes"
    ]
   },
   {
@@ -28,11 +38,12 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Initialize SpacyEmbeddings.This will load the Spacy model into memory."
+    "## Example\n",
+    "\n",
+    "Initialize SpacyEmbeddings.This will load the Spacy model into memory."
    ]
   },
   {
@@ -45,11 +56,10 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
+    "Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
    ]
   },
   {
@@ -67,11 +77,10 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Generate and print embeddings for the texts . The SpacyEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
+    "Generate and print embeddings for the texts . The SpacyEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
    ]
   },
   {
@@ -86,11 +95,10 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
+    "Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
    ]
   },
   {
@@ -106,11 +114,24 @@
   }
  ],
  "metadata": {
-  "language_info": {
-   "name": "python"
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
   },
-  "orig_nbformat": 4
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/extras/integrations/vectorstores/supabase.ipynb

@@ -28,43 +28,41 @@
     "The following function determines cosine similarity, but you can adjust to your needs.\n",
     "\n",
     "```sql\n",
-    "       -- Enable the pgvector extension to work with embedding vectors\n",
-    "       create extension vector;\n",
+    "-- Enable the pgvector extension to work with embedding vectors\n",
+    "create extension if not exists vector;\n",
     "\n",
-    "       -- Create a table to store your documents\n",
-    "       create table documents (\n",
-    "       id uuid primary key,\n",
-    "       content text, -- corresponds to Document.pageContent\n",
-    "       metadata jsonb, -- corresponds to Document.metadata\n",
-    "       embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed\n",
-    "       );\n",
+    "-- Create a table to store your documents\n",
+    "create table\n",
+    "  documents (\n",
+    "    id uuid primary key,\n",
+    "    content text, -- corresponds to Document.pageContent\n",
+    "    metadata jsonb, -- corresponds to Document.metadata\n",
+    "    embedding vector (1536) -- 1536 works for OpenAI embeddings, change if needed\n",
+    "  );\n",
     "\n",
-    "       CREATE FUNCTION match_documents(query_embedding vector(1536), match_count int)\n",
-    "           RETURNS TABLE(\n",
-    "               id uuid,\n",
-    "               content text,\n",
-    "               metadata jsonb,\n",
-    "               -- we return matched vectors to enable maximal marginal relevance searches\n",
-    "               embedding vector(1536),\n",
-    "               similarity float)\n",
-    "           LANGUAGE plpgsql\n",
-    "           AS $$\n",
-    "           # variable_conflict use_column\n",
-    "       BEGIN\n",
-    "           RETURN query\n",
-    "           SELECT\n",
-    "               id,\n",
-    "               content,\n",
-    "               metadata,\n",
-    "               embedding,\n",
-    "               1 -(documents.embedding <=> query_embedding) AS similarity\n",
-    "           FROM\n",
-    "               documents\n",
-    "           ORDER BY\n",
-    "               documents.embedding <=> query_embedding\n",
-    "           LIMIT match_count;\n",
-    "       END;\n",
-    "       $$;\n",
+    "-- Create a function to search for documents\n",
+    "create function match_documents (\n",
+    "  query_embedding vector (1536),\n",
+    "  filter jsonb default '{}'\n",
+    ") returns table (\n",
+    "  id uuid,\n",
+    "  content text,\n",
+    "  metadata jsonb,\n",
+    "  similarity float\n",
+    ") language plpgsql as $$\n",
+    "#variable_conflict use_column\n",
+    "begin\n",
+    "  return query\n",
+    "  select\n",
+    "    id,\n",
+    "    content,\n",
+    "    metadata,\n",
+    "    1 - (documents.embedding <=> query_embedding) as similarity\n",
+    "  from documents\n",
+    "  where metadata @> filter\n",
+    "  order by documents.embedding <=> query_embedding;\n",
+    "end;\n",
+    "$$;\n",
     "```"
    ]
   },

docs/extras/integrations/vectorstores/vectara.ipynb

@@ -26,7 +26,7 @@
    "source": [
     "# Setup\n",
     "\n",
-    "You will need a Vectara account to use Vectara with LangChain. To get started, use the following steps:\n",
+    "You will need a Vectara account to use Vectara with LangChain. To get started, use the following steps (see our [quickstart](https://docs.vectara.com/docs/quickstart) guide):\n",
     "1. [Sign up](https://console.vectara.com/signup) for a Vectara account if you don't already have one. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
     "2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
     "3. Next you'll need to create API keys to access the corpus. Click on the **\"Authorization\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
@@ -47,7 +47,7 @@
     "os.environ[\"VECTARA_API_KEY\"] = getpass.getpass(\"Vectara API Key:\")\n",
     "```\n",
     "\n",
-    "2. Add them to the Vectara vectorstore constructor:\n",
+    "1. Provide them as arguments when creating the Vectara vectorstore object:\n",
     "\n",
     "```python\n",
     "vectorstore = Vectara(\n",
@@ -65,13 +65,22 @@
    "source": [
     "## Connecting to Vectara from LangChain\n",
     "\n",
-    "To get started, let's ingest the documents using the from_documents() method.\n",
-    "We assume here that you've added your VECTARA_CUSTOMER_ID, VECTARA_CORPUS_ID and query+indexing VECTARA_API_KEY as environment variables."
+    "In this example, we assume that you've created an account and a corpus, and added your VECTARA_CUSTOMER_ID, VECTARA_CORPUS_ID and VECTARA_API_KEY (created with permissions for both indexing and query) as environment variables.\n",
+    "\n",
+    "The corpus has 3 fields defined as metadata for filtering:\n",
+    "* url: a string field containing the source URL of the document (where relevant)\n",
+    "* speech: a string field containing the name of the speech\n",
+    "* author: the name of the author\n",
+    "\n",
+    "Let's start by ingesting 3 documents into the corpus:\n",
+    "1. The State of the Union speech from 2022, available in the LangChain repository as a text file\n",
+    "2. The \"I have a dream\" speech by Dr. Kind\n",
+    "3. The \"We shall Fight on the Beaches\" speech by Winston Churchil"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "04a1f1a0",
    "metadata": {},
    "outputs": [],
@@ -79,12 +88,17 @@
     "from langchain.embeddings import FakeEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.vectorstores import Vectara\n",
-    "from langchain.document_loaders import TextLoader"
+    "from langchain.document_loaders import TextLoader\n",
+    "\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain.chains.query_constructor.base import AttributeInfo"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "be0a4973",
    "metadata": {},
    "outputs": [],
@@ -97,7 +111,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "8429667e",
    "metadata": {
     "ExecuteTime": {
@@ -111,7 +125,7 @@
     "vectara = Vectara.from_documents(\n",
     "    docs,\n",
     "    embedding=FakeEmbeddings(size=768),\n",
-    "    doc_metadata={\"speech\": \"state-of-the-union\"},\n",
+    "    doc_metadata={\"speech\": \"state-of-the-union\", \"author\": \"Biden\"},\n",
     ")"
    ]
   },
@@ -130,7 +144,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "85ef3468",
    "metadata": {},
    "outputs": [],
@@ -142,14 +156,16 @@
     "    [\n",
     "        \"https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf\",\n",
     "        \"I-have-a-dream\",\n",
+    "        \"Dr. King\"\n",
     "    ],\n",
     "    [\n",
     "        \"https://www.parkwayschools.net/cms/lib/MO01931486/Centricity/Domain/1578/Churchill_Beaches_Speech.pdf\",\n",
     "        \"we shall fight on the beaches\",\n",
+    "        \"Churchil\"\n",
     "    ],\n",
     "]\n",
     "files_list = []\n",
-    "for url, _ in urls:\n",
+    "for url, _, _ in urls:\n",
     "    name = tempfile.NamedTemporaryFile().name\n",
     "    urllib.request.urlretrieve(url, name)\n",
     "    files_list.append(name)\n",
@@ -157,7 +173,7 @@
     "docsearch: Vectara = Vectara.from_files(\n",
     "    files=files_list,\n",
     "    embedding=FakeEmbeddings(size=768),\n",
-    "    metadatas=[{\"url\": url, \"speech\": title} for url, title in urls],\n",
+    "    metadatas=[{\"url\": url, \"speech\": title, \"author\": author} for url, title, author in urls],\n",
     ")"
    ]
   },
@@ -178,7 +194,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "a8c513ab",
    "metadata": {
     "ExecuteTime": {
@@ -197,7 +213,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "fc516993",
    "metadata": {
     "ExecuteTime": {
@@ -231,7 +247,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "8804a21d",
    "metadata": {
     "ExecuteTime": {
@@ -249,7 +265,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "756a6887",
    "metadata": {
     "ExecuteTime": {
@@ -264,7 +280,7 @@
      "text": [
       "Justice Breyer, thank you for your service. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 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. A former top litigator in private practice.\n",
       "\n",
-      "Score: 0.786569\n"
+      "Score: 0.8299499\n"
      ]
     }
    ],
@@ -284,7 +300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "47784de5",
    "metadata": {},
    "outputs": [
@@ -307,7 +323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "3e22949f",
    "metadata": {},
    "outputs": [
@@ -315,7 +331,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "With this threshold of 0.2 we have 3 documents\n"
+      "With this threshold of 0.2 we have 5 documents\n"
      ]
     }
    ],
@@ -340,7 +356,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 12,
    "id": "9427195f",
    "metadata": {
     "ExecuteTime": {
@@ -352,10 +368,10 @@
     {
      "data": {
       "text/plain": [
-       "VectaraRetriever(tags=['Vectara'], metadata=None, vectorstore=<langchain.vectorstores.vectara.Vectara object at 0x1586bd330>, search_type='similarity', search_kwargs={'lambda_val': 0.025, 'k': 5, 'filter': '', 'n_sentence_context': '2'})"
+       "VectaraRetriever(tags=['Vectara'], metadata=None, vectorstore=<langchain.vectorstores.vectara.Vectara object at 0x13b15e9b0>, search_type='similarity', search_kwargs={'lambda_val': 0.025, 'k': 5, 'filter': '', 'n_sentence_context': '2'})"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -367,7 +383,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 13,
    "id": "f3c70c31",
    "metadata": {
     "ExecuteTime": {
@@ -379,10 +395,10 @@
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Justice Breyer, thank you for your service. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 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. A former top litigator in private practice.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '596', 'len': '97', 'speech': 'state-of-the-union'})"
+       "Document(page_content='Justice Breyer, thank you for your service. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 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. A former top litigator in private practice.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '596', 'len': '97', 'speech': 'state-of-the-union', 'author': 'Biden'})"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -392,10 +408,118 @@
     "retriever.get_relevant_documents(query)[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "e944c26a",
+   "metadata": {},
+   "source": [
+    "## Using Vectara as a SelfQuery Retriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "8be674de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metadata_field_info = [\n",
+    "    AttributeInfo(\n",
+    "        name=\"speech\",\n",
+    "        description=\"what name of the speech\",\n",
+    "        type=\"string or list[string]\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"author\",\n",
+    "        description=\"author of the speech\",\n",
+    "        type=\"string or list[string]\",\n",
+    "    ),\n",
+    "]\n",
+    "document_content_description = \"the text of the speech\"\n",
+    "\n",
+    "vectordb = Vectara()\n",
+    "llm = OpenAI(temperature=0)\n",
+    "retriever = SelfQueryRetriever.from_llm(llm, vectara, \n",
+    "                                        document_content_description, metadata_field_info, \n",
+    "                                        verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "f8938999",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/ofer/dev/langchain/libs/langchain/langchain/chains/llm.py:278: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query='freedom' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='author', value='Biden') limit=None\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Well I know this nation. We will meet the test. To protect freedom and liberty, to expand fairness and opportunity. We will save democracy. As hard as these times have been, I am more optimistic about America today than I have been my whole life.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '346', 'len': '67', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
+       " Document(page_content='To our fellow Ukrainian Americans who forge a deep bond that connects our two nations we stand with you. Putin may circle Kyiv with tanks, but he will never gain the hearts and souls of the Ukrainian people. He will never extinguish their love of freedom. He will never weaken the resolve of the free world. We meet tonight in an America that has lived through two of the hardest years this nation has ever faced.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '740', 'len': '47', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
+       " Document(page_content='But most importantly as Americans. With a duty to one another to the American people to the Constitution. And with an unwavering resolve that freedom will always triumph over tyranny. Six 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.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '413', 'len': '77', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
+       " Document(page_content='We can do this. \\n\\nMy fellow Americans—tonight , we have gathered in a sacred space—the citadel of our democracy. In this Capitol, generation after generation, Americans have debated great questions amid great strife, and have done great things. We have fought for freedom, expanded liberty, defeated totalitarianism and terror. And built the strongest, freest, and most prosperous nation the world has ever known. Now is the hour. \\n\\nOur moment of responsibility.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '906', 'len': '82', 'speech': 'state-of-the-union', 'author': 'Biden'}),\n",
+       " Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. We cannot let this happen. 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.', metadata={'source': 'langchain', 'lang': 'eng', 'offset': '0', 'len': '63', 'speech': 'state-of-the-union', 'author': 'Biden'})]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.get_relevant_documents(\"what did Biden say about the freedom?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "a97037fb",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query='freedom' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='author', value='Dr. King') limit=None\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='And if America is to be a great nation, this must become true. So\\nlet freedom ring from the prodigious hilltops of New Hampshire. Let freedom ring from the mighty\\nmountains of New York. Let freedom ring from the heightening Alleghenies of Pennsylvania. Let\\nfreedom ring from the snowcapped Rockies of Colorado.', metadata={'lang': 'eng', 'section': '3', 'offset': '1534', 'len': '55', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
+       " Document(page_content='And if America is to be a great nation, this must become true. So\\nlet freedom ring from the prodigious hilltops of New Hampshire. Let freedom ring from the mighty\\nmountains of New York. Let freedom ring from the heightening Alleghenies of Pennsylvania. Let\\nfreedom ring from the snowcapped Rockies of Colorado.', metadata={'lang': 'eng', 'section': '3', 'offset': '1534', 'len': '55', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
+       " Document(page_content='Let freedom ring from the curvaceous slopes of\\nCalifornia. But not only that. Let freedom ring from Stone Mountain of Georgia. Let freedom ring from Lookout\\nMountain of Tennessee. Let freedom ring from every hill and molehill of Mississippi, from every\\nmountain side. Let freedom ring . . .\\nWhen we allow freedom to ring—when we let it ring from every city and every hamlet, from every state\\nand every city, we will be able to speed up that day when all of God’s children, black men and white\\nmen, Jews and Gentiles, Protestants and Catholics, will be able to join hands and sing in the words of the\\nold Negro spiritual, “Free at last, Free at last, Great God a-mighty, We are free at last.”', metadata={'lang': 'eng', 'section': '3', 'offset': '1842', 'len': '52', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
+       " Document(page_content='Let freedom ring from the curvaceous slopes of\\nCalifornia. But not only that. Let freedom ring from Stone Mountain of Georgia. Let freedom ring from Lookout\\nMountain of Tennessee. Let freedom ring from every hill and molehill of Mississippi, from every\\nmountain side. Let freedom ring . . .\\nWhen we allow freedom to ring—when we let it ring from every city and every hamlet, from every state\\nand every city, we will be able to speed up that day when all of God’s children, black men and white\\nmen, Jews and Gentiles, Protestants and Catholics, will be able to join hands and sing in the words of the\\nold Negro spiritual, “Free at last, Free at last, Great God a-mighty, We are free at last.”', metadata={'lang': 'eng', 'section': '3', 'offset': '1842', 'len': '52', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'}),\n",
+       " Document(page_content='Let freedom ring from the mighty\\nmountains of New York. Let freedom ring from the heightening Alleghenies of Pennsylvania. Let\\nfreedom ring from the snowcapped Rockies of Colorado. Let freedom ring from the curvaceous slopes of\\nCalifornia. But not only that. Let freedom ring from Stone Mountain of Georgia.', metadata={'lang': 'eng', 'section': '3', 'offset': '1657', 'len': '57', 'CreationDate': '1424880481', 'Producer': 'Adobe PDF Library 10.0', 'Author': 'Sasha Rolon-Pereira', 'Title': 'Martin Luther King Jr.pdf', 'Creator': 'Acrobat PDFMaker 10.1 for Word', 'ModDate': '1424880524', 'url': 'https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'speech': 'I-have-a-dream', 'author': 'Dr. King', 'title': 'Martin Luther King Jr.pdf'})]"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.get_relevant_documents(\"what did Dr. King say about the freedom?\")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2300e785",
+   "id": "f6d17e90",
    "metadata": {},
    "outputs": [],
    "source": []

docs/extras/modules/data_connection/retrievers/self_query/supabase_self_query.ipynb

@@ -0,0 +1,587 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "13afcae7",
+      "metadata": {},
+      "source": [
+        "# Supabase Vector self-querying \n",
+        "\n",
+        ">[Supabase](https://supabase.com/docs) is an open source `Firebase` alternative. \n",
+        "> `Supabase` is built on top of `PostgreSQL`, which offers strong `SQL` \n",
+        "> querying capabilities and enables a simple interface with already-existing tools and frameworks.\n",
+        "\n",
+        ">[PostgreSQL](https://en.wikipedia.org/wiki/PostgreSQL) also known as `Postgres`,\n",
+        "> is a free and open-source relational database management system (RDBMS) \n",
+        "> emphasizing extensibility and `SQL` compliance.\n",
+        "\n",
+        "In the notebook we'll demo the `SelfQueryRetriever` wrapped around a Supabase vector store.\n",
+        "\n",
+        "Specifically we will:\n",
+        "1. Create a Supabase database\n",
+        "2. Enable the `pgvector` extension\n",
+        "3. Create a `documents` table and `match_documents` function that will be used by `SupabaseVectorStore`\n",
+        "4. Load sample documents into the vector store (database table)\n",
+        "5. Build and test a self-querying retriever"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "347935ad",
+      "metadata": {},
+      "source": [
+        "## Setup Supabase Database\n",
+        "\n",
+        "1. Head over to https://database.new to provision your Supabase database.\n",
+        "2. In the studio, jump to the [SQL editor](https://supabase.com/dashboard/project/_/sql/new) and run the following script to enable `pgvector` and setup your database as a vector store:\n",
+        "    ```sql\n",
+        "    -- Enable the pgvector extension to work with embedding vectors\n",
+        "    create extension if not exists vector;\n",
+        "\n",
+        "    -- Create a table to store your documents\n",
+        "    create table\n",
+        "      documents (\n",
+        "        id uuid primary key,\n",
+        "        content text, -- corresponds to Document.pageContent\n",
+        "        metadata jsonb, -- corresponds to Document.metadata\n",
+        "        embedding vector (1536) -- 1536 works for OpenAI embeddings, change if needed\n",
+        "      );\n",
+        "\n",
+        "    -- Create a function to search for documents\n",
+        "    create function match_documents (\n",
+        "      query_embedding vector (1536),\n",
+        "      filter jsonb default '{}'\n",
+        "    ) returns table (\n",
+        "      id uuid,\n",
+        "      content text,\n",
+        "      metadata jsonb,\n",
+        "      similarity float\n",
+        "    ) language plpgsql as $$\n",
+        "    #variable_conflict use_column\n",
+        "    begin\n",
+        "      return query\n",
+        "      select\n",
+        "        id,\n",
+        "        content,\n",
+        "        metadata,\n",
+        "        1 - (documents.embedding <=> query_embedding) as similarity\n",
+        "      from documents\n",
+        "      where metadata @> filter\n",
+        "      order by documents.embedding <=> query_embedding;\n",
+        "    end;\n",
+        "    $$;\n",
+        "    ```"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "68e75fb9",
+      "metadata": {},
+      "source": [
+        "## Creating a Supabase vector store\n",
+        "Next we'll want to create a Supabase vector store and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
+        "\n",
+        "Be sure to install the latest version of `langchain`:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "78546fd7",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install langchain"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e06df198",
+      "metadata": {},
+      "source": [
+        "The self-query retriever requires you to have `lark` installed:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "63a8af5b",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "%pip install lark"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "114f768f",
+      "metadata": {},
+      "source": [
+        "We also need the `openai` and `supabase` packages:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "434ae558",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install openai"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "22431060-52c4-48a7-a97b-9f542b8b0928",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "%pip install supabase==1.0.0"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
+      "metadata": {},
+      "source": [
+        "Since we are using `SupabaseVectorStore` and `OpenAIEmbeddings`, we have to load their API keys.\n",
+        "\n",
+        "- To find your `SUPABASE_URL` and `SUPABASE_SERVICE_KEY`, head to your Supabase project's [API settings](https://supabase.com/dashboard/project/_/settings/api).\n",
+        "  - `SUPABASE_URL` corresponds to the Project URL\n",
+        "  - `SUPABASE_SERVICE_KEY` corresponds to the `service_role` API key\n",
+        "\n",
+        "- To get your `OPENAI_API_KEY`, navigate to [API keys](https://platform.openai.com/account/api-keys) on your OpenAI account and create a new secret key."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import getpass\n",
+        "\n",
+        "os.environ[\"SUPABASE_URL\"] = getpass.getpass(\"Supabase URL:\")\n",
+        "os.environ[\"SUPABASE_SERVICE_KEY\"] = getpass.getpass(\"Supabase Service Key:\")\n",
+        "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "3aaf5075",
+      "metadata": {},
+      "source": [
+        "_Optional:_ If you're storing your Supabase and OpenAI API keys in a `.env` file, you can load them with [`dotenv`](https://github.com/theskumar/python-dotenv)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "e0089221",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "%pip install python-dotenv"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "3d56c5ef",
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "from dotenv import load_dotenv\n",
+        "\n",
+        "load_dotenv()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f6dd9aef",
+      "metadata": {},
+      "source": [
+        "First we'll create a Supabase client and instantiate a OpenAI embeddings class."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "cb4a5787",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from supabase.client import Client, create_client\n",
+        "from langchain.schema import Document\n",
+        "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+        "from langchain.vectorstores import SupabaseVectorStore\n",
+        "\n",
+        "supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
+        "supabase_key = os.environ.get(\"SUPABASE_SERVICE_KEY\")\n",
+        "supabase: Client = create_client(supabase_url, supabase_key)\n",
+        "\n",
+        "embeddings = OpenAIEmbeddings()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "0fca9b0b",
+      "metadata": {},
+      "source": [
+        "Next let's create our documents."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "id": "bcbe04d9",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "docs = [\n",
+        "    Document(\n",
+        "        page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
+        "        metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n",
+        "    ),\n",
+        "    Document(\n",
+        "        page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
+        "        metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n",
+        "    ),\n",
+        "    Document(\n",
+        "        page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
+        "        metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
+        "    ),\n",
+        "    Document(\n",
+        "        page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
+        "        metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
+        "    ),\n",
+        "    Document(\n",
+        "        page_content=\"Toys come alive and have a blast doing so\",\n",
+        "        metadata={\"year\": 1995, \"genre\": \"animated\"},\n",
+        "    ),\n",
+        "    Document(\n",
+        "        page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
+        "        metadata={\n",
+        "            \"year\": 1979,\n",
+        "            \"rating\": 9.9,\n",
+        "            \"director\": \"Andrei Tarkovsky\",\n",
+        "            \"genre\": \"science fiction\",\n",
+        "            \"rating\": 9.9,\n",
+        "        },\n",
+        "    ),\n",
+        "]\n",
+        "\n",
+        "vectorstore = SupabaseVectorStore.from_documents(docs, embeddings, client=supabase, table_name=\"documents\", query_name=\"match_documents\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "5ecaab6d",
+      "metadata": {},
+      "source": [
+        "## Creating our self-querying retriever\n",
+        "Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "86e34dbf",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "from langchain.llms import OpenAI\n",
+        "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+        "from langchain.chains.query_constructor.base import AttributeInfo\n",
+        "\n",
+        "metadata_field_info = [\n",
+        "    AttributeInfo(\n",
+        "        name=\"genre\",\n",
+        "        description=\"The genre of the movie\",\n",
+        "        type=\"string or list[string]\",\n",
+        "    ),\n",
+        "    AttributeInfo(\n",
+        "        name=\"year\",\n",
+        "        description=\"The year the movie was released\",\n",
+        "        type=\"integer\",\n",
+        "    ),\n",
+        "    AttributeInfo(\n",
+        "        name=\"director\",\n",
+        "        description=\"The name of the movie director\",\n",
+        "        type=\"string\",\n",
+        "    ),\n",
+        "    AttributeInfo(\n",
+        "        name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
+        "    ),\n",
+        "]\n",
+        "document_content_description = \"Brief summary of a movie\"\n",
+        "llm = OpenAI(temperature=0)\n",
+        "retriever = SelfQueryRetriever.from_llm(\n",
+        "    llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ea9df8d4",
+      "metadata": {},
+      "source": [
+        "## Testing it out\n",
+        "And now we can try actually using our retriever!"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "38a126e9",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "query='dinosaur' filter=None limit=None\n"
+          ]
+        },
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),\n",
+              " Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),\n",
+              " Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
+              " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]"
+            ]
+          },
+          "execution_count": 5,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# This example only specifies a relevant query\n",
+        "retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "fc3f1e6e",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None\n"
+          ]
+        },
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
+              " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]"
+            ]
+          },
+          "execution_count": 7,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# This example only specifies a filter\n",
+        "retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "b19d4da0",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None\n"
+          ]
+        },
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'year': 2019, 'rating': 8.3, 'director': 'Greta Gerwig'})]"
+            ]
+          },
+          "execution_count": 9,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# This example specifies a query and a filter\n",
+        "retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women?\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "f900e40e",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None\n"
+          ]
+        },
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'})]"
+            ]
+          },
+          "execution_count": 8,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# This example specifies a composite filter\n",
+        "retriever.get_relevant_documents(\n",
+        "    \"What's a highly rated (above 8.5) science fiction film?\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "12a51522",
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LTE: 'lte'>, attribute='year', value=2005), Comparison(comparator=<Comparator.LIKE: 'like'>, attribute='genre', value='animated')]) limit=None\n"
+          ]
+        },
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
+            ]
+          },
+          "execution_count": 9,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# This example specifies a query and composite filter\n",
+        "retriever.get_relevant_documents(\n",
+        "    \"What's a movie after 1990 but before (or on) 2005 that's all about toys, and preferably is animated\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
+      "metadata": {},
+      "source": [
+        "## Filter k\n",
+        "\n",
+        "We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
+        "\n",
+        "We can do this by passing `enable_limit=True` to the constructor."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "id": "bff36b88-b506-4877-9c63-e5a1a8d78e64",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "retriever = SelfQueryRetriever.from_llm(\n",
+        "    llm,\n",
+        "    vectorstore,\n",
+        "    document_content_description,\n",
+        "    metadata_field_info,\n",
+        "    enable_limit=True,\n",
+        "    verbose=True,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "id": "2758d229-4f97-499c-819f-888acaf8ee10",
+      "metadata": {
+        "tags": []
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "query='dinosaur' filter=None limit=2\n"
+          ]
+        },
+        {
+          "data": {
+            "text/plain": [
+              "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),\n",
+              " Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
+            ]
+          },
+          "execution_count": 11,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "# This example only specifies a relevant query\n",
+        "retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
+      ]
+    }
+  ],
+  "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": "3.10.12"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}

docs/extras/modules/data_connection/retrievers/self_query/vectara_self_query.ipynb

@@ -0,0 +1,440 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "13afcae7",
+   "metadata": {},
+   "source": [
+    "# Vectara self-querying \n",
+    "\n",
+    ">[Vectara](https://docs.vectara.com/docs/) is a GenAI platform for developers. It provides a simple API to build Grounded Generation (aka Retrieval-augmented-generation) applications.\n",
+    "\n",
+    "In the notebook we'll demo the `SelfQueryRetriever` wrapped around a Vectara vector store. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68e75fb9",
+   "metadata": {},
+   "source": [
+    "# Setup\n",
+    "\n",
+    "You will need a Vectara account to use Vectara with LangChain. To get started, use the following steps (see our [quickstart](https://docs.vectara.com/docs/quickstart) guide):\n",
+    "1. [Sign up](https://console.vectara.com/signup) for a Vectara account if you don't already have one. Once you have completed your sign up you will have a Vectara customer ID. You can find your customer ID by clicking on your name, on the top-right of the Vectara console window.\n",
+    "2. Within your account you can create one or more corpora. Each corpus represents an area that stores text data upon ingest from input documents. To create a corpus, use the **\"Create Corpus\"** button. You then provide a name to your corpus as well as a description. Optionally you can define filtering attributes and apply some advanced options. If you click on your created corpus, you can see its name and corpus ID right on the top.\n",
+    "3. Next you'll need to create API keys to access the corpus. Click on the **\"Authorization\"** tab in the corpus view and then the **\"Create API Key\"** button. Give your key a name, and choose whether you want query only or query+index for your key. Click \"Create\" and you now have an active API key. Keep this key confidential. \n",
+    "\n",
+    "To use LangChain with Vectara, you'll need to have these three values: customer ID, corpus ID and api_key.\n",
+    "You can provide those to LangChain in two ways:\n",
+    "\n",
+    "1. Include in your environment these three variables: `VECTARA_CUSTOMER_ID`, `VECTARA_CORPUS_ID` and `VECTARA_API_KEY`.\n",
+    "\n",
+    "> For example, you can set these variables using os.environ and getpass as follows:\n",
+    "\n",
+    "```python\n",
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "os.environ[\"VECTARA_CUSTOMER_ID\"] = getpass.getpass(\"Vectara Customer ID:\")\n",
+    "os.environ[\"VECTARA_CORPUS_ID\"] = getpass.getpass(\"Vectara Corpus ID:\")\n",
+    "os.environ[\"VECTARA_API_KEY\"] = getpass.getpass(\"Vectara API Key:\")\n",
+    "```\n",
+    "\n",
+    "1. Provide them as arguments when creating the Vectara vectorstore object:\n",
+    "\n",
+    "```python\n",
+    "vectorstore = Vectara(\n",
+    "                vectara_customer_id=vectara_customer_id,\n",
+    "                vectara_corpus_id=vectara_corpus_id,\n",
+    "                vectara_api_key=vectara_api_key\n",
+    "            )\n",
+    "```\n",
+    "\n",
+    "**Note:** The self-query retriever requires you to have `lark` installed (`pip install lark`). "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "742ac16d",
+   "metadata": {},
+   "source": [
+    "## Connecting to Vectara from LangChain\n",
+    "\n",
+    "In this example, we assume that you've created an account and a corpus, and added your VECTARA_CUSTOMER_ID, VECTARA_CORPUS_ID and VECTARA_API_KEY (created with permissions for both indexing and query) as environment variables.\n",
+    "\n",
+    "The corpus has 4 fields defined as metadata for filtering: year, director, rating, and genre\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "cb4a5787",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import FakeEmbeddings\n",
+    "from langchain.schema import Document\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores import Vectara\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain.chains.query_constructor.base import AttributeInfo\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "bcbe04d9",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
+    "        metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
+    "        metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
+    "        metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
+    "        metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Toys come alive and have a blast doing so\",\n",
+    "        metadata={\"year\": 1995, \"genre\": \"animated\"},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
+    "        metadata={\n",
+    "            \"year\": 1979,\n",
+    "            \"rating\": 9.9,\n",
+    "            \"director\": \"Andrei Tarkovsky\",\n",
+    "            \"genre\": \"science fiction\",\n",
+    "        },\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "vectara = Vectara()\n",
+    "for doc in docs:\n",
+    "    vectara.add_texts([doc.page_content], embedding=FakeEmbeddings(size=768), doc_metadata=doc.metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5ecaab6d",
+   "metadata": {},
+   "source": [
+    "## Creating our self-querying retriever\n",
+    "Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "86e34dbf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain.chains.query_constructor.base import AttributeInfo\n",
+    "\n",
+    "metadata_field_info = [\n",
+    "    AttributeInfo(\n",
+    "        name=\"genre\",\n",
+    "        description=\"The genre of the movie\",\n",
+    "        type=\"string or list[string]\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"year\",\n",
+    "        description=\"The year the movie was released\",\n",
+    "        type=\"integer\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"director\",\n",
+    "        description=\"The name of the movie director\",\n",
+    "        type=\"string\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
+    "    ),\n",
+    "]\n",
+    "document_content_description = \"Brief summary of a movie\"\n",
+    "llm = OpenAI(temperature=0)\n",
+    "retriever = SelfQueryRetriever.from_llm(\n",
+    "    llm, vectara, document_content_description, metadata_field_info, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ea9df8d4",
+   "metadata": {},
+   "source": [
+    "## Testing it out\n",
+    "And now we can try actually using our retriever!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "38a126e9",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/ofer/dev/langchain/libs/langchain/langchain/chains/llm.py:278: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query='dinosaur' filter=None limit=None\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'lang': 'eng', 'offset': '0', 'len': '66', 'year': '1993', 'rating': '7.7', 'genre': 'science fiction', 'source': 'langchain'}),\n",
+       " Document(page_content='Toys come alive and have a blast doing so', metadata={'lang': 'eng', 'offset': '0', 'len': '41', 'year': '1995', 'genre': 'animated', 'source': 'langchain'}),\n",
+       " Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'lang': 'eng', 'offset': '0', 'len': '60', 'year': '1979', 'rating': '9.9', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'source': 'langchain'}),\n",
+       " Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'lang': 'eng', 'offset': '0', 'len': '76', 'year': '2010', 'director': 'Christopher Nolan', 'rating': '8.2', 'source': 'langchain'}),\n",
+       " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'lang': 'eng', 'offset': '0', 'len': '116', 'year': '2006', 'director': 'Satoshi Kon', 'rating': '8.6', 'source': 'langchain'})]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example only specifies a relevant query\n",
+    "retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fc3f1e6e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'lang': 'eng', 'offset': '0', 'len': '60', 'year': '1979', 'rating': '9.9', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'source': 'langchain'}),\n",
+       " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'lang': 'eng', 'offset': '0', 'len': '116', 'year': '2006', 'director': 'Satoshi Kon', 'rating': '8.6', 'source': 'langchain'})]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example only specifies a filter\n",
+    "retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b19d4da0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'lang': 'eng', 'offset': '0', 'len': '82', 'year': '2019', 'director': 'Greta Gerwig', 'rating': '8.3', 'source': 'langchain'})]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example specifies a query and a filter\n",
+    "retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "f900e40e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'lang': 'eng', 'offset': '0', 'len': '60', 'year': '1979', 'rating': '9.9', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'source': 'langchain'})]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example specifies a composite filter\n",
+    "retriever.get_relevant_documents(\n",
+    "    \"What's a highly rated (above 8.5) science fiction film?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "12a51522",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')]) limit=None\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Toys come alive and have a blast doing so', metadata={'lang': 'eng', 'offset': '0', 'len': '41', 'year': '1995', 'genre': 'animated', 'source': 'langchain'})]"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example specifies a query and composite filter\n",
+    "retriever.get_relevant_documents(\n",
+    "    \"What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
+   "metadata": {},
+   "source": [
+    "## Filter k\n",
+    "\n",
+    "We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
+    "\n",
+    "We can do this by passing `enable_limit=True` to the constructor."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "bff36b88-b506-4877-9c63-e5a1a8d78e64",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "retriever = SelfQueryRetriever.from_llm(\n",
+    "    llm,\n",
+    "    vectara,\n",
+    "    document_content_description,\n",
+    "    metadata_field_info,\n",
+    "    enable_limit=True,\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "2758d229-4f97-499c-819f-888acaf8ee10",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "query='dinosaur' filter=None limit=2\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'lang': 'eng', 'offset': '0', 'len': '66', 'year': '1993', 'rating': '7.7', 'genre': 'science fiction', 'source': 'langchain'}),\n",
+       " Document(page_content='Toys come alive and have a blast doing so', metadata={'lang': 'eng', 'offset': '0', 'len': '41', 'year': '1995', 'genre': 'animated', 'source': 'langchain'})]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# This example only specifies a relevant query\n",
+    "retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
+   ]
+  }
+ ],
+ "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/use_cases/more/graph/diffbot_graphtransformer.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Diffbot Graph Transformer\n",
     "\n",
-    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/more/graph/diffbot_transformer.ipynb)\n",
+    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/more/graph/diffbot_graphtransformer.ipynb)\n",
     "\n",
     "## Use case\n",
     "\n",
@@ -77,7 +77,7 @@
    "id": "5e3b894a-e3ee-46c7-8116-f8377f8f0159",
    "metadata": {},
    "source": [
-    "This code fetches Wikipedia articles about \"Baldur's Gate 3\" and then uses `DiffbotGraphTransformer` to extract entities and relationships.\n",
+    "This code fetches Wikipedia articles about \"Warren Buffett\" and then uses `DiffbotGraphTransformer` to extract entities and relationships.\n",
     "The `DiffbotGraphTransformer` outputs a structured data `GraphDocument`, which can be used to populate a graph database.\n",
     "Note that text chunking is avoided due to Diffbot's [character limit per API request](https://docs.diffbot.com/reference/introduction-to-natural-language-api)."
    ]

libs/experimental/langchain_experimental/data_anonymizer/base.py

@@ -1,4 +1,5 @@
 from abc import ABC, abstractmethod
+from typing import Optional
 
 
 class AnonymizerBase(ABC):
@@ -8,12 +9,12 @@ class AnonymizerBase(ABC):
         wrapping the behavior for all methods in a base class.
     """
 
-    def anonymize(self, text: str) -> str:
+    def anonymize(self, text: str, language: Optional[str] = None) -> str:
         """Anonymize text"""
-        return self._anonymize(text)
+        return self._anonymize(text, language)
 
     @abstractmethod
-    def _anonymize(self, text: str) -> str:
+    def _anonymize(self, text: str, language: Optional[str]) -> str:
         """Abstract method to anonymize text"""
 
 

libs/experimental/langchain_experimental/data_anonymizer/faker_presidio_mapping.py

@@ -27,8 +27,8 @@ def get_pseudoanonymizer_mapping(seed: Optional[int] = None) -> Dict[str, Callab
             fake.random_choices(string.ascii_lowercase + string.digits, length=26)
         ),
         "IP_ADDRESS": lambda _: fake.ipv4_public(),
-        "LOCATION": lambda _: fake.address(),
-        "DATE_TIME": lambda _: fake.iso8601(),
+        "LOCATION": lambda _: fake.city(),
+        "DATE_TIME": lambda _: fake.date(),
         "NRP": lambda _: str(fake.random_number(digits=8, fix_len=True)),
         "MEDICAL_LICENSE": lambda _: fake.bothify(text="??######").upper(),
         "URL": lambda _: fake.url(),

libs/experimental/langchain_experimental/data_anonymizer/presidio.py

@@ -24,6 +24,8 @@ from langchain_experimental.data_anonymizer.faker_presidio_mapping import (
 
 try:
     from presidio_analyzer import AnalyzerEngine
+    from presidio_analyzer.nlp_engine import NlpEngineProvider
+
 except ImportError as e:
     raise ImportError(
         "Could not import presidio_analyzer, please install with "
@@ -44,12 +46,29 @@ if TYPE_CHECKING:
     from presidio_analyzer import EntityRecognizer, RecognizerResult
     from presidio_anonymizer.entities import EngineResult
 
+# Configuring Anonymizer for multiple languages
+# Detailed description and examples can be found here:
+# langchain/docs/extras/guides/privacy/multi_language_anonymization.ipynb
+DEFAULT_LANGUAGES_CONFIG = {
+    # You can also use Stanza or transformers library.
+    # See https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/
+    "nlp_engine_name": "spacy",
+    "models": [
+        {"lang_code": "en", "model_name": "en_core_web_lg"},
+        # {"lang_code": "de", "model_name": "de_core_news_md"},
+        # {"lang_code": "es", "model_name": "es_core_news_md"},
+        # ...
+        # List of available models: https://spacy.io/usage/models
+    ],
+}
+
 
 class PresidioAnonymizerBase(AnonymizerBase):
     def __init__(
         self,
         analyzed_fields: Optional[List[str]] = None,
         operators: Optional[Dict[str, OperatorConfig]] = None,
+        languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
         faker_seed: Optional[int] = None,
     ):
         """
@@ -60,6 +79,11 @@ class PresidioAnonymizerBase(AnonymizerBase):
                 Operators allow for custom anonymization of detected PII.
                 Learn more:
                 https://microsoft.github.io/presidio/tutorial/10_simple_anonymization/
+            languages_config: Configuration for the NLP engine.
+                First language in the list will be used as the main language
+                in self.anonymize(...) when no language is specified.
+                Learn more:
+                https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/
             faker_seed: Seed used to initialize faker.
                 Defaults to None, in which case faker will be seeded randomly
                 and provide random values.
@@ -81,7 +105,15 @@ class PresidioAnonymizerBase(AnonymizerBase):
                 ).items()
             }
         )
-        self._analyzer = AnalyzerEngine()
+
+        provider = NlpEngineProvider(nlp_configuration=languages_config)
+        nlp_engine = provider.create_engine()
+
+        self.supported_languages = list(nlp_engine.nlp.keys())
+
+        self._analyzer = AnalyzerEngine(
+            supported_languages=self.supported_languages, nlp_engine=nlp_engine
+        )
         self._anonymizer = AnonymizerEngine()
 
     def add_recognizer(self, recognizer: EntityRecognizer) -> None:
@@ -103,18 +135,31 @@ class PresidioAnonymizerBase(AnonymizerBase):
 
 
 class PresidioAnonymizer(PresidioAnonymizerBase):
-    def _anonymize(self, text: str) -> str:
+    def _anonymize(self, text: str, language: Optional[str] = None) -> str:
         """Anonymize text.
         Each PII entity is replaced with a fake value.
         Each time fake values will be different, as they are generated randomly.
 
         Args:
             text: text to anonymize
+            language: language to use for analysis of PII
+                If None, the first (main) language in the list
+                of languages specified in the configuration will be used.
         """
+        if language is None:
+            language = self.supported_languages[0]
+
+        if language not in self.supported_languages:
+            raise ValueError(
+                f"Language '{language}' is not supported. "
+                f"Supported languages are: {self.supported_languages}. "
+                "Change your language configuration file to add more languages."
+            )
+
         results = self._analyzer.analyze(
             text,
             entities=self.analyzed_fields,
-            language="en",
+            language=language,
         )
 
         return self._anonymizer.anonymize(
@@ -129,9 +174,10 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
         self,
         analyzed_fields: Optional[List[str]] = None,
         operators: Optional[Dict[str, OperatorConfig]] = None,
+        languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
         faker_seed: Optional[int] = None,
     ):
-        super().__init__(analyzed_fields, operators, faker_seed)
+        super().__init__(analyzed_fields, operators, languages_config, faker_seed)
         self._deanonymizer_mapping = DeanonymizerMapping()
 
     @property
@@ -191,7 +237,7 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
 
         self._deanonymizer_mapping.update(new_deanonymizer_mapping)
 
-    def _anonymize(self, text: str) -> str:
+    def _anonymize(self, text: str, language: Optional[str] = None) -> str:
         """Anonymize text.
         Each PII entity is replaced with a fake value.
         Each time fake values will be different, as they are generated randomly.
@@ -200,11 +246,24 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
 
         Args:
             text: text to anonymize
+            language: language to use for analysis of PII
+                If None, the first (main) language in the list
+                of languages specified in the configuration will be used.
         """
+        if language is None:
+            language = self.supported_languages[0]
+
+        if language not in self.supported_languages:
+            raise ValueError(
+                f"Language '{language}' is not supported. "
+                f"Supported languages are: {self.supported_languages}. "
+                "Change your language configuration file to add more languages."
+            )
+
         analyzer_results = self._analyzer.analyze(
             text,
             entities=self.analyzed_fields,
-            language="en",
+            language=language,
         )
 
         filtered_analyzer_results = (

libs/experimental/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-experimental"
-version = "0.0.15"
+version = "0.0.16"
 description = "Building applications with LLMs through composability"
 authors = []
 license = "MIT"

libs/langchain/langchain/callbacks/tracers/evaluation.py

@@ -2,29 +2,20 @@
 from __future__ import annotations
 
 import logging
-from concurrent.futures import Future, ThreadPoolExecutor, wait
+from concurrent.futures import Future, ThreadPoolExecutor
 from typing import Any, Dict, List, Optional, Sequence, Set, Union
 from uuid import UUID
 
 import langsmith
 from langsmith import schemas as langsmith_schemas
 
-from langchain.callbacks.manager import tracing_v2_enabled
+from langchain.callbacks import manager
+from langchain.callbacks.tracers import langchain as langchain_tracer
 from langchain.callbacks.tracers.base import BaseTracer
-from langchain.callbacks.tracers.langchain import _get_client
 from langchain.callbacks.tracers.schemas import Run
 
 logger = logging.getLogger(__name__)
 
-_TRACERS: List[EvaluatorCallbackHandler] = []
-
-
-def wait_for_all_evaluators() -> None:
-    """Wait for all tracers to finish."""
-    global _TRACERS
-    for tracer in _TRACERS:
-        tracer.wait_for_futures()
-
 
 class EvaluatorCallbackHandler(BaseTracer):
     """A tracer that runs a run evaluator whenever a run is persisted.
@@ -79,17 +70,13 @@ class EvaluatorCallbackHandler(BaseTracer):
         self.example_id = (
             UUID(example_id) if isinstance(example_id, str) else example_id
         )
-        self.client = client or _get_client()
+        self.client = client or langchain_tracer.get_client()
         self.evaluators = evaluators
-        self.executor = ThreadPoolExecutor(
-            max_workers=max(max_workers or len(evaluators), 1)
-        )
+        self.max_workers = max_workers or len(evaluators)
         self.futures: Set[Future] = set()
         self.skip_unfinished = skip_unfinished
         self.project_name = project_name
         self.logged_feedback: Dict[str, List[langsmith_schemas.Feedback]] = {}
-        global _TRACERS
-        _TRACERS.append(self)
 
     def _evaluate_in_project(self, run: Run, evaluator: langsmith.RunEvaluator) -> None:
         """Evaluate the run in the project.
@@ -105,7 +92,7 @@ class EvaluatorCallbackHandler(BaseTracer):
         try:
             if self.project_name is None:
                 feedback = self.client.evaluate_run(run, evaluator)
-            with tracing_v2_enabled(
+            with manager.tracing_v2_enabled(
                 project_name=self.project_name, tags=["eval"], client=self.client
             ):
                 feedback = self.client.evaluate_run(run, evaluator)
@@ -133,14 +120,15 @@ class EvaluatorCallbackHandler(BaseTracer):
             return
         run_ = run.copy()
         run_.reference_example_id = self.example_id
-        for evaluator in self.evaluators:
-            self.futures.add(
-                self.executor.submit(self._evaluate_in_project, run_, evaluator)
-            )
-
-    def wait_for_futures(self) -> None:
-        """Wait for all futures to complete."""
-        futures = list(self.futures)
-        wait(futures)
-        for future in futures:
-            self.futures.remove(future)
+        if self.max_workers > 0:
+            with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
+                list(
+                    executor.map(
+                        self._evaluate_in_project,
+                        [run_ for _ in range(len(self.evaluators))],
+                        self.evaluators,
+                    )
+                )
+        else:
+            for evaluator in self.evaluators:
+                self._evaluate_in_project(run_, evaluator)

libs/langchain/langchain/callbacks/tracers/langchain.py

@@ -42,7 +42,7 @@ def wait_for_all_tracers() -> None:
             tracer.wait_for_futures()
 
 
-def _get_client() -> Client:
+def get_client() -> Client:
     """Get the client."""
     global _CLIENT
     if _CLIENT is None:
@@ -83,7 +83,7 @@ class LangChainTracer(BaseTracer):
                 _EXECUTORS.append(self.executor)
         else:
             self.executor = None
-        self.client = client or _get_client()
+        self.client = client or get_client()
         self._futures: Set[Future] = set()
         self.tags = tags or []
         global _TRACERS

libs/langchain/langchain/chat_loaders/__init__.py

@@ -1,6 +1,19 @@
-"""Load chat messages from common communications platforms for finetuning.
+"""**Chat Loaders** load chat messages from common communications platforms.
 
-This module provides functions to load chat messages from various
+Load chat messages from various
 communications platforms such as Facebook Messenger, Telegram, and
-WhatsApp. The loaded chat messages can be used for finetuning models.
-"""
+WhatsApp. The loaded chat messages can be used for fine-tuning models.
+
+**Class hierarchy:**
+
+.. code-block::
+
+    BaseChatLoader --> <name>ChatLoader  # Examples: WhatsAppChatLoader, IMessageChatLoader
+
+**Main helpers:**
+
+.. code-block::
+
+    ChatSession
+
+"""  # noqa: E501

libs/langchain/langchain/chat_loaders/base.py

@@ -1,10 +1,3 @@
-"""Base definitions for chat loaders.
-
-A chat loader is a class that loads chat messages from an external
-source such as a file or a database. The chat messages can then be
-used for finetuning.
-"""
-
 from abc import ABC, abstractmethod
 from typing import Iterator, List, Sequence, TypedDict
 
@@ -12,7 +5,7 @@ from langchain.schema.messages import BaseMessage
 
 
 class ChatSession(TypedDict):
-    """A chat session represents a single
+    """Chat Session represents a single
     conversation, channel, or other group of messages."""
 
     messages: Sequence[BaseMessage]

libs/langchain/langchain/chat_loaders/facebook_messenger.py

@@ -10,7 +10,7 @@ logger = logging.getLogger(__file__)
 
 
 class SingleFileFacebookMessengerChatLoader(BaseChatLoader):
-    """A chat loader for loading Facebook Messenger chat data from a single file.
+    """Load `Facebook Messenger` chat data from a single file.
 
     Args:
         path (Union[Path, str]): The path to the chat file.
@@ -45,7 +45,7 @@ class SingleFileFacebookMessengerChatLoader(BaseChatLoader):
 
 
 class FolderFacebookMessengerChatLoader(BaseChatLoader):
-    """A chat loader for loading Facebook Messenger chat data from a folder.
+    """Load `Facebook Messenger` chat data from a folder.
 
     Args:
         path (Union[str, Path]): The path to the directory

libs/langchain/langchain/chat_loaders/gmail.py

@@ -62,7 +62,7 @@ def _get_message_data(service: Any, message: Any) -> ChatSession:
 
 
 class GMailLoader(BaseChatLoader):
-    """This loader goes over how to load data from GMail.
+    """Load data from `GMail`.
 
     There are many ways you could want to load data from GMail.
     This loader is currently fairly opinionated in how to do so.

libs/langchain/langchain/chat_loaders/imessage.py

@@ -1,14 +1,3 @@
-"""IMessage Chat Loader.
-
-This class is used to load chat sessions from the iMessage chat.db SQLite file.
-It only works on macOS when you have iMessage enabled and have the chat.db file.
-
-The chat.db file is likely located at ~/Library/Messages/chat.db. However, your
-terminal may not have permission to access this file. To resolve this, you can
-copy the file to a different location, change the permissions of the file, or
-grant full disk access for your terminal emulator in System Settings > Security
-and Privacy > Full Disk Access.
-"""
 from __future__ import annotations
 
 from pathlib import Path
@@ -22,6 +11,17 @@ if TYPE_CHECKING:
 
 
 class IMessageChatLoader(chat_loaders.BaseChatLoader):
+    """Load chat sessions from the `iMessage` chat.db SQLite file.
+
+    It only works on macOS when you have iMessage enabled and have the chat.db file.
+
+    The chat.db file is likely located at ~/Library/Messages/chat.db. However, your
+    terminal may not have permission to access this file. To resolve this, you can
+    copy the file to a different location, change the permissions of the file, or
+    grant full disk access for your terminal emulator in System Settings > Security
+    and Privacy > Full Disk Access.
+    """
+
     def __init__(self, path: Optional[Union[str, Path]] = None):
         """
         Initialize the IMessageChatLoader.

libs/langchain/langchain/chat_loaders/slack.py

@@ -12,6 +12,8 @@ logger = logging.getLogger(__name__)
 
 
 class SlackChatLoader(chat_loaders.BaseChatLoader):
+    """Load `Slack` conversations from a dump zip file."""
+
     def __init__(
         self,
         path: Union[str, Path],

libs/langchain/langchain/chat_loaders/telegram.py

@@ -13,8 +13,7 @@ logger = logging.getLogger(__name__)
 
 
 class TelegramChatLoader(chat_loaders.BaseChatLoader):
-    """A loading utility for converting telegram conversations
-    to LangChain chat messages.
+    """Load `telegram` conversations to LangChain chat messages.
 
     To export, use the Telegram Desktop app from
     https://desktop.telegram.org/, select a conversation, click the three dots

libs/langchain/langchain/chat_loaders/whatsapp.py

@@ -12,6 +12,8 @@ logger = logging.getLogger(__name__)
 
 
 class WhatsAppChatLoader(chat_loaders.BaseChatLoader):
+    """Load `WhatsApp` conversations from a dump zip file or directory."""
+
     def __init__(self, path: str):
         """Initialize the WhatsAppChatLoader.
 

libs/langchain/langchain/chat_models/__init__.py

@@ -20,12 +20,12 @@ an interface where "chat messages" are the inputs and outputs.
 from langchain.chat_models.anthropic import ChatAnthropic
 from langchain.chat_models.anyscale import ChatAnyscale
 from langchain.chat_models.azure_openai import AzureChatOpenAI
-from langchain.chat_models.bedrock import BedrockChat
 from langchain.chat_models.ernie import ErnieBotChat
 from langchain.chat_models.fake import FakeListChatModel
 from langchain.chat_models.google_palm import ChatGooglePalm
 from langchain.chat_models.human import HumanInputChatModel
 from langchain.chat_models.jinachat import JinaChat
+from langchain.chat_models.konko import ChatKonko
 from langchain.chat_models.litellm import ChatLiteLLM
 from langchain.chat_models.mlflow_ai_gateway import ChatMLflowAIGateway
 from langchain.chat_models.ollama import ChatOllama
@@ -36,7 +36,6 @@ from langchain.chat_models.vertexai import ChatVertexAI
 __all__ = [
     "ChatOpenAI",
     "AzureChatOpenAI",
-    "BedrockChat",
     "FakeListChatModel",
     "PromptLayerChatOpenAI",
     "ChatAnthropic",
@@ -49,4 +48,5 @@ __all__ = [
     "ChatAnyscale",
     "ChatLiteLLM",
     "ErnieBotChat",
+    "ChatKonko",
 ]

libs/langchain/langchain/chat_models/konko.py

@@ -0,0 +1,292 @@
+"""KonkoAI chat wrapper."""
+from __future__ import annotations
+
+import logging
+import os
+from typing import (
+    Any,
+    Dict,
+    Iterator,
+    List,
+    Mapping,
+    Optional,
+    Set,
+    Tuple,
+    Union,
+)
+
+import requests
+
+from langchain.adapters.openai import convert_dict_to_message, convert_message_to_dict
+from langchain.callbacks.manager import (
+    CallbackManagerForLLMRun,
+)
+from langchain.chat_models.openai import ChatOpenAI, _convert_delta_to_message_chunk
+from langchain.pydantic_v1 import Field, root_validator
+from langchain.schema import ChatGeneration, ChatResult
+from langchain.schema.messages import AIMessageChunk, BaseMessage
+from langchain.schema.output import ChatGenerationChunk
+from langchain.utils import get_from_dict_or_env
+
+DEFAULT_API_BASE = "https://api.konko.ai/v1"
+DEFAULT_MODEL = "meta-llama/Llama-2-13b-chat-hf"
+
+logger = logging.getLogger(__name__)
+
+
+class ChatKonko(ChatOpenAI):
+    """`ChatKonko` Chat large language models API.
+
+    To use, you should have the ``konko`` python package installed, and the
+    environment variable ``KONKO_API_KEY`` and ``OPENAI_API_KEY`` set with your API key.
+
+    Any parameters that are valid to be passed to the konko.create call can be passed
+    in, even if not explicitly saved on this class.
+
+    Example:
+        .. code-block:: python
+
+            from langchain.chat_models import ChatKonko
+            llm = ChatKonko(model="meta-llama/Llama-2-13b-chat-hf")
+    """
+
+    @property
+    def lc_secrets(self) -> Dict[str, str]:
+        return {"konko_api_key": "KONKO_API_KEY", "openai_api_key": "OPENAI_API_KEY"}
+
+    @property
+    def lc_serializable(self) -> bool:
+        return True
+
+    client: Any = None  #: :meta private:
+    model: str = Field(default=DEFAULT_MODEL, alias="model")
+    """Model name to use."""
+    temperature: float = 0.7
+    """What sampling temperature to use."""
+    model_kwargs: Dict[str, Any] = Field(default_factory=dict)
+    """Holds any model parameters valid for `create` call not explicitly specified."""
+    openai_api_key: Optional[str] = None
+    konko_api_key: Optional[str] = None
+    request_timeout: Optional[Union[float, Tuple[float, float]]] = None
+    """Timeout for requests to Konko completion API."""
+    max_retries: int = 6
+    """Maximum number of retries to make when generating."""
+    streaming: bool = False
+    """Whether to stream the results or not."""
+    n: int = 1
+    """Number of chat completions to generate for each prompt."""
+    max_tokens: int = 20
+    """Maximum number of tokens to generate."""
+
+    @root_validator()
+    def validate_environment(cls, values: Dict) -> Dict:
+        """Validate that api key and python package exists in environment."""
+        values["konko_api_key"] = get_from_dict_or_env(
+            values, "konko_api_key", "KONKO_API_KEY"
+        )
+        try:
+            import konko
+
+        except ImportError:
+            raise ValueError(
+                "Could not import konko python package. "
+                "Please install it with `pip install konko`."
+            )
+        try:
+            values["client"] = konko.ChatCompletion
+        except AttributeError:
+            raise ValueError(
+                "`konko` has no `ChatCompletion` attribute, this is likely "
+                "due to an old version of the konko package. Try upgrading it "
+                "with `pip install --upgrade konko`."
+            )
+        if values["n"] < 1:
+            raise ValueError("n must be at least 1.")
+        if values["n"] > 1 and values["streaming"]:
+            raise ValueError("n must be 1 when streaming.")
+        return values
+
+    @property
+    def _default_params(self) -> Dict[str, Any]:
+        """Get the default parameters for calling Konko API."""
+        return {
+            "model": self.model,
+            "request_timeout": self.request_timeout,
+            "max_tokens": self.max_tokens,
+            "stream": self.streaming,
+            "n": self.n,
+            "temperature": self.temperature,
+            **self.model_kwargs,
+        }
+
+    @staticmethod
+    def get_available_models(
+        konko_api_key: Optional[str] = None,
+        openai_api_key: Optional[str] = None,
+        konko_api_base: str = DEFAULT_API_BASE,
+    ) -> Set[str]:
+        """Get available models from Konko API."""
+
+        # Try to retrieve the OpenAI API key if it's not passed as an argument
+        if not openai_api_key:
+            try:
+                openai_api_key = os.environ["OPENAI_API_KEY"]
+            except KeyError:
+                pass  # It's okay if it's not set, we just won't use it
+
+        # Try to retrieve the Konko API key if it's not passed as an argument
+        if not konko_api_key:
+            try:
+                konko_api_key = os.environ["KONKO_API_KEY"]
+            except KeyError:
+                raise ValueError(
+                    "Konko API key must be passed as keyword argument or "
+                    "set in environment variable KONKO_API_KEY."
+                )
+
+        models_url = f"{konko_api_base}/models"
+
+        headers = {
+            "Authorization": f"Bearer {konko_api_key}",
+        }
+
+        if openai_api_key:
+            headers["X-OpenAI-Api-Key"] = openai_api_key
+
+        models_response = requests.get(models_url, headers=headers)
+
+        if models_response.status_code != 200:
+            raise ValueError(
+                f"Error getting models from {models_url}: "
+                f"{models_response.status_code}"
+            )
+
+        return {model["id"] for model in models_response.json()["data"]}
+
+    def completion_with_retry(
+        self, run_manager: Optional[CallbackManagerForLLMRun] = None, **kwargs: Any
+    ) -> Any:
+        def _completion_with_retry(**kwargs: Any) -> Any:
+            return self.client.create(**kwargs)
+
+        return _completion_with_retry(**kwargs)
+
+    def _combine_llm_outputs(self, llm_outputs: List[Optional[dict]]) -> dict:
+        overall_token_usage: dict = {}
+        for output in llm_outputs:
+            if output is None:
+                # Happens in streaming
+                continue
+            token_usage = output["token_usage"]
+            for k, v in token_usage.items():
+                if k in overall_token_usage:
+                    overall_token_usage[k] += v
+                else:
+                    overall_token_usage[k] = v
+        return {"token_usage": overall_token_usage, "model_name": self.model}
+
+    def _stream(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        **kwargs: Any,
+    ) -> Iterator[ChatGenerationChunk]:
+        message_dicts, params = self._create_message_dicts(messages, stop)
+        params = {**params, **kwargs, "stream": True}
+
+        default_chunk_class = AIMessageChunk
+        for chunk in self.completion_with_retry(
+            messages=message_dicts, run_manager=run_manager, **params
+        ):
+            if len(chunk["choices"]) == 0:
+                continue
+            choice = chunk["choices"][0]
+            chunk = _convert_delta_to_message_chunk(
+                choice["delta"], default_chunk_class
+            )
+            finish_reason = choice.get("finish_reason")
+            generation_info = (
+                dict(finish_reason=finish_reason) if finish_reason is not None else None
+            )
+            default_chunk_class = chunk.__class__
+            yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
+            if run_manager:
+                run_manager.on_llm_new_token(chunk.content, chunk=chunk)
+
+    def _generate(
+        self,
+        messages: List[BaseMessage],
+        stop: Optional[List[str]] = None,
+        run_manager: Optional[CallbackManagerForLLMRun] = None,
+        stream: Optional[bool] = None,
+        **kwargs: Any,
+    ) -> ChatResult:
+        if stream if stream is not None else self.streaming:
+            generation: Optional[ChatGenerationChunk] = None
+            for chunk in self._stream(
+                messages=messages, stop=stop, run_manager=run_manager, **kwargs
+            ):
+                if generation is None:
+                    generation = chunk
+                else:
+                    generation += chunk
+            assert generation is not None
+            return ChatResult(generations=[generation])
+
+        message_dicts, params = self._create_message_dicts(messages, stop)
+        params = {**params, **kwargs}
+        response = self.completion_with_retry(
+            messages=message_dicts, run_manager=run_manager, **params
+        )
+        return self._create_chat_result(response)
+
+    def _create_message_dicts(
+        self, messages: List[BaseMessage], stop: Optional[List[str]]
+    ) -> Tuple[List[Dict[str, Any]], Dict[str, Any]]:
+        params = self._client_params
+        if stop is not None:
+            if "stop" in params:
+                raise ValueError("`stop` found in both the input and default params.")
+            params["stop"] = stop
+        message_dicts = [convert_message_to_dict(m) for m in messages]
+        return message_dicts, params
+
+    def _create_chat_result(self, response: Mapping[str, Any]) -> ChatResult:
+        generations = []
+        for res in response["choices"]:
+            message = convert_dict_to_message(res["message"])
+            gen = ChatGeneration(
+                message=message,
+                generation_info=dict(finish_reason=res.get("finish_reason")),
+            )
+            generations.append(gen)
+        token_usage = response.get("usage", {})
+        llm_output = {"token_usage": token_usage, "model_name": self.model}
+        return ChatResult(generations=generations, llm_output=llm_output)
+
+    @property
+    def _identifying_params(self) -> Dict[str, Any]:
+        """Get the identifying parameters."""
+        return {**{"model_name": self.model}, **self._default_params}
+
+    @property
+    def _client_params(self) -> Dict[str, Any]:
+        """Get the parameters used for the konko client."""
+        return {**self._default_params}
+
+    def _get_invocation_params(
+        self, stop: Optional[List[str]] = None, **kwargs: Any
+    ) -> Dict[str, Any]:
+        """Get the parameters used to invoke the model."""
+        return {
+            "model": self.model,
+            **super()._get_invocation_params(stop=stop),
+            **self._default_params,
+            **kwargs,
+        }
+
+    @property
+    def _llm_type(self) -> str:
+        """Return type of chat model."""
+        return "konko-chat"

libs/langchain/langchain/llms/vertexai.py

@@ -169,7 +169,7 @@ class VertexAI(_VertexAICommon, LLM):
         tuned_model_name = values.get("tuned_model_name")
         model_name = values["model_name"]
         try:
-            if tuned_model_name or not is_codey_model(model_name):
+            if not is_codey_model(model_name):
                 from vertexai.preview.language_models import TextGenerationModel
 
                 if tuned_model_name:
@@ -181,7 +181,12 @@ class VertexAI(_VertexAICommon, LLM):
             else:
                 from vertexai.preview.language_models import CodeGenerationModel
 
-                values["client"] = CodeGenerationModel.from_pretrained(model_name)
+                if tuned_model_name:
+                    values["client"] = CodeGenerationModel.get_tuned_model(
+                        tuned_model_name
+                    )
+                else:
+                    values["client"] = CodeGenerationModel.from_pretrained(model_name)
         except ImportError:
             raise_vertex_import_error()
         return values

libs/langchain/langchain/memory/chat_message_histories/dynamodb.py

@@ -1,5 +1,7 @@
+from __future__ import annotations
+
 import logging
-from typing import Dict, List, Optional
+from typing import TYPE_CHECKING, Dict, List, Optional
 
 from langchain.schema import (
     BaseChatMessageHistory,
@@ -11,6 +13,9 @@ from langchain.schema.messages import (
     messages_to_dict,
 )
 
+if TYPE_CHECKING:
+    from boto3.session import Session
+
 logger = logging.getLogger(__name__)
 
 
@@ -42,13 +47,21 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
         endpoint_url: Optional[str] = None,
         primary_key_name: str = "SessionId",
         key: Optional[Dict[str, str]] = None,
+        boto3_session: Optional[Session] = None,
     ):
-        import boto3
-
-        if endpoint_url:
-            client = boto3.resource("dynamodb", endpoint_url=endpoint_url)
+        if boto3_session:
+            client = boto3_session.resource("dynamodb")
         else:
-            client = boto3.resource("dynamodb")
+            try:
+                import boto3
+            except ImportError as e:
+                raise ImportError(
+                    "Unable to import boto3, please install with `pip install boto3`."
+                ) from e
+            if endpoint_url:
+                client = boto3.resource("dynamodb", endpoint_url=endpoint_url)
+            else:
+                client = boto3.resource("dynamodb")
         self.table = client.Table(table_name)
         self.session_id = session_id
         self.key: Dict = key or {primary_key_name: session_id}
@@ -56,7 +69,12 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
     @property
     def messages(self) -> List[BaseMessage]:  # type: ignore
         """Retrieve the messages from DynamoDB"""
-        from botocore.exceptions import ClientError
+        try:
+            from botocore.exceptions import ClientError
+        except ImportError as e:
+            raise ImportError(
+                "Unable to import botocore, please install with `pip install botocore`."
+            ) from e
 
         response = None
         try:
@@ -77,7 +95,12 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
 
     def add_message(self, message: BaseMessage) -> None:
         """Append the message to the record in DynamoDB"""
-        from botocore.exceptions import ClientError
+        try:
+            from botocore.exceptions import ClientError
+        except ImportError as e:
+            raise ImportError(
+                "Unable to import botocore, please install with `pip install botocore`."
+            ) from e
 
         messages = messages_to_dict(self.messages)
         _message = _message_to_dict(message)
@@ -90,7 +113,12 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
 
     def clear(self) -> None:
         """Clear session memory from DynamoDB"""
-        from botocore.exceptions import ClientError
+        try:
+            from botocore.exceptions import ClientError
+        except ImportError as e:
+            raise ImportError(
+                "Unable to import botocore, please install with `pip install botocore`."
+            ) from e
 
         try:
             self.table.delete_item(self.key)

libs/langchain/langchain/retrievers/self_query/base.py

@@ -16,6 +16,8 @@ from langchain.retrievers.self_query.milvus import MilvusTranslator
 from langchain.retrievers.self_query.myscale import MyScaleTranslator
 from langchain.retrievers.self_query.pinecone import PineconeTranslator
 from langchain.retrievers.self_query.qdrant import QdrantTranslator
+from langchain.retrievers.self_query.supabase import SupabaseVectorTranslator
+from langchain.retrievers.self_query.vectara import VectaraTranslator
 from langchain.retrievers.self_query.weaviate import WeaviateTranslator
 from langchain.schema import BaseRetriever, Document
 from langchain.schema.language_model import BaseLanguageModel
@@ -28,6 +30,8 @@ from langchain.vectorstores import (
     MyScale,
     Pinecone,
     Qdrant,
+    SupabaseVectorStore,
+    Vectara,
     VectorStore,
     Weaviate,
 )
@@ -41,11 +45,13 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
         Chroma: ChromaTranslator,
         DashVector: DashvectorTranslator,
         Weaviate: WeaviateTranslator,
+        Vectara: VectaraTranslator,
         Qdrant: QdrantTranslator,
         MyScale: MyScaleTranslator,
         DeepLake: DeepLakeTranslator,
         ElasticsearchStore: ElasticsearchTranslator,
         Milvus: MilvusTranslator,
+        SupabaseVectorStore: SupabaseVectorTranslator,
     }
     if vectorstore_cls not in BUILTIN_TRANSLATORS:
         raise ValueError(

libs/langchain/langchain/retrievers/self_query/supabase.py

@@ -0,0 +1,97 @@
+from typing import Any, Dict, Tuple
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+    Visitor,
+)
+
+
+class SupabaseVectorTranslator(Visitor):
+    """Translate Langchain filters to Supabase PostgREST filters."""
+
+    allowed_operators = [Operator.AND, Operator.OR]
+    """Subset of allowed logical operators."""
+
+    allowed_comparators = [
+        Comparator.EQ,
+        Comparator.NE,
+        Comparator.GT,
+        Comparator.GTE,
+        Comparator.LT,
+        Comparator.LTE,
+        Comparator.LIKE,
+    ]
+    """Subset of allowed logical comparators."""
+
+    metadata_column = "metadata"
+
+    def _map_comparator(self, comparator: Comparator) -> str:
+        """
+        Maps Langchain comparator to PostgREST comparator:
+
+        https://postgrest.org/en/stable/references/api/tables_views.html#operators
+        """
+        postgrest_comparator = {
+            Comparator.EQ: "eq",
+            Comparator.NE: "neq",
+            Comparator.GT: "gt",
+            Comparator.GTE: "gte",
+            Comparator.LT: "lt",
+            Comparator.LTE: "lte",
+            Comparator.LIKE: "like",
+        }.get(comparator)
+
+        if postgrest_comparator is None:
+            raise Exception(
+                f"Comparator '{comparator}' is not currently "
+                "supported in Supabase Vector"
+            )
+
+        return postgrest_comparator
+
+    def _get_json_operator(self, value: Any) -> str:
+        if isinstance(value, str):
+            return "->>"
+        else:
+            return "->"
+
+    def visit_operation(self, operation: Operation) -> str:
+        args = [arg.accept(self) for arg in operation.arguments]
+        return f"{operation.operator.value}({','.join(args)})"
+
+    def visit_comparison(self, comparison: Comparison) -> str:
+        if isinstance(comparison.value, list):
+            return self.visit_operation(
+                Operation(
+                    operator=Operator.AND,
+                    arguments=(
+                        Comparison(
+                            comparator=comparison.comparator,
+                            attribute=comparison.attribute,
+                            value=value,
+                        )
+                        for value in comparison.value
+                    ),
+                )
+            )
+
+        return ".".join(
+            [
+                f"{self.metadata_column}{self._get_json_operator(comparison.value)}{comparison.attribute}",
+                f"{self._map_comparator(comparison.comparator)}",
+                f"{comparison.value}",
+            ]
+        )
+
+    def visit_structured_query(
+        self, structured_query: StructuredQuery
+    ) -> Tuple[str, Dict[str, str]]:
+        if structured_query.filter is None:
+            kwargs = {}
+        else:
+            kwargs = {"postgrest_filter": structured_query.filter.accept(self)}
+        return structured_query.query, kwargs

libs/langchain/langchain/retrievers/self_query/vectara.py

@@ -0,0 +1,69 @@
+from typing import Tuple, Union
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+    Visitor,
+)
+
+
+def process_value(value: Union[int, float, str]) -> str:
+    if isinstance(value, str):
+        return f"'{value}'"
+    else:
+        return str(value)
+
+
+class VectaraTranslator(Visitor):
+    """Translate `Vectara` internal query language elements to valid filters."""
+
+    allowed_operators = [Operator.AND, Operator.OR]
+    """Subset of allowed logical operators."""
+    allowed_comparators = [
+        Comparator.EQ,
+        Comparator.NE,
+        Comparator.GT,
+        Comparator.GTE,
+        Comparator.LT,
+        Comparator.LTE,
+    ]
+    """Subset of allowed logical comparators."""
+
+    def _format_func(self, func: Union[Operator, Comparator]) -> str:
+        map_dict = {
+            Operator.AND: " and ",
+            Operator.OR: " or ",
+            Comparator.EQ: "=",
+            Comparator.NE: "!=",
+            Comparator.GT: ">",
+            Comparator.GTE: ">=",
+            Comparator.LT: "<",
+            Comparator.LTE: "<=",
+        }
+        self._validate_func(func)
+        return map_dict[func]
+
+    def visit_operation(self, operation: Operation) -> str:
+        args = [arg.accept(self) for arg in operation.arguments]
+        operator = self._format_func(operation.operator)
+        return "( " + operator.join(args) + " )"
+
+    def visit_comparison(self, comparison: Comparison) -> str:
+        comparator = self._format_func(comparison.comparator)
+        processed_value = process_value(comparison.value)
+        attribute = comparison.attribute
+        return (
+            "( " + "doc." + attribute + " " + comparator + " " + processed_value + " )"
+        )
+
+    def visit_structured_query(
+        self, structured_query: StructuredQuery
+    ) -> Tuple[str, dict]:
+        if structured_query.filter is None:
+            kwargs = {}
+        else:
+            kwargs = {"filter": structured_query.filter.accept(self)}
+        return structured_query.query, kwargs

libs/langchain/langchain/schema/runnable/base.py

@@ -254,7 +254,7 @@ class Runnable(Generic[Input, Output], ABC):
     def with_retry(
         self,
         *,
-        retry_if_exception_type: Tuple[Type[BaseException]] = (Exception,),
+        retry_if_exception_type: Tuple[Type[BaseException], ...] = (Exception,),
         wait_exponential_jitter: bool = True,
         stop_after_attempt: int = 3,
     ) -> Runnable[Input, Output]:
@@ -280,7 +280,7 @@ class Runnable(Generic[Input, Output], ABC):
         self,
         fallbacks: Sequence[Runnable[Input, Output]],
         *,
-        exceptions_to_handle: Tuple[Type[BaseException]] = (Exception,),
+        exceptions_to_handle: Tuple[Type[BaseException], ...] = (Exception,),
     ) -> RunnableWithFallbacks[Input, Output]:
         return RunnableWithFallbacks(
             runnable=self,
@@ -653,7 +653,7 @@ class RunnableWithFallbacks(Serializable, Runnable[Input, Output]):
 
     runnable: Runnable[Input, Output]
     fallbacks: Sequence[Runnable[Input, Output]]
-    exceptions_to_handle: Tuple[Type[BaseException]] = (Exception,)
+    exceptions_to_handle: Tuple[Type[BaseException], ...] = (Exception,)
 
     class Config:
         arbitrary_types_allowed = True

libs/langchain/langchain/schema/runnable/retry.py

@@ -24,7 +24,7 @@ U = TypeVar("U")
 class RunnableRetry(RunnableBinding[Input, Output]):
     """Retry a Runnable if it fails."""
 
-    retry_exception_types: Tuple[Type[BaseException]] = (Exception,)
+    retry_exception_types: Tuple[Type[BaseException], ...] = (Exception,)
 
     wait_exponential_jitter: bool = True
 

libs/langchain/langchain/smith/evaluation/name_generation.py

@@ -0,0 +1,729 @@
+import random
+
+adjectives = [
+    "abandoned",
+    "aching",
+    "advanced",
+    "ample",
+    "artistic",
+    "back",
+    "best",
+    "bold",
+    "brief",
+    "clear",
+    "cold",
+    "complicated",
+    "cooked",
+    "crazy",
+    "crushing",
+    "damp",
+    "dear",
+    "definite",
+    "dependable",
+    "diligent",
+    "drab",
+    "earnest",
+    "elderly",
+    "enchanted",
+    "essential",
+    "excellent",
+    "extraneous",
+    "fixed",
+    "flowery",
+    "formal",
+    "fresh",
+    "frosty",
+    "giving",
+    "glossy",
+    "healthy",
+    "helpful",
+    "impressionable",
+    "kind",
+    "large",
+    "left",
+    "long",
+    "loyal",
+    "mealy",
+    "memorable",
+    "monthly",
+    "new",
+    "notable",
+    "only",
+    "ordinary",
+    "passionate",
+    "perfect",
+    "pertinent",
+    "proper",
+    "puzzled",
+    "reflecting",
+    "respectful",
+    "roasted",
+    "scholarly",
+    "shiny",
+    "slight",
+    "sparkling",
+    "spotless",
+    "stupendous",
+    "sunny",
+    "tart",
+    "terrific",
+    "timely",
+    "unique",
+    "upbeat",
+    "vacant",
+    "virtual",
+    "warm",
+    "weary",
+    "whispered",
+    "worthwhile",
+    "yellow",
+]
+
+nouns = [
+    "account",
+    "acknowledgment",
+    "address",
+    "advertising",
+    "airplane",
+    "animal",
+    "appointment",
+    "arrival",
+    "artist",
+    "attachment",
+    "attitude",
+    "availability",
+    "backpack",
+    "bag",
+    "balance",
+    "bass",
+    "bean",
+    "beauty",
+    "bibliography",
+    "bill",
+    "bite",
+    "blossom",
+    "boat",
+    "book",
+    "box",
+    "boy",
+    "bread",
+    "bridge",
+    "broccoli",
+    "building",
+    "butter",
+    "button",
+    "cabbage",
+    "cake",
+    "camera",
+    "camp",
+    "candle",
+    "candy",
+    "canvas",
+    "car",
+    "card",
+    "carrot",
+    "cart",
+    "case",
+    "cat",
+    "chain",
+    "chair",
+    "chalk",
+    "chance",
+    "change",
+    "channel",
+    "character",
+    "charge",
+    "charm",
+    "chart",
+    "check",
+    "cheek",
+    "cheese",
+    "chef",
+    "cherry",
+    "chicken",
+    "child",
+    "church",
+    "circle",
+    "class",
+    "clay",
+    "click",
+    "clock",
+    "cloth",
+    "cloud",
+    "clove",
+    "club",
+    "coach",
+    "coal",
+    "coast",
+    "coat",
+    "cod",
+    "coffee",
+    "collar",
+    "color",
+    "comb",
+    "comfort",
+    "comic",
+    "committee",
+    "community",
+    "company",
+    "comparison",
+    "competition",
+    "condition",
+    "connection",
+    "control",
+    "cook",
+    "copper",
+    "copy",
+    "corn",
+    "cough",
+    "country",
+    "cover",
+    "crate",
+    "crayon",
+    "cream",
+    "creator",
+    "crew",
+    "crown",
+    "current",
+    "curtain",
+    "curve",
+    "cushion",
+    "dad",
+    "daughter",
+    "day",
+    "death",
+    "debt",
+    "decision",
+    "deer",
+    "degree",
+    "design",
+    "desire",
+    "desk",
+    "detail",
+    "development",
+    "digestion",
+    "dime",
+    "dinner",
+    "direction",
+    "dirt",
+    "discovery",
+    "discussion",
+    "disease",
+    "disgust",
+    "distance",
+    "distribution",
+    "division",
+    "doctor",
+    "dog",
+    "door",
+    "drain",
+    "drawer",
+    "dress",
+    "drink",
+    "driving",
+    "dust",
+    "ear",
+    "earth",
+    "edge",
+    "education",
+    "effect",
+    "egg",
+    "end",
+    "energy",
+    "engine",
+    "error",
+    "event",
+    "example",
+    "exchange",
+    "existence",
+    "expansion",
+    "experience",
+    "expert",
+    "eye",
+    "face",
+    "fact",
+    "fall",
+    "family",
+    "farm",
+    "father",
+    "fear",
+    "feeling",
+    "field",
+    "finger",
+    "fire",
+    "fish",
+    "flag",
+    "flight",
+    "floor",
+    "flower",
+    "fold",
+    "food",
+    "football",
+    "force",
+    "form",
+    "frame",
+    "friend",
+    "frog",
+    "fruit",
+    "fuel",
+    "furniture",
+    "game",
+    "garden",
+    "gate",
+    "girl",
+    "glass",
+    "glove",
+    "goat",
+    "gold",
+    "government",
+    "grade",
+    "grain",
+    "grass",
+    "green",
+    "grip",
+    "group",
+    "growth",
+    "guide",
+    "guitar",
+    "hair",
+    "hall",
+    "hand",
+    "harbor",
+    "harmony",
+    "hat",
+    "head",
+    "health",
+    "heart",
+    "heat",
+    "hill",
+    "history",
+    "hobbies",
+    "hole",
+    "hope",
+    "horn",
+    "horse",
+    "hospital",
+    "hour",
+    "house",
+    "humor",
+    "idea",
+    "impulse",
+    "income",
+    "increase",
+    "industry",
+    "ink",
+    "insect",
+    "instrument",
+    "insurance",
+    "interest",
+    "invention",
+    "iron",
+    "island",
+    "jelly",
+    "jet",
+    "jewel",
+    "join",
+    "judge",
+    "juice",
+    "jump",
+    "kettle",
+    "key",
+    "kick",
+    "kiss",
+    "kitten",
+    "knee",
+    "knife",
+    "knowledge",
+    "land",
+    "language",
+    "laugh",
+    "law",
+    "lead",
+    "learning",
+    "leather",
+    "leg",
+    "lettuce",
+    "level",
+    "library",
+    "lift",
+    "light",
+    "limit",
+    "line",
+    "linen",
+    "lip",
+    "liquid",
+    "list",
+    "look",
+    "loss",
+    "love",
+    "lunch",
+    "machine",
+    "man",
+    "manager",
+    "map",
+    "marble",
+    "mark",
+    "market",
+    "mass",
+    "match",
+    "meal",
+    "measure",
+    "meat",
+    "meeting",
+    "memory",
+    "metal",
+    "middle",
+    "milk",
+    "mind",
+    "mine",
+    "minute",
+    "mist",
+    "mitten",
+    "mom",
+    "money",
+    "monkey",
+    "month",
+    "moon",
+    "morning",
+    "mother",
+    "motion",
+    "mountain",
+    "mouth",
+    "muscle",
+    "music",
+    "nail",
+    "name",
+    "nation",
+    "neck",
+    "need",
+    "news",
+    "night",
+    "noise",
+    "note",
+    "number",
+    "nut",
+    "observation",
+    "offer",
+    "oil",
+    "operation",
+    "opinion",
+    "orange",
+    "order",
+    "organization",
+    "ornament",
+    "oven",
+    "page",
+    "pail",
+    "pain",
+    "paint",
+    "pan",
+    "pancake",
+    "paper",
+    "parcel",
+    "parent",
+    "part",
+    "passenger",
+    "paste",
+    "payment",
+    "peace",
+    "pear",
+    "pen",
+    "pencil",
+    "person",
+    "pest",
+    "pet",
+    "picture",
+    "pie",
+    "pin",
+    "pipe",
+    "pizza",
+    "place",
+    "plane",
+    "plant",
+    "plastic",
+    "plate",
+    "play",
+    "pleasure",
+    "plot",
+    "plough",
+    "pocket",
+    "point",
+    "poison",
+    "police",
+    "pollution",
+    "popcorn",
+    "porter",
+    "position",
+    "pot",
+    "potato",
+    "powder",
+    "power",
+    "price",
+    "print",
+    "process",
+    "produce",
+    "product",
+    "profit",
+    "property",
+    "prose",
+    "protest",
+    "pull",
+    "pump",
+    "punishment",
+    "purpose",
+    "push",
+    "quarter",
+    "question",
+    "quiet",
+    "quill",
+    "quilt",
+    "quince",
+    "rabbit",
+    "rail",
+    "rain",
+    "range",
+    "rat",
+    "rate",
+    "ray",
+    "reaction",
+    "reading",
+    "reason",
+    "record",
+    "regret",
+    "relation",
+    "religion",
+    "representative",
+    "request",
+    "respect",
+    "rest",
+    "reward",
+    "rhythm",
+    "rice",
+    "river",
+    "road",
+    "roll",
+    "room",
+    "root",
+    "rose",
+    "route",
+    "rub",
+    "rule",
+    "run",
+    "sack",
+    "sail",
+    "salt",
+    "sand",
+    "scale",
+    "scarecrow",
+    "scarf",
+    "scene",
+    "scent",
+    "school",
+    "science",
+    "scissors",
+    "screw",
+    "sea",
+    "seat",
+    "secretary",
+    "seed",
+    "selection",
+    "self",
+    "sense",
+    "servant",
+    "shade",
+    "shake",
+    "shame",
+    "shape",
+    "sheep",
+    "sheet",
+    "shelf",
+    "ship",
+    "shirt",
+    "shock",
+    "shoe",
+    "shop",
+    "show",
+    "side",
+    "sign",
+    "silk",
+    "sink",
+    "sister",
+    "size",
+    "sky",
+    "slave",
+    "sleep",
+    "smash",
+    "smell",
+    "smile",
+    "smoke",
+    "snail",
+    "snake",
+    "sneeze",
+    "snow",
+    "soap",
+    "society",
+    "sock",
+    "soda",
+    "sofa",
+    "son",
+    "song",
+    "sort",
+    "sound",
+    "soup",
+    "space",
+    "spark",
+    "speed",
+    "sponge",
+    "spoon",
+    "spray",
+    "spring",
+    "spy",
+    "square",
+    "stamp",
+    "star",
+    "start",
+    "statement",
+    "station",
+    "steam",
+    "steel",
+    "stem",
+    "step",
+    "stew",
+    "stick",
+    "stitch",
+    "stocking",
+    "stomach",
+    "stone",
+    "stop",
+    "store",
+    "story",
+    "stove",
+    "stranger",
+    "straw",
+    "stream",
+    "street",
+    "stretch",
+    "string",
+    "structure",
+    "substance",
+    "sugar",
+    "suggestion",
+    "suit",
+    "summer",
+    "sun",
+    "support",
+    "surprise",
+    "sweater",
+    "swim",
+    "system",
+    "table",
+    "tail",
+    "talk",
+    "tank",
+    "taste",
+    "tax",
+    "tea",
+    "teaching",
+    "team",
+    "tendency",
+    "test",
+    "texture",
+    "theory",
+    "thing",
+    "thought",
+    "thread",
+    "throat",
+    "thumb",
+    "thunder",
+    "ticket",
+    "time",
+    "tin",
+    "title",
+    "toad",
+    "toe",
+    "tooth",
+    "toothpaste",
+    "touch",
+    "town",
+    "toy",
+    "trade",
+    "train",
+    "transport",
+    "tray",
+    "treatment",
+    "tree",
+    "trick",
+    "trip",
+    "trouble",
+    "trousers",
+    "truck",
+    "tub",
+    "turkey",
+    "turn",
+    "twist",
+    "umbrella",
+    "uncle",
+    "underwear",
+    "unit",
+    "use",
+    "vacation",
+    "value",
+    "van",
+    "vase",
+    "vegetable",
+    "veil",
+    "vein",
+    "verse",
+    "vessel",
+    "view",
+    "visitor",
+    "voice",
+    "volcano",
+    "walk",
+    "wall",
+    "war",
+    "wash",
+    "waste",
+    "watch",
+    "water",
+    "wave",
+    "wax",
+    "way",
+    "wealth",
+    "weather",
+    "week",
+    "weight",
+    "wheel",
+    "whip",
+    "whistle",
+    "window",
+    "wine",
+    "wing",
+    "winter",
+    "wire",
+    "wish",
+    "woman",
+    "wood",
+    "wool",
+    "word",
+    "work",
+    "worm",
+    "wound",
+    "wrist",
+    "writer",
+    "yard",
+    "yoke",
+    "zebra",
+    "zinc",
+    "zipper",
+    "zone",
+]
+
+
+def random_name(prefix: str = "test") -> str:
+    """Generate a random name."""
+    adjective = random.choice(adjectives)
+    noun = random.choice(nouns)
+    number = random.randint(1, 100)
+
+    return f"{prefix}-{adjective}-{noun}-{number}"

libs/langchain/langchain/smith/evaluation/progress.py

@@ -0,0 +1,82 @@
+"""A simple progress bar for the console."""
+import threading
+from typing import Any, Dict, Optional, Sequence
+from uuid import UUID
+
+from langchain.callbacks import base as base_callbacks
+from langchain.schema.document import Document
+from langchain.schema.output import LLMResult
+
+
+class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
+    """A simple progress bar for the console."""
+
+    def __init__(self, total: int, ncols: int = 50, **kwargs: Any):
+        """Initialize the progress bar.
+
+        Args:
+            total: int, the total number of items to be processed.
+            ncols: int, the character width of the progress bar.
+        """
+        self.total = total
+        self.ncols = ncols
+        self.counter = 0
+        self.lock = threading.Lock()
+        self._print_bar()
+
+    def increment(self) -> None:
+        """Increment the counter and update the progress bar."""
+        with self.lock:
+            self.counter += 1
+            self._print_bar()
+
+    def _print_bar(self) -> None:
+        """Print the progress bar to the console."""
+        progress = self.counter / self.total
+        arrow = "-" * int(round(progress * self.ncols) - 1) + ">"
+        spaces = " " * (self.ncols - len(arrow))
+        print(f"\r[{arrow + spaces}] {self.counter}/{self.total}", end="")
+
+    def on_chain_end(
+        self,
+        outputs: Dict[str, Any],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        if parent_run_id is None:
+            self.increment()
+
+    def on_retriever_end(
+        self,
+        documents: Sequence[Document],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        if parent_run_id is None:
+            self.increment()
+
+    def on_llm_end(
+        self,
+        response: LLMResult,
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        if parent_run_id is None:
+            self.increment()
+
+    def on_tool_end(
+        self,
+        output: str,
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        if parent_run_id is None:
+            self.increment()

libs/langchain/langchain/smith/evaluation/string_run_evaluator.py

@@ -148,13 +148,27 @@ class ChainStringRunMapper(StringRunMapper):
     def map(self, run: Run) -> Dict[str, str]:
         """Maps the Run to a dictionary."""
         if not run.outputs:
-            raise ValueError(f"Run {run.id} has no outputs to evaluate.")
-        if self.input_key is not None and self.input_key not in run.inputs:
-            raise ValueError(f"Run {run.id} does not have input key {self.input_key}.")
-        elif self.prediction_key is not None and self.prediction_key not in run.outputs:
             raise ValueError(
-                f"Run {run.id} does not have prediction key {self.prediction_key}."
+                f"Run with ID {run.id} lacks outputs required for evaluation."
+                " Ensure the Run has valid outputs."
             )
+        if self.input_key is not None and self.input_key not in run.inputs:
+            raise ValueError(
+                f"Run with ID {run.id} is missing the expected input key"
+                f" '{self.input_key}'.\nAvailable input keys in this Run"
+                f"  are: {run.inputs.keys()}.\nAdjust the evaluator's"
+                f" input_key or ensure your input data includes key"
+                f" '{self.input_key}'."
+            )
+        elif self.prediction_key is not None and self.prediction_key not in run.outputs:
+            available_keys = ", ".join(run.outputs.keys())
+            raise ValueError(
+                f"Run with ID {run.id} doesn't have the expected prediction key"
+                f" '{self.prediction_key}'. Available prediction keys in this Run are:"
+                f" {available_keys}. Adjust the evaluator's prediction_key or"
+                " ensure the Run object's outputs the expected key."
+            )
+
         else:
             input_ = self._get_key(run.inputs, self.input_key, "input")
             prediction = self._get_key(run.outputs, self.prediction_key, "prediction")

libs/langchain/langchain/tools/base.py

@@ -592,7 +592,7 @@ class StructuredTool(BaseTool):
                 None, partial(self.invoke, input, config, **kwargs)
             )
 
-        return super().ainvoke(input, config, **kwargs)
+        return await super().ainvoke(input, config, **kwargs)
 
     # --- Tool ---
 

libs/langchain/langchain/tools/sql_database/tool.py

@@ -93,7 +93,7 @@ class QuerySQLCheckerTool(BaseSQLDatabaseTool, BaseTool):
     name: str = "sql_db_query_checker"
     description: str = """
     Use this tool to double check if your query is correct before executing it.
-    Always use this tool before executing a query with query_sql_db!
+    Always use this tool before executing a query with sql_db_query!
     """
 
     @root_validator(pre=True)

libs/langchain/langchain/vectorstores/supabase.py

@@ -199,18 +199,31 @@ class SupabaseVectorStore(VectorStore):
         )
 
     def match_args(
-        self, query: List[float], k: int, filter: Optional[Dict[str, Any]]
+        self, query: List[float], filter: Optional[Dict[str, Any]]
     ) -> Dict[str, Any]:
-        ret = dict(query_embedding=query, match_count=k)
+        ret: Dict[str, Any] = dict(query_embedding=query)
         if filter:
             ret["filter"] = filter
         return ret
 
     def similarity_search_by_vector_with_relevance_scores(
-        self, query: List[float], k: int, filter: Optional[Dict[str, Any]] = None
+        self,
+        query: List[float],
+        k: int,
+        filter: Optional[Dict[str, Any]] = None,
+        postgrest_filter: Optional[str] = None,
     ) -> List[Tuple[Document, float]]:
-        match_documents_params = self.match_args(query, k, filter)
-        res = self._client.rpc(self.query_name, match_documents_params).execute()
+        match_documents_params = self.match_args(query, filter)
+        query_builder = self._client.rpc(self.query_name, match_documents_params)
+
+        if postgrest_filter:
+            query_builder.params = query_builder.params.set(
+                "and", f"({postgrest_filter})"
+            )
+
+        query_builder.params = query_builder.params.set("limit", k)
+
+        res = query_builder.execute()
 
         match_result = [
             (
@@ -227,10 +240,23 @@ class SupabaseVectorStore(VectorStore):
         return match_result
 
     def similarity_search_by_vector_returning_embeddings(
-        self, query: List[float], k: int, filter: Optional[Dict[str, Any]] = None
+        self,
+        query: List[float],
+        k: int,
+        filter: Optional[Dict[str, Any]] = None,
+        postgrest_filter: Optional[str] = None,
     ) -> List[Tuple[Document, float, np.ndarray[np.float32, Any]]]:
-        match_documents_params = self.match_args(query, k, filter)
-        res = self._client.rpc(self.query_name, match_documents_params).execute()
+        match_documents_params = self.match_args(query, filter)
+        query_builder = self._client.rpc(self.query_name, match_documents_params)
+
+        if postgrest_filter:
+            query_builder.params = query_builder.params.set(
+                "and", f"({postgrest_filter})"
+            )
+
+        query_builder.params = query_builder.params.set("limit", k)
+
+        res = query_builder.execute()
 
         match_result = [
             (

libs/langchain/langchain/vectorstores/vectara.py

@@ -396,8 +396,12 @@ class Vectara(VectorStore):
                     vectara_api_key=api_key,
                 )
         """
-        # Note: Vectara generates its own embeddings, so we ignore the provided
-        # embeddings (required by interface)
+        # Notes:
+        # * Vectara generates its own embeddings, so we ignore the provided
+        #   embeddings (required by interface)
+        # * when metadatas[] are provided they are associated with each "part"
+        #   in Vectara. doc_metadata can be used to provide additional metadata
+        #   for the document itself (applies to all "texts" in this call)
         doc_metadata = kwargs.pop("doc_metadata", {})
         vectara = cls(**kwargs)
         vectara.add_texts(texts, metadatas, doc_metadata=doc_metadata, **kwargs)

libs/langchain/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain"
-version = "0.0.284"
+version = "0.0.285"
 description = "Building applications with LLMs through composability"
 authors = []
 license = "MIT"

libs/langchain/tests/integration_tests/chat_models/test_konko.py

@@ -0,0 +1,178 @@
+"""Evaluate ChatKonko Interface."""
+from typing import Any
+
+import pytest
+
+from langchain.callbacks.manager import CallbackManager
+from langchain.chat_models.konko import ChatKonko
+from langchain.schema import (
+    ChatGeneration,
+    ChatResult,
+    LLMResult,
+)
+from langchain.schema.messages import BaseMessage, HumanMessage, SystemMessage
+from tests.unit_tests.callbacks.fake_callback_handler import FakeCallbackHandler
+
+
+def test_konko_chat_test() -> None:
+    """Evaluate basic ChatKonko functionality."""
+    chat_instance = ChatKonko(max_tokens=10)
+    msg = HumanMessage(content="Hi")
+    chat_response = chat_instance([msg])
+    assert isinstance(chat_response, BaseMessage)
+    assert isinstance(chat_response.content, str)
+
+
+def test_konko_chat_test_openai() -> None:
+    """Evaluate basic ChatKonko functionality."""
+    chat_instance = ChatKonko(max_tokens=10, model="gpt-3.5-turbo")
+    msg = HumanMessage(content="Hi")
+    chat_response = chat_instance([msg])
+    assert isinstance(chat_response, BaseMessage)
+    assert isinstance(chat_response.content, str)
+
+
+def test_konko_model_test() -> None:
+    """Check how ChatKonko manages model_name."""
+    chat_instance = ChatKonko(model="alpha")
+    assert chat_instance.model == "alpha"
+    chat_instance = ChatKonko(model="beta")
+    assert chat_instance.model == "beta"
+
+
+def test_konko_available_model_test() -> None:
+    """Check how ChatKonko manages model_name."""
+    chat_instance = ChatKonko(max_tokens=10, n=2)
+    res = chat_instance.get_available_models()
+    assert isinstance(res, set)
+
+
+def test_konko_system_msg_test() -> None:
+    """Evaluate ChatKonko's handling of system messages."""
+    chat_instance = ChatKonko(max_tokens=10)
+    sys_msg = SystemMessage(content="Initiate user chat.")
+    user_msg = HumanMessage(content="Hi there")
+    chat_response = chat_instance([sys_msg, user_msg])
+    assert isinstance(chat_response, BaseMessage)
+    assert isinstance(chat_response.content, str)
+
+
+def test_konko_generation_test() -> None:
+    """Check ChatKonko's generation ability."""
+    chat_instance = ChatKonko(max_tokens=10, n=2)
+    msg = HumanMessage(content="Hi")
+    gen_response = chat_instance.generate([[msg], [msg]])
+    assert isinstance(gen_response, LLMResult)
+    assert len(gen_response.generations) == 2
+    for gen_list in gen_response.generations:
+        assert len(gen_list) == 2
+        for gen in gen_list:
+            assert isinstance(gen, ChatGeneration)
+            assert isinstance(gen.text, str)
+            assert gen.text == gen.message.content
+
+
+def test_konko_multiple_outputs_test() -> None:
+    """Test multiple completions with ChatKonko."""
+    chat_instance = ChatKonko(max_tokens=10, n=5)
+    msg = HumanMessage(content="Hi")
+    gen_response = chat_instance._generate([msg])
+    assert isinstance(gen_response, ChatResult)
+    assert len(gen_response.generations) == 5
+    for gen in gen_response.generations:
+        assert isinstance(gen.message, BaseMessage)
+        assert isinstance(gen.message.content, str)
+
+
+def test_konko_streaming_callback_test() -> None:
+    """Evaluate streaming's token callback functionality."""
+    callback_instance = FakeCallbackHandler()
+    callback_mgr = CallbackManager([callback_instance])
+    chat_instance = ChatKonko(
+        max_tokens=10,
+        streaming=True,
+        temperature=0,
+        callback_manager=callback_mgr,
+        verbose=True,
+    )
+    msg = HumanMessage(content="Hi")
+    chat_response = chat_instance([msg])
+    assert callback_instance.llm_streams > 0
+    assert isinstance(chat_response, BaseMessage)
+
+
+def test_konko_streaming_info_test() -> None:
+    """Ensure generation details are retained during streaming."""
+
+    class TestCallback(FakeCallbackHandler):
+        data_store: dict = {}
+
+        def on_llm_end(self, *args: Any, **kwargs: Any) -> Any:
+            self.data_store["generation"] = args[0]
+
+    callback_instance = TestCallback()
+    callback_mgr = CallbackManager([callback_instance])
+    chat_instance = ChatKonko(
+        max_tokens=2,
+        temperature=0,
+        callback_manager=callback_mgr,
+    )
+    list(chat_instance.stream("hey"))
+    gen_data = callback_instance.data_store["generation"]
+    assert gen_data.generations[0][0].text == " Hey"
+
+
+def test_konko_llm_model_name_test() -> None:
+    """Check if llm_output has model info."""
+    chat_instance = ChatKonko(max_tokens=10)
+    msg = HumanMessage(content="Hi")
+    llm_data = chat_instance.generate([[msg]])
+    assert llm_data.llm_output is not None
+    assert llm_data.llm_output["model_name"] == chat_instance.model
+
+
+def test_konko_streaming_model_name_test() -> None:
+    """Check model info during streaming."""
+    chat_instance = ChatKonko(max_tokens=10, streaming=True)
+    msg = HumanMessage(content="Hi")
+    llm_data = chat_instance.generate([[msg]])
+    assert llm_data.llm_output is not None
+    assert llm_data.llm_output["model_name"] == chat_instance.model
+
+
+def test_konko_streaming_param_validation_test() -> None:
+    """Ensure correct token callback during streaming."""
+    with pytest.raises(ValueError):
+        ChatKonko(
+            max_tokens=10,
+            streaming=True,
+            temperature=0,
+            n=5,
+        )
+
+
+def test_konko_additional_args_test() -> None:
+    """Evaluate extra arguments for ChatKonko."""
+    chat_instance = ChatKonko(extra=3, max_tokens=10)
+    assert chat_instance.max_tokens == 10
+    assert chat_instance.model_kwargs == {"extra": 3}
+
+    chat_instance = ChatKonko(extra=3, model_kwargs={"addition": 2})
+    assert chat_instance.model_kwargs == {"extra": 3, "addition": 2}
+
+    with pytest.raises(ValueError):
+        ChatKonko(extra=3, model_kwargs={"extra": 2})
+
+    with pytest.raises(ValueError):
+        ChatKonko(model_kwargs={"temperature": 0.2})
+
+    with pytest.raises(ValueError):
+        ChatKonko(model_kwargs={"model": "text-davinci-003"})
+
+
+def test_konko_token_streaming_test() -> None:
+    """Check token streaming for ChatKonko."""
+    chat_instance = ChatKonko(max_tokens=10)
+
+    for token in chat_instance.stream("Just a test"):
+        assert isinstance(token.content, str)

libs/langchain/tests/integration_tests/document_loaders/test_polars_dataframe.py

@@ -34,8 +34,6 @@ def test_load_returns_list_of_documents(sample_data_frame: pl.DataFrame) -> None
 def test_load_converts_dataframe_columns_to_document_metadata(
     sample_data_frame: pl.DataFrame,
 ) -> None:
-    import polars as pl
-
     loader = PolarsDataFrameLoader(sample_data_frame)
     docs = loader.load()
 

libs/langchain/tests/integration_tests/smith/evaluation/test_runner_utils.py

@@ -5,7 +5,6 @@ import pytest
 from langsmith import Client as Client
 from langsmith.schemas import DataType
 
-from langchain.callbacks.tracers.evaluation import wait_for_all_evaluators
 from langchain.chains.llm import LLMChain
 from langchain.chat_models import ChatOpenAI
 from langchain.evaluation import EvaluatorType
@@ -22,7 +21,6 @@ def _check_all_feedback_passed(_project_name: str, client: Client) -> None:
     # chain or llm passes for the feedback provided.
     runs = list(client.list_runs(project_name=_project_name, execution_order=1))
     assert len(runs) == 4
-    wait_for_all_evaluators()
     feedback = list(client.list_feedback(run_ids=[run.id for run in runs]))
     assert len(feedback) == 8
     assert all([f.score == 1 for f in feedback])

libs/langchain/tests/unit_tests/retrievers/self_query/test_supabase.py

@@ -0,0 +1,85 @@
+from typing import Dict, Tuple
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+)
+from langchain.retrievers.self_query.supabase import SupabaseVectorTranslator
+
+DEFAULT_TRANSLATOR = SupabaseVectorTranslator()
+
+
+def test_visit_comparison() -> None:
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value=["1", "2"])
+    expected = "and(metadata->>foo.lt.1,metadata->>foo.lt.2)"
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_operation() -> None:
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.LT, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+            Comparison(comparator=Comparator.LT, attribute="abc", value=["1", "2"]),
+        ],
+    )
+    expected = (
+        "and("
+        "metadata->foo.lt.2,"
+        "metadata->>bar.eq.baz,"
+        "and(metadata->>abc.lt.1,metadata->>abc.lt.2)"
+        ")"
+    )
+    actual = DEFAULT_TRANSLATOR.visit_operation(op)
+    assert expected == actual
+
+
+def test_visit_structured_query() -> None:
+    query = "What is the capital of France?"
+    structured_query = StructuredQuery(
+        query=query,
+        filter=None,
+    )
+    expected: Tuple[str, Dict] = (query, {})
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value=["1", "2"])
+    expected = (
+        query,
+        {"postgrest_filter": "and(metadata->>foo.lt.1,metadata->>foo.lt.2)"},
+    )
+    structured_query = StructuredQuery(
+        query=query,
+        filter=comp,
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.LT, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+            Comparison(comparator=Comparator.LT, attribute="abc", value=["1", "2"]),
+        ],
+    )
+    structured_query = StructuredQuery(
+        query=query,
+        filter=op,
+    )
+    expected = (
+        query,
+        {
+            "postgrest_filter": (
+                "and(metadata->foo.lt.2,metadata->>bar.eq.baz,and(metadata->>abc.lt.1,metadata->>abc.lt.2))"
+            )
+        },
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual

libs/langchain/tests/unit_tests/retrievers/self_query/test_vectara.py

@@ -0,0 +1,71 @@
+from typing import Dict, Tuple
+
+from langchain.chains.query_constructor.ir import (
+    Comparator,
+    Comparison,
+    Operation,
+    Operator,
+    StructuredQuery,
+)
+from langchain.retrievers.self_query.vectara import VectaraTranslator
+
+DEFAULT_TRANSLATOR = VectaraTranslator()
+
+
+def test_visit_comparison() -> None:
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value="1")
+    expected = "( doc.foo < '1' )"
+    actual = DEFAULT_TRANSLATOR.visit_comparison(comp)
+    assert expected == actual
+
+
+def test_visit_operation() -> None:
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.LT, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+            Comparison(comparator=Comparator.LT, attribute="abc", value=1),
+        ],
+    )
+    expected = "( ( doc.foo < 2 ) and ( doc.bar = 'baz' ) and ( doc.abc < 1 ) )"
+    actual = DEFAULT_TRANSLATOR.visit_operation(op)
+    assert expected == actual
+
+
+def test_visit_structured_query() -> None:
+    query = "What is the capital of France?"
+    structured_query = StructuredQuery(
+        query=query,
+        filter=None,
+        limit=None,
+    )
+    expected: Tuple[str, Dict] = (query, {})
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+    comp = Comparison(comparator=Comparator.LT, attribute="foo", value=1)
+    expected = (query, {"filter": "( doc.foo < 1 )"})
+    structured_query = StructuredQuery(
+        query=query,
+        filter=comp,
+        limit=None,
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual
+
+    op = Operation(
+        operator=Operator.AND,
+        arguments=[
+            Comparison(comparator=Comparator.LT, attribute="foo", value=2),
+            Comparison(comparator=Comparator.EQ, attribute="bar", value="baz"),
+            Comparison(comparator=Comparator.LT, attribute="abc", value=1),
+        ],
+    )
+    structured_query = StructuredQuery(query=query, filter=op, limit=None)
+    expected = (
+        query,
+        {"filter": "( ( doc.foo < 2 ) and ( doc.bar = 'baz' ) and ( doc.abc < 1 ) )"},
+    )
+    actual = DEFAULT_TRANSLATOR.visit_structured_query(structured_query)
+    assert expected == actual

libs/langchain/tests/unit_tests/schema/runnable/test_runnable.py

@@ -1507,7 +1507,7 @@ async def test_async_retrying(mocker: MockerFixture) -> None:
     with pytest.raises(ValueError):
         await runnable.with_retry(
             stop_after_attempt=2,
-            retry_if_exception_type=(ValueError,),
+            retry_if_exception_type=(ValueError, KeyError),
         ).ainvoke(1)
 
     assert _lambda_mock.call_count == 2  # retried

libs/langchain/tests/unit_tests/smith/evaluation/test_runner_utils.py

@@ -181,11 +181,15 @@ def test_run_llm_or_chain_with_input_mapper() -> None:
         assert "the wrong input" in inputs
         return {"the right input": inputs["the wrong input"]}
 
-    result = _run_llm_or_chain(example, lambda: mock_chain, input_mapper=input_mapper)
+    result = _run_llm_or_chain(
+        example,
+        {"callbacks": [], "tags": []},
+        llm_or_chain_factory=lambda: mock_chain,
+        input_mapper=input_mapper,
+    )
     assert result == {"output": "2", "the right input": "1"}
     bad_result = _run_llm_or_chain(
-        example,
-        lambda: mock_chain,
+        example, {"callbacks": [], "tags": []}, llm_or_chain_factory=lambda: mock_chain
     )
     assert "Error" in bad_result
 
@@ -195,7 +199,12 @@ def test_run_llm_or_chain_with_input_mapper() -> None:
         return "the right input"
 
     mock_llm = FakeLLM(queries={"the right input": "somenumber"})
-    llm_result = _run_llm_or_chain(example, mock_llm, input_mapper=llm_input_mapper)
+    llm_result = _run_llm_or_chain(
+        example,
+        {"callbacks": [], "tags": []},
+        llm_or_chain_factory=mock_llm,
+        input_mapper=llm_input_mapper,
+    )
     assert isinstance(llm_result, str)
     assert llm_result == "somenumber"
 
@@ -324,10 +333,14 @@ async def test_arun_on_dataset(monkeypatch: pytest.MonkeyPatch) -> None:
         )
 
         expected = {
-            uuid_: {
-                "output": {"result": f"Result for example {uuid.UUID(uuid_)}"},
+            str(example.id): {
+                "output": {
+                    "result": f"Result for example {uuid.UUID(str(example.id))}"
+                },
+                "input": {"input": example.inputs["input"]},
+                "reference": {"output": example.outputs["output"]},
                 "feedback": [],
             }
-            for uuid_ in uuids
+            for example in examples
         }
         assert results["results"] == expected