bump 222 (#7086)

- Description: Added a new SpacyEmbeddings class for generating
embeddings using the Spacy library.
- Issue: Sentencebert/Bert/Spacy/Doc2vec embedding support #6952
- Dependencies: This change requires the Spacy library and the
'en_core_web_sm' Spacy model.
- Tag maintainer: @dev2049
- Twitter handle: N/A

This change includes a new SpacyEmbeddings class, but does not include a
test or an example notebook.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

.readthedocs.yaml

@@ -9,6 +9,9 @@ build:
   os: ubuntu-22.04
   tools:
     python: "3.11"
+  jobs:
+    pre_build:
+      - python docs/api_reference/create_api_rst.py
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:

docs/api_reference/_static/js/mendablesearch.js

@@ -1,57 +0,0 @@
-document.addEventListener('DOMContentLoaded', () => {
-  // Load the external dependencies
-  function loadScript(src, onLoadCallback) {
-    const script = document.createElement('script');
-    script.src = src;
-    script.onload = onLoadCallback;
-    document.head.appendChild(script);
-  }
-
-  function createRootElement() {
-    const rootElement = document.createElement('div');
-    rootElement.id = 'my-component-root';
-    document.body.appendChild(rootElement);
-    return rootElement;
-  }
-
-  
-
-  function initializeMendable() {
-    const rootElement = createRootElement();
-    const { MendableFloatingButton } = Mendable;
-    
-
-    const iconSpan1 = React.createElement('span', {
-    }, '🦜');
-
-    const iconSpan2 = React.createElement('span', {
-    }, '🔗');
-
-    const icon = React.createElement('p', {
-      style: { color: '#ffffff', fontSize: '22px',width: '48px', height: '48px', margin: '0px', padding: '0px', display: 'flex', alignItems: 'center', justifyContent: 'center', textAlign: 'center' },
-    }, [iconSpan1, iconSpan2]);
-    
-    const mendableFloatingButton = React.createElement(
-      MendableFloatingButton,
-      {
-        style: { darkMode: false, accentColor: '#010810' },
-        floatingButtonStyle: { color: '#ffffff', backgroundColor: '#010810' },
-        anon_key: '82842b36-3ea6-49b2-9fb8-52cfc4bde6bf', // Mendable Search Public ANON key, ok to be public
-        cmdShortcutKey:'j',
-        messageSettings: {
-          openSourcesInNewTab: false,
-          prettySources: true // Prettify the sources displayed now
-        },
-        icon: icon,
-      }
-    );
-
-    ReactDOM.render(mendableFloatingButton, rootElement);
-  }
-
-  loadScript('https://unpkg.com/react@17/umd/react.production.min.js', () => {
-    loadScript('https://unpkg.com/react-dom@17/umd/react-dom.production.min.js', () => {
-      loadScript('https://unpkg.com/@mendable/search@0.0.102/dist/umd/mendable.min.js', initializeMendable);
-    });
-  });
-});

docs/api_reference/agents.rst

@@ -1,12 +0,0 @@
-Agents
-==============
-
-Reference guide for Agents and associated abstractions.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   modules/agents
-   modules/tools
-   modules/agent_toolkits

docs/api_reference/conf.py

@@ -11,12 +11,13 @@
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
-# import os
-# import sys
-# sys.path.insert(0, os.path.abspath('.'))
+import os
+import sys
 
 import toml
 
+sys.path.insert(0, os.path.abspath("."))
+
 with open("../../pyproject.toml") as f:
     data = toml.load(f)
 
@@ -45,11 +46,9 @@ extensions = [
     "sphinx.ext.napoleon",
     "sphinx.ext.viewcode",
     "sphinxcontrib.autodoc_pydantic",
-    "myst_nb",
     "sphinx_copybutton",
     "sphinx_panels",
     "IPython.sphinxext.ipython_console_highlighting",
-    "sphinx_tabs.tabs",
 ]
 source_suffix = [".rst"]
 
@@ -59,24 +58,22 @@ autodoc_pydantic_config_members = False
 autodoc_pydantic_model_show_config_summary = False
 autodoc_pydantic_model_show_validator_members = False
 autodoc_pydantic_model_show_validator_summary = False
-autodoc_pydantic_model_show_field_summary = False
-autodoc_pydantic_model_members = False
-autodoc_pydantic_model_undoc_members = False
-autodoc_pydantic_model_hide_paramlist = False
 autodoc_pydantic_model_signature_prefix = "class"
-autodoc_pydantic_field_signature_prefix = "attribute"
-autodoc_pydantic_model_summary_list_order = "bysource"
-autodoc_member_order = "bysource"
+autodoc_pydantic_field_signature_prefix = "param"
+autodoc_member_order = "groupwise"
+autoclass_content = "both"
+autodoc_typehints_format = "short"
+
 autodoc_default_options = {
     "members": True,
     "show-inheritance": True,
-    "undoc_members": True,
-    "inherited_members": "BaseModel",
+    "inherited-members": "BaseModel",
+    "undoc-members": True,
+    "special-members": "__call__",
 }
-autodoc_typehints = "description"
-
+# autodoc_typehints = "description"
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ["_templates"]
+templates_path = ["templates"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -89,14 +86,16 @@ exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = "sphinx_rtd_theme"
+html_theme = "scikit-learn-modern"
+html_theme_path = ["themes"]
 
-html_theme_options = {
-    "path_to_docs": "docs",
-    "repository_url": "https://github.com/hwchase17/langchain",
-    "use_repository_button": True,
-    # "style_nav_header_background": "white"
+# redirects dictionary maps from old links to new links
+html_additional_pages = {}
+redirects = {
+    "index": "api_reference",
 }
+for old_link in redirects:
+    html_additional_pages[old_link] = "redirects.html"
 
 html_context = {
     "display_github": True,  # Integrate GitHub
@@ -104,6 +103,7 @@ html_context = {
     "github_repo": "langchain",  # Repo name
     "github_version": "master",  # Version
     "conf_py_path": "/docs/api_reference",  # Path in the checkout to the docs root
+    "redirects": redirects,
 }
 
 # Add any paths that contain custom static files (such as style sheets) here,
@@ -116,10 +116,9 @@ html_static_path = ["_static"]
 html_css_files = [
     "css/custom.css",
 ]
+html_use_index = False
 
-html_js_files = [
-    "js/mendablesearch.js",
-]
-
-nb_execution_mode = "off"
 myst_enable_extensions = ["colon_fence"]
+
+# generate autosummary even if no references
+autosummary_generate = True

docs/api_reference/create_api_rst.py

@@ -0,0 +1,94 @@
+"""Script for auto-generating api_reference.rst"""
+import glob
+import re
+from pathlib import Path
+
+ROOT_DIR = Path(__file__).parents[2].absolute()
+PKG_DIR = ROOT_DIR / "langchain"
+WRITE_FILE = Path(__file__).parent / "api_reference.rst"
+
+
+def load_members() -> dict:
+    members: dict = {}
+    for py in glob.glob(str(PKG_DIR) + "/**/*.py", recursive=True):
+        module = py[len(str(PKG_DIR)) + 1 :].replace(".py", "").replace("/", ".")
+        top_level = module.split(".")[0]
+        if top_level not in members:
+            members[top_level] = {"classes": [], "functions": []}
+        with open(py, "r") as f:
+            for line in f.readlines():
+                cls = re.findall(r"^class ([^_].*)\(", line)
+                members[top_level]["classes"].extend([module + "." + c for c in cls])
+                func = re.findall(r"^def ([^_].*)\(", line)
+                members[top_level]["functions"].extend([module + "." + f for f in func])
+    return members
+
+
+def construct_doc(members: dict) -> str:
+    full_doc = """\
+.. _api_reference:
+
+=============
+API Reference
+=============
+
+"""
+    for module, _members in sorted(members.items(), key=lambda kv: kv[0]):
+        classes = _members["classes"]
+        functions = _members["functions"]
+        if not (classes or functions):
+            continue
+
+        module_title = module.replace("_", " ").title()
+        if module_title == "Llms":
+            module_title = "LLMs"
+        section = f":mod:`langchain.{module}`: {module_title}"
+        full_doc += f"""\
+{section}
+{'=' * (len(section) + 1)}
+
+.. automodule:: langchain.{module}
+    :no-members:
+    :no-inherited-members:
+
+"""
+
+        if classes:
+            cstring = "\n    ".join(sorted(classes))
+            full_doc += f"""\
+Classes
+--------------
+.. currentmodule:: langchain
+
+.. autosummary::
+    :toctree: {module}
+    :template: class.rst
+
+    {cstring}
+
+"""
+        if functions:
+            fstring = "\n    ".join(sorted(functions))
+            full_doc += f"""\
+Functions
+--------------
+.. currentmodule:: langchain
+
+.. autosummary::
+    :toctree: {module}
+
+    {fstring}
+
+"""
+    return full_doc
+
+
+def main() -> None:
+    members = load_members()
+    full_doc = construct_doc(members)
+    with open(WRITE_FILE, "w") as f:
+        f.write(full_doc)
+
+
+if __name__ == "__main__":
+    main()

docs/api_reference/data_connection.rst

@@ -1,13 +0,0 @@
-Data connection
-==============
-LangChain has a number of modules that help you load, structure, store, and retrieve documents.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   modules/document_loaders
-   modules/document_transformers
-   modules/embeddings
-   modules/vectorstores
-   modules/retrievers

docs/api_reference/index.rst

@@ -1,29 +1,8 @@
-API Reference
-==========================
-
-| Full documentation on all methods, classes, and APIs in the LangChain Python package.
+=============
+LangChain API
+=============
 
 .. toctree::
-   :maxdepth: 1
-   :caption: Abstractions
+    :maxdepth: 2
 
-   ./modules/base_classes.rst
-
-
-.. toctree::
-   :maxdepth: 1
-   :caption: Core
-
-   ./model_io.rst
-   ./data_connection.rst
-   ./modules/chains.rst
-   ./agents.rst
-   ./modules/memory.rst
-   ./modules/callbacks.rst
-
-.. toctree::
-   :maxdepth: 1
-   :caption: Additional
-
-   ./modules/utilities.rst
-   ./modules/experimental.rst
+    api_reference.rst

docs/api_reference/model_io.rst

@@ -1,12 +0,0 @@
-Model I/O
-==============
-
-LangChain provides interfaces and integrations for working with language models.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   ./prompts.rst
-   ./models.rst
-   ./modules/output_parsers.rst

docs/api_reference/models.rst

@@ -1,11 +0,0 @@
-Models
-==============
-
-LangChain provides interfaces and integrations for a number of different types of models.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   modules/llms
-   modules/chat_models

docs/api_reference/modules/agent_toolkits.rst

@@ -1,7 +0,0 @@
-Agent Toolkits
-===============================
-
-.. automodule:: langchain.agents.agent_toolkits
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/agents.rst

@@ -1,7 +0,0 @@
-Agents
-===============================
-
-.. automodule:: langchain.agents
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/base_classes.rst

@@ -1,5 +0,0 @@
-Base classes
-========================
-
-.. automodule:: langchain.schema
-   :inherited-members:

docs/api_reference/modules/callbacks.rst

@@ -1,7 +0,0 @@
-Callbacks
-=======================
-
-.. automodule:: langchain.callbacks
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/chains.rst

@@ -1,8 +0,0 @@
-Chains
-=======================
-
-.. automodule:: langchain.chains
-   :members:
-   :undoc-members:
-   :inherited-members: BaseModel
-

docs/api_reference/modules/chat_models.rst

@@ -1,7 +0,0 @@
-Chat Models
-===============================
-
-.. automodule:: langchain.chat_models
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/document_loaders.rst

@@ -1,7 +0,0 @@
-Document Loaders
-===============================
-
-.. automodule:: langchain.document_loaders
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/document_transformers.rst

@@ -1,13 +0,0 @@
-Document Transformers
-===============================
-
-.. automodule:: langchain.document_transformers
-   :members:
-   :undoc-members:
-
-Text Splitters
-------------------------------
-
-.. automodule:: langchain.text_splitter
-   :members:
-   :undoc-members:

docs/api_reference/modules/embeddings.rst

@@ -1,5 +0,0 @@
-Embeddings
-===========================
-
-.. automodule:: langchain.embeddings
-   :members:

docs/api_reference/modules/example_selector.rst

@@ -1,5 +0,0 @@
-Example Selector
-=========================================
-
-.. automodule:: langchain.prompts.example_selector
-   :members:

docs/api_reference/modules/experimental.rst

@@ -1,28 +0,0 @@
-====================
-Experimental
-====================
-
-This module contains experimental modules and reproductions of existing work using LangChain primitives.
-
-Autonomous agents
-------------------
-
-Here, we document the BabyAGI and AutoGPT classes from the langchain.experimental module.
-
-.. autoclass:: langchain.experimental.BabyAGI
-   :members:
-
-.. autoclass:: langchain.experimental.AutoGPT
-   :members:
-
-
-Generative agents
-------------------
-
-Here, we document the GenerativeAgent and GenerativeAgentMemory classes from the langchain.experimental module.
-
-.. autoclass:: langchain.experimental.GenerativeAgent
-   :members:
-
-.. autoclass:: langchain.experimental.GenerativeAgentMemory
-   :members:

docs/api_reference/modules/llms.rst

@@ -1,7 +0,0 @@
-LLMs
-=======================
-
-.. automodule:: langchain.llms
-   :members:
-   :inherited-members:
-   :special-members: __call__

docs/api_reference/modules/memory.rst

@@ -1,7 +0,0 @@
-Memory
-===============================
-
-.. automodule:: langchain.memory
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/output_parsers.rst

@@ -1,7 +0,0 @@
-Output Parsers
-===============================
-
-.. automodule:: langchain.output_parsers
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/prompts.rst

@@ -1,6 +0,0 @@
-Prompt Templates
-========================
-
-.. automodule:: langchain.prompts
-   :members:
-   :undoc-members:

docs/api_reference/modules/retrievers.rst

@@ -1,14 +0,0 @@
-Retrievers
-===============================
-
-.. automodule:: langchain.retrievers
-   :members:
-   :undoc-members:
-
-Document compressors
--------------------------------
-
-.. automodule:: langchain.retrievers.document_compressors
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/tools.rst

@@ -1,7 +0,0 @@
-Tools
-===============================
-
-.. automodule:: langchain.tools
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/utilities.rst

@@ -1,7 +0,0 @@
-Utilities
-===============================
-
-.. automodule:: langchain.utilities
-   :members:
-   :undoc-members:
-

docs/api_reference/modules/vectorstores.rst

@@ -1,6 +0,0 @@
-Vector Stores
-=============================
-
-.. automodule:: langchain.vectorstores
-   :members:
-   :undoc-members:

docs/api_reference/prompts.rst

@@ -1,11 +0,0 @@
-Prompts
-==============
-
-The reference guides here all relate to objects for working with Prompts.
-
-.. toctree::
-   :maxdepth: 1
-   :glob:
-
-   modules/prompts
-   modules/example_selector

docs/api_reference/templates/COPYRIGHT.txt

@@ -0,0 +1,27 @@
+Copyright (c) 2007-2023 The scikit-learn developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

docs/api_reference/templates/class.rst

@@ -0,0 +1,28 @@
+:mod:`{{module}}`.{{objname}}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+   {% block methods %}
+   {% if methods %}
+   .. rubric:: {{ _('Methods') }}
+
+   .. autosummary::
+   {% for item in methods %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+   {% endif %}
+   {% endblock %}
+
+   {% block attributes %}
+   {% if attributes %}
+   .. rubric:: {{ _('Attributes') }}
+
+   .. autosummary::
+   {% for item in attributes %}
+      ~{{ name }}.{{ item }}
+   {%- endfor %}
+   {% endif %}
+   {% endblock %}

docs/api_reference/templates/redirects.html

@@ -0,0 +1,15 @@
+{% set redirect = pathto(redirects[pagename]) %}
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <meta http-equiv="Refresh" content="0; url={{ redirect }}" />
+    <meta name="Description" content="scikit-learn: machine learning in Python">
+    <link rel="canonical" href="{{ redirect }}" />
+    <title>scikit-learn: machine learning in Python</title>
+  </head>
+  <body>
+    <p>You will be automatically redirected to the <a href="{{ redirect }}">new location of this page</a>.</p>
+  </body>
+</html>

docs/api_reference/themes/COPYRIGHT.txt

@@ -0,0 +1,27 @@
+Copyright (c) 2007-2023 The scikit-learn developers.
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are met:
+
+* Redistributions of source code must retain the above copyright notice, this
+  list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright notice,
+  this list of conditions and the following disclaimer in the documentation
+  and/or other materials provided with the distribution.
+
+* Neither the name of the copyright holder nor the names of its
+  contributors may be used to endorse or promote products derived from
+  this software without specific prior written permission.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
+FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
+SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
+CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

docs/api_reference/themes/scikit-learn-modern/javascript.html

@@ -0,0 +1,67 @@
+<script>
+$(document).ready(function() {
+    /* Add a [>>>] button on the top-right corner of code samples to hide
+     * the >>> and ... prompts and the output and thus make the code
+     * copyable. */
+    var div = $('.highlight-python .highlight,' +
+                '.highlight-python3 .highlight,' +
+                '.highlight-pycon .highlight,' +
+		'.highlight-default .highlight')
+    var pre = div.find('pre');
+
+    // get the styles from the current theme
+    pre.parent().parent().css('position', 'relative');
+    var hide_text = 'Hide prompts and outputs';
+    var show_text = 'Show prompts and outputs';
+
+    // create and add the button to all the code blocks that contain >>>
+    div.each(function(index) {
+        var jthis = $(this);
+        if (jthis.find('.gp').length > 0) {
+            var button = $('<span class="copybutton">&gt;&gt;&gt;</span>');
+            button.attr('title', hide_text);
+            button.data('hidden', 'false');
+            jthis.prepend(button);
+        }
+        // tracebacks (.gt) contain bare text elements that need to be
+        // wrapped in a span to work with .nextUntil() (see later)
+        jthis.find('pre:has(.gt)').contents().filter(function() {
+            return ((this.nodeType == 3) && (this.data.trim().length > 0));
+        }).wrap('<span>');
+    });
+
+    // define the behavior of the button when it's clicked
+    $('.copybutton').click(function(e){
+        e.preventDefault();
+        var button = $(this);
+        if (button.data('hidden') === 'false') {
+            // hide the code output
+            button.parent().find('.go, .gp, .gt').hide();
+            button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'hidden');
+            button.css('text-decoration', 'line-through');
+            button.attr('title', show_text);
+            button.data('hidden', 'true');
+        } else {
+            // show the code output
+            button.parent().find('.go, .gp, .gt').show();
+            button.next('pre').find('.gt').nextUntil('.gp, .go').css('visibility', 'visible');
+            button.css('text-decoration', 'none');
+            button.attr('title', hide_text);
+            button.data('hidden', 'false');
+        }
+    });
+
+	/*** Add permalink buttons next to glossary terms ***/
+	$('dl.glossary > dt[id]').append(function() {
+		return ('<a class="headerlink" href="#' +
+			    this.getAttribute('id') +
+			    '" title="Permalink to this term">¶</a>');
+	});
+});
+
+</script>
+{%- if pagename != 'index' and pagename != 'documentation' %}
+    {% if theme_mathjax_path %}
+<script id="MathJax-script" async src="{{ theme_mathjax_path }}"></script>
+    {% endif %}
+{%- endif %}

docs/api_reference/themes/scikit-learn-modern/layout.html

@@ -0,0 +1,142 @@
+{# TEMPLATE VAR SETTINGS #}
+{%- set url_root = pathto('', 1) %}
+{%- if url_root == '#' %}{% set url_root = '' %}{% endif %}
+{%- if not embedded and docstitle %}
+  {%- set titlesuffix = " — "|safe + docstitle|e %}
+{%- else %}
+  {%- set titlesuffix = "" %}
+{%- endif %}
+{%- set lang_attr = 'en' %}
+
+<!DOCTYPE html>
+<!--[if IE 8]><html class="no-js lt-ie9" lang="{{ lang_attr }}" > <![endif]-->
+<!--[if gt IE 8]><!--> <html class="no-js" lang="{{ lang_attr }}" > <!--<![endif]-->
+<head>
+  <meta charset="utf-8">
+  {{ metatags }}
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+
+  {% block htmltitle %}
+  <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
+  {% endblock %}
+  <link rel="canonical" href="http://scikit-learn.org/stable/{{pagename}}.html" />
+
+  {% if favicon_url %}
+  <link rel="shortcut icon" href="{{ favicon_url|e }}"/>
+  {% endif %}
+
+  <link rel="stylesheet" href="{{ pathto('_static/css/vendor/bootstrap.min.css', 1) }}" type="text/css" />
+  {%- for css in css_files %}
+    {%- if css|attr("rel") %}
+  <link rel="{{ css.rel }}" href="{{ pathto(css.filename, 1) }}" type="text/css"{% if css.title is not none %} title="{{ css.title }}"{% endif %} />
+    {%- else %}
+  <link rel="stylesheet" href="{{ pathto(css, 1) }}" type="text/css" />
+    {%- endif %}
+  {%- endfor %}
+  <link rel="stylesheet" href="{{ pathto('_static/' + style, 1) }}" type="text/css" />
+<script id="documentation_options" data-url_root="{{ pathto('', 1) }}" src="{{ pathto('_static/documentation_options.js', 1) }}"></script>
+<script src="{{ pathto('_static/jquery.js', 1) }}"></script>
+{%- block extrahead %} {% endblock %}
+</head>
+<body>
+{% include "nav.html" %}
+{%- block content %}
+<div class="d-flex" id="sk-doc-wrapper">
+    <input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
+    <label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary" for="sk-toggle-checkbox">Toggle Menu</label>
+    <div id="sk-sidebar-wrapper" class="border-right">
+      <div class="sk-sidebar-toc-wrapper">
+        <div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
+          {%- if prev %}
+            <a href="{{ prev.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ prev.title|striptags }}">Prev</a>
+          {%- else %}
+            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Prev</a>
+          {%- endif %}
+          {%- if parents -%}
+            <a href="{{ parents[-1].link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ parents[-1].title|striptags }}">Up</a>
+          {%- else %}
+            <a href="#" role="button" class="btn sk-btn-rellink disabled py-1">Up</a>
+          {%- endif %}
+          {%- if next %}
+            <a href="{{ next.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ next.title|striptags }}">Next</a>
+          {%- else %}
+            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Next</a>
+          {%- endif %}
+        </div>
+        {%- if pagename != "install" %}
+        <div class="alert alert-warning p-1 mb-2" role="alert">
+          <p class="text-center mb-0">
+          <strong>LangChain {{ release }}</strong><br/>
+          </p>
+        </div>
+        {%- endif %}
+            {%- if meta and meta['parenttoc']|tobool %}
+            <div class="sk-sidebar-toc">
+            {% set nav = get_nav_object(maxdepth=3, collapse=True, numbered=True) %}
+              <ul>
+              {% for main_nav_item in nav %}
+              {% if main_nav_item.active %}
+              <li>
+                <a href="{{ main_nav_item.url }}" class="sk-toc-active">{{ main_nav_item.title }}</a>
+              </li>
+              <ul>
+              {% for nav_item in main_nav_item.children %}
+                <li>
+                  <a href="{{ nav_item.url }}" class="{% if nav_item.active %}sk-toc-active{% endif %}">{{ nav_item.title }}</a>
+                  {% if nav_item.children %}
+                  <ul>
+                    {% for inner_child in nav_item.children %}
+                      <li class="sk-toctree-l3">
+                        <a href="{{ inner_child.url }}">{{ inner_child.title }}</a>
+                      </li>
+                    {% endfor %}
+                  </ul>
+                  {% endif %}
+                </li>
+              {% endfor %}
+              </ul>
+              {% endif %}
+              {% endfor %}
+              </ul>
+            </div>
+            {%- elif meta and meta['globalsidebartoc']|tobool %}
+            <div class="sk-sidebar-toc sk-sidebar-global-toc">
+              {{ toctree(maxdepth=2, titles_only=True) }}
+            </div>
+            {%- else %}
+            <div class="sk-sidebar-toc">
+              {{ toc }}
+            </div>
+            {%- endif %}
+      </div>
+    </div>
+    <div id="sk-page-content-wrapper">
+      <div class="sk-page-content container-fluid body px-md-3" role="main">
+        {% block body %}{% endblock %}
+      </div>
+    <div class="container">
+      <footer class="sk-content-footer">
+        {%- if pagename != 'index' %}
+        {%- if show_copyright %}
+          {%- if hasdoc('copyright') %}
+            {% trans path=pathto('copyright'), copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
+          {%- else %}
+            {% trans copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
+          {%- endif %}
+        {%- endif %}
+        {%- if last_updated %}
+          {% trans last_updated=last_updated|e %}Last updated on {{ last_updated }}.{% endtrans %}
+        {%- endif %}
+        {%- if show_source and has_source and sourcename %}
+          <a href="{{ pathto('_sources/' + sourcename, true)|e }}" rel="nofollow">{{ _('Show this page source') }}</a>
+        {%- endif %}
+        {%- endif %}
+      </footer>
+    </div>
+  </div>
+</div>
+{%- endblock %}
+<script src="{{ pathto('_static/js/vendor/bootstrap.min.js', 1) }}"></script>
+{% include "javascript.html" %}
+</body>
+</html>

docs/api_reference/themes/scikit-learn-modern/nav.html

@@ -0,0 +1,85 @@
+{%- if pagename != 'index' and pagename != 'documentation' %}
+  {%- set nav_bar_class = "sk-docs-navbar" %}
+  {%- set top_container_cls = "sk-docs-container" %}
+{%- else %}
+  {%- set nav_bar_class = "sk-landing-navbar" %}
+  {%- set top_container_cls = "sk-landing-container" %}
+{%- endif %}
+
+{% if theme_link_to_live_contributing_page|tobool %}
+{# Link to development page for live builds #}
+  {%- set development_link = "https://scikit-learn.org/dev/developers/index.html" %}
+{# Open on a new development page in new window/tab for live builds #}
+  {%- set development_attrs = 'target="_blank" rel="noopener noreferrer"' %}
+{%- else %}
+  {%- set development_link = pathto('developers/index') %}
+  {%- set development_attrs = '' %}
+{%- endif %}
+
+{# title, link, link_attrs #}
+{%- set drop_down_navigation = [
+  ('Getting Started', pathto('getting_started'), ''),
+  ('Tutorial', pathto('tutorial/index'), ''),
+  ("What's new", pathto('whats_new/v' + version), ''),
+  ('Glossary', pathto('glossary'), ''),
+  ('Development', development_link, development_attrs),
+  ('FAQ', pathto('faq'), ''),
+  ('Support', pathto('support'), ''),
+  ('Related packages', pathto('related_projects'), ''),
+  ('Roadmap', pathto('roadmap'), ''),
+  ('Governance', pathto('governance'), ''),
+  ('About us', pathto('about'), ''),
+  ('GitHub', 'https://github.com/scikit-learn/scikit-learn', ''),
+  ('Other Versions and Download', 'https://scikit-learn.org/dev/versions.html', '')]
+-%}
+
+<nav id="navbar" class="{{ nav_bar_class }} navbar navbar-expand-md navbar-light bg-light py-0">
+  <div class="container-fluid {{ top_container_cls }} px-0">
+    {%- if logo_url %}
+      <a class="navbar-brand py-0" href="{{ pathto('index') }}">
+        <img
+          class="sk-brand-img"
+          src="{{ logo_url|e }}"
+          alt="logo"/>
+      </a>
+    {%- endif %}
+    <button
+      id="sk-navbar-toggler"
+      class="navbar-toggler"
+      type="button"
+      data-toggle="collapse"
+      data-target="#navbarSupportedContent"
+      aria-controls="navbarSupportedContent"
+      aria-expanded="false"
+      aria-label="Toggle navigation"
+    >
+      <span class="navbar-toggler-icon"></span>
+    </button>
+
+    <div class="sk-navbar-collapse collapse navbar-collapse" id="navbarSupportedContent">
+      <ul class="navbar-nav mr-auto">
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link" href="{{ pathto('api_reference') }}">API</a>
+        </li>
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://python.langchain.com/">Python Docs</a>
+        </li>
+        {%- for title, link, link_attrs in drop_down_navigation %}
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link nav-more-item-mobile-items" href="{{ link }}" {{ link_attrs }}>{{ title }}</a>
+        </li>
+        {%- endfor %}
+      </ul>
+      {%- if pagename != "search"%}
+      <div id="searchbox" role="search">
+          <div class="searchformwrapper">
+          <form class="search" action="{{ pathto('search') }}" method="get">
+            <input class="sk-search-text-input" type="text" name="q" aria-labelledby="searchlabel" />
+            <input class="sk-search-text-btn" type="submit" value="{{ _('Go') }}" />
+          </form>
+          </div>
+      </div>
+      {%- endif %}
+    </div>
+  </div>
+</nav>

docs/api_reference/themes/scikit-learn-modern/search.html

@@ -0,0 +1,16 @@
+{%- extends "basic/search.html" %}
+{% block extrahead %}
+  <script type="text/javascript" src="{{ pathto('_static/underscore.js', 1) }}"></script>
+  <script type="text/javascript" src="{{ pathto('searchindex.js', 1) }}" defer></script>
+  <script type="text/javascript" src="{{ pathto('_static/doctools.js', 1) }}"></script>
+  <script type="text/javascript" src="{{ pathto('_static/language_data.js', 1) }}"></script>
+  <script type="text/javascript" src="{{ pathto('_static/searchtools.js', 1) }}"></script>
+  <!-- <script type="text/javascript" src="{{ pathto('_static/sphinx_highlight.js', 1) }}"></script> -->
+  <script type="text/javascript">
+    $(document).ready(function() {
+      if (!Search.out) {
+        Search.init();
+      }
+    });
+  </script>
+{% endblock %}

docs/api_reference/themes/scikit-learn-modern/theme.conf

@@ -0,0 +1,8 @@
+[theme]
+inherit = basic
+pygments_style = default
+stylesheet = css/theme.css
+
+[options]
+link_to_live_contributing_page = false
+mathjax_path =

docs/docs_skeleton/docs/get_started/quickstart.mdx

@@ -47,7 +47,7 @@ import ChatModel from "@snippets/get_started/quickstart/chat_model.mdx"
 
 ## Prompt templates
 
-Most LLM applications do not pass user input directly into to an LLM. Usually they will add the user input to a larger piece of text, called a prompt template, that provides additional context on the specific task at hand.
+Most LLM applications do not pass user input directly into an LLM. Usually they will add the user input to a larger piece of text, called a prompt template, that provides additional context on the specific task at hand.
 
 In the previous example, the text we passed to the model contained instructions to generate a company name. For our application, it'd be great if the user only had to provide the description of a company/product, without having to worry about giving the model instructions.
 
@@ -138,7 +138,7 @@ The chains and agents we've looked at so far have been stateless, but for many a
 
 The Memory module gives you a way to maintain application state. The base Memory interface is simple: it lets you update state given the latest run inputs and outputs and it lets you modify (or contextualize) the next input using the stored state.
 
-There are a number of built-in memory systems. The simplest of these are is a buffer memory which just prepends the last few inputs/outputs to the current input - we will use this in the example below.
+There are a number of built-in memory systems. The simplest of these is a buffer memory which just prepends the last few inputs/outputs to the current input - we will use this in the example below.
 
 import MemoryLLM from "@snippets/get_started/quickstart/memory_llms.mdx"
 import MemoryChatModel from "@snippets/get_started/quickstart/memory_chat_models.mdx"
@@ -155,4 +155,4 @@ You can use Memory with chains and agents initialized with chat models. The main
 <MemoryChatModel/>
 
 </TabItem>
-</Tabs>
+</Tabs>

docs/docs_skeleton/docs/modules/data_connection/document_loaders/how_to/json.mdx

@@ -2,6 +2,8 @@
 
 >[JSON (JavaScript Object Notation)](https://en.wikipedia.org/wiki/JSON) is an open standard file format and data interchange format that uses human-readable text to store and transmit data objects consisting of attribute–value pairs and arrays (or other serializable values).
 
+>[JSON Lines](https://jsonlines.org/) is a file format where each line is a valid JSON value.
+
 import Example from "@snippets/modules/data_connection/document_loaders/how_to/json.mdx"
 
 <Example/>

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

@@ -10,7 +10,7 @@ for you.
 
 ## Get started
 
-This walkthrough showcases basic functionality related to VectorStores. A key part of working with vector stores is creating the vector to put in them, which is usually created via embeddings. Therefore, it is recommended that you familiarize yourself with the [text embedding model](/docs/modules/model_io/models/embeddings.html) interfaces before diving into this.
+This walkthrough showcases basic functionality related to VectorStores. A key part of working with vector stores is creating the vector to put in them, which is usually created via embeddings. Therefore, it is recommended that you familiarize yourself with the [text embedding model](/docs/modules/data_connection/text_embedding/) interfaces before diving into this.
 
 import GetStarted from "@snippets/modules/data_connection/vectorstores/get_started.mdx"
 

docs/docs_skeleton/docusaurus.config.js

@@ -87,7 +87,6 @@ const config = {
       ({
         docs: {
           sidebarPath: require.resolve("./sidebars.js"),
-          editUrl: "https://github.com/hwchase17/langchain/edit/master/docs/",
           remarkPlugins: [
             [require("@docusaurus/remark-plugin-npm2yarn"), { sync: true }],
           ],

docs/extras/ecosystem/integrations/airtable.md

@@ -0,0 +1,28 @@
+# Airtable
+
+>[Airtable](https://en.wikipedia.org/wiki/Airtable) is a cloud collaboration service.
+`Airtable` is a spreadsheet-database hybrid, with the features of a database but applied to a spreadsheet. 
+> The fields in an Airtable table are similar to cells in a spreadsheet, but have types such as 'checkbox', 
+> 'phone number', and 'drop-down list', and can reference file attachments like images.
+
+>Users can create a database, set up column types, add records, link tables to one another, collaborate, sort records
+> and publish views to external websites.
+
+## Installation and Setup
+
+```bash
+pip install pyairtable
+```
+
+* Get your [API key](https://support.airtable.com/docs/creating-and-using-api-keys-and-access-tokens).
+* Get the [ID of your base](https://airtable.com/developers/web/api/introduction).
+* Get the [table ID from the table url](https://www.highviewapps.com/kb/where-can-i-find-the-airtable-base-id-and-table-id/#:~:text=Both%20the%20Airtable%20Base%20ID,URL%20that%20begins%20with%20tbl).
+
+## Document Loader
+
+
+```python
+from langchain.document_loaders import AirtableLoader
+```
+
+See an [example](/docs/modules/data_connection/document_loaders/integrations/airtable.html).

docs/extras/ecosystem/integrations/arthur_tracking.ipynb

@@ -0,0 +1,464 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "944e4194",
+   "metadata": {},
+   "source": [
+    "# Arthur LangChain integration"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b1ccdfe8",
+   "metadata": {},
+   "source": [
+    "[Arthur](https://www.arthur.ai/) is a model monitoring and observability platform.\n",
+    "\n",
+    "This notebook shows how to register LLMs (chat and non-chat) as models with the Arthur platform. Then we show how to set up langchain LLMs with an Arthur callback that will automatically log model inferences to Arthur.\n",
+    "\n",
+    "For more information about how to use the Arthur SDK, visit our [docs](http://docs.arthur.ai), in particular our [model onboarding guide](https://docs.arthur.ai/user-guide/walkthroughs/model-onboarding/index.html)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "961c6691",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.callbacks import ArthurCallbackHandler\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "from langchain.chat_models import ChatOpenAI, ChatAnthropic\n",
+    "from langchain.schema import HumanMessage\n",
+    "from langchain.llms import OpenAI, Cohere, HuggingFacePipeline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a23d1963",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from arthurai import ArthurAI\n",
+    "from arthurai.common.constants import InputType, OutputType, Stage, ValueType\n",
+    "from arthurai.core.attributes import ArthurAttribute, AttributeCategory"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4d1b90c0",
+   "metadata": {},
+   "source": [
+    "# ArthurModel for chatbot with only input text and output text attributes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a4a4a8a",
+   "metadata": {},
+   "source": [
+    "Connect to Arthur client"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f49e9b79",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "arthur_url = \"https://app.arthur.ai\"\n",
+    "arthur_login = \"your-username-here\"\n",
+    "arthur = ArthurAI(url=arthur_url, login=arthur_login)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c6e063bf",
+   "metadata": {},
+   "source": [
+    "Before you can register model inferences to Arthur, you must have a registered model with an ID in the Arthur platform. We will provide this ID to the ArthurCallbackHandler.\n",
+    "\n",
+    "You can register a model with Arthur here in the notebook using this `register_chat_llm()` function. This function returns the ID of the model saved to the platform. To use the function, uncomment `arthur_model_chatbot_id = register_chat_llm()` in the cell below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "31b17b5e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def register_chat_llm():\n",
+    "\n",
+    "    arthur_model = arthur.model(\n",
+    "        display_name=\"LangChainChat\",\n",
+    "        input_type=InputType.NLP,\n",
+    "        output_type=OutputType.TokenSequence\n",
+    "    )\n",
+    "\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"my_input_text\",\n",
+    "        stage=Stage.ModelPipelineInput,\n",
+    "        value_type=ValueType.Unstructured_Text,\n",
+    "        categorical=True,\n",
+    "        is_unique=True\n",
+    "    ))\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"my_output_text\",\n",
+    "        stage=Stage.PredictedValue,\n",
+    "        value_type=ValueType.Unstructured_Text,\n",
+    "        categorical=True,\n",
+    "        is_unique=False,\n",
+    "    ))\n",
+    "    \n",
+    "    return arthur_model.save()\n",
+    "# arthur_model_chatbot_id = register_chat_llm()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0d1d1e60",
+   "metadata": {},
+   "source": [
+    "Alternatively, you can set the `arthur_model_chatbot_id` variable to be the ID of your model on your [model dashboard](https://app.arthur.ai/)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "cdfa02c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "arthur_model_chatbot_id = \"your-model-id-here\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "58be5234",
+   "metadata": {},
+   "source": [
+    "This function creates a Langchain chat LLM with the ArthurCallbackHandler to log inferences to Arthur. We provide our `arthur_model_chatbot_id`, as well as the Arthur url and login we are using."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "448a8fee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def make_langchain_chat_llm(chat_model=ChatOpenAI):\n",
+    "    if chat_model not in [ChatOpenAI, ChatAnthropic]:\n",
+    "        raise ValueError(\"For this notebook, use one of the chat models imported from langchain.chat_models\")\n",
+    "    return chat_model(\n",
+    "        streaming=True, \n",
+    "        temperature=0.1,\n",
+    "        callbacks=[\n",
+    "            StreamingStdOutCallbackHandler(), \n",
+    "            ArthurCallbackHandler.from_credentials(arthur_model_chatbot_id, arthur_url=arthur_url, arthur_login=arthur_login)\n",
+    "        ])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17c182da",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "2dfc00ed",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_llm = make_langchain_chat_llm()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "139291f2",
+   "metadata": {},
+   "source": [
+    "Run the chatbot (it will save the chat history in the `history` list so that the conversation can reference earlier messages)\n",
+    "\n",
+    "Type `q` to quit"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7480a443",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def run_langchain_chat_llm(llm):\n",
+    "    history = []\n",
+    "    while True:\n",
+    "        user_input = input(\"\\n>>> input >>>\\n>>>: \")\n",
+    "        if user_input == 'q': break\n",
+    "        history.append(HumanMessage(content=user_input))\n",
+    "        history.append(llm(history))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "6868ce71",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "run_langchain_chat_llm(chat_llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a0be7d01",
+   "metadata": {},
+   "source": [
+    "# ArthurModel with input text, output text, token likelihoods, finish reason, and amount of token usage attributes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1ee4b741",
+   "metadata": {},
+   "source": [
+    "This function registers an LLM with additional metadata attributes to log to Arthur with each inference\n",
+    "\n",
+    "As above, you can register your callback handler for an LLM using this function here in the notebook or by pasting the ID of an already-registered model from your [model dashboard](https://app.arthur.ai/)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "e671836c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def register_llm():\n",
+    "\n",
+    "    arthur_model = arthur.model(\n",
+    "        display_name=\"LangChainLLM\",\n",
+    "        input_type=InputType.NLP,\n",
+    "        output_type=OutputType.TokenSequence\n",
+    "    )\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"my_input_text\",\n",
+    "        stage=Stage.ModelPipelineInput,\n",
+    "        value_type=ValueType.Unstructured_Text,\n",
+    "        categorical=True,\n",
+    "        is_unique=True\n",
+    "    ))\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"my_output_text\",\n",
+    "        stage=Stage.PredictedValue,\n",
+    "        value_type=ValueType.Unstructured_Text,\n",
+    "        categorical=True,\n",
+    "        is_unique=False,\n",
+    "        token_attribute_link=\"my_output_likelihoods\"\n",
+    "    ))\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"my_output_likelihoods\",\n",
+    "        stage=Stage.PredictedValue,\n",
+    "        value_type=ValueType.TokenLikelihoods,\n",
+    "        token_attribute_link=\"my_output_text\"\n",
+    "    ))\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"finish_reason\",\n",
+    "        stage=Stage.NonInputData,\n",
+    "        value_type=ValueType.String,\n",
+    "        categorical=True,\n",
+    "        categories=[\n",
+    "            AttributeCategory(value='stop'),\n",
+    "            AttributeCategory(value='length'),\n",
+    "            AttributeCategory(value='content_filter'),\n",
+    "            AttributeCategory(value='null')\n",
+    "        ]\n",
+    "    ))\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"prompt_tokens\",\n",
+    "        stage=Stage.NonInputData,\n",
+    "        value_type=ValueType.Integer\n",
+    "    ))\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"completion_tokens\",\n",
+    "        stage=Stage.NonInputData,\n",
+    "        value_type=ValueType.Integer\n",
+    "    ))\n",
+    "    arthur_model._add_attribute_to_model(ArthurAttribute(\n",
+    "        name=\"duration\",\n",
+    "        stage=Stage.NonInputData,\n",
+    "        value_type=ValueType.Float\n",
+    "    ))\n",
+    "    \n",
+    "    return arthur_model.save()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "2a6686f7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "arthur_model_llm_id = \"your-model-id-here\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2dcacb96",
+   "metadata": {},
+   "source": [
+    "These functions create Langchain LLMs with the ArthurCallbackHandler to log inferences to Arthur.\n",
+    "\n",
+    "There are small differences in the underlying Langchain integrations with these libraries and the available metadata for model inputs & outputs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "34cf0072",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def make_langchain_openai_llm():\n",
+    "    return OpenAI(\n",
+    "        temperature=0.1,\n",
+    "        model_kwargs = {'logprobs': 3},\n",
+    "        callbacks=[\n",
+    "            ArthurCallbackHandler.from_credentials(arthur_model_llm_id, arthur_url=arthur_url, arthur_login=arthur_login)\n",
+    "        ])\n",
+    "\n",
+    "def make_langchain_cohere_llm():\n",
+    "    return Cohere(\n",
+    "        temperature=0.1,\n",
+    "        callbacks=[\n",
+    "            ArthurCallbackHandler.from_credentials(arthur_model_chatbot_id, arthur_url=arthur_url, arthur_login=arthur_login)\n",
+    "        ])\n",
+    "\n",
+    "def make_langchain_huggingface_llm():\n",
+    "    llm = HuggingFacePipeline.from_model_id(\n",
+    "        model_id=\"bert-base-uncased\", \n",
+    "        task=\"text-generation\", \n",
+    "        model_kwargs={\"temperature\":2.5, \"max_length\":64})\n",
+    "    llm.callbacks = [\n",
+    "        ArthurCallbackHandler.from_credentials(arthur_model_chatbot_id, arthur_url=arthur_url, arthur_login=arthur_login)\n",
+    "    ]\n",
+    "    return llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "f40c3ce0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai_llm = make_langchain_openai_llm()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "8476d531",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cohere_llm = make_langchain_cohere_llm()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7483b9d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "huggingface_llm = make_langchain_huggingface_llm()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c17d8e86",
+   "metadata": {},
+   "source": [
+    "Run the LLM (each completion is independent, no chat history is saved as we were doing above with the chat llms)\n",
+    "\n",
+    "Type `q` to quit"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "72ee0790",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def run_langchain_llm(llm):\n",
+    "    while True:\n",
+    "        print(\"Type your text for completion:\\n\")\n",
+    "        user_input = input(\"\\n>>> input >>>\\n>>>: \")\n",
+    "        if user_input == 'q': break\n",
+    "        print(llm(user_input), \"\\n================\\n\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "fb864057",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "run_langchain_llm(openai_llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "e6673769",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "run_langchain_llm(cohere_llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "85541f1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "run_langchain_llm(huggingface_llm)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/ecosystem/integrations/brave_search.mdx

@@ -0,0 +1,36 @@
+# Brave Search
+
+
+>[Brave Search](https://en.wikipedia.org/wiki/Brave_Search) is a search engine developed by Brave Software.
+> - `Brave Search` uses its own web index. As of May 2022, it covered over 10 billion pages and was used to serve 92% 
+> of search results without relying on any third-parties, with the remainder being retrieved 
+> server-side from the Bing API or (on an opt-in basis) client-side from Google. According 
+> to Brave, the index was kept "intentionally smaller than that of Google or Bing" in order to 
+> help avoid spam and other low-quality content, with the disadvantage that "Brave Search is 
+> not yet as good as Google in recovering long-tail queries."
+>- `Brave Search Premium`: As of April 2023 Brave Search is an ad-free website, but it will 
+> eventually switch to a new model that will include ads and premium users will get an ad-free experience.
+> User data including IP addresses won't be collected from its users by default. A premium account 
+> will be required for opt-in data-collection.
+
+
+## Installation and Setup
+
+To get access to the Brave Search API, you need to [create an account and get an API key](https://api.search.brave.com/app/dashboard).
+
+
+## Document Loader
+
+See a [usage example](/docs/modules/data_connection/document_loaders/integrations/brave_search.html).
+
+```python
+from langchain.document_loaders import BraveSearchLoader
+```
+
+## Tool
+
+See a [usage example](/docs/modules/agents/tools/integrations/brave_search.html).
+
+```python
+from langchain.tools import BraveSearch
+```

docs/extras/ecosystem/integrations/cassandra.mdx

@@ -1,10 +1,10 @@
 # Cassandra
 
->[Apache Cassandra®](https://cassandra.apache.org/) is a free and open-source, distributed, wide-column 
+>[Apache Cassandra®](https://cassandra.apache.org/) is a free and open-source, distributed, wide-column
 > store, NoSQL database management system designed to handle large amounts of data across many commodity servers, 
-> providing high availability with no single point of failure. Cassandra offers support for clusters spanning 
+> providing high availability with no single point of failure. Cassandra offers support for clusters spanning
 > multiple datacenters, with asynchronous masterless replication allowing low latency operations for all clients. 
-> Cassandra was designed to implement a combination of _Amazon's Dynamo_ distributed storage and replication 
+> Cassandra was designed to implement a combination of _Amazon's Dynamo_ distributed storage and replication
 > techniques combined with _Google's Bigtable_ data and storage engine model.
  
 ## Installation and Setup
@@ -16,6 +16,16 @@ pip install cassio
 
 
 
+## Vector Store
+
+See a [usage example](/docs/modules/data_connection/vectorstores/integrations/cassandra.html).
+
+```python
+from langchain.memory import CassandraChatMessageHistory
+```
+
+
+
 ## Memory
 
 See a [usage example](/docs/modules/memory/integrations/cassandra_chat_message_history.html).

docs/extras/ecosystem/integrations/flyte.mdx

@@ -0,0 +1,153 @@
+# Flyte
+
+> [Flyte](https://github.com/flyteorg/flyte) is an open-source orchestrator that facilitates building production-grade data and ML pipelines.
+> It is built for scalability and reproducibility, leveraging Kubernetes as its underlying platform.
+
+The purpose of this notebook is to demonstrate the integration of a `FlyteCallback` into your Flyte task, enabling you to effectively monitor and track your LangChain experiments.
+
+## Installation & Setup
+
+- Install the Flytekit library by running the command `pip install flytekit`.
+- Install the Flytekit-Envd plugin by running the command `pip install flytekitplugins-envd`.
+- Install LangChain by running the command `pip install langchain`.
+- Install [Docker](https://docs.docker.com/engine/install/) on your system.
+
+## Flyte Tasks
+
+A Flyte [task](https://docs.flyte.org/projects/cookbook/en/latest/auto/core/flyte_basics/task.html) serves as the foundational building block of Flyte.
+To execute LangChain experiments, you need to write Flyte tasks that define the specific steps and operations involved.
+
+NOTE: The [getting started guide](https://docs.flyte.org/projects/cookbook/en/latest/index.html) offers detailed, step-by-step instructions on installing Flyte locally and running your initial Flyte pipeline.
+
+First, import the necessary dependencies to support your LangChain experiments.
+
+```python
+import os
+
+from flytekit import ImageSpec, task
+from langchain.agents import AgentType, initialize_agent, load_tools
+from langchain.callbacks import FlyteCallbackHandler
+from langchain.chains import LLMChain
+from langchain.chat_models import ChatOpenAI
+from langchain.prompts import PromptTemplate
+from langchain.schema import HumanMessage
+```
+
+Set up the necessary environment variables to utilize the OpenAI API and Serp API:
+
+```python
+# Set OpenAI API key
+os.environ["OPENAI_API_KEY"] = "<your_openai_api_key>"
+
+# Set Serp API key
+os.environ["SERPAPI_API_KEY"] = "<your_serp_api_key>"
+```
+
+Replace `<your_openai_api_key>` and `<your_serp_api_key>` with your respective API keys obtained from OpenAI and Serp API.
+
+To guarantee reproducibility of your pipelines, Flyte tasks are containerized.
+Each Flyte task must be associated with an image, which can either be shared across the entire Flyte [workflow](https://docs.flyte.org/projects/cookbook/en/latest/auto/core/flyte_basics/basic_workflow.html) or provided separately for each task.
+
+To streamline the process of supplying the required dependencies for each Flyte task, you can initialize an [`ImageSpec`](https://docs.flyte.org/projects/cookbook/en/latest/auto/core/image_spec/image_spec.html) object.
+This approach automatically triggers a Docker build, alleviating the need for users to manually create a Docker image.
+
+```python
+custom_image = ImageSpec(
+    name="langchain-flyte",
+    packages=[
+        "langchain",
+        "openai",
+        "spacy",
+        "https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0.tar.gz",
+        "textstat",
+        "google-search-results",
+    ],
+    registry="<your-registry>",
+)
+```
+
+You have the flexibility to push the Docker image to a registry of your preference.
+[Docker Hub](https://hub.docker.com/) or [GitHub Container Registry (GHCR)](https://docs.github.com/en/packages/working-with-a-github-packages-registry/working-with-the-container-registry) is a convenient option to begin with.
+
+Once you have selected a registry, you can proceed to create Flyte tasks that log the LangChain metrics to Flyte Deck.
+
+The following examples demonstrate tasks related to OpenAI LLM, chains and agent with tools:
+
+### LLM
+
+```python
+@task(disable_deck=False, container_image=custom_image)
+def langchain_llm() -> str:
+    llm = ChatOpenAI(
+        model_name="gpt-3.5-turbo",
+        temperature=0.2,
+        callbacks=[FlyteCallbackHandler()],
+    )
+    return llm([HumanMessage(content="Tell me a joke")]).content
+```
+
+### Chain
+
+```python
+@task(disable_deck=False, container_image=custom_image)
+def langchain_chain() -> list[dict[str, str]]:
+    template = """You are a playwright. Given the title of play, it is your job to write a synopsis for that title.
+Title: {title}
+Playwright: This is a synopsis for the above play:"""
+    llm = ChatOpenAI(
+        model_name="gpt-3.5-turbo",
+        temperature=0,
+        callbacks=[FlyteCallbackHandler()],
+    )
+    prompt_template = PromptTemplate(input_variables=["title"], template=template)
+    synopsis_chain = LLMChain(
+        llm=llm, prompt=prompt_template, callbacks=[FlyteCallbackHandler()]
+    )
+    test_prompts = [
+        {
+            "title": "documentary about good video games that push the boundary of game design"
+        },
+    ]
+    return synopsis_chain.apply(test_prompts)
+```
+
+### Agent
+
+```python
+@task(disable_deck=False, container_image=custom_image)
+def langchain_agent() -> str:
+    llm = OpenAI(
+        model_name="gpt-3.5-turbo",
+        temperature=0,
+        callbacks=[FlyteCallbackHandler()],
+    )
+    tools = load_tools(
+        ["serpapi", "llm-math"], llm=llm, callbacks=[FlyteCallbackHandler()]
+    )
+    agent = initialize_agent(
+        tools,
+        llm,
+        agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+        callbacks=[FlyteCallbackHandler()],
+        verbose=True,
+    )
+    return agent.run(
+        "Who is Leonardo DiCaprio's girlfriend? Could you calculate her current age and raise it to the power of 0.43?"
+    )
+```
+
+These tasks serve as a starting point for running your LangChain experiments within Flyte.
+
+## Execute the Flyte Tasks on Kubernetes
+
+To execute the Flyte tasks on the configured Flyte backend, use the following command:
+
+```bash
+pyflyte run --image <your-image> langchain_flyte.py langchain_llm
+```
+
+This command will initiate the execution of the `langchain_llm` task on the Flyte backend. You can trigger the remaining two tasks in a similar manner.
+
+The metrics will be displayed on the Flyte UI as follows:
+
+![LangChain LLM](https://ik.imagekit.io/c8zl7irwkdda/Screenshot_2023-06-20_at_1.23.29_PM_MZYeG0dKa.png?updatedAt=1687247642993)

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

@@ -39,6 +39,21 @@ vectara = Vectara(
 ```
 The customer_id, corpus_id and api_key are optional, and if they are not supplied will be read from the environment variables `VECTARA_CUSTOMER_ID`, `VECTARA_CORPUS_ID` and `VECTARA_API_KEY`, respectively.
 
+Afer you have the vectorstore, you can `add_texts` or `add_documents` as per the standard `VectorStore` interface, for example:
+
+```python
+vectara.add_texts(["to be or not to be", "that is the question"])
+```
+
+
+Since Vectara supports file-upload, we also added the ability to upload files (PDF, TXT, HTML, PPT, DOC, etc) directly as file. When using this method, the file is uploaded directly to the Vectara backend, processed and chunked optimally there, so you don't have to use the LangChain document loader or chunking mechanism.
+
+As an example:
+
+```python
+vectara.add_files(["path/to/file1.pdf", "path/to/file2.pdf",...])
+```
+
 To query the vectorstore, you can use the `similarity_search` method (or `similarity_search_with_score`), which takes a query string and returns a list of results:
 ```python
 results = vectara.similarity_score("what is LangChain?")

docs/extras/guides/evaluation/comparisons.ipynb

@@ -243,8 +243,8 @@
     "            pred_a, pred_b = res_b, res_a\n",
     "            a, b = \"b\", \"a\"\n",
     "        eval_res = eval_chain.evaluate_string_pairs(\n",
-    "            output_a=pred_a['output'] if isinstance(pred_a, dict) else str(pred_a),\n",
-    "            output_b=pred_b['output'] if isinstance(pred_b, dict) else str(pred_b),\n",
+    "            prediction=pred_a['output'] if isinstance(pred_a, dict) else str(pred_a),\n",
+    "            prediction_b=pred_b['output'] if isinstance(pred_b, dict) else str(pred_b),\n",
     "            input=input_\n",
     "        )\n",
     "        if eval_res[\"value\"] == \"A\":\n",

docs/extras/guides/evaluation/openapi_eval.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Evaluating an OpenAPI Chain\n",
     "\n",
-    "This notebook goes over ways to semantically evaluate an [OpenAPI Chain](/docs/modules/chains/additiona/openapi.html), which calls an endpoint defined by the OpenAPI specification using purely natural language."
+    "This notebook goes over ways to semantically evaluate an [OpenAPI Chain](/docs/modules/chains/additional/openapi.html), which calls an endpoint defined by the OpenAPI specification using purely natural language."
    ]
   },
   {

docs/extras/modules/agents/tools/integrations/brave_search.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "a4c896e5",
    "metadata": {},
    "outputs": [],
@@ -27,7 +27,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "api_key = \"...\""
+    "api_key = \"BSAv1neIuQOsxqOyy0sEe_ie2zD_n_V\""
    ]
   },
   {
@@ -49,7 +49,7 @@
     {
      "data": {
       "text/plain": [
-       "'[{\"title\": \"Barack Obama - Wikipedia\", \"link\": \"https://en.wikipedia.org/wiki/Barack_Obama\", \"snippet\": \"Outside of politics, <strong>Obama</strong> has published three bestselling books: Dreams from My Father (1995), The Audacity of Hope (2006) and A Promised Land (2020). Rankings by scholars and historians, in which he has been featured since 2010, place him in the <strong>middle</strong> to upper tier of American presidents.\"}, {\"title\": \"Obama\\'s Middle Name -- My Last Name -- is \\'Hussein.\\' So?\", \"link\": \"https://www.cair.com/cair_in_the_news/obamas-middle-name-my-last-name-is-hussein-so/\", \"snippet\": \"Many Americans understand that common names don\\\\u2019t only come in the form of a \\\\u201cSmith\\\\u201d or a \\\\u201cJohnson.\\\\u201d Perhaps, they have a neighbor, mechanic or teacher named Hussein. Or maybe they\\\\u2019ve seen fashion designer Hussein Chalayan in the pages of Vogue or recall <strong>King Hussein</strong>, our ally in the Middle East.\"}, {\"title\": \"What\\'s up with Obama\\'s middle name? - Quora\", \"link\": \"https://www.quora.com/Whats-up-with-Obamas-middle-name\", \"snippet\": \"Answer (1 of 15): A better question would be, \\\\u201cWhat\\\\u2019s up with Obama\\\\u2019s first name?\\\\u201d President <strong>Barack Hussein Obama</strong>\\\\u2019s father\\\\u2019s name was <strong>Barack Hussein Obama</strong>. He was named after his father. Hussein, Obama\\\\u2019s middle name, is a very common Arabic name, meaning &quot;good,&quot; &quot;handsome,&quot; or &quot;beautiful.&quot;\"}]'"
+       "'[{\"title\": \"Obama\\'s Middle Name -- My Last Name -- is \\'Hussein.\\' So?\", \"link\": \"https://www.cair.com/cair_in_the_news/obamas-middle-name-my-last-name-is-hussein-so/\", \"snippet\": \"I wasn\\\\u2019t sure whether to laugh or cry a few days back listening to radio talk show host Bill Cunningham repeatedly scream Barack <strong>Obama</strong>\\\\u2019<strong>s</strong> <strong>middle</strong> <strong>name</strong> \\\\u2014 my last <strong>name</strong> \\\\u2014 as if he had anti-Muslim Tourette\\\\u2019s. \\\\u201cHussein,\\\\u201d Cunningham hissed like he was beckoning Satan when shouting the ...\"}, {\"title\": \"What\\'s up with Obama\\'s middle name? - Quora\", \"link\": \"https://www.quora.com/Whats-up-with-Obamas-middle-name\", \"snippet\": \"Answer (1 of 15): A better question would be, \\\\u201cWhat\\\\u2019s up with <strong>Obama</strong>\\\\u2019s first <strong>name</strong>?\\\\u201d President Barack Hussein <strong>Obama</strong>\\\\u2019s father\\\\u2019s <strong>name</strong> was Barack Hussein <strong>Obama</strong>. He was <strong>named</strong> after his father. Hussein, <strong>Obama</strong>\\\\u2019<strong>s</strong> <strong>middle</strong> <strong>name</strong>, is a very common Arabic <strong>name</strong>, meaning &quot;good,&quot; &quot;handsome,&quot; or ...\"}, {\"title\": \"Barack Obama | Biography, Parents, Education, Presidency, Books, ...\", \"link\": \"https://www.britannica.com/biography/Barack-Obama\", \"snippet\": \"Barack <strong>Obama</strong>, in full Barack Hussein <strong>Obama</strong> II, (born August 4, 1961, Honolulu, Hawaii, U.S.), 44th president of the United States (2009\\\\u201317) and the first African American to hold the office. Before winning the presidency, <strong>Obama</strong> represented Illinois in the U.S.\"}]'"
       ]
      },
      "execution_count": 4,
@@ -86,7 +86,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/extras/modules/chains/additional/flare.ipynb

@@ -71,11 +71,13 @@
     "import numpy as np\n",
     "\n",
     "from langchain.schema import BaseRetriever\n",
+    "from langchain.callbacks.manager import AsyncCallbackManagerForRetrieverRun, CallbackManagerForRetrieverRun\n",
     "from langchain.utilities import GoogleSerperAPIWrapper\n",
     "from langchain.embeddings import OpenAIEmbeddings\n",
     "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.llms import OpenAI\n",
-    "from langchain.schema import Document"
+    "from langchain.schema import Document\n",
+    "from typing import Any"
    ]
   },
   {
@@ -97,11 +99,16 @@
     "    def __init__(self, search):\n",
     "        self.search = search\n",
     "\n",
-    "    def get_relevant_documents(self, query: str):\n",
+    "    def _get_relevant_documents(self, query: str, *, run_manager: CallbackManagerForRetrieverRun, **kwargs: Any) -> List[Document]:\n",
     "        return [Document(page_content=self.search.run(query))]\n",
     "\n",
-    "    async def aget_relevant_documents(self, query: str):\n",
-    "        raise NotImplemented\n",
+    "    async def _aget_relevant_documents(self,\n",
+    "        query: str,\n",
+    "        *,\n",
+    "        run_manager: AsyncCallbackManagerForRetrieverRun,\n",
+    "        **kwargs: Any,\n",
+    "    ) -> List[Document]:\n",
+    "        raise NotImplementedError()\n",
     "\n",
     "\n",
     "retriever = SerperSearchRetriever(GoogleSerperAPIWrapper())"

docs/extras/modules/data_connection/document_loaders/integrations/airtable.ipynb

@@ -134,7 +134,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/extras/modules/data_connection/document_loaders/integrations/brave_search.ipynb

@@ -0,0 +1,164 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "3dd292b1-9a73-4ea8-af19-5fa6e3c1a62a",
+   "metadata": {},
+   "source": [
+    "# Brave Search\n",
+    "\n",
+    "\n",
+    ">[Brave Search](https://en.wikipedia.org/wiki/Brave_Search) is a search engine developed by Brave Software.\n",
+    "> - `Brave Search` uses its own web index. As of May 2022, it covered over 10 billion pages and was used to serve 92% \n",
+    "> of search results without relying on any third-parties, with the remainder being retrieved \n",
+    "> server-side from the Bing API or (on an opt-in basis) client-side from Google. According \n",
+    "> to Brave, the index was kept \"intentionally smaller than that of Google or Bing\" in order to \n",
+    "> help avoid spam and other low-quality content, with the disadvantage that \"Brave Search is \n",
+    "> not yet as good as Google in recovering long-tail queries.\"\n",
+    ">- `Brave Search Premium`: As of April 2023 Brave Search is an ad-free website, but it will \n",
+    "> eventually switch to a new model that will include ads and premium users will get an ad-free experience.\n",
+    "> User data including IP addresses won't be collected from its users by default. A premium account \n",
+    "> will be required for opt-in data-collection.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "26f0888e-3f3e-4b82-ac4a-2df6feeccbe0",
+   "metadata": {},
+   "source": [
+    "## Installation and Setup\n",
+    "\n",
+    "To get access to the Brave Search API, you need to [create an account and get an API key](https://api.search.brave.com/app/dashboard).\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "d7d7be09-58bd-47d7-bf1b-33964564f777",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "api_key = \"...\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3ac92df-6ff0-4dbb-b32b-a7dc140c48ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import BraveSearchLoader"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7f483caf-58ef-4138-975a-5b783559dc1b",
+   "metadata": {},
+   "source": [
+    "## Example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "766634cf-3bc7-4656-939a-cafa218807a6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "3"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader = BraveSearchLoader(query=\"obama middle name\", api_key=api_key, search_kwargs={\"count\": 3})\n",
+    "docs = loader.load()\n",
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "f1fcc9f1-cbdc-46b3-89d3-80311d557dc6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'title': \"Obama's Middle Name -- My Last Name -- is 'Hussein.' So?\",\n",
+       "  'link': 'https://www.cair.com/cair_in_the_news/obamas-middle-name-my-last-name-is-hussein-so/'},\n",
+       " {'title': \"What's up with Obama's middle name? - Quora\",\n",
+       "  'link': 'https://www.quora.com/Whats-up-with-Obamas-middle-name'},\n",
+       " {'title': 'Barack Obama | Biography, Parents, Education, Presidency, Books, ...',\n",
+       "  'link': 'https://www.britannica.com/biography/Barack-Obama'}]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "[doc.metadata for doc in docs]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "601bfd77-03d3-468e-843f-2523d5e215bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['I wasn’t sure whether to laugh or cry a few days back listening to radio talk show host Bill Cunningham repeatedly scream Barack <strong>Obama</strong>’<strong>s</strong> <strong>middle</strong> <strong>name</strong> — my last <strong>name</strong> — as if he had anti-Muslim Tourette’s. “Hussein,” Cunningham hissed like he was beckoning Satan when shouting the ...',\n",
+       " 'Answer (1 of 15): A better question would be, “What’s up with <strong>Obama</strong>’s first <strong>name</strong>?” President Barack Hussein <strong>Obama</strong>’s father’s <strong>name</strong> was Barack Hussein <strong>Obama</strong>. He was <strong>named</strong> after his father. Hussein, <strong>Obama</strong>’<strong>s</strong> <strong>middle</strong> <strong>name</strong>, is a very common Arabic <strong>name</strong>, meaning &quot;good,&quot; &quot;handsome,&quot; or ...',\n",
+       " 'Barack <strong>Obama</strong>, in full Barack Hussein <strong>Obama</strong> II, (born August 4, 1961, Honolulu, Hawaii, U.S.), 44th president of the United States (2009–17) and the first African American to hold the office. Before winning the presidency, <strong>Obama</strong> represented Illinois in the U.S.']"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "[doc.page_content for doc in docs]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "74a6ba54-9e48-4bac-ab9b-03eabd19eb81",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/extras/modules/data_connection/document_loaders/integrations/email.ipynb

@@ -32,7 +32,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 1,
    "id": "40cd9806",
    "metadata": {
     "tags": []
@@ -44,7 +44,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 2,
    "id": "2d20b852",
    "metadata": {
     "tags": []
@@ -56,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "579fa702",
    "metadata": {
     "tags": []
@@ -68,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
    "id": "90c1d899",
    "metadata": {
     "tags": []
@@ -80,7 +80,7 @@
        "[Document(page_content='This is a test email to use for unit tests.\\n\\nImportant points:\\n\\nRoses are red\\n\\nViolets are blue', metadata={'source': 'example_data/fake-email.eml'})]"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -128,7 +128,7 @@
     {
      "data": {
       "text/plain": [
-       "Document(page_content='This is a test email to use for unit tests.', lookup_str='', metadata={'source': 'example_data/fake-email.eml'}, lookup_index=0)"
+       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'filename': 'fake-email.eml', 'file_directory': 'example_data', 'date': '2022-12-16T17:04:16-05:00', 'filetype': 'message/rfc822', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'category': 'NarrativeText'})"
       ]
      },
      "execution_count": 7,
@@ -140,6 +140,61 @@
     "data[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5021f20a",
+   "metadata": {},
+   "source": [
+    "### Processing Attachments\n",
+    "\n",
+    "You can process attachments with `UnstructuredEmailLoader` by setting `process_attachments=True` in the constructor. By default, attachments will be partitioned using the `partition` function from `unstructured`. You can use a different partitioning function by passing the function to the `attachment_partitioner` kwarg."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "6539f166",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredEmailLoader(\n",
+    "    \"example_data/fake-email.eml\",\n",
+    "    mode=\"elements\",\n",
+    "    process_attachments=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "aebead38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "ddeb60f4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='This is a test email to use for unit tests.', metadata={'source': 'example_data/fake-email.eml', 'filename': 'fake-email.eml', 'file_directory': 'example_data', 'date': '2022-12-16T17:04:16-05:00', 'filetype': 'message/rfc822', 'sent_from': ['Matthew Robinson <mrobinson@unstructured.io>'], 'sent_to': ['Matthew Robinson <mrobinson@unstructured.io>'], 'subject': 'Test Email', 'category': 'NarrativeText'})"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data[0]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "6a074515",
@@ -234,7 +289,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.8.13"
   }
  },
  "nbformat": 4,

docs/extras/modules/data_connection/document_loaders/integrations/example_data/facebook_chat_messages.jsonl

@@ -0,0 +1,3 @@
+{"sender_name": "User 2", "timestamp_ms": 1675597571851, "content": "Bye!"}
+{"sender_name": "User 1", "timestamp_ms": 1675597435669, "content": "Oh no worries! Bye"}
+{"sender_name": "User 2", "timestamp_ms": 1675596277579, "content": "No Im sorry it was my mistake, the blue one is not for sale"}

docs/extras/modules/data_connection/document_loaders/integrations/example_data/fake-email-attachment.eml

@@ -0,0 +1,50 @@
+MIME-Version: 1.0
+Date: Fri, 23 Dec 2022 12:08:48 -0600
+Message-ID: <CAPgNNXSzLVJ-d1OCX_TjFgJU7ugtQrjFybPtAMmmYZzphxNFYg@mail.gmail.com>
+Subject: Fake email with attachment
+From: Mallori Harrell <mallori@unstructured.io>
+To: Mallori Harrell <mallori@unstructured.io>
+Content-Type: multipart/mixed; boundary="0000000000005d654405f082adb7"
+
+--0000000000005d654405f082adb7
+Content-Type: multipart/alternative; boundary="0000000000005d654205f082adb5"
+
+--0000000000005d654205f082adb5
+Content-Type: text/plain; charset="UTF-8"
+
+Hello!
+
+Here's the attachments!
+
+It includes:
+
+   - Lots of whitespace
+   - Little to no content
+   - and is a quick read
+
+Best,
+
+Mallori
+
+--0000000000005d654205f082adb5
+Content-Type: text/html; charset="UTF-8"
+Content-Transfer-Encoding: quoted-printable
+
+<div dir=3D"ltr">Hello!=C2=A0<div><br></div><div>Here&#39;s the attachments=
+!</div><div><br></div><div>It includes:</div><div><ul><li style=3D"margin-l=
+eft:15px">Lots of whitespace</li><li style=3D"margin-left:15px">Little=C2=
+=A0to no content</li><li style=3D"margin-left:15px">and is a quick read</li=
+></ul><div>Best,</div></div><div><br></div><div>Mallori</div><div dir=3D"lt=
+r" class=3D"gmail_signature" data-smartmail=3D"gmail_signature"><div dir=3D=
+"ltr"><div><div><br></div></div></div></div></div>
+
+--0000000000005d654205f082adb5--
+--0000000000005d654405f082adb7
+Content-Type: text/plain; charset="US-ASCII"; name="fake-attachment.txt"
+Content-Disposition: attachment; filename="fake-attachment.txt"
+Content-Transfer-Encoding: base64
+X-Attachment-Id: f_lc0tto5j0
+Content-ID: <f_lc0tto5j0>
+
+SGV5IHRoaXMgaXMgYSBmYWtlIGF0dGFjaG1lbnQh
+--0000000000005d654405f082adb7--

docs/extras/modules/data_connection/retrievers/integrations/zep_memorystore.ipynb

@@ -58,6 +58,7 @@
     "from langchain.memory.chat_message_histories import ZepChatMessageHistory\n",
     "from langchain.schema import HumanMessage, AIMessage\n",
     "from uuid import uuid4\n",
+    "import getpass\n",
     "\n",
     "# Set this to your Zep server URL\n",
     "ZEP_API_URL = \"http://localhost:8000\""
@@ -75,6 +76,25 @@
   {
    "cell_type": "code",
    "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Provide your Zep API key. Note that this is optional. See https://docs.getzep.com/deployment/auth\n",
+    "\n",
+    "zep_api_key = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:03:29.118416Z",
@@ -93,12 +113,13 @@
     "zep_chat_history = ZepChatMessageHistory(\n",
     "    session_id=session_id,\n",
     "    url=ZEP_API_URL,\n",
+    "    api_key=zep_api_key\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:03:30.271181Z",
@@ -172,7 +193,7 @@
     "]\n",
     "\n",
     "for msg in test_history:\n",
-    "    zep_chat_history.append(\n",
+    "    zep_chat_history.add_message(\n",
     "        HumanMessage(content=msg[\"content\"])\n",
     "        if msg[\"role\"] == \"human\"\n",
     "        else AIMessage(content=msg[\"content\"])\n",
@@ -192,7 +213,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:03:32.979155Z",
@@ -207,14 +228,14 @@
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7759001673780126, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count': 8}),\n",
-       " Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7602262941130749, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),\n",
-       " Document(page_content='Who were her contemporaries?', metadata={'score': 0.757553366415519, 'uuid': '41f9c41a-a205-41e1-b48b-a0a4cd943fc8', 'created_at': '2023-05-25T15:03:30.243995Z', 'role': 'human', 'token_count': 8}),\n",
-       " Document(page_content='Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American science fiction author.', metadata={'score': 0.7546211059317948, 'uuid': '34678311-0098-4f1a-8fd4-5615ac692deb', 'created_at': '2023-05-25T15:03:30.231427Z', 'role': 'ai', 'token_count': 31}),\n",
-       " Document(page_content='Which books of hers were made into movies?', metadata={'score': 0.7496714959247069, 'uuid': '18046c3a-9666-4d3e-b4f0-43d1394732b7', 'created_at': '2023-05-25T15:03:30.236837Z', 'role': 'human', 'token_count': 11})]"
+       "[Document(page_content='Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', metadata={'score': 0.8897116216176073, 'uuid': 'db60ff57-f259-4ec4-8a81-178ed4c6e54f', 'created_at': '2023-06-26T23:40:22.816214Z', 'role': 'ai', 'metadata': {'system': {'entities': [{'Label': 'GPE', 'Matches': [{'End': 20, 'Start': 15, 'Text': 'Sower'}], 'Name': 'Sower'}, {'Label': 'PERSON', 'Matches': [{'End': 65, 'Start': 51, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'DATE', 'Matches': [{'End': 84, 'Start': 80, 'Text': '1993'}], 'Name': '1993'}, {'Label': 'PERSON', 'Matches': [{'End': 124, 'Start': 110, 'Text': 'Lauren Olamina'}], 'Name': 'Lauren Olamina'}]}}, 'token_count': 56}),\n",
+       " Document(page_content=\"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", metadata={'score': 0.8856661080361157, 'uuid': 'f1a5981a-8f6d-4168-a548-6e9c32f35fa1', 'created_at': '2023-06-26T23:40:22.809621Z', 'role': 'human', 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 32, 'Start': 26, 'Text': 'Butler'}], 'Name': 'Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 61, 'Start': 41, 'Text': 'Parable of the Sower'}], 'Name': 'Parable of the Sower'}]}}, 'token_count': 23}),\n",
+       " Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7757595298492976, 'uuid': '361d0043-1009-4e13-a7f0-8aea8b1ee869', 'created_at': '2023-06-26T23:40:22.709886Z', 'role': 'human', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 22, 'Start': 8, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}], 'intent': 'The subject wants to know about the identity or background of an individual named Octavia Butler.'}}, 'token_count': 8}),\n",
+       " Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7601242516059306, 'uuid': '56c45e8a-0f65-45f0-bc46-d9e65164b563', 'created_at': '2023-06-26T23:40:22.778836Z', 'role': 'ai', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 16, 'Start': 0, 'Text': \"Octavia Butler's\"}], 'Name': \"Octavia Butler's\"}, {'Label': 'ORG', 'Matches': [{'End': 58, 'Start': 41, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 76, 'Start': 60, 'Text': 'Samuel R. Delany'}], 'Name': 'Samuel R. Delany'}, {'Label': 'PERSON', 'Matches': [{'End': 93, 'Start': 82, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': \"The subject is providing information about Octavia Butler's contemporaries.\"}}, 'token_count': 27}),\n",
+       " Document(page_content='You might want to read Ursula K. Le Guin or Joanna Russ.', metadata={'score': 0.7594731095320668, 'uuid': '6951f2fd-dfa4-4e05-9380-f322ef8f72f8', 'created_at': '2023-06-26T23:40:22.80464Z', 'role': 'ai', 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 40, 'Start': 23, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 55, 'Start': 44, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}]}}, 'token_count': 18})]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -226,6 +247,7 @@
     "    session_id=session_id,  # Ensure that you provide the session_id when instantiating the Retriever\n",
     "    url=ZEP_API_URL,\n",
     "    top_k=5,\n",
+    "    api_key=zep_api_key\n",
     ")\n",
     "\n",
     "await zep_retriever.aget_relevant_documents(\"Who wrote Parable of the Sower?\")"
@@ -240,7 +262,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:03:34.713354Z",
@@ -255,14 +277,14 @@
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', metadata={'score': 0.8897321402776546, 'uuid': '1c09603a-52c1-40d7-9d69-29f26256029c', 'created_at': '2023-05-25T15:03:30.268257Z', 'role': 'ai', 'token_count': 56}),\n",
-       " Document(page_content=\"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", metadata={'score': 0.8857628682610436, 'uuid': 'f6706e8c-6c91-452f-8c1b-9559fd924657', 'created_at': '2023-05-25T15:03:30.265302Z', 'role': 'human', 'token_count': 23}),\n",
-       " Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7759670375149477, 'uuid': '3a82a02f-056e-4c6a-b960-67ebdf3b2b93', 'created_at': '2023-05-25T15:03:30.2041Z', 'role': 'human', 'token_count': 8}),\n",
-       " Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7602854653476563, 'uuid': 'a2fc9c21-0897-46c8-bef7-6f5c0f71b04a', 'created_at': '2023-05-25T15:03:30.248065Z', 'role': 'ai', 'token_count': 27}),\n",
-       " Document(page_content='You might want to read Ursula K. Le Guin or Joanna Russ.', metadata={'score': 0.7595293992240313, 'uuid': 'f22f2498-6118-4c74-8718-aa89ccd7e3d6', 'created_at': '2023-05-25T15:03:30.261198Z', 'role': 'ai', 'token_count': 18})]"
+       "[Document(page_content='Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', metadata={'score': 0.889661105796371, 'uuid': 'db60ff57-f259-4ec4-8a81-178ed4c6e54f', 'created_at': '2023-06-26T23:40:22.816214Z', 'role': 'ai', 'metadata': {'system': {'entities': [{'Label': 'GPE', 'Matches': [{'End': 20, 'Start': 15, 'Text': 'Sower'}], 'Name': 'Sower'}, {'Label': 'PERSON', 'Matches': [{'End': 65, 'Start': 51, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'DATE', 'Matches': [{'End': 84, 'Start': 80, 'Text': '1993'}], 'Name': '1993'}, {'Label': 'PERSON', 'Matches': [{'End': 124, 'Start': 110, 'Text': 'Lauren Olamina'}], 'Name': 'Lauren Olamina'}]}}, 'token_count': 56}),\n",
+       " Document(page_content=\"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", metadata={'score': 0.885754241595424, 'uuid': 'f1a5981a-8f6d-4168-a548-6e9c32f35fa1', 'created_at': '2023-06-26T23:40:22.809621Z', 'role': 'human', 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 32, 'Start': 26, 'Text': 'Butler'}], 'Name': 'Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 61, 'Start': 41, 'Text': 'Parable of the Sower'}], 'Name': 'Parable of the Sower'}]}}, 'token_count': 23}),\n",
+       " Document(page_content='Who was Octavia Butler?', metadata={'score': 0.7758688965570713, 'uuid': '361d0043-1009-4e13-a7f0-8aea8b1ee869', 'created_at': '2023-06-26T23:40:22.709886Z', 'role': 'human', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 22, 'Start': 8, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}], 'intent': 'The subject wants to know about the identity or background of an individual named Octavia Butler.'}}, 'token_count': 8}),\n",
+       " Document(page_content=\"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", metadata={'score': 0.7602672137411663, 'uuid': '56c45e8a-0f65-45f0-bc46-d9e65164b563', 'created_at': '2023-06-26T23:40:22.778836Z', 'role': 'ai', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 16, 'Start': 0, 'Text': \"Octavia Butler's\"}], 'Name': \"Octavia Butler's\"}, {'Label': 'ORG', 'Matches': [{'End': 58, 'Start': 41, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 76, 'Start': 60, 'Text': 'Samuel R. Delany'}], 'Name': 'Samuel R. Delany'}, {'Label': 'PERSON', 'Matches': [{'End': 93, 'Start': 82, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': \"The subject is providing information about Octavia Butler's contemporaries.\"}}, 'token_count': 27}),\n",
+       " Document(page_content='You might want to read Ursula K. Le Guin or Joanna Russ.', metadata={'score': 0.7596040989115522, 'uuid': '6951f2fd-dfa4-4e05-9380-f322ef8f72f8', 'created_at': '2023-06-26T23:40:22.80464Z', 'role': 'ai', 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 40, 'Start': 23, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 55, 'Start': 44, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}]}}, 'token_count': 18})]"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -304,7 +326,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

docs/extras/modules/data_connection/text_embedding/integrations/spacy_embedding.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Spacy Embedding\n",
+    "\n",
+    "### Loading the Spacy embedding class to generate and query embeddings"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Import the necessary classes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "from langchain.embeddings.spacy_embeddings import SpacyEmbeddings\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Initialize SpacyEmbeddings.This will load the Spacy model into memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "embedder = SpacyEmbeddings()\n"
+   ]
+  },
+  {
+   "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."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "texts = [\n",
+    "    \"The quick brown fox jumps over the lazy dog.\",\n",
+    "    \"Pack my box with five dozen liquor jugs.\",\n",
+    "    \"How vexingly quick daft zebras jump!\",\n",
+    "    \"Bright vixens jump; dozy fowl quack.\"\n",
+    "]\n",
+    "\n"
+   ]
+  },
+  {
+   "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."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "embeddings = embedder.embed_documents(texts)\n",
+    "for i, embedding in enumerate(embeddings):\n",
+    "    print(f\"Embedding for document {i+1}: {embedding}\")\n",
+    "\n"
+   ]
+  },
+  {
+   "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."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "query = \"Quick foxes and lazy dogs.\"\n",
+    "query_embedding = embedder.embed_query(query)\n",
+    "print(f\"Embedding for query: {query_embedding}\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/extras/modules/data_connection/vectorstores/integrations/azuresearch.ipynb

@@ -43,7 +43,6 @@
     "import openai\n",
     "from dotenv import load_dotenv\n",
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.schema import BaseRetriever\n",
     "from langchain.vectorstores.azuresearch import AzureSearch"
    ]
   },

docs/extras/modules/data_connection/vectorstores/integrations/cassandra.ipynb

@@ -23,7 +23,7 @@
    },
    "outputs": [],
    "source": [
-    "!pip install \"cassio>=0.0.5\""
+    "!pip install \"cassio>=0.0.7\""
    ]
   },
   {
@@ -44,14 +44,16 @@
     "import os\n",
     "import getpass\n",
     "\n",
-    "database_mode = (input('\\n(L)ocal Cassandra or (A)stra DB? ')).upper()\n",
+    "database_mode = (input('\\n(C)assandra or (A)stra DB? ')).upper()\n",
     "\n",
     "keyspace_name = input('\\nKeyspace name? ')\n",
     "\n",
     "if database_mode == 'A':\n",
     "    ASTRA_DB_APPLICATION_TOKEN = getpass.getpass('\\nAstra DB Token (\"AstraCS:...\") ')\n",
     "    #\n",
-    "    ASTRA_DB_SECURE_BUNDLE_PATH = input('Full path to your Secure Connect Bundle? ')"
+    "    ASTRA_DB_SECURE_BUNDLE_PATH = input('Full path to your Secure Connect Bundle? ')\n",
+    "elif database_mode == 'C':\n",
+    "    CASSANDRA_CONTACT_POINTS = input('Contact points? (comma-separated, empty for localhost) ').strip()"
    ]
   },
   {
@@ -72,8 +74,15 @@
     "from cassandra.cluster import Cluster\n",
     "from cassandra.auth import PlainTextAuthProvider\n",
     "\n",
-    "if database_mode == 'L':\n",
-    "    cluster = Cluster()\n",
+    "if database_mode == 'C':\n",
+    "    if CASSANDRA_CONTACT_POINTS:\n",
+    "        cluster = Cluster([\n",
+    "            cp.strip()\n",
+    "            for cp in CASSANDRA_CONTACT_POINTS.split(',')\n",
+    "            if cp.strip()\n",
+    "        ])\n",
+    "    else:\n",
+    "        cluster = Cluster()\n",
     "    session = cluster.connect()\n",
     "elif database_mode == 'A':\n",
     "    ASTRA_DB_CLIENT_ID = \"token\"\n",
@@ -261,7 +270,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.10.6"
   }
  },
  "nbformat": 4,

docs/extras/modules/data_connection/vectorstores/integrations/faiss.ipynb

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "683953b3",
    "metadata": {},
@@ -30,7 +29,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "38237514-b3fa-44a4-9cff-30cd6bf50073",
    "metadata": {},
@@ -58,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "aac9563e",
    "metadata": {
     "tags": []
@@ -73,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 2,
    "id": "a3c3999a",
    "metadata": {
     "tags": []
@@ -132,7 +130,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "f13473b5",
    "metadata": {},
@@ -174,7 +171,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "f34420cf",
    "metadata": {},
@@ -194,7 +190,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "31bda7fd",
    "metadata": {},
@@ -255,7 +250,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "57da60d4",
    "metadata": {},
@@ -350,7 +344,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "f4294b96",
    "metadata": {},
@@ -361,7 +354,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 3,
    "id": "d5bf812c",
    "metadata": {},
    "outputs": [
@@ -396,7 +389,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "3d33c126",
    "metadata": {},
@@ -426,7 +418,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "0be136e0",
    "metadata": {},
@@ -456,7 +447,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "1b4ecd86",
    "metadata": {},
@@ -466,7 +456,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 4,
    "id": "1fd60fd1",
    "metadata": {},
    "outputs": [
@@ -474,15 +464,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Content: foo, Metadata: {'page': 1}, Score: 5.159960813797904e-15\n",
-      "Content: bar, Metadata: {'page': 1}, Score: 0.3131446838378906\n"
+      "Content: foo, Metadata: {'page': 1}\n"
      ]
     }
    ],
    "source": [
     "results = db.similarity_search(\"foo\", filter=dict(page=1), k=1, fetch_k=4)\n",
-    "for doc, score in results_with_scores:\n",
-    "    print(f\"Content: {doc.page_content}, Metadata: {doc.metadata}, Score: {score}\")"
+    "for doc in results:\n",
+    "    print(f\"Content: {doc.page_content}, Metadata: {doc.metadata}\")"
    ]
   }
  ],
@@ -502,7 +491,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.10.9"
   }
  },
  "nbformat": 4,

docs/extras/modules/data_connection/vectorstores/integrations/mongodb_atlas_vector_search.ipynb

@@ -1,169 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "683953b3",
-   "metadata": {},
-   "source": [
-    "# MongoDB Atlas Vector Search\n",
-    "\n",
-    ">[MongoDB Atlas](https://www.mongodb.com/docs/atlas/) is a document database managed in the cloud. It also enables Lucene and its vector search feature.\n",
-    "\n",
-    "This notebook shows how to use the functionality related to the `MongoDB Atlas Vector Search` feature where you can store your embeddings in MongoDB documents and create a Lucene vector index to perform a KNN search.\n",
-    "\n",
-    "It uses the [knnBeta Operator](https://www.mongodb.com/docs/atlas/atlas-search/knn-beta) available in MongoDB Atlas Search. This feature is in early access and available only for evaluation purposes, to validate functionality, and to gather feedback from a small closed group of early access users. It is not recommended for production deployments as we may introduce breaking changes.\n",
-    "\n",
-    "To use MongoDB Atlas, you must have first deployed a cluster. Free clusters are available. \n",
-    "Here is the MongoDB Atlas [quick start](https://www.mongodb.com/docs/atlas/getting-started/)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b4c41cad-08ef-4f72-a545-2151e4598efe",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "!pip install pymongo"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c1e38361-c1fe-4ac6-86e9-c90ebaf7ae87",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "MONGODB_ATLAS_URI = os.environ['MONGODB_ATLAS_URI']"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "320af802-9271-46ee-948f-d2453933d44b",
-   "metadata": {},
-   "source": [
-    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key. Make sure the environment variable `OPENAI_API_KEY` is set up before proceeding."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1f3ecc42",
-   "metadata": {},
-   "source": [
-    "Now, let's create a Lucene vector index on your cluster. In the below example, `embedding` is the name of the field that contains the embedding vector. Please refer to the [documentation](https://www.mongodb.com/docs/atlas/atlas-search/define-field-mappings-for-vector-search) to get more details on how to define an Atlas Search index.\n",
-    "You can name the index `langchain_demo` and create the index on the namespace `lanchain_db.langchain_col`. Finally, write the following definition in the JSON editor:\n",
-    "\n",
-    "```json\n",
-    "{\n",
-    "  \"mappings\": {\n",
-    "    \"dynamic\": true,\n",
-    "    \"fields\": {\n",
-    "      \"embedding\": {\n",
-    "        \"dimensions\": 1536,\n",
-    "        \"similarity\": \"cosine\",\n",
-    "        \"type\": \"knnVector\"\n",
-    "      }\n",
-    "    }\n",
-    "  }\n",
-    "}\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "aac9563e",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import MongoDBAtlasVectorSearch\n",
-    "from langchain.document_loaders import TextLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a3c3999a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.document_loaders import TextLoader\n",
-    "loader = TextLoader('../../../state_of_the_union.txt')\n",
-    "documents = loader.load()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "docs = text_splitter.split_documents(documents)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "6e104aee",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from pymongo import MongoClient\n",
-    "\n",
-    "# initialize MongoDB python client\n",
-    "client = MongoClient(MONGODB_ATLAS_CONNECTION_STRING)\n",
-    "\n",
-    "db_name = \"lanchain_db\"\n",
-    "collection_name = \"langchain_col\"\n",
-    "collection = client[db_name][collection_name]\n",
-    "index_name = \"langchain_demo\"\n",
-    "\n",
-    "# insert the documents in MongoDB Atlas with their embedding\n",
-    "docsearch = MongoDBAtlasVectorSearch.from_documents(\n",
-    "    docs,\n",
-    "    embeddings,\n",
-    "    collection=collection,\n",
-    "    index_name=index_name\n",
-    ")\n",
-    "\n",
-    "# perform a similarity search between the embedding of the query and the embeddings of the documents\n",
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9c608226",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(docs[0].page_content)"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/extras/modules/data_connection/vectorstores/integrations/vectara.ipynb

@@ -11,43 +11,11 @@
     ">[Vectara](https://vectara.com/) is a API platform for building LLM-powered applications. It provides a simple to use API for document indexing and query that is managed by Vectara and is optimized for performance and accuracy. \n",
     "\n",
     "\n",
-    "This notebook shows how to use functionality related to the `Vectara` vector database. \n",
+    "This notebook shows how to use functionality related to the `Vectara` vector database or the `Vectara` retriever. \n",
     "\n",
     "See the [Vectara API documentation ](https://docs.vectara.com/docs/) for more information on how to use the API."
    ]
   },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "7b2f111b-357a-4f42-9730-ef0603bdc1b5",
-   "metadata": {},
-   "source": [
-    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "082e7e8b-ac52-430c-98d6-8f0924457642",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "OpenAI API Key:········\n"
-     ]
-    }
-   ],
-   "source": [
-    "import os\n",
-    "import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -61,33 +29,13 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "import os\n",
+    "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"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "a3c3999a",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-04-04T10:51:22.520144Z",
-     "start_time": "2023-04-04T10:51:22.285826Z"
-    },
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
-    "documents = loader.load()\n",
-    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
-    "docs = text_splitter.split_documents(documents)\n",
-    "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -96,7 +44,21 @@
    "source": [
     "## Connecting to Vectara from LangChain\n",
     "\n",
-    "The Vectara API provides simple API endpoints for indexing and querying."
+    "The Vectara API provides simple API endpoints for indexing and querying, which is encapsulated in the Vectara integration.\n",
+    "First let's ingest the documents using the from_documents() method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "be0a4973",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = TextLoader('../../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)\n"
    ]
   },
   {
@@ -112,7 +74,50 @@
    },
    "outputs": [],
    "source": [
-    "vectara = Vectara.from_documents(docs, embedding=None)"
+    "vectara = Vectara.from_documents(docs, \n",
+    "                                 embedding=FakeEmbeddings(size=768), \n",
+    "                                 doc_metadata = {\"speech\": \"state-of-the-union\"})"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "90dbf3e7",
+   "metadata": {},
+   "source": [
+    "Vectara's indexing API provides a file upload API where the file is handled directly by Vectara - pre-processed, chunked optimally and added to the Vectara vector store.\n",
+    "To use this, we added the add_files() method (and from_files()). \n",
+    "\n",
+    "Let's see this in action. We pick two PDF documents to upload: \n",
+    "1. The \"I have a dream\" speech by Dr. King\n",
+    "2. Churchill's \"We Shall Fight on the Beaches\" speech"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "85ef3468",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tempfile\n",
+    "import urllib.request\n",
+    "\n",
+    "urls = [\n",
+    "    ['https://www.gilderlehrman.org/sites/default/files/inline-pdfs/king.dreamspeech.excerpts.pdf', 'I-have-a-dream'],\n",
+    "    ['https://www.parkwayschools.net/cms/lib/MO01931486/Centricity/Domain/1578/Churchill_Beaches_Speech.pdf', 'we shall fight on the beaches'],\n",
+    "]\n",
+    "files_list = []\n",
+    "for url,_ in urls:\n",
+    "    name = tempfile.NamedTemporaryFile().name\n",
+    "    urllib.request.urlretrieve(url, name)\n",
+    "    files_list.append(name)\n",
+    "\n",
+    "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",
+    ")"
    ]
   },
   {
@@ -133,7 +138,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "a8c513ab",
    "metadata": {
     "ExecuteTime": {
@@ -145,12 +150,12 @@
    "outputs": [],
    "source": [
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "found_docs = vectara.similarity_search(query, n_sentence_context=0)"
+    "found_docs = vectara.similarity_search(query, n_sentence_context=0, filter=\"doc.speech = 'state-of-the-union'\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "fc516993",
    "metadata": {
     "ExecuteTime": {
@@ -191,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "8804a21d",
    "metadata": {
     "ExecuteTime": {
@@ -202,12 +207,12 @@
    "outputs": [],
    "source": [
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "found_docs = vectara.similarity_search_with_score(query)"
+    "found_docs = vectara.similarity_search_with_score(query, filter=\"doc.speech = 'state-of-the-union'\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "756a6887",
    "metadata": {
     "ExecuteTime": {
@@ -228,7 +233,7 @@
       "\n",
       "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
       "\n",
-      "Score: 0.7129974\n"
+      "Score: 0.4917977\n"
      ]
     }
    ],
@@ -238,6 +243,37 @@
     "print(f\"\\nScore: {score}\")"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "1f9876a8",
+   "metadata": {},
+   "source": [
+    "Now let's do similar search for content in the files we uploaded"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "47784de5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(Document(page_content='We must forever conduct our struggle on the high plane of dignity and discipline.', metadata={'section': '1'}), 0.7962591)\n",
+      "(Document(page_content='We must not allow our\\ncreative protests to degenerate into physical violence. . . .', metadata={'section': '1'}), 0.25983918)\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"We must forever conduct our struggle\"\n",
+    "found_docs = vectara.similarity_search_with_score(query, filter=\"doc.speech = 'I-have-a-dream'\")\n",
+    "print(found_docs[0])\n",
+    "print(found_docs[1])"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -246,12 +282,12 @@
    "source": [
     "## Vectara as a Retriever\n",
     "\n",
-    "Vectara, as all the other vector stores, is a LangChain Retriever, by using cosine similarity. "
+    "Vectara, as all the other vector stores, can be used also as a LangChain Retriever:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
    "id": "9427195f",
    "metadata": {
     "ExecuteTime": {
@@ -263,10 +299,10 @@
     {
      "data": {
       "text/plain": [
-       "VectaraRetriever(vectorstore=<langchain.vectorstores.vectara.Vectara object at 0x122db2830>, search_type='similarity', search_kwargs={'lambda_val': 0.025, 'k': 5, 'filter': '', 'n_sentence_context': '0'})"
+       "VectaraRetriever(vectorstore=<langchain.vectorstores.vectara.Vectara object at 0x12772caf0>, search_type='similarity', search_kwargs={'lambda_val': 0.025, 'k': 5, 'filter': '', 'n_sentence_context': '0'})"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -278,7 +314,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 12,
    "id": "f3c70c31",
    "metadata": {
     "ExecuteTime": {
@@ -293,7 +329,7 @@
        "Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd 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.', metadata={'source': '../../../state_of_the_union.txt'})"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/extras/modules/memory/integrations/zep_memory.ipynb

@@ -40,10 +40,7 @@
    "cell_type": "code",
    "execution_count": 1,
    "metadata": {
-    "ExecuteTime": {
-     "end_time": "2023-05-25T15:09:41.754535Z",
-     "start_time": "2023-05-25T15:09:40.897232Z"
-    }
+    "is_executing": true
    },
    "outputs": [],
    "source": [
@@ -51,8 +48,8 @@
     "from langchain.memory import ConversationBufferMemory\n",
     "from langchain import OpenAI\n",
     "from langchain.schema import HumanMessage, AIMessage\n",
-    "from langchain.tools import DuckDuckGoSearchRun\n",
-    "from langchain.agents import initialize_agent, AgentType\n",
+    "from langchain.utilities import WikipediaAPIWrapper\n",
+    "from langchain.agents import initialize_agent, AgentType, Tool\n",
     "from uuid import uuid4\n",
     "\n",
     "\n",
@@ -73,19 +70,37 @@
    },
    "outputs": [
     {
-     "data": {
-      "text/plain": "True"
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
     }
    ],
    "source": [
-    "# Load your OpenAI key from a .env file\n",
-    "from dotenv import load_dotenv\n",
+    "# Provide your OpenAI key\n",
+    "import getpass\n",
     "\n",
-    "load_dotenv()"
+    "openai_key = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Provide your Zep API key. Note that this is optional. See https://docs.getzep.com/deployment/auth\n",
+    "\n",
+    "zep_api_key = getpass.getpass()"
    ]
   },
   {
@@ -98,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:09:41.840440Z",
@@ -107,13 +122,20 @@
    },
    "outputs": [],
    "source": [
-    "ddg = DuckDuckGoSearchRun()\n",
-    "tools = [ddg]\n",
+    "search = WikipediaAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name=\"Search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to search online for answers. You should ask targeted questions\",\n",
+    "    ),\n",
+    "]\n",
     "\n",
     "# Set up Zep Chat History\n",
     "zep_chat_history = ZepChatMessageHistory(\n",
     "    session_id=session_id,\n",
     "    url=ZEP_API_URL,\n",
+    "    api_key=zep_api_key\n",
     ")\n",
     "\n",
     "# Use a standard ConversationBufferMemory to encapsulate the Zep chat history\n",
@@ -122,7 +144,7 @@
     ")\n",
     "\n",
     "# Initialize the agent\n",
-    "llm = OpenAI(temperature=0)\n",
+    "llm = OpenAI(temperature=0, openai_api_key=openai_key)\n",
     "agent_chain = initialize_agent(\n",
     "    tools,\n",
     "    llm,\n",
@@ -142,7 +164,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:09:41.960661Z",
@@ -212,7 +234,7 @@
     "]\n",
     "\n",
     "for msg in test_history:\n",
-    "    zep_chat_history.append(\n",
+    "    zep_chat_history.add_message(\n",
     "        HumanMessage(content=msg[\"content\"])\n",
     "        if msg[\"role\"] == \"human\"\n",
     "        else AIMessage(content=msg[\"content\"])\n",
@@ -231,7 +253,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:09:50.485377Z",
@@ -245,18 +267,20 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: Do I need to use a tool? No\n",
-      "AI: Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, economic inequality, and the rise of authoritarianism. It is a cautionary tale that warns of the dangers of ignoring these issues and the importance of taking action to address them.\u001b[0m\n",
+      "\u001B[1m> Entering new  chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: Do I need to use a tool? No\n",
+      "AI: Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, economic inequality, and the rise of authoritarianism. It is a cautionary tale that warns of the dangers of ignoring these issues and the importance of taking action to address them.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
      "data": {
-      "text/plain": "'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, economic inequality, and the rise of authoritarianism. It is a cautionary tale that warns of the dangers of ignoring these issues and the importance of taking action to address them.'"
+      "text/plain": [
+       "'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, economic inequality, and the rise of authoritarianism. It is a cautionary tale that warns of the dangers of ignoring these issues and the importance of taking action to address them.'"
+      ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -281,7 +305,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:09:50.493438Z",
@@ -293,19 +317,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "The conversation is about Octavia Butler. The AI describes her as an American science fiction author and mentions the\n",
-      "FX series Kindred as a well-known adaptation of her work. The human then asks about her contemporaries, and the AI lists \n",
-      "Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\n",
+      "The human asks about Octavia Butler and the AI identifies her as an American science fiction author. They continue to discuss her works and the fact that the FX series Kindred is based on one of her novels. The AI also lists Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ as Butler's contemporaries.\n",
       "\n",
       "\n",
-      "{'role': 'human', 'content': 'What awards did she win?', 'uuid': '9fa75c3c-edae-41e3-b9bc-9fcf16b523c9', 'created_at': '2023-05-25T15:09:41.91662Z', 'token_count': 8}\n",
-      "{'role': 'ai', 'content': 'Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur Fellowship.', 'uuid': 'def4636c-32cb-49ed-b671-32035a034712', 'created_at': '2023-05-25T15:09:41.919874Z', 'token_count': 21}\n",
-      "{'role': 'human', 'content': 'Which other women sci-fi writers might I want to read?', 'uuid': '6e87bd4a-bc23-451e-ae36-05a140415270', 'created_at': '2023-05-25T15:09:41.923771Z', 'token_count': 14}\n",
-      "{'role': 'ai', 'content': 'You might want to read Ursula K. Le Guin or Joanna Russ.', 'uuid': 'f65d8dde-9ee8-4983-9da6-ba789b7e8aa4', 'created_at': '2023-05-25T15:09:41.935254Z', 'token_count': 18}\n",
-      "{'role': 'human', 'content': \"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", 'uuid': '5678d056-7f05-4e70-b8e5-f85efa56db01', 'created_at': '2023-05-25T15:09:41.938974Z', 'token_count': 23}\n",
-      "{'role': 'ai', 'content': 'Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', 'uuid': '50d64946-9239-4327-83e6-71dcbdd16198', 'created_at': '2023-05-25T15:09:41.957437Z', 'token_count': 56}\n",
-      "{'role': 'human', 'content': \"WWhat is the book's relevance to the challenges facing contemporary society?\", 'uuid': 'a39cfc07-8858-480a-9026-fc47a8ef7001', 'created_at': '2023-05-25T15:09:50.469533Z', 'token_count': 16}\n",
-      "{'role': 'ai', 'content': 'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, economic inequality, and the rise of authoritarianism. It is a cautionary tale that warns of the dangers of ignoring these issues and the importance of taking action to address them.', 'uuid': 'a4ecf0fe-fdd0-4aad-b72b-efde2e6830cc', 'created_at': '2023-05-25T15:09:50.473793Z', 'token_count': 62}\n"
+      "{'role': 'human', 'content': 'What awards did she win?', 'uuid': 'a4bdc592-71a5-47d0-9c64-230b882aab48', 'created_at': '2023-06-26T23:37:56.383953Z', 'token_count': 8, 'metadata': {'system': {'entities': [], 'intent': 'The subject is asking about the awards someone won, likely referring to a specific individual.'}}}\n",
+      "{'role': 'ai', 'content': 'Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur Fellowship.', 'uuid': '60cc6e6b-7cd4-4a81-aebc-72ef997286b4', 'created_at': '2023-06-26T23:37:56.389935Z', 'token_count': 21, 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 14, 'Start': 0, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 33, 'Start': 19, 'Text': 'the Hugo Award'}], 'Name': 'the Hugo Award'}, {'Label': 'EVENT', 'Matches': [{'End': 81, 'Start': 57, 'Text': 'the MacArthur Fellowship'}], 'Name': 'the MacArthur Fellowship'}], 'intent': 'The subject is stating the accomplishments and awards received by Octavia Butler.'}}}\n",
+      "{'role': 'human', 'content': 'Which other women sci-fi writers might I want to read?', 'uuid': 'b189fc60-1510-4a4b-a503-899481d652de', 'created_at': '2023-06-26T23:37:56.395722Z', 'token_count': 14, 'metadata': {'system': {'entities': [], 'intent': 'The subject is looking for recommendations on women science fiction writers to read.'}}}\n",
+      "{'role': 'ai', 'content': 'You might want to read Ursula K. Le Guin or Joanna Russ.', 'uuid': '4be1ccbb-a915-45d6-9f18-7a0c1cbd9907', 'created_at': '2023-06-26T23:37:56.403596Z', 'token_count': 18, 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 40, 'Start': 23, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 55, 'Start': 44, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': 'The subject is suggesting reading material and making a literary recommendation.'}}}\n",
+      "{'role': 'human', 'content': \"Write a short synopsis of Butler's book, Parable of the Sower. What is it about?\", 'uuid': 'ac3c5e3e-26a7-4f3b-aeb0-bba084e22753', 'created_at': '2023-06-26T23:37:56.410662Z', 'token_count': 23, 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 32, 'Start': 26, 'Text': 'Butler'}], 'Name': 'Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 61, 'Start': 41, 'Text': 'Parable of the Sower'}], 'Name': 'Parable of the Sower'}], 'intent': 'The subject is asking for a brief overview or summary of the book \"Parable of the Sower\" written by Butler.'}}}\n",
+      "{'role': 'ai', 'content': 'Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', 'uuid': '4a463b4c-bcab-473c-bed1-fc56a7a20ae2', 'created_at': '2023-06-26T23:37:56.41764Z', 'token_count': 56, 'metadata': {'system': {'entities': [{'Label': 'GPE', 'Matches': [{'End': 20, 'Start': 15, 'Text': 'Sower'}], 'Name': 'Sower'}, {'Label': 'PERSON', 'Matches': [{'End': 65, 'Start': 51, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'DATE', 'Matches': [{'End': 84, 'Start': 80, 'Text': '1993'}], 'Name': '1993'}, {'Label': 'PERSON', 'Matches': [{'End': 124, 'Start': 110, 'Text': 'Lauren Olamina'}], 'Name': 'Lauren Olamina'}]}}}\n",
+      "{'role': 'human', 'content': \"WWhat is the book's relevance to the challenges facing contemporary society?\", 'uuid': '41bab0c7-5e20-40a4-9303-f82069977c91', 'created_at': '2023-06-26T23:38:03.559642Z', 'token_count': 16, 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 5, 'Start': 0, 'Text': 'WWhat'}], 'Name': 'WWhat'}]}}}\n",
+      "{'role': 'ai', 'content': 'Parable of the Sower is a prescient novel that speaks to the challenges facing contemporary society, such as climate change, economic inequality, and the rise of authoritarianism. It is a cautionary tale that warns of the dangers of ignoring these issues and the importance of taking action to address them.', 'uuid': 'bfd8146a-4632-4c8c-98b6-9468bb624339', 'created_at': '2023-06-26T23:38:03.589312Z', 'token_count': 62, 'metadata': {'system': {'entities': [{'Label': 'GPE', 'Matches': [{'End': 20, 'Start': 15, 'Text': 'Sower'}], 'Name': 'Sower'}]}}}\n"
      ]
     }
    ],
@@ -332,7 +354,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "metadata": {
     "ExecuteTime": {
      "end_time": "2023-05-25T15:09:50.751203Z",
@@ -344,16 +366,16 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'uuid': '6e87bd4a-bc23-451e-ae36-05a140415270', 'created_at': '2023-05-25T15:09:41.923771Z', 'role': 'human', 'content': 'Which other women sci-fi writers might I want to read?', 'token_count': 14} 0.9118298949424545\n",
-      "{'uuid': 'f65d8dde-9ee8-4983-9da6-ba789b7e8aa4', 'created_at': '2023-05-25T15:09:41.935254Z', 'role': 'ai', 'content': 'You might want to read Ursula K. Le Guin or Joanna Russ.', 'token_count': 18} 0.8533024416448016\n",
-      "{'uuid': '52cfe3e8-b800-4dd8-a7dd-8e9e4764dfc8', 'created_at': '2023-05-25T15:09:41.913856Z', 'role': 'ai', 'content': \"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", 'token_count': 27} 0.852352466457884\n",
-      "{'uuid': 'd40da612-0867-4a43-92ec-778b86490a39', 'created_at': '2023-05-25T15:09:41.858543Z', 'role': 'human', 'content': 'Who was Octavia Butler?', 'token_count': 8} 0.8235468913583194\n",
-      "{'uuid': '4fcfbce4-7bfa-44bd-879a-8cbf265bdcf9', 'created_at': '2023-05-25T15:09:41.893848Z', 'role': 'ai', 'content': 'Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American science fiction author.', 'token_count': 31} 0.8204317130595353\n",
-      "{'uuid': 'def4636c-32cb-49ed-b671-32035a034712', 'created_at': '2023-05-25T15:09:41.919874Z', 'role': 'ai', 'content': 'Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur Fellowship.', 'token_count': 21} 0.8196714827228725\n",
-      "{'uuid': '862107de-8f6f-43c0-91fa-4441f01b2b3a', 'created_at': '2023-05-25T15:09:41.898149Z', 'role': 'human', 'content': 'Which books of hers were made into movies?', 'token_count': 11} 0.7954322970428519\n",
-      "{'uuid': '97164506-90fe-4c71-9539-69ebcd1d90a2', 'created_at': '2023-05-25T15:09:41.90887Z', 'role': 'human', 'content': 'Who were her contemporaries?', 'token_count': 8} 0.7942531405021976\n",
-      "{'uuid': '50d64946-9239-4327-83e6-71dcbdd16198', 'created_at': '2023-05-25T15:09:41.957437Z', 'role': 'ai', 'content': 'Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', 'token_count': 56} 0.78144769172694\n",
-      "{'uuid': 'c460ffd4-0715-4c69-b793-1092054973e6', 'created_at': '2023-05-25T15:09:41.903082Z', 'role': 'ai', 'content': \"The most well-known adaptation of Octavia Butler's work is the FX series Kindred, based on her novel of the same name.\", 'token_count': 29} 0.7811962820699464\n"
+      "{'uuid': 'b189fc60-1510-4a4b-a503-899481d652de', 'created_at': '2023-06-26T23:37:56.395722Z', 'role': 'human', 'content': 'Which other women sci-fi writers might I want to read?', 'metadata': {'system': {'entities': [], 'intent': 'The subject is looking for recommendations on women science fiction writers to read.'}}, 'token_count': 14} 0.9119619869747062\n",
+      "{'uuid': '4be1ccbb-a915-45d6-9f18-7a0c1cbd9907', 'created_at': '2023-06-26T23:37:56.403596Z', 'role': 'ai', 'content': 'You might want to read Ursula K. Le Guin or Joanna Russ.', 'metadata': {'system': {'entities': [{'Label': 'ORG', 'Matches': [{'End': 40, 'Start': 23, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 55, 'Start': 44, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': 'The subject is suggesting reading material and making a literary recommendation.'}}, 'token_count': 18} 0.8534346954749745\n",
+      "{'uuid': '76ec2a3d-b908-4c23-a55d-71ff92865a7a', 'created_at': '2023-06-26T23:37:56.378345Z', 'role': 'ai', 'content': \"Octavia Butler's contemporaries included Ursula K. Le Guin, Samuel R. Delany, and Joanna Russ.\", 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 16, 'Start': 0, 'Text': \"Octavia Butler's\"}], 'Name': \"Octavia Butler's\"}, {'Label': 'ORG', 'Matches': [{'End': 58, 'Start': 41, 'Text': 'Ursula K. Le Guin'}], 'Name': 'Ursula K. Le Guin'}, {'Label': 'PERSON', 'Matches': [{'End': 76, 'Start': 60, 'Text': 'Samuel R. Delany'}], 'Name': 'Samuel R. Delany'}, {'Label': 'PERSON', 'Matches': [{'End': 93, 'Start': 82, 'Text': 'Joanna Russ'}], 'Name': 'Joanna Russ'}], 'intent': 'The subject is stating the contemporaries of Octavia Butler, who are also science fiction writers.'}}, 'token_count': 27} 0.8523930955780226\n",
+      "{'uuid': '1feb02c7-63c9-4616-854d-0d97fb590ea5', 'created_at': '2023-06-26T23:37:56.313009Z', 'role': 'human', 'content': 'Who was Octavia Butler?', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 22, 'Start': 8, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}], 'intent': 'The subject is asking about the identity of Octavia Butler, likely seeking information about her background or accomplishments.'}}, 'token_count': 8} 0.8236355436055457\n",
+      "{'uuid': 'ebe4696d-b5fa-4ca0-88c9-da794d9611ab', 'created_at': '2023-06-26T23:37:56.332247Z', 'role': 'ai', 'content': 'Octavia Estelle Butler (June 22, 1947 – February 24, 2006) was an American science fiction author.', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 22, 'Start': 0, 'Text': 'Octavia Estelle Butler'}], 'Name': 'Octavia Estelle Butler'}, {'Label': 'DATE', 'Matches': [{'End': 37, 'Start': 24, 'Text': 'June 22, 1947'}], 'Name': 'June 22, 1947'}, {'Label': 'DATE', 'Matches': [{'End': 57, 'Start': 40, 'Text': 'February 24, 2006'}], 'Name': 'February 24, 2006'}, {'Label': 'NORP', 'Matches': [{'End': 74, 'Start': 66, 'Text': 'American'}], 'Name': 'American'}], 'intent': 'The subject is making a statement about the background and profession of Octavia Estelle Butler, an American author.'}}, 'token_count': 31} 0.8206687242257686\n",
+      "{'uuid': '60cc6e6b-7cd4-4a81-aebc-72ef997286b4', 'created_at': '2023-06-26T23:37:56.389935Z', 'role': 'ai', 'content': 'Octavia Butler won the Hugo Award, the Nebula Award, and the MacArthur Fellowship.', 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 14, 'Start': 0, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'WORK_OF_ART', 'Matches': [{'End': 33, 'Start': 19, 'Text': 'the Hugo Award'}], 'Name': 'the Hugo Award'}, {'Label': 'EVENT', 'Matches': [{'End': 81, 'Start': 57, 'Text': 'the MacArthur Fellowship'}], 'Name': 'the MacArthur Fellowship'}], 'intent': 'The subject is stating the accomplishments and awards received by Octavia Butler.'}}, 'token_count': 21} 0.8194249796585193\n",
+      "{'uuid': '0fa4f336-909d-4880-b01a-8e80e91fa8f2', 'created_at': '2023-06-26T23:37:56.344552Z', 'role': 'human', 'content': 'Which books of hers were made into movies?', 'metadata': {'system': {'entities': [], 'intent': 'The subject is inquiring about which books written by an unknown female author were adapted into movies.'}}, 'token_count': 11} 0.7955105671310818\n",
+      "{'uuid': 'f91de7f2-4b84-4c5a-8a33-a71f38f3a59c', 'created_at': '2023-06-26T23:37:56.368146Z', 'role': 'human', 'content': 'Who were her contemporaries?', 'metadata': {'system': {'entities': [], 'intent': 'The subject is asking about the people who lived during the same time period as a specific individual.'}}, 'token_count': 8} 0.7942358617914813\n",
+      "{'uuid': '4a463b4c-bcab-473c-bed1-fc56a7a20ae2', 'created_at': '2023-06-26T23:37:56.41764Z', 'role': 'ai', 'content': 'Parable of the Sower is a science fiction novel by Octavia Butler, published in 1993. It follows the story of Lauren Olamina, a young woman living in a dystopian future where society has collapsed due to environmental disasters, poverty, and violence.', 'metadata': {'system': {'entities': [{'Label': 'GPE', 'Matches': [{'End': 20, 'Start': 15, 'Text': 'Sower'}], 'Name': 'Sower'}, {'Label': 'PERSON', 'Matches': [{'End': 65, 'Start': 51, 'Text': 'Octavia Butler'}], 'Name': 'Octavia Butler'}, {'Label': 'DATE', 'Matches': [{'End': 84, 'Start': 80, 'Text': '1993'}], 'Name': '1993'}, {'Label': 'PERSON', 'Matches': [{'End': 124, 'Start': 110, 'Text': 'Lauren Olamina'}], 'Name': 'Lauren Olamina'}]}}, 'token_count': 56} 0.7816448549236643\n",
+      "{'uuid': '6161d934-a629-4ba2-8bba-0b0996c93964', 'created_at': '2023-06-26T23:37:56.358632Z', 'role': 'ai', 'content': \"The most well-known adaptation of Octavia Butler's work is the FX series Kindred, based on her novel of the same name.\", 'metadata': {'system': {'entities': [{'Label': 'PERSON', 'Matches': [{'End': 50, 'Start': 34, 'Text': \"Octavia Butler's\"}], 'Name': \"Octavia Butler's\"}, {'Label': 'ORG', 'Matches': [{'End': 65, 'Start': 63, 'Text': 'FX'}], 'Name': 'FX'}, {'Label': 'GPE', 'Matches': [{'End': 80, 'Start': 73, 'Text': 'Kindred'}], 'Name': 'Kindred'}], 'intent': \"The subject is discussing Octavia Butler's work being adapted into a TV series called Kindred.\"}}, 'token_count': 29} 0.7815841371388998\n"
      ]
     }
    ],
@@ -362,11 +384,25 @@
     "for r in search_results:\n",
     "    print(r.message, r.dist)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -380,10 +416,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  },
-  "orig_nbformat": 4
+   "version": "3.11.4"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/requirements.txt

@@ -11,5 +11,4 @@ myst_nb
 sphinx_copybutton
 pydata-sphinx-theme==0.13.1
 nbdoc
-urllib3<2
-sphinx_tabs
+urllib3<2

docs/snippets/modules/data_connection/document_loaders/how_to/json.mdx

@@ -78,11 +78,14 @@ pprint(data)
 
 </CodeOutputBlock>
 
+
 ## Using `JSONLoader`
 
 Suppose we are interested in extracting the values under the `content` field within the `messages` key of the JSON data. This can easily be done through the `JSONLoader` as shown below.
 
 
+### JSON file
+
 ```python
 loader = JSONLoader(
     file_path='./example_data/facebook_chat.json',
@@ -114,6 +117,81 @@ pprint(data)
 
 </CodeOutputBlock>
 
+
+### JSON Lines file
+
+If you want to load documents from a JSON Lines file, you pass `json_lines=True`
+and specify `jq_schema` to extract `page_content` from a single JSON object.
+
+```python
+file_path = './example_data/facebook_chat_messages.jsonl'
+pprint(Path(file_path).read_text())
+```
+
+<CodeOutputBlock lang="python">
+
+```
+    ('{"sender_name": "User 2", "timestamp_ms": 1675597571851, "content": "Bye!"}\n'
+     '{"sender_name": "User 1", "timestamp_ms": 1675597435669, "content": "Oh no '
+     'worries! Bye"}\n'
+     '{"sender_name": "User 2", "timestamp_ms": 1675596277579, "content": "No Im '
+     'sorry it was my mistake, the blue one is not for sale"}\n')
+```
+
+</CodeOutputBlock>
+
+
+```python
+loader = JSONLoader(
+    file_path='./example_data/facebook_chat_messages.jsonl',
+    jq_schema='.content',
+    json_lines=True)
+
+data = loader.load()
+```
+
+```python
+pprint(data)
+```
+
+<CodeOutputBlock lang="python">
+
+```
+    [Document(page_content='Bye!', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat_messages.jsonl', 'seq_num': 1}),
+     Document(page_content='Oh no worries! Bye', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat_messages.jsonl', 'seq_num': 2}),
+     Document(page_content='No Im sorry it was my mistake, the blue one is not for sale', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat_messages.jsonl', 'seq_num': 3})]
+```
+
+</CodeOutputBlock>
+
+
+Another option is set `jq_schema='.'` and provide `content_key`:
+
+```python
+loader = JSONLoader(
+    file_path='./example_data/facebook_chat_messages.jsonl',
+    jq_schema='.',
+    content_key='sender_name',
+    json_lines=True)
+
+data = loader.load()
+```
+
+```python
+pprint(data)
+```
+
+<CodeOutputBlock lang="python">
+
+```
+    [Document(page_content='User 2', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat_messages.jsonl', 'seq_num': 1}),
+     Document(page_content='User 1', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat_messages.jsonl', 'seq_num': 2}),
+     Document(page_content='User 2', metadata={'source': 'langchain/docs/modules/indexes/document_loaders/examples/example_data/facebook_chat_messages.jsonl', 'seq_num': 3})]
+```
+
+</CodeOutputBlock>
+
+
 ## Extracting metadata
 
 Generally, we want to include metadata available in the JSON file into the documents that we create from the content.

docs/snippets/modules/data_connection/retrievers/get_started.mdx

@@ -1,24 +1,40 @@
-The `BaseRetriever` class in LangChain is as follows:
+The public API of the `BaseRetriever` class in LangChain is as follows:
 
 ```python
 from abc import ABC, abstractmethod
-from typing import List
+from typing import Any, List
 from langchain.schema import Document
+from langchain.callbacks.manager import Callbacks
 
 class BaseRetriever(ABC):
-    @abstractmethod
-    def get_relevant_documents(self, query: str) -> List[Document]:
-        """Get texts relevant for a query.
-
+    ...
+    def get_relevant_documents(
+        self, query: str, *, callbacks: Callbacks = None, **kwargs: Any
+    ) -> List[Document]:
+        """Retrieve documents relevant to a query.
         Args:
-            query: string to find relevant texts for
-
+            query: string to find relevant documents for
+            callbacks: Callback manager or list of callbacks
         Returns:
             List of relevant documents
         """
+        ...
+
+    async def aget_relevant_documents(
+        self, query: str, *, callbacks: Callbacks = None, **kwargs: Any
+    ) -> List[Document]:
+        """Asynchronously get documents relevant to a query.
+        Args:
+            query: string to find relevant documents for
+            callbacks: Callback manager or list of callbacks
+        Returns:
+            List of relevant documents
+        """
+        ...
 ```
 
-It's that simple! The `get_relevant_documents` method can be implemented however you see fit.
+It's that simple! You can call `get_relevant_documents` or the async `get_relevant_documents` methods to retrieve documents relevant to a query, where "relevance" is defined by
+the specific retriever object you are calling.
 
 Of course, we also help construct what we think useful Retrievers are. The main type of Retriever that we focus on is a Vectorstore retriever. We will focus on that for the rest of this guide.
 

docs/snippets/modules/data_connection/retrievers/how_to/custom_retriever.mdx

@@ -0,0 +1,161 @@
+# Implement a Custom Retriever
+
+In this walkthrough, you will implement a simple custom retriever in LangChain using a simple dot product distance lookup.
+
+All retrievers inherit from the `BaseRetriever` class and override the following abstract methods:
+
+```python
+from abc import ABC, abstractmethod
+from typing import Any, List
+from langchain.schema import Document
+from langchain.callbacks.manager import (
+        AsyncCallbackManagerForRetrieverRun,
+        CallbackManagerForRetrieverRun,
+)
+
+class BaseRetriever(ABC):
+
+    @abstractmethod
+    def _get_relevant_documents(
+        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
+    ) -> List[Document]:
+        """Get documents relevant to a query.
+        Args:
+            query: string to find relevant documents for
+            run_manager: The callbacks handler to use
+        Returns:
+            List of relevant documents
+        """
+
+    @abstractmethod
+    async def _aget_relevant_documents(
+        self,
+        query: str,
+        *,
+        run_manager: AsyncCallbackManagerForRetrieverRun,
+    ) -> List[Document]:
+        """Asynchronously get documents relevant to a query.
+        Args:
+            query: string to find relevant documents for
+            run_manager: The callbacks handler to use
+        Returns:
+            List of relevant documents
+        """
+```
+
+
+The `_get_relevant_documents` and async `_get_relevant_documents` methods can be implemented however you see fit. The `run_manager` is useful if your retriever calls other traceable LangChain primitives like LLMs, chains, or tools.
+
+
+Below, implement an example that fetches the most similar documents from a list of documents using a numpy array of embeddings.
+
+
+```python
+from typing import Any, List, Optional
+
+import numpy as np
+
+from langchain.callbacks.manager import (
+    AsyncCallbackManagerForRetrieverRun,
+    CallbackManagerForRetrieverRun,
+)
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings.base import Embeddings
+from langchain.schema import BaseRetriever, Document
+
+
+class NumpyRetriever(BaseRetriever):
+    """Retrieves documents from a numpy array."""
+
+    def __init__(
+        self,
+        texts: List[str],
+        vectors: np.ndarray,
+        embeddings: Optional[Embeddings] = None,
+        num_to_return: int = 1,
+    ) -> None:
+        super().__init__()
+        self.embeddings = embeddings or OpenAIEmbeddings()
+        self.texts = texts
+        self.vectors = vectors
+        self.num_to_return = num_to_return
+
+    @classmethod
+    def from_texts(
+        cls,
+        texts: List[str],
+        embeddings: Optional[Embeddings] = None,
+        **kwargs: Any,
+    ) -> "NumpyRetriever":
+        embeddings = embeddings or OpenAIEmbeddings()
+        vectors = np.array(embeddings.embed_documents(texts))
+        return cls(texts, vectors, embeddings)
+
+    def _get_relevant_documents_from_query_vector(
+        self, vector_query: np.ndarray
+    ) -> List[Document]:
+        dot_product = np.dot(self.vectors, vector_query)
+        # Get the indices of the min 5 documents
+        indices = np.argpartition(
+            dot_product, -min(self.num_to_return, len(self.vectors))
+        )[-self.num_to_return :]
+        # Sort indices by distance
+        indices = indices[np.argsort(dot_product[indices])]
+        return [
+            Document(
+                page_content=self.texts[idx],
+                metadata={"index": idx},
+            )
+            for idx in indices
+        ]
+
+    def _get_relevant_documents(
+        self, query: str, *, run_manager: CallbackManagerForRetrieverRun
+    ) -> List[Document]:
+        """Get documents relevant to a query.
+        Args:
+            query: string to find relevant documents for
+            run_manager: The callbacks handler to use
+        Returns:
+            List of relevant documents
+        """
+        vector_query = np.array(self.embeddings.embed_query(query))
+        return self._get_relevant_documents_from_query_vector(vector_query)
+
+    async def _aget_relevant_documents(
+        self,
+        query: str,
+        *,
+        run_manager: AsyncCallbackManagerForRetrieverRun,
+    ) -> List[Document]:
+        """Asynchronously get documents relevant to a query.
+        Args:
+            query: string to find relevant documents for
+            run_manager: The callbacks handler to use
+        Returns:
+            List of relevant documents
+        """
+        query_emb = await self.embeddings.aembed_query(query)
+        return self._get_relevant_documents_from_query_vector(np.array(query_emb))
+```
+
+The retriever can be instantiated through the class method `from_texts`. It embeds the texts and stores them in a numpy array. To look up documents, it embeds the query and finds the most similar documents using a simple dot product distance.
+Once the retriever is implemented, you can use it like any other retriever in LangChain.
+
+
+```python
+retriever = NumpyRetriever.from_texts(texts= ["hello world", "goodbye world"])
+```
+
+You can then use the retriever to get relevant documents.
+
+```python
+retriever.get_relevant_documents("Hi there!")
+
+# [Document(page_content='hello world', metadata={'index': 0})]
+```
+
+```python
+retriever.get_relevant_documents("Bye!")
+# [Document(page_content='goodbye world', metadata={'index': 1})]
+```

docs/snippets/modules/data_connection/text_embedding/get_started.mdx

@@ -31,7 +31,7 @@ embeddings_model = OpenAIEmbeddings()
 #### Embed list of texts
 
 ```python
-embeddings = embedding_model.embed_documents(
+embeddings = embeddings_model.embed_documents(
     [
         "Hi there!",
         "Oh, hello!",
@@ -56,7 +56,7 @@ len(embeddings), len(embeddings[0])
 Embed a single piece of text for the purpose of comparing to other embedded pieces of texts.
 
 ```python
-embedded_query = embedding_model.embed_query("What was the name mentioned in the conversation?")
+embedded_query = embeddings_model.embed_query("What was the name mentioned in the conversation?")
 embedded_query[:5]
 ```
 

docs/snippets/modules/data_connection/vectorstores/get_started.mdx

@@ -26,7 +26,8 @@ raw_documents = TextLoader('../../../state_of_the_union.txt').load()
 text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
 documents = text_splitter.split_documents(raw_documents)
 
-db = FAISS.from_documents(documents, OpenAIEmbeddings())
+embeddings = OpenAIEmbeddings()
+db = FAISS.from_documents(documents, embeddings)
 ```
 
 ### Similarity search

docs/snippets/modules/model_io/models/chat/get_started.mdx

@@ -16,7 +16,7 @@ If you'd prefer not to set an environment variable you can pass the key in direc
 ```python
 from langchain.chat_models import ChatOpenAI
 
-chat = ChatOpenAI(open_api_key="...")
+chat = ChatOpenAI(openai_api_key="...")
 ```
 
 otherwise you can initialize without any params:

docs/snippets/modules/model_io/prompts/prompt_templates/prompt_composition.mdx

@@ -65,7 +65,7 @@ pipeline_prompt.input_variables
 print(pipeline_prompt.format(
     person="Elon Musk",
     example_q="What's your favorite car?",
-    example_a="Telsa",
+    example_a="Tesla",
     input="What's your favorite social media site?"
 ))
 ```
@@ -77,7 +77,7 @@ print(pipeline_prompt.format(
     Here's an example of an interaction: 
     
     Q: What's your favorite car?
-    A: Telsa
+    A: Tesla
     Now, do this for real!
     
     Q: What's your favorite social media site?

langchain/__init__.py

@@ -38,11 +38,11 @@ from langchain.llms import (
 )
 from langchain.llms.huggingface_pipeline import HuggingFacePipeline
 from langchain.prompts import (
-    BasePromptTemplate,
     FewShotPromptTemplate,
     Prompt,
     PromptTemplate,
 )
+from langchain.schema.prompt_template import BasePromptTemplate
 from langchain.sql_database import SQLDatabase
 from langchain.utilities.arxiv import ArxivAPIWrapper
 from langchain.utilities.google_search import GoogleSearchAPIWrapper

langchain/agents/agent.py

@@ -26,16 +26,16 @@ from langchain.callbacks.manager import (
 from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain
 from langchain.input import get_color_mapping
-from langchain.prompts.base import BasePromptTemplate
 from langchain.prompts.few_shot import FewShotPromptTemplate
 from langchain.prompts.prompt import PromptTemplate
 from langchain.schema import (
     AgentAction,
     AgentFinish,
-    BaseMessage,
     BaseOutputParser,
+    BasePromptTemplate,
     OutputParserException,
 )
+from langchain.schema.messages import BaseMessage
 from langchain.tools.base import BaseTool
 from langchain.utilities.asyncio import asyncio_timeout
 

langchain/agents/agent_toolkits/openapi/planner.py

@@ -34,8 +34,8 @@ from langchain.chains.llm import LLMChain
 from langchain.llms.openai import OpenAI
 from langchain.memory import ReadOnlySharedMemory
 from langchain.prompts import PromptTemplate
-from langchain.prompts.base import BasePromptTemplate
 from langchain.requests import RequestsWrapper
+from langchain.schema import BasePromptTemplate
 from langchain.tools.base import BaseTool
 from langchain.tools.requests.tool import BaseRequestsTool
 

langchain/agents/agent_toolkits/pandas/base.py

@@ -19,8 +19,8 @@ from langchain.agents.types import AgentType
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.base import BaseCallbackManager
 from langchain.chains.llm import LLMChain
-from langchain.prompts.base import BasePromptTemplate
-from langchain.schema import SystemMessage
+from langchain.schema import BasePromptTemplate
+from langchain.schema.messages import SystemMessage
 from langchain.tools.python.tool import PythonAstREPLTool
 
 

langchain/agents/agent_toolkits/python/base.py

@@ -10,7 +10,7 @@ from langchain.agents.types import AgentType
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.base import BaseCallbackManager
 from langchain.chains.llm import LLMChain
-from langchain.schema import SystemMessage
+from langchain.schema.messages import SystemMessage
 from langchain.tools.python.tool import PythonREPLTool
 
 

langchain/agents/agent_toolkits/sql/base.py

@@ -20,7 +20,7 @@ from langchain.prompts.chat import (
     HumanMessagePromptTemplate,
     MessagesPlaceholder,
 )
-from langchain.schema import AIMessage, SystemMessage
+from langchain.schema.messages import AIMessage, SystemMessage
 
 
 def create_sql_agent(

langchain/agents/chat/base.py

@@ -14,13 +14,12 @@ from langchain.agents.utils import validate_tools_single_input
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.base import BaseCallbackManager
 from langchain.chains.llm import LLMChain
-from langchain.prompts.base import BasePromptTemplate
 from langchain.prompts.chat import (
     ChatPromptTemplate,
     HumanMessagePromptTemplate,
     SystemMessagePromptTemplate,
 )
-from langchain.schema import AgentAction
+from langchain.schema import AgentAction, BasePromptTemplate
 from langchain.tools.base import BaseTool
 
 

langchain/agents/conversational_chat/base.py

@@ -16,20 +16,14 @@ from langchain.agents.utils import validate_tools_single_input
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.base import BaseCallbackManager
 from langchain.chains import LLMChain
-from langchain.prompts.base import BasePromptTemplate
 from langchain.prompts.chat import (
     ChatPromptTemplate,
     HumanMessagePromptTemplate,
     MessagesPlaceholder,
     SystemMessagePromptTemplate,
 )
-from langchain.schema import (
-    AgentAction,
-    AIMessage,
-    BaseMessage,
-    BaseOutputParser,
-    HumanMessage,
-)
+from langchain.schema import AgentAction, BaseOutputParser, BasePromptTemplate
+from langchain.schema.messages import AIMessage, BaseMessage, HumanMessage
 from langchain.tools.base import BaseTool
 
 

langchain/agents/openai_functions_agent/base.py

@@ -11,7 +11,6 @@ from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.base import BaseCallbackManager
 from langchain.callbacks.manager import Callbacks
 from langchain.chat_models.openai import ChatOpenAI
-from langchain.prompts.base import BasePromptTemplate
 from langchain.prompts.chat import (
     BaseMessagePromptTemplate,
     ChatPromptTemplate,
@@ -21,10 +20,13 @@ from langchain.prompts.chat import (
 from langchain.schema import (
     AgentAction,
     AgentFinish,
+    BasePromptTemplate,
+    OutputParserException,
+)
+from langchain.schema.messages import (
     AIMessage,
     BaseMessage,
     FunctionMessage,
-    OutputParserException,
     SystemMessage,
 )
 from langchain.tools import BaseTool

langchain/agents/openai_functions_multi_agent/base.py

@@ -11,7 +11,6 @@ from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.base import BaseCallbackManager
 from langchain.callbacks.manager import Callbacks
 from langchain.chat_models.openai import ChatOpenAI
-from langchain.prompts.base import BasePromptTemplate
 from langchain.prompts.chat import (
     BaseMessagePromptTemplate,
     ChatPromptTemplate,
@@ -21,10 +20,13 @@ from langchain.prompts.chat import (
 from langchain.schema import (
     AgentAction,
     AgentFinish,
+    BasePromptTemplate,
+    OutputParserException,
+)
+from langchain.schema.messages import (
     AIMessage,
     BaseMessage,
     FunctionMessage,
-    OutputParserException,
     SystemMessage,
 )
 from langchain.tools import BaseTool
@@ -152,7 +154,7 @@ class OpenAIMultiFunctionsAgent(BaseMultiActionAgent):
         tools: The tools this agent has access to.
         prompt: The prompt for this agent, should support agent_scratchpad as one
             of the variables. For an easy way to construct this prompt, use
-            `OpenAIFunctionsAgent.create_prompt(...)`
+            `OpenAIMultiFunctionsAgent.create_prompt(...)`
     """
 
     llm: BaseLanguageModel

langchain/agents/react/base.py

@@ -13,7 +13,7 @@ from langchain.agents.utils import validate_tools_single_input
 from langchain.base_language import BaseLanguageModel
 from langchain.docstore.base import Docstore
 from langchain.docstore.document import Document
-from langchain.prompts.base import BasePromptTemplate
+from langchain.schema import BasePromptTemplate
 from langchain.tools.base import BaseTool
 
 

langchain/agents/self_ask_with_search/base.py

@@ -10,7 +10,7 @@ from langchain.agents.self_ask_with_search.prompt import PROMPT
 from langchain.agents.tools import Tool
 from langchain.agents.utils import validate_tools_single_input
 from langchain.base_language import BaseLanguageModel
-from langchain.prompts.base import BasePromptTemplate
+from langchain.schema import BasePromptTemplate
 from langchain.tools.base import BaseTool
 from langchain.utilities.google_serper import GoogleSerperAPIWrapper
 from langchain.utilities.serpapi import SerpAPIWrapper

langchain/agents/structured_chat/base.py

@@ -11,13 +11,12 @@ from langchain.agents.structured_chat.prompt import FORMAT_INSTRUCTIONS, PREFIX,
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.base import BaseCallbackManager
 from langchain.chains.llm import LLMChain
-from langchain.prompts.base import BasePromptTemplate
 from langchain.prompts.chat import (
     ChatPromptTemplate,
     HumanMessagePromptTemplate,
     SystemMessagePromptTemplate,
 )
-from langchain.schema import AgentAction
+from langchain.schema import AgentAction, BasePromptTemplate
 from langchain.tools import BaseTool
 
 HUMAN_MESSAGE_TEMPLATE = "{input}\n\n{agent_scratchpad}"

langchain/base_language.py

@@ -6,7 +6,8 @@ from typing import Any, List, Optional, Sequence, Set
 
 from langchain.callbacks.manager import Callbacks
 from langchain.load.serializable import Serializable
-from langchain.schema import BaseMessage, LLMResult, PromptValue, get_buffer_string
+from langchain.schema import LLMResult, PromptValue
+from langchain.schema.messages import BaseMessage, get_buffer_string
 
 
 def _get_token_ids_default_method(text: str) -> List[int]:

langchain/cache.py

@@ -262,7 +262,9 @@ class RedisSemanticCache(BaseCache):
             score_threshold (float, 0.2):
 
         Example:
+
         .. code-block:: python
+
             import langchain
 
             from langchain.cache import RedisSemanticCache

langchain/callbacks/__init__.py

@@ -3,9 +3,11 @@
 from langchain.callbacks.aim_callback import AimCallbackHandler
 from langchain.callbacks.argilla_callback import ArgillaCallbackHandler
 from langchain.callbacks.arize_callback import ArizeCallbackHandler
+from langchain.callbacks.arthur_callback import ArthurCallbackHandler
 from langchain.callbacks.clearml_callback import ClearMLCallbackHandler
 from langchain.callbacks.comet_ml_callback import CometCallbackHandler
 from langchain.callbacks.file import FileCallbackHandler
+from langchain.callbacks.flyte_callback import FlyteCallbackHandler
 from langchain.callbacks.human import HumanApprovalCallbackHandler
 from langchain.callbacks.infino_callback import InfinoCallbackHandler
 from langchain.callbacks.manager import (
@@ -15,6 +17,7 @@ from langchain.callbacks.manager import (
 )
 from langchain.callbacks.mlflow_callback import MlflowCallbackHandler
 from langchain.callbacks.openai_info import OpenAICallbackHandler
+from langchain.callbacks.promptlayer_callback import PromptLayerCallbackHandler
 from langchain.callbacks.stdout import StdOutCallbackHandler
 from langchain.callbacks.streaming_aiter import AsyncIteratorCallbackHandler
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
@@ -29,22 +32,25 @@ __all__ = [
     "AimCallbackHandler",
     "ArgillaCallbackHandler",
     "ArizeCallbackHandler",
-    "AsyncIteratorCallbackHandler",
+    "PromptLayerCallbackHandler",
+    "ArthurCallbackHandler",
     "ClearMLCallbackHandler",
     "CometCallbackHandler",
     "FileCallbackHandler",
-    "FinalStreamingStdOutCallbackHandler",
     "HumanApprovalCallbackHandler",
     "InfinoCallbackHandler",
     "MlflowCallbackHandler",
     "OpenAICallbackHandler",
     "StdOutCallbackHandler",
+    "AsyncIteratorCallbackHandler",
     "StreamingStdOutCallbackHandler",
-    "StreamlitCallbackHandler",
+    "FinalStreamingStdOutCallbackHandler",
     "LLMThoughtLabeler",
+    "StreamlitCallbackHandler",
     "WandbCallbackHandler",
     "WhyLabsCallbackHandler",
     "get_openai_callback",
     "tracing_enabled",
     "wandb_tracing_enabled",
+    "FlyteCallbackHandler",
 ]

langchain/callbacks/aim_callback.py

@@ -30,6 +30,7 @@ class BaseMetadataCallbackHandler:
         ignore_llm_ (bool): Whether to ignore llm callbacks.
         ignore_chain_ (bool): Whether to ignore chain callbacks.
         ignore_agent_ (bool): Whether to ignore agent callbacks.
+        ignore_retriever_ (bool): Whether to ignore retriever callbacks.
         always_verbose_ (bool): Whether to always be verbose.
         chain_starts (int): The number of times the chain start method has been called.
         chain_ends (int): The number of times the chain end method has been called.
@@ -52,6 +53,7 @@ class BaseMetadataCallbackHandler:
         self.ignore_llm_ = False
         self.ignore_chain_ = False
         self.ignore_agent_ = False
+        self.ignore_retriever_ = False
         self.always_verbose_ = False
 
         self.chain_starts = 0
@@ -86,6 +88,11 @@ class BaseMetadataCallbackHandler:
         """Whether to ignore agent callbacks."""
         return self.ignore_agent_
 
+    @property
+    def ignore_retriever(self) -> bool:
+        """Whether to ignore retriever callbacks."""
+        return self.ignore_retriever_
+
     def get_custom_callback_meta(self) -> Dict[str, Any]:
         return {
             "step": self.step,

langchain/callbacks/arthur_callback.py

@@ -0,0 +1,302 @@
+"""ArthurAI's Callback Handler."""
+from __future__ import annotations
+
+import os
+import uuid
+from collections import defaultdict
+from datetime import datetime
+from time import time
+from typing import TYPE_CHECKING, Any, DefaultDict, Dict, List, Optional, Union
+
+import numpy as np
+
+from langchain.callbacks.base import BaseCallbackHandler
+from langchain.schema import AgentAction, AgentFinish, LLMResult
+
+if TYPE_CHECKING:
+    import arthurai
+    from arthurai.core.models import ArthurModel
+
+PROMPT_TOKENS = "prompt_tokens"
+COMPLETION_TOKENS = "completion_tokens"
+TOKEN_USAGE = "token_usage"
+FINISH_REASON = "finish_reason"
+DURATION = "duration"
+
+
+def _lazy_load_arthur() -> arthurai:
+    """Lazy load Arthur."""
+    try:
+        import arthurai
+    except ImportError as e:
+        raise ImportError(
+            "To use the ArthurCallbackHandler you need the"
+            " `arthurai` package. Please install it with"
+            " `pip install arthurai`.",
+            e,
+        )
+
+    return arthurai
+
+
+class ArthurCallbackHandler(BaseCallbackHandler):
+    """Callback Handler that logs to Arthur platform.
+
+    Arthur helps enterprise teams optimize model operations
+    and performance at scale. The Arthur API tracks model
+    performance, explainability, and fairness across tabular,
+    NLP, and CV models. Our API is model- and platform-agnostic,
+    and continuously scales with complex and dynamic enterprise needs.
+    To learn more about Arthur, visit our website at
+    https://www.arthur.ai/ or read the Arthur docs at
+    https://docs.arthur.ai/
+    """
+
+    def __init__(
+        self,
+        arthur_model: ArthurModel,
+    ) -> None:
+        """Initialize callback handler."""
+        super().__init__()
+        arthurai = _lazy_load_arthur()
+        Stage = arthurai.common.constants.Stage
+        ValueType = arthurai.common.constants.ValueType
+        self.arthur_model = arthur_model
+        # save the attributes of this model to be used when preparing
+        # inferences to log to Arthur in on_llm_end()
+        self.attr_names = set([a.name for a in self.arthur_model.get_attributes()])
+        self.input_attr = [
+            x
+            for x in self.arthur_model.get_attributes()
+            if x.stage == Stage.ModelPipelineInput
+            and x.value_type == ValueType.Unstructured_Text
+        ][0].name
+        self.output_attr = [
+            x
+            for x in self.arthur_model.get_attributes()
+            if x.stage == Stage.PredictedValue
+            and x.value_type == ValueType.Unstructured_Text
+        ][0].name
+        self.token_likelihood_attr = None
+        if (
+            len(
+                [
+                    x
+                    for x in self.arthur_model.get_attributes()
+                    if x.value_type == ValueType.TokenLikelihoods
+                ]
+            )
+            > 0
+        ):
+            self.token_likelihood_attr = [
+                x
+                for x in self.arthur_model.get_attributes()
+                if x.value_type == ValueType.TokenLikelihoods
+            ][0].name
+
+        self.run_map: DefaultDict[str, Any] = defaultdict(dict)
+
+    @classmethod
+    def from_credentials(
+        cls,
+        model_id: str,
+        arthur_url: Optional[str] = "https://app.arthur.ai",
+        arthur_login: Optional[str] = None,
+        arthur_password: Optional[str] = None,
+    ) -> ArthurCallbackHandler:
+        """Initialize callback handler from Arthur credentials.
+
+        Args:
+            model_id (str): The ID of the arthur model to log to.
+            arthur_url (str, optional): The URL of the Arthur instance to log to.
+                Defaults to "https://app.arthur.ai".
+            arthur_login (str, optional): The login to use to connect to Arthur.
+                Defaults to None.
+            arthur_password (str, optional): The password to use to connect to
+                Arthur. Defaults to None.
+
+        Returns:
+            ArthurCallbackHandler: The initialized callback handler.
+        """
+        arthurai = _lazy_load_arthur()
+        ArthurAI = arthurai.ArthurAI
+        ResponseClientError = arthurai.common.exceptions.ResponseClientError
+
+        # connect to Arthur
+        if arthur_login is None:
+            try:
+                arthur_api_key = os.environ["ARTHUR_API_KEY"]
+            except KeyError:
+                raise ValueError(
+                    "No Arthur authentication provided. Either give"
+                    " a login to the ArthurCallbackHandler"
+                    " or set an ARTHUR_API_KEY as an environment variable."
+                )
+            arthur = ArthurAI(url=arthur_url, access_key=arthur_api_key)
+        else:
+            if arthur_password is None:
+                arthur = ArthurAI(url=arthur_url, login=arthur_login)
+            else:
+                arthur = ArthurAI(
+                    url=arthur_url, login=arthur_login, password=arthur_password
+                )
+        # get model from Arthur by the provided model ID
+        try:
+            arthur_model = arthur.get_model(model_id)
+        except ResponseClientError:
+            raise ValueError(
+                f"Was unable to retrieve model with id {model_id} from Arthur."
+                " Make sure the ID corresponds to a model that is currently"
+                " registered with your Arthur account."
+            )
+        return cls(arthur_model)
+
+    def on_llm_start(
+        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
+    ) -> None:
+        """On LLM start, save the input prompts"""
+        run_id = kwargs["run_id"]
+        self.run_map[run_id]["input_texts"] = prompts
+        self.run_map[run_id]["start_time"] = time()
+
+    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
+        """On LLM end, send data to Arthur."""
+        try:
+            import pytz  # type: ignore[import]
+        except ImportError as e:
+            raise ImportError(
+                "Could not import pytz. Please install it with 'pip install pytz'."
+            ) from e
+
+        run_id = kwargs["run_id"]
+
+        # get the run params from this run ID,
+        # or raise an error if this run ID has no corresponding metadata in self.run_map
+        try:
+            run_map_data = self.run_map[run_id]
+        except KeyError as e:
+            raise KeyError(
+                "This function has been called with a run_id"
+                " that was never registered in on_llm_start()."
+                " Restart and try running the LLM again"
+            ) from e
+
+        # mark the duration time between on_llm_start() and on_llm_end()
+        time_from_start_to_end = time() - run_map_data["start_time"]
+
+        # create inferences to log to Arthur
+        inferences = []
+        for i, generations in enumerate(response.generations):
+            for generation in generations:
+                inference = {
+                    "partner_inference_id": str(uuid.uuid4()),
+                    "inference_timestamp": datetime.now(tz=pytz.UTC),
+                    self.input_attr: run_map_data["input_texts"][i],
+                    self.output_attr: generation.text,
+                }
+
+                if generation.generation_info is not None:
+                    # add finish reason to the inference
+                    # if generation info contains a finish reason and
+                    # if the ArthurModel was registered to monitor finish_reason
+                    if (
+                        FINISH_REASON in generation.generation_info
+                        and FINISH_REASON in self.attr_names
+                    ):
+                        inference[FINISH_REASON] = generation.generation_info[
+                            FINISH_REASON
+                        ]
+
+                    # add token likelihoods data to the inference if the ArthurModel
+                    # was registered to monitor token likelihoods
+                    logprobs_data = generation.generation_info["logprobs"]
+                    if (
+                        logprobs_data is not None
+                        and self.token_likelihood_attr is not None
+                    ):
+                        logprobs = logprobs_data["top_logprobs"]
+                        likelihoods = [
+                            {k: np.exp(v) for k, v in logprobs[i].items()}
+                            for i in range(len(logprobs))
+                        ]
+                        inference[self.token_likelihood_attr] = likelihoods
+
+                # add token usage counts to the inference if the
+                # ArthurModel was registered to monitor token usage
+                if (
+                    isinstance(response.llm_output, dict)
+                    and TOKEN_USAGE in response.llm_output
+                ):
+                    token_usage = response.llm_output[TOKEN_USAGE]
+                    if (
+                        PROMPT_TOKENS in token_usage
+                        and PROMPT_TOKENS in self.attr_names
+                    ):
+                        inference[PROMPT_TOKENS] = token_usage[PROMPT_TOKENS]
+                    if (
+                        COMPLETION_TOKENS in token_usage
+                        and COMPLETION_TOKENS in self.attr_names
+                    ):
+                        inference[COMPLETION_TOKENS] = token_usage[COMPLETION_TOKENS]
+
+                # add inference duration to the inference if the ArthurModel
+                # was registered to monitor inference duration
+                if DURATION in self.attr_names:
+                    inference[DURATION] = time_from_start_to_end
+
+                inferences.append(inference)
+
+        # send inferences to arthur
+        self.arthur_model.send_inferences(inferences)
+
+    def on_chain_start(
+        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
+    ) -> None:
+        """On chain start, do nothing."""
+
+    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
+        """On chain end, do nothing."""
+
+    def on_llm_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Do nothing when LLM outputs an error."""
+
+    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
+        """On new token, pass."""
+
+    def on_chain_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Do nothing when LLM chain outputs an error."""
+
+    def on_tool_start(
+        self,
+        serialized: Dict[str, Any],
+        input_str: str,
+        **kwargs: Any,
+    ) -> None:
+        """Do nothing when tool starts."""
+
+    def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:
+        """Do nothing when agent takes a specific action."""
+
+    def on_tool_end(
+        self,
+        output: str,
+        observation_prefix: Optional[str] = None,
+        llm_prefix: Optional[str] = None,
+        **kwargs: Any,
+    ) -> None:
+        """Do nothing when tool ends."""
+
+    def on_tool_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Do nothing when tool outputs an error."""
+
+    def on_text(self, text: str, **kwargs: Any) -> None:
+        """Do nothing"""
+
+    def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> None:
+        """Do nothing"""

langchain/callbacks/base.py

@@ -1,15 +1,37 @@
 """Base callback handler that can be used to handle callbacks in langchain."""
 from __future__ import annotations
 
-from typing import Any, Dict, List, Optional, Union
+from typing import Any, Dict, List, Optional, Sequence, Union
 from uuid import UUID
 
-from langchain.schema import (
-    AgentAction,
-    AgentFinish,
-    BaseMessage,
-    LLMResult,
-)
+from langchain.schema.agent import AgentAction, AgentFinish
+from langchain.schema.document import Document
+from langchain.schema.messages import BaseMessage
+from langchain.schema.output import LLMResult
+
+
+class RetrieverManagerMixin:
+    """Mixin for Retriever callbacks."""
+
+    def on_retriever_error(
+        self,
+        error: Union[Exception, KeyboardInterrupt],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        """Run when Retriever errors."""
+
+    def on_retriever_end(
+        self,
+        documents: Sequence[Document],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        """Run when Retriever ends running."""
 
 
 class LLMManagerMixin:
@@ -144,6 +166,16 @@ class CallbackManagerMixin:
             f"{self.__class__.__name__} does not implement `on_chat_model_start`"
         )
 
+    def on_retriever_start(
+        self,
+        query: str,
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> Any:
+        """Run when Retriever starts running."""
+
     def on_chain_start(
         self,
         serialized: Dict[str, Any],
@@ -187,6 +219,7 @@ class BaseCallbackHandler(
     LLMManagerMixin,
     ChainManagerMixin,
     ToolManagerMixin,
+    RetrieverManagerMixin,
     CallbackManagerMixin,
     RunManagerMixin,
 ):
@@ -211,6 +244,11 @@ class BaseCallbackHandler(
         """Whether to ignore agent callbacks."""
         return False
 
+    @property
+    def ignore_retriever(self) -> bool:
+        """Whether to ignore retriever callbacks."""
+        return False
+
     @property
     def ignore_chat_model(self) -> bool:
         """Whether to ignore chat model callbacks."""
@@ -371,6 +409,36 @@ class AsyncCallbackHandler(BaseCallbackHandler):
     ) -> None:
         """Run on agent end."""
 
+    async def on_retriever_start(
+        self,
+        query: str,
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> None:
+        """Run on retriever start."""
+
+    async def on_retriever_end(
+        self,
+        documents: Sequence[Document],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> None:
+        """Run on retriever end."""
+
+    async def on_retriever_error(
+        self,
+        error: Union[Exception, KeyboardInterrupt],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> None:
+        """Run on retriever error."""
+
 
 class BaseCallbackManager(CallbackManagerMixin):
     """Base callback manager that can be used to handle callbacks from LangChain."""

langchain/callbacks/flyte_callback.py

@@ -0,0 +1,366 @@
+"""FlyteKit callback handler."""
+from __future__ import annotations
+
+import logging
+from copy import deepcopy
+from typing import TYPE_CHECKING, Any, Dict, List, Tuple, Union
+
+from langchain.callbacks.base import BaseCallbackHandler
+from langchain.callbacks.utils import (
+    BaseMetadataCallbackHandler,
+    flatten_dict,
+    import_pandas,
+    import_spacy,
+    import_textstat,
+)
+from langchain.schema import AgentAction, AgentFinish, LLMResult
+
+if TYPE_CHECKING:
+    import flytekit
+    from flytekitplugins.deck import renderer
+
+logger = logging.getLogger(__name__)
+
+
+def import_flytekit() -> Tuple[flytekit, renderer]:
+    try:
+        import flytekit  # noqa: F401
+        from flytekitplugins.deck import renderer  # noqa: F401
+    except ImportError:
+        raise ImportError(
+            "To use the flyte callback manager you need"
+            "to have the `flytekit` and `flytekitplugins-deck-standard`"
+            "packages installed. Please install them with `pip install flytekit`"
+            "and `pip install flytekitplugins-deck-standard`."
+        )
+    return flytekit, renderer
+
+
+def analyze_text(
+    text: str,
+    nlp: Any = None,
+) -> dict:
+    """Analyze text using textstat and spacy.
+
+    Parameters:
+        text (str): The text to analyze.
+        nlp (spacy.lang): The spacy language model to use for visualization.
+
+    Returns:
+        (dict): A dictionary containing the complexity metrics and visualization
+            files serialized to HTML string.
+    """
+    resp: Dict[str, Any] = {}
+    textstat = import_textstat()
+    text_complexity_metrics = {
+        "flesch_reading_ease": textstat.flesch_reading_ease(text),
+        "flesch_kincaid_grade": textstat.flesch_kincaid_grade(text),
+        "smog_index": textstat.smog_index(text),
+        "coleman_liau_index": textstat.coleman_liau_index(text),
+        "automated_readability_index": textstat.automated_readability_index(text),
+        "dale_chall_readability_score": textstat.dale_chall_readability_score(text),
+        "difficult_words": textstat.difficult_words(text),
+        "linsear_write_formula": textstat.linsear_write_formula(text),
+        "gunning_fog": textstat.gunning_fog(text),
+        "fernandez_huerta": textstat.fernandez_huerta(text),
+        "szigriszt_pazos": textstat.szigriszt_pazos(text),
+        "gutierrez_polini": textstat.gutierrez_polini(text),
+        "crawford": textstat.crawford(text),
+        "gulpease_index": textstat.gulpease_index(text),
+        "osman": textstat.osman(text),
+    }
+    resp.update({"text_complexity_metrics": text_complexity_metrics})
+    resp.update(text_complexity_metrics)
+
+    if nlp is not None:
+        spacy = import_spacy()
+        doc = nlp(text)
+        dep_out = spacy.displacy.render(  # type: ignore
+            doc, style="dep", jupyter=False, page=True
+        )
+
+        ent_out = spacy.displacy.render(  # type: ignore
+            doc, style="ent", jupyter=False, page=True
+        )
+
+        text_visualizations = {
+            "dependency_tree": dep_out,
+            "entities": ent_out,
+        }
+
+        resp.update(text_visualizations)
+
+    return resp
+
+
+class FlyteCallbackHandler(BaseMetadataCallbackHandler, BaseCallbackHandler):
+    """This callback handler is designed specifically for usage within a Flyte task."""
+
+    def __init__(self) -> None:
+        """Initialize callback handler."""
+        import_textstat()  # Raise error since it is required
+        flytekit, renderer = import_flytekit()
+        self.pandas = import_pandas()
+
+        spacy = None
+        try:
+            spacy = import_spacy()
+        except ImportError:
+            logger.warning(
+                "Spacy library is not installed. \
+                It may result in the inability to log \
+                certain metrics that can be captured with Spacy."
+            )
+
+        super().__init__()
+
+        self.nlp = None
+        if spacy:
+            try:
+                self.nlp = spacy.load("en_core_web_sm")
+            except OSError:
+                logger.warning(
+                    "FlyteCallbackHandler uses spacy's en_core_web_sm model"
+                    " for certain metrics. To download,"
+                    " run the following command in your terminal:"
+                    " `python -m spacy download en_core_web_sm` command."
+                )
+
+        self.table_renderer = renderer.TableRenderer
+        self.markdown_renderer = renderer.MarkdownRenderer
+
+        self.deck = flytekit.Deck(
+            "LangChain Metrics",
+            self.markdown_renderer().to_html("## LangChain Metrics"),
+        )
+
+    def on_llm_start(
+        self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
+    ) -> None:
+        """Run when LLM starts."""
+
+        self.step += 1
+        self.llm_starts += 1
+        self.starts += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update({"action": "on_llm_start"})
+        resp.update(flatten_dict(serialized))
+        resp.update(self.get_custom_callback_meta())
+
+        prompt_responses = []
+        for prompt in prompts:
+            prompt_responses.append(prompt)
+
+        resp.update({"prompts": prompt_responses})
+
+        self.deck.append(self.markdown_renderer().to_html("### LLM Start"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([resp])) + "\n"
+        )
+
+    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
+        """Run when LLM generates a new token."""
+
+    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
+        """Run when LLM ends running."""
+        self.step += 1
+        self.llm_ends += 1
+        self.ends += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update({"action": "on_llm_end"})
+        resp.update(flatten_dict(response.llm_output or {}))
+        resp.update(self.get_custom_callback_meta())
+
+        self.deck.append(self.markdown_renderer().to_html("### LLM End"))
+        self.deck.append(self.table_renderer().to_html(self.pandas.DataFrame([resp])))
+
+        for generations in response.generations:
+            for generation in generations:
+                generation_resp = deepcopy(resp)
+                generation_resp.update(flatten_dict(generation.dict()))
+                if self.nlp:
+                    generation_resp.update(
+                        analyze_text(
+                            generation.text,
+                            nlp=self.nlp,
+                        )
+                    )
+
+                    complexity_metrics: Dict[str, float] = generation_resp.pop("text_complexity_metrics")  # type: ignore  # noqa: E501
+                    self.deck.append(
+                        self.markdown_renderer().to_html("#### Text Complexity Metrics")
+                    )
+                    self.deck.append(
+                        self.table_renderer().to_html(
+                            self.pandas.DataFrame([complexity_metrics])
+                        )
+                        + "\n"
+                    )
+
+                    dependency_tree = generation_resp["dependency_tree"]
+                    self.deck.append(
+                        self.markdown_renderer().to_html("#### Dependency Tree")
+                    )
+                    self.deck.append(dependency_tree)
+
+                    entities = generation_resp["entities"]
+                    self.deck.append(self.markdown_renderer().to_html("#### Entities"))
+                    self.deck.append(entities)
+                else:
+                    self.deck.append(
+                        self.markdown_renderer().to_html("#### Generated Response")
+                    )
+                    self.deck.append(self.markdown_renderer().to_html(generation.text))
+
+    def on_llm_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Run when LLM errors."""
+        self.step += 1
+        self.errors += 1
+
+    def on_chain_start(
+        self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
+    ) -> None:
+        """Run when chain starts running."""
+        self.step += 1
+        self.chain_starts += 1
+        self.starts += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update({"action": "on_chain_start"})
+        resp.update(flatten_dict(serialized))
+        resp.update(self.get_custom_callback_meta())
+
+        chain_input = ",".join([f"{k}={v}" for k, v in inputs.items()])
+        input_resp = deepcopy(resp)
+        input_resp["inputs"] = chain_input
+
+        self.deck.append(self.markdown_renderer().to_html("### Chain Start"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([input_resp])) + "\n"
+        )
+
+    def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
+        """Run when chain ends running."""
+        self.step += 1
+        self.chain_ends += 1
+        self.ends += 1
+
+        resp: Dict[str, Any] = {}
+        chain_output = ",".join([f"{k}={v}" for k, v in outputs.items()])
+        resp.update({"action": "on_chain_end", "outputs": chain_output})
+        resp.update(self.get_custom_callback_meta())
+
+        self.deck.append(self.markdown_renderer().to_html("### Chain End"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([resp])) + "\n"
+        )
+
+    def on_chain_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Run when chain errors."""
+        self.step += 1
+        self.errors += 1
+
+    def on_tool_start(
+        self, serialized: Dict[str, Any], input_str: str, **kwargs: Any
+    ) -> None:
+        """Run when tool starts running."""
+        self.step += 1
+        self.tool_starts += 1
+        self.starts += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update({"action": "on_tool_start", "input_str": input_str})
+        resp.update(flatten_dict(serialized))
+        resp.update(self.get_custom_callback_meta())
+
+        self.deck.append(self.markdown_renderer().to_html("### Tool Start"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([resp])) + "\n"
+        )
+
+    def on_tool_end(self, output: str, **kwargs: Any) -> None:
+        """Run when tool ends running."""
+        self.step += 1
+        self.tool_ends += 1
+        self.ends += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update({"action": "on_tool_end", "output": output})
+        resp.update(self.get_custom_callback_meta())
+
+        self.deck.append(self.markdown_renderer().to_html("### Tool End"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([resp])) + "\n"
+        )
+
+    def on_tool_error(
+        self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
+    ) -> None:
+        """Run when tool errors."""
+        self.step += 1
+        self.errors += 1
+
+    def on_text(self, text: str, **kwargs: Any) -> None:
+        """
+        Run when agent is ending.
+        """
+        self.step += 1
+        self.text_ctr += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update({"action": "on_text", "text": text})
+        resp.update(self.get_custom_callback_meta())
+
+        self.deck.append(self.markdown_renderer().to_html("### On Text"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([resp])) + "\n"
+        )
+
+    def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> None:
+        """Run when agent ends running."""
+        self.step += 1
+        self.agent_ends += 1
+        self.ends += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update(
+            {
+                "action": "on_agent_finish",
+                "output": finish.return_values["output"],
+                "log": finish.log,
+            }
+        )
+        resp.update(self.get_custom_callback_meta())
+
+        self.deck.append(self.markdown_renderer().to_html("### Agent Finish"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([resp])) + "\n"
+        )
+
+    def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:
+        """Run on agent action."""
+        self.step += 1
+        self.tool_starts += 1
+        self.starts += 1
+
+        resp: Dict[str, Any] = {}
+        resp.update(
+            {
+                "action": "on_agent_action",
+                "tool": action.tool,
+                "tool_input": action.tool_input,
+                "log": action.log,
+            }
+        )
+        resp.update(self.get_custom_callback_meta())
+
+        self.deck.append(self.markdown_renderer().to_html("### Agent Action"))
+        self.deck.append(
+            self.table_renderer().to_html(self.pandas.DataFrame([resp])) + "\n"
+        )

langchain/callbacks/manager.py

@@ -14,6 +14,7 @@ from typing import (
     Generator,
     List,
     Optional,
+    Sequence,
     Type,
     TypeVar,
     Union,
@@ -27,6 +28,7 @@ from langchain.callbacks.base import (
     BaseCallbackManager,
     ChainManagerMixin,
     LLMManagerMixin,
+    RetrieverManagerMixin,
     RunManagerMixin,
     ToolManagerMixin,
 )
@@ -39,10 +41,10 @@ from langchain.callbacks.tracers.wandb import WandbTracer
 from langchain.schema import (
     AgentAction,
     AgentFinish,
-    BaseMessage,
+    Document,
     LLMResult,
-    get_buffer_string,
 )
+from langchain.schema.messages import BaseMessage, get_buffer_string
 
 logger = logging.getLogger(__name__)
 Callbacks = Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]]
@@ -899,6 +901,97 @@ class AsyncCallbackManagerForToolRun(AsyncRunManager, ToolManagerMixin):
         )
 
 
+class CallbackManagerForRetrieverRun(RunManager, RetrieverManagerMixin):
+    """Callback manager for retriever run."""
+
+    def get_child(self, tag: Optional[str] = None) -> CallbackManager:
+        """Get a child callback manager."""
+        manager = CallbackManager([], parent_run_id=self.run_id)
+        manager.set_handlers(self.inheritable_handlers)
+        manager.add_tags(self.inheritable_tags)
+        if tag is not None:
+            manager.add_tags([tag], False)
+        return manager
+
+    def on_retriever_end(
+        self,
+        documents: Sequence[Document],
+        **kwargs: Any,
+    ) -> None:
+        """Run when retriever ends running."""
+        _handle_event(
+            self.handlers,
+            "on_retriever_end",
+            "ignore_retriever",
+            documents,
+            run_id=self.run_id,
+            parent_run_id=self.parent_run_id,
+            **kwargs,
+        )
+
+    def on_retriever_error(
+        self,
+        error: Union[Exception, KeyboardInterrupt],
+        **kwargs: Any,
+    ) -> None:
+        """Run when retriever errors."""
+        _handle_event(
+            self.handlers,
+            "on_retriever_error",
+            "ignore_retriever",
+            error,
+            run_id=self.run_id,
+            parent_run_id=self.parent_run_id,
+            **kwargs,
+        )
+
+
+class AsyncCallbackManagerForRetrieverRun(
+    AsyncRunManager,
+    RetrieverManagerMixin,
+):
+    """Async callback manager for retriever run."""
+
+    def get_child(self, tag: Optional[str] = None) -> AsyncCallbackManager:
+        """Get a child callback manager."""
+        manager = AsyncCallbackManager([], parent_run_id=self.run_id)
+        manager.set_handlers(self.inheritable_handlers)
+        manager.add_tags(self.inheritable_tags)
+        if tag is not None:
+            manager.add_tags([tag], False)
+        return manager
+
+    async def on_retriever_end(
+        self, documents: Sequence[Document], **kwargs: Any
+    ) -> None:
+        """Run when retriever ends running."""
+        await _ahandle_event(
+            self.handlers,
+            "on_retriever_end",
+            "ignore_retriever",
+            documents,
+            run_id=self.run_id,
+            parent_run_id=self.parent_run_id,
+            **kwargs,
+        )
+
+    async def on_retriever_error(
+        self,
+        error: Union[Exception, KeyboardInterrupt],
+        **kwargs: Any,
+    ) -> None:
+        """Run when retriever errors."""
+        await _ahandle_event(
+            self.handlers,
+            "on_retriever_error",
+            "ignore_retriever",
+            error,
+            run_id=self.run_id,
+            parent_run_id=self.parent_run_id,
+            **kwargs,
+        )
+
+
 class CallbackManager(BaseCallbackManager):
     """Callback manager that can be used to handle callbacks from langchain."""
 
@@ -1077,6 +1170,36 @@ class CallbackManager(BaseCallbackManager):
             inheritable_tags=self.inheritable_tags,
         )
 
+    def on_retriever_start(
+        self,
+        query: str,
+        run_id: Optional[UUID] = None,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> CallbackManagerForRetrieverRun:
+        """Run when retriever starts running."""
+        if run_id is None:
+            run_id = uuid4()
+
+        _handle_event(
+            self.handlers,
+            "on_retriever_start",
+            "ignore_retriever",
+            query,
+            run_id=run_id,
+            parent_run_id=self.parent_run_id,
+            **kwargs,
+        )
+
+        return CallbackManagerForRetrieverRun(
+            run_id=run_id,
+            handlers=self.handlers,
+            inheritable_handlers=self.inheritable_handlers,
+            parent_run_id=self.parent_run_id,
+            tags=self.tags,
+            inheritable_tags=self.inheritable_tags,
+        )
+
     @classmethod
     def configure(
         cls,
@@ -1313,6 +1436,36 @@ class AsyncCallbackManager(BaseCallbackManager):
             inheritable_tags=self.inheritable_tags,
         )
 
+    async def on_retriever_start(
+        self,
+        query: str,
+        run_id: Optional[UUID] = None,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> AsyncCallbackManagerForRetrieverRun:
+        """Run when retriever starts running."""
+        if run_id is None:
+            run_id = uuid4()
+
+        await _ahandle_event(
+            self.handlers,
+            "on_retriever_start",
+            "ignore_retriever",
+            query,
+            run_id=run_id,
+            parent_run_id=self.parent_run_id,
+            **kwargs,
+        )
+
+        return AsyncCallbackManagerForRetrieverRun(
+            run_id=run_id,
+            handlers=self.handlers,
+            inheritable_handlers=self.inheritable_handlers,
+            parent_run_id=self.parent_run_id,
+            tags=self.tags,
+            inheritable_tags=self.inheritable_tags,
+        )
+
     @classmethod
     def configure(
         cls,

langchain/callbacks/promptlayer_callback.py

@@ -0,0 +1,162 @@
+"""Callback handler for promptlayer."""
+from __future__ import annotations
+
+import datetime
+from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Tuple
+from uuid import UUID
+
+from langchain.callbacks.base import BaseCallbackHandler
+from langchain.schema import (
+    ChatGeneration,
+    LLMResult,
+)
+from langchain.schema.messages import (
+    AIMessage,
+    BaseMessage,
+    ChatMessage,
+    HumanMessage,
+    SystemMessage,
+)
+
+if TYPE_CHECKING:
+    import promptlayer
+
+
+def _lazy_import_promptlayer() -> promptlayer:
+    """Lazy import promptlayer to avoid circular imports."""
+    try:
+        import promptlayer
+    except ImportError:
+        raise ImportError(
+            "The PromptLayerCallbackHandler requires the promptlayer package. "
+            " Please install it with `pip install promptlayer`."
+        )
+    return promptlayer
+
+
+class PromptLayerCallbackHandler(BaseCallbackHandler):
+    """Callback handler for promptlayer."""
+
+    def __init__(
+        self,
+        pl_id_callback: Optional[Callable[..., Any]] = None,
+        pl_tags: Optional[List[str]] = [],
+    ) -> None:
+        """Initialize the PromptLayerCallbackHandler."""
+        _lazy_import_promptlayer()
+        self.pl_id_callback = pl_id_callback
+        self.pl_tags = pl_tags
+        self.runs: Dict[UUID, Dict[str, Any]] = {}
+
+    def on_chat_model_start(
+        self,
+        serialized: Dict[str, Any],
+        messages: List[List[BaseMessage]],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        tags: Optional[List[str]] = None,
+        **kwargs: Any,
+    ) -> Any:
+        self.runs[run_id] = {
+            "messages": [self._create_message_dicts(m)[0] for m in messages],
+            "invocation_params": kwargs.get("invocation_params", {}),
+            "name": ".".join(serialized["id"]),
+            "request_start_time": datetime.datetime.now().timestamp(),
+            "tags": tags,
+        }
+
+    def on_llm_start(
+        self,
+        serialized: Dict[str, Any],
+        prompts: List[str],
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        tags: Optional[List[str]] = None,
+        **kwargs: Any,
+    ) -> Any:
+        self.runs[run_id] = {
+            "prompts": prompts,
+            "invocation_params": kwargs.get("invocation_params", {}),
+            "name": ".".join(serialized["id"]),
+            "request_start_time": datetime.datetime.now().timestamp(),
+            "tags": tags,
+        }
+
+    def on_llm_end(
+        self,
+        response: LLMResult,
+        *,
+        run_id: UUID,
+        parent_run_id: Optional[UUID] = None,
+        **kwargs: Any,
+    ) -> None:
+        from promptlayer.utils import get_api_key, promptlayer_api_request
+
+        run_info = self.runs.get(run_id, {})
+        if not run_info:
+            return
+        run_info["request_end_time"] = datetime.datetime.now().timestamp()
+        for i in range(len(response.generations)):
+            generation = response.generations[i][0]
+
+            resp = {
+                "text": generation.text,
+                "llm_output": response.llm_output,
+            }
+            model_params = run_info.get("invocation_params", {})
+            is_chat_model = run_info.get("messages", None) is not None
+            model_input = (
+                run_info.get("messages", [])[i]
+                if is_chat_model
+                else [run_info.get("prompts", [])[i]]
+            )
+            model_response = (
+                [self._convert_message_to_dict(generation.message)]
+                if is_chat_model and isinstance(generation, ChatGeneration)
+                else resp
+            )
+
+            pl_request_id = promptlayer_api_request(
+                run_info.get("name"),
+                "langchain",
+                model_input,
+                model_params,
+                self.pl_tags,
+                model_response,
+                run_info.get("request_start_time"),
+                run_info.get("request_end_time"),
+                get_api_key(),
+                return_pl_id=bool(self.pl_id_callback is not None),
+                metadata={
+                    "_langchain_run_id": str(run_id),
+                    "_langchain_parent_run_id": str(parent_run_id),
+                    "_langchain_tags": str(run_info.get("tags", [])),
+                },
+            )
+
+            if self.pl_id_callback:
+                self.pl_id_callback(pl_request_id)
+
+    def _convert_message_to_dict(self, message: BaseMessage) -> Dict[str, Any]:
+        if isinstance(message, HumanMessage):
+            message_dict = {"role": "user", "content": message.content}
+        elif isinstance(message, AIMessage):
+            message_dict = {"role": "assistant", "content": message.content}
+        elif isinstance(message, SystemMessage):
+            message_dict = {"role": "system", "content": message.content}
+        elif isinstance(message, ChatMessage):
+            message_dict = {"role": message.role, "content": message.content}
+        else:
+            raise ValueError(f"Got unknown type {message}")
+        if "name" in message.additional_kwargs:
+            message_dict["name"] = message.additional_kwargs["name"]
+        return message_dict
+
+    def _create_message_dicts(
+        self, messages: List[BaseMessage]
+    ) -> Tuple[List[Dict[str, Any]], Dict[str, Any]]:
+        params: Dict[str, Any] = {}
+        message_dicts = [self._convert_message_to_dict(m) for m in messages]
+        return message_dicts, params