x

Fixes https://github.com/langchain-ai/langchain/issues/25413

.gitignore

@@ -172,6 +172,8 @@ docs/api_reference/*/
 !docs/api_reference/_static/
 !docs/api_reference/templates/
 !docs/api_reference/themes/
+!docs/api_reference/_extensions/
+!docs/api_reference/scripts/
 docs/docs/build
 docs/docs/node_modules
 docs/docs/yarn.lock

MIGRATE.md

@@ -52,7 +52,7 @@ Now:
 
 `from langchain_experimental.sql import SQLDatabaseChain`
 
-Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out [`create_sql_query_chain`](https://github.com/langchain-ai/langchain/blob/master/docs/extras/use_cases/tabular/sql_query.ipynb)
+Alternatively, if you are just interested in using the query generation part of the SQL chain, you can check out this [`SQL question-answering tutorial`](https://python.langchain.com/v0.2/docs/tutorials/sql_qa/#convert-question-to-sql-query)
 
 `from langchain.chains import create_sql_query_chain`
 

Makefile

@@ -31,6 +31,7 @@ docs_linkcheck:
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
+	poetry run python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
 
 API_PKG ?= text-splitters
 
@@ -38,12 +39,14 @@ api_docs_quick_preview:
 	poetry run pip install "pydantic<2"
 	poetry run python docs/api_reference/create_api_rst.py $(API_PKG)
 	cd docs/api_reference && poetry run make html
-	open docs/api_reference/_build/html/$(shell echo $(API_PKG) | sed 's/-/_/g')_api_reference.html
+	poetry run python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
+	open docs/api_reference/_build/html/reference.html
 
 ## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
 	find ./docs/api_reference -name '*_api_reference.rst' -delete
 	git clean -fdX ./docs/api_reference
+	rm docs/api_reference/index.md
 	
 
 ## api_docs_linkcheck: Run linkchecker on the API Reference documentation.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma unstructured[all-docs] pydantic lxml langchainhub"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml langchainhub"
    ]
   },
   {

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
    ]
   },
   {

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
    ]
   },
   {

cookbook/databricks_sql_db.ipynb

@@ -166,7 +166,7 @@
    "source": [
     "### SQL Database Agent example\n",
     "\n",
-    "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/toolkits/sql_database.html) for answering questions over a Databricks database."
+    "This example demonstrates the use of the [SQL Database Agent](/docs/integrations/tools/sql_database) for answering questions over a Databricks database."
    ]
   },
   {

docs/Makefile

@@ -13,7 +13,12 @@ OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
 
 PYTHON = .venv/bin/python
 
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ')
+PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec sh -c ' \
+for dir; do \
+    if find "$$dir" -maxdepth 1 -type f \( -name "pyproject.toml" -o -name "setup.py" \) | grep -q .; then \
+        echo "$$dir"; \
+    fi \
+done' sh {} + | grep -vE "airbyte|ibm|couchbase" | tr '\n' ' ')
 
 PORT ?= 3001
 
@@ -36,12 +41,8 @@ generate-files:
 	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
 	mkdir -p $(INTERMEDIATE_DIR)/templates
 
-	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
-
 	$(PYTHON) scripts/tool_feat_table.py $(INTERMEDIATE_DIR)
 
-	$(PYTHON) scripts/document_loader_feat_table.py $(INTERMEDIATE_DIR)
-
 	$(PYTHON) scripts/kv_store_feat_table.py $(INTERMEDIATE_DIR)
 
 	$(PYTHON) scripts/partner_pkg_table.py $(INTERMEDIATE_DIR)
@@ -81,7 +82,11 @@ vercel-build: install-vercel-deps build generate-references
 	rm -rf docs
 	mv $(OUTPUT_NEW_DOCS_DIR) docs
 	rm -rf build
-	yarn run docusaurus build
+	mkdir static/api_reference
+	git clone --depth=1 https://github.com/baskaryan/langchain-api-docs-build.git
+	mv langchain-api-docs-build/api_reference_build/html/* static/api_reference/
+	rm -rf langchain-api-docs-build
+	NODE_OPTIONS="--max-old-space-size=5000" yarn run docusaurus build
 	mv build v0.2
 	mkdir build
 	mv v0.2 build

docs/api_reference/_extensions/gallery_directive.py

@@ -0,0 +1,144 @@
+"""A directive to generate a gallery of images from structured data.
+
+Generating a gallery of images that are all the same size is a common
+pattern in documentation, and this can be cumbersome if the gallery is
+generated programmatically. This directive wraps this particular use-case
+in a helper-directive to generate it with a single YAML configuration file.
+
+It currently exists for maintainers of the pydata-sphinx-theme,
+but might be abstracted into a standalone package if it proves useful.
+"""
+
+from pathlib import Path
+from typing import Any, ClassVar, Dict, List
+
+from docutils import nodes
+from docutils.parsers.rst import directives
+from sphinx.application import Sphinx
+from sphinx.util import logging
+from sphinx.util.docutils import SphinxDirective
+from yaml import safe_load
+
+logger = logging.getLogger(__name__)
+
+
+TEMPLATE_GRID = """
+`````{{grid}} {columns}
+{options}
+
+{content}
+
+`````
+"""
+
+GRID_CARD = """
+````{{grid-item-card}} {title}
+{options}
+
+{content}
+````
+"""
+
+
+class GalleryGridDirective(SphinxDirective):
+    """A directive to show a gallery of images and links in a Bootstrap grid.
+
+    The grid can be generated from a YAML file that contains a list of items, or
+    from the content of the directive (also formatted in YAML). Use the parameter
+    "class-card" to add an additional CSS class to all cards. When specifying the grid
+    items, you can use all parameters from "grid-item-card" directive to customize
+    individual cards + ["image", "header", "content", "title"].
+
+    Danger:
+        This directive can only be used in the context of a Myst documentation page as
+        the templates use Markdown flavored formatting.
+    """
+
+    name = "gallery-grid"
+    has_content = True
+    required_arguments = 0
+    optional_arguments = 1
+    final_argument_whitespace = True
+    option_spec: ClassVar[dict[str, Any]] = {
+        # A class to be added to the resulting container
+        "grid-columns": directives.unchanged,
+        "class-container": directives.unchanged,
+        "class-card": directives.unchanged,
+    }
+
+    def run(self) -> List[nodes.Node]:
+        """Create the gallery grid."""
+        if self.arguments:
+            # If an argument is given, assume it's a path to a YAML file
+            # Parse it and load it into the directive content
+            path_data_rel = Path(self.arguments[0])
+            path_doc, _ = self.get_source_info()
+            path_doc = Path(path_doc).parent
+            path_data = (path_doc / path_data_rel).resolve()
+            if not path_data.exists():
+                logger.info(f"Could not find grid data at {path_data}.")
+                nodes.text("No grid data found at {path_data}.")
+                return
+            yaml_string = path_data.read_text()
+        else:
+            yaml_string = "\n".join(self.content)
+
+        # Use all the element with an img-bottom key as sites to show
+        # and generate a card item for each of them
+        grid_items = []
+        for item in safe_load(yaml_string):
+            # remove parameters that are not needed for the card options
+            title = item.pop("title", "")
+
+            # build the content of the card using some extra parameters
+            header = f"{item.pop('header')}  \n^^^  \n" if "header" in item else ""
+            image = f"![image]({item.pop('image')})  \n" if "image" in item else ""
+            content = f"{item.pop('content')}  \n" if "content" in item else ""
+
+            # optional parameter that influence all cards
+            if "class-card" in self.options:
+                item["class-card"] = self.options["class-card"]
+
+            loc_options_str = "\n".join(f":{k}: {v}" for k, v in item.items()) + "  \n"
+
+            card = GRID_CARD.format(
+                options=loc_options_str, content=header + image + content, title=title
+            )
+            grid_items.append(card)
+
+        # Parse the template with Sphinx Design to create an output container
+        # Prep the options for the template grid
+        class_ = "gallery-directive" + f' {self.options.get("class-container", "")}'
+        options = {"gutter": 2, "class-container": class_}
+        options_str = "\n".join(f":{k}: {v}" for k, v in options.items())
+
+        # Create the directive string for the grid
+        grid_directive = TEMPLATE_GRID.format(
+            columns=self.options.get("grid-columns", "1 2 3 4"),
+            options=options_str,
+            content="\n".join(grid_items),
+        )
+
+        # Parse content as a directive so Sphinx Design processes it
+        container = nodes.container()
+        self.state.nested_parse([grid_directive], 0, container)
+
+        # Sphinx Design outputs a container too, so just use that
+        return [container.children[0]]
+
+
+def setup(app: Sphinx) -> Dict[str, Any]:
+    """Add custom configuration to sphinx app.
+
+    Args:
+        app: the Sphinx application
+
+    Returns:
+        the 2 parallel parameters set to ``True``.
+    """
+    app.add_directive("gallery-grid", GalleryGridDirective)
+
+    return {
+        "parallel_read_safe": True,
+        "parallel_write_safe": True,
+    }

docs/api_reference/_static/css/custom.css

@@ -1,26 +1,411 @@
-pre {
-  white-space: break-spaces;
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;700&display=swap');
+
+/*******************************************************************************
+* master color map. Only the colors that actually differ between light and dark
+* themes are specified separately.
+*
+* To see the full list of colors see https://www.figma.com/file/rUrrHGhUBBIAAjQ82x6pz9/PyData-Design-system---proposal-for-implementation-(2)?node-id=1234%3A765&t=ifcFT1JtnrSshGfi-1
+*/
+/**
+* Function to get items from nested maps
+*/
+/* Assign base colors for the PyData theme */
+:root {
+  --pst-teal-50: #f4fbfc;
+  --pst-teal-100: #e9f6f8;
+  --pst-teal-200: #d0ecf1;
+  --pst-teal-300: #abdde6;
+  --pst-teal-400: #3fb1c5;
+  --pst-teal-500: #0a7d91;
+  --pst-teal-600: #085d6c;
+  --pst-teal-700: #064752;
+  --pst-teal-800: #042c33;
+  --pst-teal-900: #021b1f;
+  --pst-violet-50: #f4eefb;
+  --pst-violet-100: #e0c7ff;
+  --pst-violet-200: #d5b4fd;
+  --pst-violet-300: #b780ff;
+  --pst-violet-400: #9c5ffd;
+  --pst-violet-500: #8045e5;
+  --pst-violet-600: #6432bd;
+  --pst-violet-700: #4b258f;
+  --pst-violet-800: #341a61;
+  --pst-violet-900: #1e0e39;
+  --pst-gray-50: #f9f9fa;
+  --pst-gray-100: #f3f4f5;
+  --pst-gray-200: #e5e7ea;
+  --pst-gray-300: #d1d5da;
+  --pst-gray-400: #9ca4af;
+  --pst-gray-500: #677384;
+  --pst-gray-600: #48566b;
+  --pst-gray-700: #29313d;
+  --pst-gray-800: #222832;
+  --pst-gray-900: #14181e;
+  --pst-pink-50: #fcf8fd;
+  --pst-pink-100: #fcf0fa;
+  --pst-pink-200: #f8dff5;
+  --pst-pink-300: #f3c7ee;
+  --pst-pink-400: #e47fd7;
+  --pst-pink-500: #c132af;
+  --pst-pink-600: #912583;
+  --pst-pink-700: #6e1c64;
+  --pst-pink-800: #46123f;
+  --pst-pink-900: #2b0b27;
+  --pst-foundation-white: #ffffff;
+  --pst-foundation-black: #14181e;
+  --pst-green-10: #f1fdfd;
+  --pst-green-50: #E0F7F6;
+  --pst-green-100: #B3E8E6;
+  --pst-green-200: #80D6D3;
+  --pst-green-300: #4DC4C0;
+  --pst-green-400: #4FB2AD;
+  --pst-green-500: #287977;
+  --pst-green-600: #246161;
+  --pst-green-700: #204F4F;
+  --pst-green-800: #1C3C3C;
+  --pst-green-900: #0D2427;
+  --pst-lilac-50: #f4eefb;
+  --pst-lilac-100: #DAD6FE;
+  --pst-lilac-200: #BCB2FD;
+  --pst-lilac-300: #9F8BFA;
+  --pst-lilac-400: #7F5CF6;
+  --pst-lilac-500: #6F3AED;
+  --pst-lilac-600: #6028D9;
+  --pst-lilac-700: #5021B6;
+  --pst-lilac-800: #431D95;
+  --pst-lilac-900: #1e0e39;
+  --pst-header-height: 2.5rem;
 }
 
-@media (min-width: 1200px) {
-  .container,
-  .container-lg,
-  .container-md,
-  .container-sm,
-  .container-xl {
-    max-width: 2560px !important;
-  }
+html {
+    --pst-font-family-base: 'Inter';
+    --pst-font-family-heading: 'Inter Tight', sans-serif;
 }
 
-#my-component-root *,
-#headlessui-portal-root * {
-  z-index: 10000;
+/*******************************************************************************
+* write the color rules for each theme (light/dark)
+*/
+/* NOTE:
+ * Mixins enable us to reuse the same definitions for the different modes
+ * https://sass-lang.com/documentation/at-rules/mixin
+ * something inserts a variable into a CSS selector or property name
+ * https://sass-lang.com/documentation/interpolation
+ */
+/* Defaults to light mode if data-theme is not set */
+html:not([data-theme]) {
+  --pst-color-primary: #287977;
+  --pst-color-primary-bg: #80D6D3;
+  --pst-color-secondary: #6F3AED;
+  --pst-color-secondary-bg: #DAD6FE;
+  --pst-color-accent: #c132af;
+  --pst-color-accent-bg: #f8dff5;
+  --pst-color-info: #276be9;
+  --pst-color-info-bg: #dce7fc;
+  --pst-color-warning: #f66a0a;
+  --pst-color-warning-bg: #f8e3d0;
+  --pst-color-success: #00843f;
+  --pst-color-success-bg: #d6ece1;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #d72d47;
+  --pst-color-danger-bg: #f9e1e4;
+  --pst-color-text-base: #222832;
+  --pst-color-text-muted: #48566b;
+  --pst-color-heading-color: #ffffff;
+  --pst-color-shadow: rgba(0, 0, 0, 0.1);
+  --pst-color-border: #d1d5da;
+  --pst-color-border-muted: rgba(23, 23, 26, 0.2);
+  --pst-color-inline-code: #912583;
+  --pst-color-inline-code-links: #246161;
+  --pst-color-target: #f3cf95;
+  --pst-color-background: #ffffff;
+  --pst-color-on-background: #F4F9F8;
+  --pst-color-surface: #F4F9F8;
+  --pst-color-on-surface: #222832;
+}
+html:not([data-theme]) {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html:not([data-theme]) .only-dark,
+html:not([data-theme]) .only-dark ~ figcaption {
+  display: none !important;
 }
 
-table.longtable code {
-  white-space: normal;
+/* NOTE: @each {...} is like a for-loop
+ * https://sass-lang.com/documentation/at-rules/control/each
+ */
+html[data-theme=light] {
+  --pst-color-primary: #287977;
+  --pst-color-primary-bg: #80D6D3;
+  --pst-color-secondary: #6F3AED;
+  --pst-color-secondary-bg: #DAD6FE;
+  --pst-color-accent: #c132af;
+  --pst-color-accent-bg: #f8dff5;
+  --pst-color-info: #276be9;
+  --pst-color-info-bg: #dce7fc;
+  --pst-color-warning: #f66a0a;
+  --pst-color-warning-bg: #f8e3d0;
+  --pst-color-success: #00843f;
+  --pst-color-success-bg: #d6ece1;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #d72d47;
+  --pst-color-danger-bg: #f9e1e4;
+  --pst-color-text-base: #222832;
+  --pst-color-text-muted: #48566b;
+  --pst-color-heading-color: #ffffff;
+  --pst-color-shadow: rgba(0, 0, 0, 0.1);
+  --pst-color-border: #d1d5da;
+  --pst-color-border-muted: rgba(23, 23, 26, 0.2);
+  --pst-color-inline-code: #912583;
+  --pst-color-inline-code-links: #246161;
+  --pst-color-target: #f3cf95;
+  --pst-color-background: #ffffff;
+  --pst-color-on-background: #F4F9F8;
+  --pst-color-surface: #F4F9F8;
+  --pst-color-on-surface: #222832;
+  color-scheme: light;
+}
+html[data-theme=light] {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html[data-theme=light] .only-dark,
+html[data-theme=light] .only-dark ~ figcaption {
+  display: none !important;
 }
 
-table.longtable td {
-  max-width: 600px;
+html[data-theme=dark] {
+  --pst-color-primary: #4FB2AD;
+  --pst-color-primary-bg: #1C3C3C;
+  --pst-color-secondary: #7F5CF6;
+  --pst-color-secondary-bg: #431D95;
+  --pst-color-accent: #e47fd7;
+  --pst-color-accent-bg: #46123f;
+  --pst-color-info: #79a3f2;
+  --pst-color-info-bg: #06245d;
+  --pst-color-warning: #ff9245;
+  --pst-color-warning-bg: #652a02;
+  --pst-color-success: #5fb488;
+  --pst-color-success-bg: #002f17;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #e78894;
+  --pst-color-danger-bg: #4e111b;
+  --pst-color-text-base: #ced6dd;
+  --pst-color-text-muted: #9ca4af;
+  --pst-color-heading-color: #14181e;
+  --pst-color-shadow: rgba(0, 0, 0, 0.2);
+  --pst-color-border: #48566b;
+  --pst-color-border-muted: #29313d;
+  --pst-color-inline-code: #f3c7ee;
+  --pst-color-inline-code-links: #4FB2AD;
+  --pst-color-target: #675c04;
+  --pst-color-background: #14181e;
+  --pst-color-on-background: #222832;
+  --pst-color-surface: #29313d;
+  --pst-color-on-surface: #f3f4f5;
+  /* Adjust images in dark mode (unless they have class .only-dark or
+   * .dark-light, in which case assume they're already optimized for dark
+   * mode).
+   */
+  /* Give images a light background in dark mode in case they have
+  *  transparency and black text (unless they have class .only-dark or .dark-light, in
+  *  which case assume they're already optimized for dark mode).
+  */
+  color-scheme: dark;
 }
+html[data-theme=dark] {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html[data-theme=dark] .only-light,
+html[data-theme=dark] .only-light ~ figcaption {
+  display: none !important;
+}
+html[data-theme=dark] img:not(.only-dark):not(.dark-light) {
+  filter: brightness(0.8) contrast(1.2);
+}
+html[data-theme=dark] .bd-content img:not(.only-dark):not(.dark-light) {
+  background: rgb(255, 255, 255);
+  border-radius: 0.25rem;
+}
+html[data-theme=dark] .MathJax_SVG * {
+  fill: var(--pst-color-text-base);
+}
+
+.pst-color-primary {
+  color: var(--pst-color-primary);
+}
+
+.pst-color-secondary {
+  color: var(--pst-color-secondary);
+}
+
+.pst-color-accent {
+  color: var(--pst-color-accent);
+}
+
+.pst-color-info {
+  color: var(--pst-color-info);
+}
+
+.pst-color-warning {
+  color: var(--pst-color-warning);
+}
+
+.pst-color-success {
+  color: var(--pst-color-success);
+}
+
+.pst-color-attention {
+  color: var(--pst-color-attention);
+}
+
+.pst-color-danger {
+  color: var(--pst-color-danger);
+}
+
+.pst-color-text-base {
+  color: var(--pst-color-text-base);
+}
+
+.pst-color-text-muted {
+  color: var(--pst-color-text-muted);
+}
+
+.pst-color-heading-color {
+  color: var(--pst-color-heading-color);
+}
+
+.pst-color-shadow {
+  color: var(--pst-color-shadow);
+}
+
+.pst-color-border {
+  color: var(--pst-color-border);
+}
+
+.pst-color-border-muted {
+  color: var(--pst-color-border-muted);
+}
+
+.pst-color-inline-code {
+  color: var(--pst-color-inline-code);
+}
+
+.pst-color-inline-code-links {
+  color: var(--pst-color-inline-code-links);
+}
+
+.pst-color-target {
+  color: var(--pst-color-target);
+}
+
+.pst-color-background {
+  color: var(--pst-color-background);
+}
+
+.pst-color-on-background {
+  color: var(--pst-color-on-background);
+}
+
+.pst-color-surface {
+  color: var(--pst-color-surface);
+}
+
+.pst-color-on-surface {
+  color: var(--pst-color-on-surface);
+}
+
+
+
+/* Adjust the height of the navbar */
+.bd-header .bd-header__inner{
+    height: 52px; /* Adjust this value as needed */
+}
+
+.navbar-nav > li > a {
+    line-height: 52px; /* Vertically center the navbar links */
+}
+
+/* Make sure the navbar items align properly */
+.navbar-nav {
+    display: flex;
+}
+
+
+.bd-header .navbar-header-items__start{
+  margin-left: 0rem
+}
+
+.bd-header button.primary-toggle {
+  margin-right: 0rem;
+}
+
+.bd-header ul.navbar-nav .dropdown .dropdown-menu {
+  overflow-y: auto; /* Enable vertical scrolling */
+  max-height: 80vh
+}
+
+.bd-sidebar-primary {
+    width: 22%;  /* Adjust this value to your preference */
+    line-height: 1.4;
+}
+
+.bd-sidebar-secondary {
+    line-height: 1.4;
+}
+
+.toc-entry a.nav-link, .toc-entry a>code {  
+  background-color: transparent;
+  border-color: transparent;
+}
+
+.bd-sidebar-primary code{
+  background-color: transparent;
+  border-color: transparent;
+}
+
+
+.toctree-wrapper li[class^=toctree-l1]>a {
+  font-size: 1.3em
+}
+
+.toctree-wrapper li[class^=toctree-l1] {
+  margin-bottom: 2em;
+}
+
+.toctree-wrapper li[class^=toctree-l]>ul {
+  margin-top: 0.5em;
+  font-size: 0.9em;
+}
+
+*, :after, :before {
+  font-style: normal;
+}
+
+div.deprecated {
+  margin-top: 0.5em;
+  margin-bottom: 2em;
+}
+
+.admonition-beta.admonition, div.admonition-beta.admonition {
+  border-color: var(--pst-color-warning);
+  margin-top:0.5em;
+  margin-bottom: 2em;
+}
+
+.admonition-beta>.admonition-title, div.admonition-beta>.admonition-title {
+  background-color: var(--pst-color-warning-bg);
+}
+
+dl[class]:not(.option-list):not(.field-list):not(.footnote):not(.glossary):not(.simple) dd {
+  margin-left: 1rem;
+}
+
+p {
+  font-size: 0.9rem;
+  margin-bottom: 0.5rem;
+}

docs/api_reference/_static/wordmark-api-dark.svg

@@ -0,0 +1,11 @@
+<svg width="72" height="19" viewBox="0 0 72 19" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0_4019_2020)">
+<path d="M29.4038 5.84477C30.1256 6.56657 30.1256 7.74117 29.4038 8.46296L27.7869 10.0538L27.7704 9.96259C27.6524 9.30879 27.3415 8.71552 26.8723 8.24627C26.5189 7.8936 26.1012 7.63282 25.6305 7.47143C25.3383 7.76508 25.1777 8.14989 25.1777 8.55487C25.1777 8.63706 25.1851 8.72224 25.2001 8.80742C25.4593 8.90082 25.6887 9.04503 25.8815 9.23781C26.6033 9.9596 26.6033 11.1342 25.8815 11.856L24.4738 13.2637C24.1129 13.6246 23.6392 13.8047 23.1647 13.8047C22.6902 13.8047 22.2165 13.6246 21.8556 13.2637C21.1338 12.5419 21.1338 11.3673 21.8556 10.6455L23.4725 9.05549L23.489 9.14665C23.6063 9.79896 23.9171 10.3922 24.3879 10.8622C24.742 11.2164 25.1343 11.4518 25.6043 11.6124L25.691 11.5257C25.954 11.2627 26.0982 10.913 26.0982 10.5402C26.0982 10.4572 26.0907 10.3743 26.0765 10.2929C25.8053 10.2032 25.5819 10.0754 25.3786 9.87218C25.0857 9.57928 24.9034 9.20493 24.8526 8.79024C24.8489 8.76035 24.8466 8.73121 24.8437 8.70132C24.8033 8.16109 24.9983 7.63357 25.3786 7.25399L26.7864 5.84627C27.1353 5.49733 27.6001 5.30455 28.0955 5.30455C28.5909 5.30455 29.0556 5.49658 29.4046 5.84627L29.4038 5.84477ZM36.7548 9.56583C36.7548 14.7163 32.5645 18.9058 27.4148 18.9058H9.34C4.1903 18.9058 0 14.7163 0 9.56583C0 4.41538 4.1903 0.22583 9.34 0.22583H27.4148C32.5652 0.22583 36.7548 4.41613 36.7548 9.56583ZM18 14.25C18.1472 14.0714 17.4673 13.5686 17.3283 13.384C17.0459 13.0777 17.0444 12.6368 16.8538 12.2789C16.3876 11.1985 15.8518 10.1262 15.1024 9.21166C14.3104 8.21116 13.333 7.38326 12.4745 6.44403C11.8371 5.78873 11.6668 4.85548 11.1041 4.15087C10.3285 3.00541 7.87624 2.69308 7.51683 4.31077C7.51833 4.36158 7.50264 4.39371 7.45855 4.42584C7.2598 4.57005 7.08271 4.73518 6.93402 4.93468C6.57013 5.44129 6.51409 6.30057 6.96839 6.75561C6.98333 6.51576 6.99155 6.28936 7.18134 6.1175C7.53252 6.41862 8.06304 6.52547 8.47026 6.30057C9.36989 7.585 9.14573 9.36184 9.86005 10.7457C10.0573 11.0729 10.2561 11.4069 10.5094 11.6939C10.7148 12.0137 11.4247 12.391 11.4665 12.6869C11.474 13.195 11.4142 13.7502 11.7475 14.1753C11.9044 14.4936 11.5188 14.8134 11.208 14.7738C10.8045 14.8291 10.3121 14.5026 9.95868 14.7036C9.8339 14.8388 9.58957 14.6894 9.48197 14.8769C9.44461 14.9741 9.24286 15.1108 9.36316 15.2042C9.49691 15.1026 9.62095 14.9965 9.80102 15.057C9.77412 15.2035 9.88994 15.2244 9.98184 15.267C9.97886 15.3663 9.92057 15.468 9.99679 15.5524C10.0857 15.4627 10.1388 15.3357 10.28 15.2983C10.7492 15.9238 11.2267 14.6655 12.2421 15.2318C12.0359 15.2214 11.8528 15.2475 11.7139 15.4172C11.6795 15.4553 11.6503 15.5001 11.7109 15.5494C12.2586 15.196 12.2556 15.6705 12.6112 15.5248C12.8847 15.382 13.1567 15.2035 13.4817 15.2543C13.1657 15.3454 13.153 15.5995 12.9677 15.8139C12.9363 15.8468 12.9213 15.8842 12.9579 15.9387C13.614 15.8834 13.6678 15.6652 14.1975 15.3977C14.5928 15.1564 14.9866 15.7414 15.3288 15.4082C15.4043 15.3357 15.5074 15.3604 15.6008 15.3507C15.4812 14.7133 14.1669 15.4672 14.1878 14.6124C14.6107 14.3247 14.5136 13.7741 14.542 13.3295C15.0284 13.5992 15.5694 13.7561 16.0461 14.0139C16.2867 14.4025 16.6641 14.9158 17.1669 14.8822C17.1804 14.8433 17.1923 14.8089 17.2065 14.7693C17.359 14.7955 17.5547 14.8964 17.6384 14.7036C17.8663 14.9419 18.201 14.93 18.4992 14.8687C18.7196 14.6894 18.0845 14.4338 17.9993 14.2493L18 14.25ZM31.3458 7.15387C31.3458 6.28413 31.0081 5.46744 30.3946 4.85399C29.7812 4.24054 28.9645 3.9028 28.094 3.9028C27.2235 3.9028 26.4068 4.24054 25.7933 4.85399L24.3856 6.26171C24.0569 6.59048 23.8073 6.97678 23.6436 7.40941L23.6339 7.43407L23.6085 7.44154C23.0974 7.5992 22.6469 7.86969 22.2696 8.24702L20.8618 9.65475C19.5938 10.9235 19.5938 12.9873 20.8618 14.2553C21.4753 14.8687 22.292 15.2064 23.1617 15.2064C24.0314 15.2064 24.8489 14.8687 25.4623 14.2553L26.8701 12.8475C27.1973 12.5203 27.4454 12.1355 27.609 11.7036L27.6188 11.6789L27.6442 11.6707C28.1463 11.5168 28.6095 11.2373 28.9854 10.8622L30.3931 9.4545C31.0066 8.84105 31.3443 8.02436 31.3443 7.15387H31.3458ZM12.8802 13.1972C12.7592 13.6695 12.7196 14.4742 12.1054 14.4974C12.0546 14.7701 12.2944 14.8724 12.5119 14.785C12.7278 14.6856 12.8302 14.8635 12.9026 15.0406C13.2359 15.0891 13.7291 14.9292 13.7477 14.5347C13.2501 14.2478 13.0962 13.7023 12.8795 13.1972H12.8802Z" fill="#F4F3FF"/>
+<path d="M43.5142 15.2258L47.1462 3.70583H49.9702L53.6022 15.2258H51.6182L48.3222 4.88983H48.7542L45.4982 15.2258H43.5142ZM45.5382 12.7298V10.9298H51.5862V12.7298H45.5382ZM55.0486 15.2258V3.70583H59.8086C59.9206 3.70583 60.0646 3.71116 60.2406 3.72183C60.4166 3.72716 60.5792 3.74316 60.7286 3.76983C61.3952 3.87116 61.9446 4.0925 62.3766 4.43383C62.8139 4.77516 63.1366 5.20716 63.3446 5.72983C63.5579 6.24716 63.6646 6.82316 63.6646 7.45783C63.6646 8.08716 63.5579 8.66316 63.3446 9.18583C63.1312 9.70316 62.8059 10.1325 62.3686 10.4738C61.9366 10.8152 61.3899 11.0365 60.7286 11.1378C60.5792 11.1592 60.4139 11.1752 60.2326 11.1858C60.0566 11.1965 59.9152 11.2018 59.8086 11.2018H56.9766V15.2258H55.0486ZM56.9766 9.40183H59.7286C59.8352 9.40183 59.9552 9.3965 60.0886 9.38583C60.2219 9.37516 60.3446 9.35383 60.4566 9.32183C60.7766 9.24183 61.0272 9.1005 61.2086 8.89783C61.3952 8.69516 61.5259 8.46583 61.6006 8.20983C61.6806 7.95383 61.7206 7.70316 61.7206 7.45783C61.7206 7.2125 61.6806 6.96183 61.6006 6.70583C61.5259 6.4445 61.3952 6.2125 61.2086 6.00983C61.0272 5.80716 60.7766 5.66583 60.4566 5.58583C60.3446 5.55383 60.2219 5.53516 60.0886 5.52983C59.9552 5.51916 59.8352 5.51383 59.7286 5.51383H56.9766V9.40183ZM65.4273 15.2258V3.70583H67.3553V15.2258H65.4273Z" fill="#F4F3FF"/>
+</g>
+<defs>
+<clipPath id="clip0_4019_2020">
+<rect width="71.0711" height="18.68" fill="white" transform="translate(0 0.22583)"/>
+</clipPath>
+</defs>
+</svg>

docs/api_reference/_static/wordmark-api.svg

@@ -0,0 +1,11 @@
+<svg width="72" height="20" viewBox="0 0 72 20" fill="none" xmlns="http://www.w3.org/2000/svg">
+<g clip-path="url(#clip0_4019_689)">
+<path d="M29.4038 5.97905C30.1256 6.70085 30.1256 7.87545 29.4038 8.59724L27.7869 10.188L27.7704 10.0969C27.6524 9.44307 27.3415 8.84979 26.8723 8.38055C26.5189 8.02787 26.1012 7.7671 25.6305 7.60571C25.3383 7.89936 25.1777 8.28416 25.1777 8.68915C25.1777 8.77134 25.1851 8.85652 25.2001 8.9417C25.4593 9.0351 25.6887 9.17931 25.8815 9.37209C26.6033 10.0939 26.6033 11.2685 25.8815 11.9903L24.4738 13.398C24.1129 13.7589 23.6392 13.939 23.1647 13.939C22.6902 13.939 22.2165 13.7589 21.8556 13.398C21.1338 12.6762 21.1338 11.5016 21.8556 10.7798L23.4725 9.18977L23.489 9.28093C23.6063 9.93323 23.9171 10.5265 24.3879 10.9965C24.742 11.3507 25.1343 11.586 25.6043 11.7467L25.691 11.66C25.954 11.397 26.0982 11.0473 26.0982 10.6745C26.0982 10.5915 26.0907 10.5086 26.0765 10.4271C25.8053 10.3375 25.5819 10.2097 25.3786 10.0065C25.0857 9.71356 24.9034 9.33921 24.8526 8.92451C24.8489 8.89463 24.8466 8.86549 24.8437 8.8356C24.8033 8.29537 24.9983 7.76785 25.3786 7.38827L26.7864 5.98055C27.1353 5.6316 27.6001 5.43883 28.0955 5.43883C28.5909 5.43883 29.0556 5.63086 29.4046 5.98055L29.4038 5.97905ZM36.7548 9.70011C36.7548 14.8506 32.5645 19.0401 27.4148 19.0401H9.34C4.1903 19.0401 0 14.8506 0 9.70011C0 4.54966 4.1903 0.360107 9.34 0.360107H27.4148C32.5652 0.360107 36.7548 4.55041 36.7548 9.70011ZM18 14.3843C18.1472 14.2057 17.4673 13.7029 17.3283 13.5183C17.0459 13.2119 17.0444 12.7711 16.8538 12.4132C16.3876 11.3327 15.8518 10.2605 15.1024 9.34594C14.3104 8.34543 13.333 7.51754 12.4745 6.57831C11.8371 5.92301 11.6668 4.98976 11.1041 4.28515C10.3285 3.13969 7.87624 2.82736 7.51683 4.44505C7.51833 4.49586 7.50264 4.52799 7.45855 4.56012C7.2598 4.70433 7.08271 4.86946 6.93402 5.06896C6.57013 5.57556 6.51409 6.43484 6.96839 6.88989C6.98333 6.65004 6.99155 6.42364 7.18134 6.25178C7.53252 6.5529 8.06304 6.65975 8.47026 6.43484C9.36989 7.71928 9.14573 9.49612 9.86005 10.8799C10.0573 11.2072 10.2561 11.5412 10.5094 11.8281C10.7148 12.1479 11.4247 12.5253 11.4665 12.8212C11.474 13.3293 11.4142 13.8844 11.7475 14.3096C11.9044 14.6279 11.5188 14.9477 11.208 14.9081C10.8045 14.9634 10.3121 14.6369 9.95868 14.8379C9.8339 14.9731 9.58957 14.8237 9.48197 15.0112C9.44461 15.1083 9.24286 15.2451 9.36316 15.3385C9.49691 15.2369 9.62095 15.1308 9.80102 15.1913C9.77412 15.3377 9.88994 15.3587 9.98184 15.4012C9.97886 15.5006 9.92057 15.6022 9.99679 15.6867C10.0857 15.597 10.1388 15.47 10.28 15.4326C10.7492 16.058 11.2267 14.7997 12.2421 15.3661C12.0359 15.3557 11.8528 15.3818 11.7139 15.5514C11.6795 15.5895 11.6503 15.6344 11.7109 15.6837C12.2586 15.3303 12.2556 15.8047 12.6112 15.659C12.8847 15.5163 13.1567 15.3377 13.4817 15.3885C13.1657 15.4797 13.153 15.7337 12.9677 15.9482C12.9363 15.9811 12.9213 16.0184 12.9579 16.073C13.614 16.0177 13.6678 15.7995 14.1975 15.532C14.5928 15.2907 14.9866 15.8757 15.3288 15.5425C15.4043 15.47 15.5074 15.4946 15.6008 15.4849C15.4812 14.8476 14.1669 15.6015 14.1878 14.7467C14.6107 14.459 14.5136 13.9083 14.542 13.4638C15.0284 13.7335 15.5694 13.8904 16.0461 14.1482C16.2867 14.5367 16.6641 15.0501 17.1669 15.0164C17.1804 14.9776 17.1923 14.9432 17.2065 14.9036C17.359 14.9298 17.5547 15.0306 17.6384 14.8379C17.8663 15.0762 18.201 15.0643 18.4992 15.003C18.7196 14.8237 18.0845 14.5681 17.9993 14.3836L18 14.3843ZM31.3458 7.28815C31.3458 6.41841 31.0081 5.60172 30.3946 4.98826C29.7812 4.37481 28.9645 4.03708 28.094 4.03708C27.2235 4.03708 26.4068 4.37481 25.7933 4.98826L24.3856 6.39599C24.0569 6.72476 23.8073 7.11106 23.6436 7.54369L23.6339 7.56835L23.6085 7.57582C23.0974 7.73348 22.6469 8.00396 22.2696 8.3813L20.8618 9.78902C19.5938 11.0578 19.5938 13.1215 20.8618 14.3895C21.4753 15.003 22.292 15.3407 23.1617 15.3407C24.0314 15.3407 24.8489 15.003 25.4623 14.3895L26.8701 12.9818C27.1973 12.6545 27.4454 12.2697 27.609 11.8378L27.6188 11.8132L27.6442 11.805C28.1463 11.651 28.6095 11.3716 28.9854 10.9965L30.3931 9.58878C31.0066 8.97532 31.3443 8.15863 31.3443 7.28815H31.3458ZM12.8802 13.3315C12.7592 13.8037 12.7196 14.6085 12.1054 14.6316C12.0546 14.9044 12.2944 15.0067 12.5119 14.9193C12.7278 14.8199 12.8302 14.9978 12.9026 15.1748C13.2359 15.2234 13.7291 15.0635 13.7477 14.669C13.2501 14.3821 13.0962 13.8366 12.8795 13.3315H12.8802Z" fill="#246161"/>
+<path d="M43.5142 15.3601L47.1462 3.84011H49.9702L53.6022 15.3601H51.6182L48.3222 5.02411H48.7542L45.4982 15.3601H43.5142ZM45.5382 12.8641V11.0641H51.5862V12.8641H45.5382ZM55.0486 15.3601V3.84011H59.8086C59.9206 3.84011 60.0646 3.84544 60.2406 3.85611C60.4166 3.86144 60.5792 3.87744 60.7286 3.90411C61.3952 4.00544 61.9446 4.22677 62.3766 4.56811C62.8139 4.90944 63.1366 5.34144 63.3446 5.86411C63.5579 6.38144 63.6646 6.95744 63.6646 7.59211C63.6646 8.22144 63.5579 8.79744 63.3446 9.32011C63.1312 9.83744 62.8059 10.2668 62.3686 10.6081C61.9366 10.9494 61.3899 11.1708 60.7286 11.2721C60.5792 11.2934 60.4139 11.3094 60.2326 11.3201C60.0566 11.3308 59.9152 11.3361 59.8086 11.3361H56.9766V15.3601H55.0486ZM56.9766 9.53611H59.7286C59.8352 9.53611 59.9552 9.53077 60.0886 9.52011C60.2219 9.50944 60.3446 9.48811 60.4566 9.45611C60.7766 9.37611 61.0272 9.23477 61.2086 9.03211C61.3952 8.82944 61.5259 8.60011 61.6006 8.34411C61.6806 8.08811 61.7206 7.83744 61.7206 7.59211C61.7206 7.34677 61.6806 7.09611 61.6006 6.84011C61.5259 6.57877 61.3952 6.34677 61.2086 6.14411C61.0272 5.94144 60.7766 5.80011 60.4566 5.72011C60.3446 5.68811 60.2219 5.66944 60.0886 5.66411C59.9552 5.65344 59.8352 5.64811 59.7286 5.64811H56.9766V9.53611ZM65.4273 15.3601V3.84011H67.3553V15.3601H65.4273Z" fill="#246161"/>
+</g>
+<defs>
+<clipPath id="clip0_4019_689">
+<rect width="71.0711" height="18.68" fill="white" transform="translate(0 0.360107)"/>
+</clipPath>
+</defs>
+</svg>

docs/api_reference/conf.py

@@ -15,6 +15,8 @@ from pathlib import Path
 
 import toml
 from docutils import nodes
+from docutils.parsers.rst.directives.admonitions import BaseAdmonition
+from docutils.statemachine import StringList
 from sphinx.util.docutils import SphinxDirective
 
 # If extensions (or modules to document with autodoc) are in another directory,
@@ -60,26 +62,41 @@ class ExampleLinksDirective(SphinxDirective):
             item_node.append(para_node)
             list_node.append(item_node)
         if list_node.children:
-            title_node = nodes.title()
+            title_node = nodes.rubric()
             title_node.append(nodes.Text(f"Examples using {class_or_func_name}"))
             return [title_node, list_node]
         return [list_node]
 
 
+class Beta(BaseAdmonition):
+    required_arguments = 0
+    node_class = nodes.admonition
+
+    def run(self):
+        self.content = self.content or StringList(
+            [
+                (
+                    "This feature is in beta. It is actively being worked on, so the "
+                    "API may change."
+                )
+            ]
+        )
+        self.arguments = self.arguments or ["Beta"]
+        return super().run()
+
+
 def setup(app):
     app.add_directive("example_links", ExampleLinksDirective)
+    app.add_directive("beta", Beta)
 
 
 # -- Project information -----------------------------------------------------
 
 project = "🦜🔗 LangChain"
-copyright = "2023, LangChain, Inc."
-author = "LangChain, Inc."
+copyright = "2023, LangChain Inc"
+author = "LangChain, Inc"
 
-version = data["tool"]["poetry"]["version"]
-release = version
-
-html_title = project + " " + version
+html_favicon = "_static/img/brand/favicon.png"
 html_last_updated_fmt = "%b %d, %Y"
 
 
@@ -95,11 +112,13 @@ extensions = [
     "sphinx.ext.napoleon",
     "sphinx.ext.viewcode",
     "sphinxcontrib.autodoc_pydantic",
-    "sphinx_copybutton",
-    "sphinx_panels",
     "IPython.sphinxext.ipython_console_highlighting",
+    "myst_parser",
+    "_extensions.gallery_directive",
+    "sphinx_design",
+    "sphinx_copybutton",
 ]
-source_suffix = [".rst"]
+source_suffix = [".rst", ".md"]
 
 # some autodoc pydantic options are repeated in the actual template.
 # potentially user error, but there may be bugs in the sphinx extension
@@ -131,23 +150,84 @@ 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 = "scikit-learn-modern"
-html_theme_path = ["themes"]
+# The theme to use for HTML and HTML Help pages.
+html_theme = "pydata_sphinx_theme"
 
-# redirects dictionary maps from old links to new links
-html_additional_pages = {}
-redirects = {
-    "index": "langchain_api_reference",
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+html_theme_options = {
+    #     # -- General configuration ------------------------------------------------
+    "sidebar_includehidden": True,
+    "use_edit_page_button": False,
+    #     # "analytics": {
+    #     #     "plausible_analytics_domain": "scikit-learn.org",
+    #     #     "plausible_analytics_url": "https://views.scientific-python.org/js/script.js",
+    #     # },
+    #     # If "prev-next" is included in article_footer_items, then setting show_prev_next
+    #     # to True would repeat prev and next links. See
+    #     # https://github.com/pydata/pydata-sphinx-theme/blob/b731dc230bc26a3d1d1bb039c56c977a9b3d25d8/src/pydata_sphinx_theme/theme/pydata_sphinx_theme/layout.html#L118-L129
+    "show_prev_next": False,
+    "search_bar_text": "Search",
+    "navigation_with_keys": True,
+    "collapse_navigation": True,
+    "navigation_depth": 3,
+    "show_nav_level": 1,
+    "show_toc_level": 3,
+    "navbar_align": "left",
+    "header_links_before_dropdown": 5,
+    "header_dropdown_text": "Integrations",
+    "logo": {
+        "image_light": "_static/wordmark-api.svg",
+        "image_dark": "_static/wordmark-api-dark.svg",
+    },
+    "surface_warnings": True,
+    #     # -- Template placement in theme layouts ----------------------------------
+    "navbar_start": ["navbar-logo"],
+    #     # Note that the alignment of navbar_center is controlled by navbar_align
+    "navbar_center": ["navbar-nav"],
+    "navbar_end": ["langchain_docs", "theme-switcher", "navbar-icon-links"],
+    #     # navbar_persistent is persistent right (even when on mobiles)
+    "navbar_persistent": ["search-field"],
+    "article_header_start": ["breadcrumbs"],
+    "article_header_end": [],
+    "article_footer_items": [],
+    "content_footer_items": [],
+    #     # Use html_sidebars that map page patterns to list of sidebar templates
+    #     "primary_sidebar_end": [],
+    "footer_start": ["copyright"],
+    "footer_center": [],
+    "footer_end": [],
+    #     # When specified as a dictionary, the keys should follow glob-style patterns, as in
+    #     # https://www.sphinx-doc.org/en/master/usage/configuration.html#confval-exclude_patterns
+    #     # In particular, "**" specifies the default for all pages
+    #     # Use :html_theme.sidebar_secondary.remove: for file-wide removal
+    #     "secondary_sidebar_items": {"**": ["page-toc", "sourcelink"]},
+    #     "show_version_warning_banner": True,
+    #     "announcement": None,
+    "icon_links": [
+        {
+            # Label for this link
+            "name": "GitHub",
+            # URL where the link will redirect
+            "url": "https://github.com/langchain-ai/langchain",  # required
+            # Icon class (if "type": "fontawesome"), or path to local image (if "type": "local")
+            "icon": "fa-brands fa-square-github",
+            # The type of image to be used (see below for details)
+            "type": "fontawesome",
+        },
+        {
+            "name": "X / Twitter",
+            "url": "https://twitter.com/langchainai",
+            "icon": "fab fa-twitter-square",
+        },
+    ],
+    "icon_links_label": "Quick Links",
+    "external_links": [
+        {"name": "Legacy reference", "url": "https://api.python.langchain.com/"},
+    ],
 }
-for old_link in redirects:
-    html_additional_pages[old_link] = "redirects.html"
 
-partners_dir = Path(__file__).parent.parent.parent / "libs/partners"
-partners = [
-    (p.name, p.name.replace("-", "_") + "_api_reference")
-    for p in partners_dir.iterdir()
-]
-partners = sorted(partners)
 
 html_context = {
     "display_github": True,  # Integrate GitHub
@@ -155,8 +235,6 @@ 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,
-    "partners": partners,
 }
 
 # Add any paths that contain custom static files (such as style sheets) here,
@@ -166,9 +244,7 @@ html_static_path = ["_static"]
 
 # These paths are either relative to html_static_path
 # or fully qualified paths (e.g. https://...)
-html_css_files = [
-    "css/custom.css",
-]
+html_css_files = ["css/custom.css"]
 html_use_index = False
 
 myst_enable_extensions = ["colon_fence"]
@@ -185,3 +261,5 @@ html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "")
 # Tell Jinja2 templates the build is running on Read the Docs
 if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = True
+
+master_doc = "index"

docs/api_reference/create_api_rst.py

@@ -38,6 +38,8 @@ class ClassInfo(TypedDict):
     """The kind of the class."""
     is_public: bool
     """Whether the class is public or not."""
+    is_deprecated: bool
+    """Whether the class is deprecated."""
 
 
 class FunctionInfo(TypedDict):
@@ -49,6 +51,8 @@ class FunctionInfo(TypedDict):
     """The fully qualified name of the function."""
     is_public: bool
     """Whether the function is public or not."""
+    is_deprecated: bool
+    """Whether the function is deprecated."""
 
 
 class ModuleMembers(TypedDict):
@@ -121,6 +125,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     qualified_name=f"{namespace}.{name}",
                     kind=kind,
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         elif inspect.isfunction(type_):
@@ -129,6 +134,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     name=name,
                     qualified_name=f"{namespace}.{name}",
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         else:
@@ -233,7 +239,7 @@ def _construct_doc(
     package_namespace: str,
     members_by_namespace: Dict[str, ModuleMembers],
     package_version: str,
-) -> str:
+) -> List[typing.Tuple[str, str]]:
     """Construct the contents of the reference.rst file for the given package.
 
     Args:
@@ -245,23 +251,62 @@ def _construct_doc(
     Returns:
         The contents of the reference.rst file.
     """
-    full_doc = f"""\
-=======================
-``{package_namespace}`` {package_version}
-=======================
+    docs = []
+    index_doc = f"""\
+:html_theme.sidebar_secondary.remove:
 
+.. currentmodule:: {package_namespace}
+
+.. _{package_namespace}:
+
+======================================
+{package_namespace.replace('_', '-')}: {package_version}
+======================================
+
+.. automodule:: {package_namespace}
+    :no-members:
+    :no-inherited-members:
+
+.. toctree::
+    :hidden:
+    :maxdepth: 2
+    
+"""
+    index_autosummary = """
 """
     namespaces = sorted(members_by_namespace)
 
     for module in namespaces:
+        index_doc += f"    {module}\n"
+        module_doc = f"""\
+.. currentmodule:: {package_namespace}
+
+.. _{module}:
+"""
         _members = members_by_namespace[module]
-        classes = [el for el in _members["classes_"] if el["is_public"]]
-        functions = [el for el in _members["functions"] if el["is_public"]]
+        classes = [
+            el
+            for el in _members["classes_"]
+            if el["is_public"] and not el["is_deprecated"]
+        ]
+        functions = [
+            el
+            for el in _members["functions"]
+            if el["is_public"] and not el["is_deprecated"]
+        ]
+        deprecated_classes = [
+            el for el in _members["classes_"] if el["is_public"] and el["is_deprecated"]
+        ]
+        deprecated_functions = [
+            el
+            for el in _members["functions"]
+            if el["is_public"] and el["is_deprecated"]
+        ]
         if not (classes or functions):
             continue
-        section = f":mod:`{package_namespace}.{module}`"
+        section = f":mod:`{module}`"
         underline = "=" * (len(section) + 1)
-        full_doc += f"""\
+        module_doc += f"""
 {section}
 {underline}
 
@@ -269,16 +314,26 @@ def _construct_doc(
     :no-members:
     :no-inherited-members:
 
+"""
+
+        index_autosummary += f"""
+:ref:`{module}`
+{'^' * (len(module) + 5)}
 """
 
         if classes:
-            full_doc += f"""\
-Classes
---------------
+            module_doc += f"""\
+**Classes**
+
 .. currentmodule:: {package_namespace}
 
 .. autosummary::
     :toctree: {module}
+"""
+            index_autosummary += """
+**Classes**
+
+.. autosummary::
 """
 
             for class_ in sorted(classes, key=lambda c: c["qualified_name"]):
@@ -295,19 +350,22 @@ Classes
                 else:
                     template = "class.rst"
 
-                full_doc += f"""\
+                module_doc += f"""\
     :template: {template}
     
     {class_["qualified_name"]}
     
+"""
+                index_autosummary += f"""
+    {class_['qualified_name']}
 """
 
         if functions:
             _functions = [f["qualified_name"] for f in functions]
             fstring = "\n    ".join(sorted(_functions))
-            full_doc += f"""\
-Functions
---------------
+            module_doc += f"""\
+**Functions**
+
 .. currentmodule:: {package_namespace}
 
 .. autosummary::
@@ -317,7 +375,81 @@ Functions
     {fstring}
 
 """
-    return full_doc
+
+            index_autosummary += f"""
+**Functions**
+
+.. autosummary::
+
+    {fstring}
+"""
+        if deprecated_classes:
+            module_doc += f"""\
+**Deprecated classes**
+
+.. currentmodule:: {package_namespace}
+
+.. autosummary::
+    :toctree: {module}
+"""
+
+            index_autosummary += """
+**Deprecated classes**
+
+.. autosummary::
+"""
+
+            for class_ in sorted(deprecated_classes, key=lambda c: c["qualified_name"]):
+                if class_["kind"] == "TypedDict":
+                    template = "typeddict.rst"
+                elif class_["kind"] == "enum":
+                    template = "enum.rst"
+                elif class_["kind"] == "Pydantic":
+                    template = "pydantic.rst"
+                elif class_["kind"] == "RunnablePydantic":
+                    template = "runnable_pydantic.rst"
+                elif class_["kind"] == "RunnableNonPydantic":
+                    template = "runnable_non_pydantic.rst"
+                else:
+                    template = "class.rst"
+
+                module_doc += f"""\
+    :template: {template}
+
+    {class_["qualified_name"]}
+
+"""
+                index_autosummary += f"""
+    {class_['qualified_name']}
+"""
+
+        if deprecated_functions:
+            _functions = [f["qualified_name"] for f in deprecated_functions]
+            fstring = "\n    ".join(sorted(_functions))
+            module_doc += f"""\
+**Deprecated functions**
+
+.. currentmodule:: {package_namespace}
+
+.. autosummary::
+    :toctree: {module}
+    :template: function.rst
+
+    {fstring}
+
+"""
+            index_autosummary += f"""
+**Deprecated functions**
+
+.. autosummary::
+
+    {fstring}
+
+"""
+        docs.append((f"{module}.rst", module_doc))
+    docs.append(("index.rst", index_doc + index_autosummary))
+
+    return docs
 
 
 def _build_rst_file(package_name: str = "langchain") -> None:
@@ -329,13 +461,14 @@ def _build_rst_file(package_name: str = "langchain") -> None:
     package_dir = _package_dir(package_name)
     package_members = _load_package_modules(package_dir)
     package_version = _get_package_version(package_dir)
-    with open(_out_file_path(package_name), "w") as f:
-        f.write(
-            _doc_first_line(package_name)
-            + _construct_doc(
-                _package_namespace(package_name), package_members, package_version
-            )
-        )
+    output_dir = _out_file_path(package_name)
+    os.mkdir(output_dir)
+    rsts = _construct_doc(
+        _package_namespace(package_name), package_members, package_version
+    )
+    for name, rst in rsts:
+        with open(output_dir / name, "w") as f:
+            f.write(rst)
 
 
 def _package_namespace(package_name: str) -> str:
@@ -385,12 +518,117 @@ def _get_package_version(package_dir: Path) -> str:
 
 def _out_file_path(package_name: str) -> Path:
     """Return the path to the file containing the documentation."""
-    return HERE / f"{package_name.replace('-', '_')}_api_reference.rst"
+    return HERE / f"{package_name.replace('-', '_')}"
 
 
-def _doc_first_line(package_name: str) -> str:
-    """Return the path to the file containing the documentation."""
-    return f".. {package_name.replace('-', '_')}_api_reference:\n\n"
+def _build_index(dirs: List[str]) -> None:
+    custom_names = {
+        "airbyte": "Airbyte",
+        "aws": "AWS",
+        "ai21": "AI21",
+    }
+    ordered = ["core", "langchain", "text-splitters", "community", "experimental"]
+    main_ = [dir_ for dir_ in ordered if dir_ in dirs]
+    integrations = sorted(dir_ for dir_ in dirs if dir_ not in main_)
+    main_headers = [
+        " ".join(custom_names.get(x, x.title()) for x in dir_.split("-"))
+        for dir_ in main_
+    ]
+    integration_headers = [
+        " ".join(
+            custom_names.get(x, x.title().replace("ai", "AI").replace("db", "DB"))
+            for x in dir_.split("-")
+        )
+        for dir_ in integrations
+    ]
+    main_tree = "\n".join(
+        f"{header_name}<{dir_.replace('-', '_')}/index>"
+        for header_name, dir_ in zip(main_headers, main_)
+    )
+    main_grid = "\n".join(
+        f'- header: "**{header_name}**"\n  content: "{_package_namespace(dir_).replace("_", "-")}: {_get_package_version(_package_dir(dir_))}"\n  link: {dir_.replace("-", "_")}/index.html'
+        for header_name, dir_ in zip(main_headers, main_)
+    )
+    integration_tree = "\n".join(
+        f"{header_name}<{dir_.replace('-', '_')}/index>"
+        for header_name, dir_ in zip(integration_headers, integrations)
+    )
+
+    integration_grid = ""
+    integrations_to_show = [
+        "openai",
+        "anthropic",
+        "google-vertexai",
+        "aws",
+        "huggingface",
+        "mistralai",
+    ]
+    for header_name, dir_ in sorted(
+        zip(integration_headers, integrations),
+        key=lambda h_d: integrations_to_show.index(h_d[1])
+        if h_d[1] in integrations_to_show
+        else len(integrations_to_show),
+    )[: len(integrations_to_show)]:
+        integration_grid += f'\n- header: "**{header_name}**"\n  content: {_package_namespace(dir_).replace("_", "-")} {_get_package_version(_package_dir(dir_))}\n  link: {dir_.replace("-", "_")}/index.html'
+    doc = f"""# LangChain Python API Reference
+
+Welcome to the LangChain Python API reference. This is a reference for all 
+`langchain-x` packages. 
+
+For user guides see [https://python.langchain.com](https://python.langchain.com).
+
+For the legacy API reference hosted on ReadTheDocs see [https://api.python.langchain.com/](https://api.python.langchain.com/).
+
+## Base packages
+
+```{{gallery-grid}}
+:grid-columns: "1 2 2 3"
+
+{main_grid}
+```
+
+```{{toctree}}
+:maxdepth: 2
+:hidden:
+:caption: Base packages
+
+{main_tree}
+```
+
+## Integrations
+
+```{{gallery-grid}}
+:grid-columns: "1 2 2 3"
+
+{integration_grid}
+```
+
+See the full list of integrations in the Section Navigation.
+
+```{{toctree}}
+:maxdepth: 2
+:hidden:
+:caption: Integrations
+
+{integration_tree}
+```
+
+"""
+    with open(HERE / "reference.md", "w") as f:
+        f.write(doc)
+
+    dummy_index = """\
+# API reference
+
+```{toctree}
+:maxdepth: 3
+:hidden:
+
+Reference<reference>
+```
+"""
+    with open(HERE / "index.md", "w") as f:
+        f.write(dummy_index)
 
 
 def main(dirs: Optional[list] = None) -> None:
@@ -418,6 +656,8 @@ def main(dirs: Optional[list] = None) -> None:
         else:
             print("Building package:", dir_)
             _build_rst_file(package_name=dir_)
+
+    _build_index(dirs)
     print("API reference files built.")
 
 

docs/api_reference/index.rst

@@ -1,8 +0,0 @@
-=============
-LangChain API
-=============
-
-.. toctree::
-    :maxdepth: 2
-
-    api_reference.rst

docs/api_reference/requirements.txt

@@ -1,17 +1,11 @@
--e libs/experimental
--e libs/langchain
--e libs/core
--e libs/community
-pydantic<2
-autodoc_pydantic==1.8.0
-myst_parser
-nbsphinx==0.8.9
-sphinx>=5
-sphinx-autobuild==2021.3.14
-sphinx_rtd_theme==1.0.0
-sphinx-typlog-theme==0.8.0
-sphinx-panels
-toml
-myst_nb
-sphinx_copybutton
-pydata-sphinx-theme==0.13.1
+autodoc_pydantic>=1,<2
+sphinx<=7
+myst-parser>=3
+sphinx-autobuild>=2024
+pydata-sphinx-theme>=0.15
+toml>=0.10.2
+myst-nb>=1.1.1
+pyyaml
+sphinx-design
+sphinx-copybutton
+beautifulsoup4

docs/api_reference/scripts/custom_formatter.py

@@ -0,0 +1,41 @@
+import sys
+from glob import glob
+from pathlib import Path
+
+from bs4 import BeautifulSoup
+
+CUR_DIR = Path(__file__).parents[1]
+
+
+def process_toc_h3_elements(html_content: str) -> str:
+    """Update Class.method() TOC headers to just method()."""
+    # Create a BeautifulSoup object
+    soup = BeautifulSoup(html_content, "html.parser")
+
+    # Find all <li> elements with class "toc-h3"
+    toc_h3_elements = soup.find_all("li", class_="toc-h3")
+
+    # Process each element
+    for element in toc_h3_elements:
+        element = element.a.code.span
+        # Get the text content of the element
+        content = element.get_text()
+
+        # Apply the regex substitution
+        modified_content = content.split(".")[-1]
+
+        # Update the element's content
+        element.string = modified_content
+
+    # Return the modified HTML
+    return str(soup)
+
+
+if __name__ == "__main__":
+    dir = sys.argv[1]
+    for fn in glob(str(f"{dir.rstrip('/')}/**/*.html"), recursive=True):
+        with open(fn, "r") as f:
+            html = f.read()
+        processed_html = process_toc_h3_elements(html)
+        with open(fn, "w") as f:
+            f.write(processed_html)

docs/api_reference/templates/class.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}
@@ -11,7 +11,7 @@
 
    .. autosummary::
    {% for item in attributes %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
    {% endif %}
    {% endblock %}
@@ -22,11 +22,11 @@
 
    .. autosummary::
    {% for item in methods %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
 
    {% for item in methods %}
-   .. automethod:: {{ name }}.{{ item }}
+   .. automethod:: {{ item }}
    {%- endfor %}
 
    {% endif %}

docs/api_reference/templates/enum.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/templates/function.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/templates/langchain_docs.html

@@ -0,0 +1,12 @@
+<!-- This will display a link to LangChain docs -->
+<head>
+    <style>
+        .text-link {
+            text-decoration: none; /* Remove underline */
+            color: inherit;        /* Inherit color from parent element */
+        }
+    </style>
+</head>
+<body>
+<a href="https://python.langchain.com/" class='text-link'>Docs</a>
+</body>

docs/api_reference/templates/pydantic.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/templates/runnable_non_pydantic.rst

@@ -1,21 +1,21 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
-.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
-
-    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
-
 .. currentmodule:: {{ module }}
 
 .. autoclass:: {{ objname }}
 
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
    {% block attributes %}
    {% if attributes %}
    .. rubric:: {{ _('Attributes') }}
 
    .. autosummary::
    {% for item in attributes %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
    {% endif %}
    {% endblock %}
@@ -26,11 +26,11 @@
 
    .. autosummary::
    {% for item in methods %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
 
    {% for item in methods %}
-   .. automethod:: {{ name }}.{{ item }}
+   .. automethod:: {{ item }}
    {%- endfor %}
 
    {% endif %}

docs/api_reference/templates/runnable_pydantic.rst

@@ -1,10 +1,6 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
-.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
-
-    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
-
 .. currentmodule:: {{ module }}
 
 .. autopydantic_model:: {{ objname }}
@@ -19,6 +15,10 @@
     :member-order: groupwise
     :show-inheritance: True
     :special-members: __call__
-    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, astream_log, transform, atransform, get_output_schema, get_prompts, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign
+    :exclude-members: construct, copy, dict, from_orm, parse_file, parse_obj, parse_raw, schema, schema_json, update_forward_refs, validate, json, is_lc_serializable, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, astream_log, transform, atransform, get_output_schema, get_prompts, config_schema, map, pick, pipe, with_listeners, with_alisteners, with_config, with_fallbacks, with_types, with_retry, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, bind, assign, as_tool
+
+    .. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+        The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
 
 .. example_links:: {{ objname }}

docs/api_reference/templates/typeddict.rst

@@ -1,4 +1,4 @@
-:mod:`{{module}}`.{{objname}}
+{{ objname }}
 {{ underline }}==============
 
 .. currentmodule:: {{ module }}

docs/api_reference/themes/COPYRIGHT.txt

@@ -1,27 +0,0 @@
-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

@@ -1,67 +0,0 @@
-<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

@@ -1,132 +0,0 @@
-{# 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="https://api.python.langchain.com/en/latest/{{ 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">
-                {%- 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

@@ -1,78 +0,0 @@
-{%- 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 %}
-
-<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('langchain_api_reference') }}">LangChain</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('core_api_reference') }}">Core</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('community_api_reference') }}">Community</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('experimental_api_reference') }}">Experimental</a>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" href="{{ pathto('text_splitters_api_reference') }}">Text splitters</a>
-        </li>
-        {%- for title, pathname in partners %}
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link nav-more-item-mobile-items" href="{{ pathto(pathname) }}">{{ title }}</a>
-        </li>
-        {%- endfor %}
-        <li class="nav-item dropdown nav-more-item-dropdown">
-          <a class="sk-nav-link nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false">Partner libs</a>
-          <div class="dropdown-menu" aria-labelledby="navbarDropdown">
-            {%- for title, pathname in partners %}
-              <a class="sk-nav-dropdown-item dropdown-item" href="{{ pathto(pathname) }}">{{ title }}</a>
-            {%- endfor %}
-          </div>
-        </li>
-        <li class="nav-item">
-          <a class="sk-nav-link nav-link" target="_blank" rel="noopener noreferrer" href="https://python.langchain.com/">Docs</a>
-        </li>
-      </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

@@ -1,16 +0,0 @@
-{%- 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

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

docs/docs/concepts.mdx

@@ -542,7 +542,8 @@ Typical usage may look like the following:
 ```python
 tools = [...] # Define a list of tools
 llm_with_tools = llm.bind_tools(tools)
-ai_msg = llm_with_tools.invoke("do xyz...")  # AIMessage(tool_calls=[ToolCall(...), ...], ...)
+ai_msg = llm_with_tools.invoke("do xyz...")
+# -> AIMessage(tool_calls=[ToolCall(...), ...], ...)
 ```
 
 The `AIMessage` returned from the model MAY have `tool_calls` associated with it.
@@ -559,9 +560,14 @@ This generally looks like:
 
 ```python
 # You will want to previously check that the LLM returned tool calls
-tool_call = ai_msg.tool_calls[0]  # ToolCall(args={...}, id=..., ...)
+tool_call = ai_msg.tool_calls[0]
+# ToolCall(args={...}, id=..., ...)
 tool_output = tool.invoke(tool_call["args"])
-tool_message = ToolMessage(content=tool_output, tool_call_id=tool_call["id"], name=tool_call["name"])
+tool_message = ToolMessage(
+    content=tool_output,
+    tool_call_id=tool_call["id"],
+    name=tool_call["name"]
+)
 ```
 
 Note that the `content` field will generally be passed back to the model.
@@ -571,7 +577,12 @@ you can transform the tool output but also pass it as an artifact (read more abo
 ```python
 ... # Same code as above
 response_for_llm = transform(response)
-tool_message = ToolMessage(content=response_for_llm, tool_call_id=tool_call["id"], name=tool_call["name"], artifact=tool_output)
+tool_message = ToolMessage(
+    content=response_for_llm,
+    tool_call_id=tool_call["id"],
+    name=tool_call["name"],
+    artifact=tool_output
+)
 ```
 
 #### Invoke with `ToolCall`
@@ -582,9 +593,14 @@ The benefits of this are that you don't have to write the logic yourself to tran
 This generally looks like:
 
 ```python
-tool_call = ai_msg.tool_calls[0]  # ToolCall(args={...}, id=..., ...)
+tool_call = ai_msg.tool_calls[0]
+# -> ToolCall(args={...}, id=..., ...)
 tool_message = tool.invoke(tool_call)
-# -> ToolMessage(content="tool result foobar...", tool_call_id=..., name="tool_name")
+# -> ToolMessage(
+    content="tool result foobar...",
+    tool_call_id=...,
+    name="tool_name"
+)
 ```
 
 If you are invoking the tool this way and want to include an [artifact](/docs/concepts/#toolmessage) for the ToolMessage, you will need to have the tool return two things.

docs/docs/how_to/chat_model_caching.ipynb

@@ -63,7 +63,7 @@
    "outputs": [],
    "source": [
     "# <!-- ruff: noqa: F821 -->\n",
-    "from langchain.globals import set_llm_cache"
+    "from langchain_core.globals import set_llm_cache"
    ]
   },
   {
@@ -103,7 +103,7 @@
    ],
    "source": [
     "%%time\n",
-    "from langchain.cache import InMemoryCache\n",
+    "from langchain_core.caches import InMemoryCache\n",
     "\n",
     "set_llm_cache(InMemoryCache())\n",
     "\n",

docs/docs/how_to/configure.ipynb

@@ -409,7 +409,7 @@
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"prompt\"),\n",
     "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    # If we specify this key, the default prompt (asking for a joke, as initialized above) will be used\n",
     "    default_key=\"joke\",\n",
     "    # This adds a new option, with name `poem`\n",
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
@@ -494,7 +494,7 @@
     "    # When configuring the end runnable, we can then use this id to configure this field\n",
     "    ConfigurableField(id=\"prompt\"),\n",
     "    # This sets a default_key.\n",
-    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    # If we specify this key, the default prompt (asking for a joke, as initialized above) will be used\n",
     "    default_key=\"joke\",\n",
     "    # This adds a new option, with name `poem`\n",
     "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",

docs/docs/how_to/document_loader_custom.ipynb

@@ -63,7 +63,7 @@
     "* The `load` methods is a convenience method meant solely for prototyping work -- it just invokes `list(self.lazy_load())`.\n",
     "* The `alazy_load` has a default implementation that will delegate to `lazy_load`. If you're using async, we recommend overriding the default implementation and providing a native async implementation.\n",
     "\n",
-    "::: {.callout-important}\n",
+    ":::{.callout-important}\n",
     "When implementing a document loader do **NOT** provide parameters via the `lazy_load` or `alazy_load` methods.\n",
     "\n",
     "All configuration is expected to be passed through the initializer (__init__). This was a design choice made by LangChain to make sure that once a document loader has been instantiated it has all the information needed to load documents.\n",
@@ -235,7 +235,7 @@
    "id": "56cb443e-f987-4386-b4ec-975ee129adb2",
    "metadata": {},
    "source": [
-    "::: {.callout-tip}\n",
+    ":::{.callout-tip}\n",
     "\n",
     "`load()` can be helpful in an interactive environment such as a jupyter notebook.\n",
     "\n",
@@ -276,7 +276,7 @@
    "source": [
     "## Working with Files\n",
     "\n",
-    "Many document loaders invovle parsing files. The difference between such loaders usually stems from how the file is parsed rather than how the file is loaded. For example, you can use `open` to read the binary content of either a PDF or a markdown file, but you need different parsing logic to convert that binary data into text.\n",
+    "Many document loaders involve parsing files. The difference between such loaders usually stems from how the file is parsed, rather than how the file is loaded. For example, you can use `open` to read the binary content of either a PDF or a markdown file, but you need different parsing logic to convert that binary data into text.\n",
     "\n",
     "As a result, it can be helpful to decouple the parsing logic from the loading logic, which makes it easier to re-use a given parser regardless of how the data was loaded.\n",
     "\n",
@@ -355,7 +355,7 @@
    "id": "433bfb7c-7767-43bc-b71e-42413d7494a8",
    "metadata": {},
    "source": [
-    "Using the **blob** API also allows one to load content direclty from memory without having to read it from a file!"
+    "Using the **blob** API also allows one to load content directly from memory without having to read it from a file!"
    ]
   },
   {

docs/docs/how_to/functions.ipynb

@@ -28,7 +28,7 @@
     "\n",
     "You can use arbitrary functions as [Runnables](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.Runnable.html#langchain_core.runnables.base.Runnable). This is useful for formatting or when you need functionality not provided by other LangChain components, and custom functions used as Runnables are called [`RunnableLambdas`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.base.RunnableLambda.html).\n",
     "\n",
-    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single dict input and unpacks it into multiple argument.\n",
+    "Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single dict input and unpacks it into multiple arguments.\n",
     "\n",
     "This guide will cover:\n",
     "\n",

docs/docs/how_to/graph_mapping.ipynb

@@ -364,7 +364,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains.graph_qa.cypher_utils import CypherQueryCorrector, Schema\n",
+    "from langchain_community.chains.graph_qa.cypher_utils import (\n",
+    "    CypherQueryCorrector,\n",
+    "    Schema,\n",
+    ")\n",
     "\n",
     "# Cypher validation tool for relationship directions\n",
     "corrector_schema = [\n",

docs/docs/how_to/llm_caching.ipynb

@@ -36,7 +36,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.globals import set_llm_cache\n",
+    "from langchain_core.globals import set_llm_cache\n",
     "from langchain_openai import OpenAI\n",
     "\n",
     "# To make the caching really obvious, lets use a slower and older model.\n",
@@ -71,7 +71,7 @@
    ],
    "source": [
     "%%time\n",
-    "from langchain.cache import InMemoryCache\n",
+    "from langchain_core.caches import InMemoryCache\n",
     "\n",
     "set_llm_cache(InMemoryCache())\n",
     "\n",

docs/docs/how_to/pydantic_compatibility.md

@@ -13,9 +13,14 @@ the v1 namespace of Pydantic 2.
 Because Pydantic does not support mixing .v1 and .v2 objects, users should be aware of a number of issues
 when using LangChain with Pydantic.
 
+:::caution
+While LangChain supports Pydantic V2 objects in some APIs (listed below), it's suggested that users keep using Pydantic V1 objects until LangChain 0.3 is released.
+:::
+
+
 ## 1. Passing Pydantic objects to LangChain APIs
 
-Most LangChain APIs that accept Pydantic objects have been updated to accept both Pydantic v1 and v2 objects.
+Most LangChain APIs for *tool usage* (see list below) have been updated to accept either Pydantic v1 or v2 objects.
 
 * Pydantic v1 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 1` is installed or subclasses of `pydantic.v1.BaseModel` if `pydantic 2` is installed.
 * Pydantic v2 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 2` is installed.
@@ -38,6 +43,7 @@ Partner packages that accept pydantic v2 objects via `bind_tools` or `with_struc
 | langchain-robocorp  | Yes         | >=0.0.10    |
 | langchain-openai    | Yes         | >=0.1.19    |
 | langchain-fireworks | Yes         | >=0.1.5     |
+| langchain-aws       | Yes         | >=0.1.15    |
 
 Additional partner packages will be updated to accept Pydantic v2 objects in the future.
 
@@ -169,4 +175,4 @@ If you need OpenAPI docs, your options are to either install Pydantic 1:
 or else to use the `APIHandler` object in LangChain to manually create the
 routes for your API.
 
-See: https://python.langchain.com/v0.2/docs/langserve/#pydantic
+See: https://python.langchain.com/v0.2/docs/langserve/#pydantic

docs/docs/how_to/qa_chat_history_how_to.ipynb

@@ -721,9 +721,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "\n",
     "agent_executor = create_react_agent(llm, tools, checkpointer=memory)"
    ]
@@ -890,9 +890,9 @@
     "from langchain_community.document_loaders import WebBaseLoader\n",
     "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
-    "from langgraph.checkpoint.sqlite import SqliteSaver\n",
+    "from langgraph.checkpoint.memory import MemorySaver\n",
     "\n",
-    "memory = SqliteSaver.from_conn_string(\":memory:\")\n",
+    "memory = MemorySaver()\n",
     "llm = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
     "\n",
     "\n",

docs/docs/how_to/qa_sources.ipynb

@@ -14,7 +14,9 @@
     "We will cover two approaches:\n",
     "\n",
     "1. Using the built-in [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html), which returns sources by default;\n",
-    "2. Using a simple [LCEL](/docs/concepts#langchain-expression-language-lcel) implementation, to show the operating principle."
+    "2. Using a simple [LCEL](/docs/concepts#langchain-expression-language-lcel) implementation, to show the operating principle.\n",
+    "\n",
+    "We will also show how to structure sources into the model response, such that a model can report what specific sources it used in generating its answer."
    ]
   },
   {
@@ -130,8 +132,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "820244ae-74b4-4593-b392-822979dd91b8",
+   "execution_count": null,
+   "id": "24a69b8c-024e-4e34-b827-9c9de46512a3",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -211,11 +213,11 @@
      "data": {
       "text/plain": [
        "{'input': 'What is Task Decomposition?',\n",
-       " 'context': [Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Resources:\\n1. Internet access for searches and information gathering.\\n2. Long Term memory management.\\n3. GPT-3.5 powered Agents for delegation of simple tasks.\\n4. File output.\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content=\"(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user's request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\", metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'})],\n",
-       " 'answer': 'Task decomposition involves breaking down a complex task into smaller and simpler steps. This process helps agents or models handle challenging tasks by dividing them into more manageable subtasks. Techniques like Chain of Thought and Tree of Thoughts are used to decompose tasks into multiple steps for better problem-solving.'}"
+       " 'context': [Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Resources:\\n1. Internet access for searches and information gathering.\\n2. Long Term memory management.\\n3. GPT-3.5 powered Agents for delegation of simple tasks.\\n4. File output.\\n\\nPerformance Evaluation:\\n1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.\\n2. Constructively self-criticize your big-picture behavior constantly.\\n3. Reflect on past decisions and strategies to refine your approach.\\n4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content=\"(3) Task execution: Expert models execute on the specific tasks and log results.\\nInstruction:\\n\\nWith the input and the inference results, the AI assistant needs to describe the process and results. The previous stages can be formed as - User Input: {{ User Input }}, Task Planning: {{ Tasks }}, Model Selection: {{ Model Assignment }}, Task Execution: {{ Predictions }}. You must first answer the user's request in a straightforward manner. Then describe the task process and show your analysis and model inference results to the user in the first person. If inference results contain a file path, must tell the user the complete file path.\")],\n",
+       " 'answer': 'Task decomposition involves breaking down a complex task into smaller and more manageable steps. This process helps agents or models tackle difficult tasks by dividing them into simpler subtasks or components. Task decomposition can be achieved through techniques like Chain of Thought or Tree of Thoughts, which guide the agent in breaking down tasks into sequential or branching steps.'}"
       ]
      },
      "execution_count": 5,
@@ -251,18 +253,18 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "22ea137c-1a7a-44dd-ac73-281213979957",
+   "id": "1950953a-e6f1-439d-b7b9-c3bd456e388d",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "{'input': 'What is Task Decomposition',\n",
-       " 'context': [Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='The AI assistant can parse user input to several tasks: [{\"task\": task, \"id\", task_id, \"dep\": dependency_task_ids, \"args\": {\"text\": text, \"image\": URL, \"audio\": URL, \"video\": URL}}]. The \"dep\" field denotes the id of the previous task which generates a new resource that the current task relies on. A special tag \"-task_id\" refers to the generated text image, audio and video in the dependency task with id as task_id. The task MUST be selected from the following options: {{ Available Task List }}. There is a logical relationship between tasks, please note their order. If the user input can\\'t be parsed, you need to reply empty JSON. Here are several cases for your reference: {{ Demonstrations }}. The chat history is recorded as {{ Chat History }}. From this chat history, you can find the path of the user-mentioned resources for your task planning.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}),\n",
-       "  Document(page_content='Fig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'})],\n",
-       " 'answer': 'Task decomposition involves breaking down complex tasks into smaller and simpler steps to make them more manageable for autonomous agents or models. This process can be achieved by techniques like Chain of Thought (CoT) or Tree of Thoughts, which guide the model to think step by step or explore multiple reasoning possibilities at each step. Task decomposition can be done through simple prompting with language models, task-specific instructions, or human inputs.'}"
+       " 'context': [Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#\\nChain of thought (CoT; Wei et al. 2022) has become a standard prompting technique for enhancing model performance on complex tasks. The model is instructed to “think step by step” to utilize more test-time computation to decompose hard tasks into smaller and simpler steps. CoT transforms big tasks into multiple manageable tasks and shed lights into an interpretation of the model’s thinking process.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Tree of Thoughts (Yao et al. 2023) extends CoT by exploring multiple reasoning possibilities at each step. It first decomposes the problem into multiple thought steps and generates multiple thoughts per step, creating a tree structure. The search process can be BFS (breadth-first search) or DFS (depth-first search) with each state evaluated by a classifier (via a prompt) or majority vote.\\nTask decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='The AI assistant can parse user input to several tasks: [{\"task\": task, \"id\", task_id, \"dep\": dependency_task_ids, \"args\": {\"text\": text, \"image\": URL, \"audio\": URL, \"video\": URL}}]. The \"dep\" field denotes the id of the previous task which generates a new resource that the current task relies on. A special tag \"-task_id\" refers to the generated text image, audio and video in the dependency task with id as task_id. The task MUST be selected from the following options: {{ Available Task List }}. There is a logical relationship between tasks, please note their order. If the user input can\\'t be parsed, you need to reply empty JSON. Here are several cases for your reference: {{ Demonstrations }}. The chat history is recorded as {{ Chat History }}. From this chat history, you can find the path of the user-mentioned resources for your task planning.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/'}, page_content='Fig. 11. Illustration of how HuggingGPT works. (Image source: Shen et al. 2023)\\nThe system comprises of 4 stages:\\n(1) Task planning: LLM works as the brain and parses the user requests into multiple tasks. There are four attributes associated with each task: task type, ID, dependencies, and arguments. They use few-shot examples to guide LLM to do task parsing and planning.\\nInstruction:')],\n",
+       " 'answer': 'Task decomposition is a technique used in artificial intelligence to break down complex tasks into smaller and more manageable subtasks. This approach helps agents or models to tackle difficult problems by dividing them into simpler steps, improving performance and interpretability. Different methods like Chain of Thought and Tree of Thoughts have been developed to enhance task decomposition in AI systems.'}"
       ]
      },
      "execution_count": 6,
@@ -279,15 +281,25 @@
     "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
     "\n",
     "\n",
+    "# This Runnable takes a dict with keys 'input' and 'context',\n",
+    "# formats them into a prompt, and generates a response.\n",
     "rag_chain_from_docs = (\n",
-    "    RunnablePassthrough.assign(context=(lambda x: format_docs(x[\"context\"])))\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
+    "    {\n",
+    "        \"input\": lambda x: x[\"input\"],  # input query\n",
+    "        \"context\": lambda x: format_docs(x[\"context\"]),  # context\n",
+    "    }\n",
+    "    | prompt  # format query and context into prompt\n",
+    "    | llm  # generate response\n",
+    "    | StrOutputParser()  # coerce to string\n",
     ")\n",
     "\n",
+    "# Pass input query to retriever\n",
     "retrieve_docs = (lambda x: x[\"input\"]) | retriever\n",
     "\n",
+    "# Below, we chain `.assign` calls. This takes a dict and successively\n",
+    "# adds keys-- \"context\" and \"answer\"-- where the value for each key\n",
+    "# is determined by a Runnable. The Runnable operates on all existing\n",
+    "# keys in the dict.\n",
     "chain = RunnablePassthrough.assign(context=retrieve_docs).assign(\n",
     "    answer=rag_chain_from_docs\n",
     ")\n",
@@ -302,7 +314,105 @@
    "source": [
     ":::{.callout-tip}\n",
     "\n",
-    "Check out the [LangSmith trace](https://smith.langchain.com/public/0cb42685-e29e-4280-a503-bef2014d7ba2/r)\n",
+    "Check out the [LangSmith trace](https://smith.langchain.com/public/1c055a3b-0236-4670-a3fb-023d418ba796/r)\n",
+    "\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c1c17797-d965-4fd2-b8d4-d386f25dd352",
+   "metadata": {},
+   "source": [
+    "## Structure sources in model response\n",
+    "\n",
+    "Up to this point, we've simply propagated the documents returned from the retrieval step through to the final response. But this may not illustrate what subset of information the model relied on when generating its answer. Below, we show how to structure sources into the model response, allowing the model to report what specific context it relied on for its answer.\n",
+    "\n",
+    "Because the above LCEL implementation is composed of [Runnable](/docs/concepts/#runnable-interface) primitives, it is straightforward to extend. Below, we make a simple change:\n",
+    "\n",
+    "- We use the model's tool-calling features to generate [structured output](/docs/how_to/structured_output/), consisting of an answer and list of sources. The schema for the response is represented in the `AnswerWithSources` TypedDict, below.\n",
+    "- We remove the `StrOutputParser()`, as we expect `dict` output in this scenario."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "8f916b14-1b0a-4975-a62f-52f1353bde15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from typing_extensions import Annotated, TypedDict\n",
+    "\n",
+    "\n",
+    "# Desired schema for response\n",
+    "class AnswerWithSources(TypedDict):\n",
+    "    \"\"\"An answer to the question, with sources.\"\"\"\n",
+    "\n",
+    "    answer: str\n",
+    "    sources: Annotated[\n",
+    "        List[str],\n",
+    "        ...,\n",
+    "        \"List of sources (author + year) used to answer the question\",\n",
+    "    ]\n",
+    "\n",
+    "\n",
+    "# Our rag_chain_from_docs has the following changes:\n",
+    "# - add `.with_structured_output` to the LLM;\n",
+    "# - remove the output parser\n",
+    "rag_chain_from_docs = (\n",
+    "    {\n",
+    "        \"input\": lambda x: x[\"input\"],\n",
+    "        \"context\": lambda x: format_docs(x[\"context\"]),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | llm.with_structured_output(AnswerWithSources)\n",
+    ")\n",
+    "\n",
+    "retrieve_docs = (lambda x: x[\"input\"]) | retriever\n",
+    "\n",
+    "chain = RunnablePassthrough.assign(context=retrieve_docs).assign(\n",
+    "    answer=rag_chain_from_docs\n",
+    ")\n",
+    "\n",
+    "response = chain.invoke({\"input\": \"What is Chain of Thought?\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "7a8fc0c5-afb3-4012-a467-3951996a6850",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{\n",
+      "  \"answer\": \"Chain of Thought (CoT) is a prompting technique that enhances model performance on complex tasks by instructing the model to \\\"think step by step\\\" to decompose hard tasks into smaller and simpler steps. It transforms big tasks into multiple manageable tasks and sheds light on the interpretation of the model's thinking process.\",\n",
+      "  \"sources\": [\n",
+      "    \"Wei et al. 2022\"\n",
+      "  ]\n",
+      "}\n"
+     ]
+    }
+   ],
+   "source": [
+    "import json\n",
+    "\n",
+    "print(json.dumps(response[\"answer\"], indent=2))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7440f785-29c5-4c6b-9656-0d9d5efbac05",
+   "metadata": {},
+   "source": [
+    ":::{.callout-tip}\n",
+    "\n",
+    "View [LangSmith trace](https://smith.langchain.com/public/0eeddf06-3a7b-4f27-974c-310ca8160f60/r)\n",
     "\n",
     ":::"
    ]

docs/docs/how_to/query_constructing_filters.ipynb

@@ -38,8 +38,8 @@
     "    Operator,\n",
     "    StructuredQuery,\n",
     ")\n",
-    "from langchain.retrievers.self_query.chroma import ChromaTranslator\n",
-    "from langchain.retrievers.self_query.elasticsearch import ElasticsearchTranslator\n",
+    "from langchain_community.query_constructors.chroma import ChromaTranslator\n",
+    "from langchain_community.query_constructors.elasticsearch import ElasticsearchTranslator\n",
     "from langchain_core.pydantic_v1 import BaseModel"
    ]
   },

docs/docs/how_to/self_query.ipynb

@@ -512,7 +512,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.retrievers.self_query.chroma import ChromaTranslator\n",
+    "from langchain_community.query_constructors.chroma import ChromaTranslator\n",
     "\n",
     "retriever = SelfQueryRetriever(\n",
     "    query_constructor=query_constructor,\n",

docs/docs/how_to/semantic-chunker.ipynb

@@ -299,16 +299,16 @@
   },
   {
    "cell_type": "markdown",
+   "id": "423c6e099e94ca69",
+   "metadata": {
+    "collapsed": false
+   },
    "source": [
     "### Gradient\n",
     "\n",
     "In this method, the gradient of distance is used to split chunks along with the percentile method.\n",
     "This method is useful when chunks are highly correlated with each other or specific to a domain e.g. legal or medical. The idea is to apply anomaly detection on gradient array so that the distribution become wider and easy to identify boundaries in highly semantic data."
-   ],
-   "metadata": {
-    "collapsed": false
-   },
-   "id": "423c6e099e94ca69"
+   ]
   },
   {
    "cell_type": "code",
@@ -325,6 +325,8 @@
   {
    "cell_type": "code",
    "execution_count": 6,
+   "id": "e9f393d316ce1f6c",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -337,13 +339,13 @@
    "source": [
     "docs = text_splitter.create_documents([state_of_the_union])\n",
     "print(docs[0].page_content)"
-   ],
-   "metadata": {},
-   "id": "e9f393d316ce1f6c"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
+   "id": "a407cd57f02a0db4",
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
@@ -355,9 +357,7 @@
    ],
    "source": [
     "print(len(docs))"
-   ],
-   "metadata": {},
-   "id": "a407cd57f02a0db4"
+   ]
   }
  ],
  "metadata": {

docs/docs/how_to/sql_csv.ipynb

@@ -761,7 +761,7 @@
     "* [SQL tutorial](/docs/tutorials/sql_qa): Many of the challenges of working with SQL db's and CSV's are generic to any structured data type, so it's useful to read the SQL techniques even if you're using Pandas for CSV data analysis.\n",
     "* [Tool use](/docs/how_to/tool_calling): Guides on general best practices when working with chains and agents that invoke tools\n",
     "* [Agents](/docs/tutorials/agents): Understand the fundamentals of building LLM agents.\n",
-    "* Integrations: Sandboxed envs like [E2B](/docs/integrations/tools/e2b_data_analysis) and [Bearly](/docs/integrations/tools/bearly), utilities like [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), related agents like [Spark DataFrame agent](/docs/integrations/toolkits/spark)."
+    "* Integrations: Sandboxed envs like [E2B](/docs/integrations/tools/e2b_data_analysis) and [Bearly](/docs/integrations/tools/bearly), utilities like [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase), related agents like [Spark DataFrame agent](/docs/integrations/tools/spark_sql)."
    ]
   }
  ],

docs/docs/how_to/toolkits.mdx

@@ -5,7 +5,6 @@ sidebar_position: 3
 
 
 Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.
-For a complete list of available ready-made toolkits, visit [Integrations](/docs/integrations/toolkits/).
 
 All Toolkits expose a `get_tools` method which returns a list of tools.
 You can therefore do:

docs/docs/how_to/tools_builtin.ipynb

@@ -196,8 +196,6 @@
     "\n",
     "Toolkits are collections of tools that are designed to be used together for specific tasks. They have convenient loading methods.\n",
     "\n",
-    "For a complete list of available ready-made toolkits, visit [Integrations](/docs/integrations/toolkits/).\n",
-    "\n",
     "All Toolkits expose a `get_tools` method which returns a list of tools.\n",
     "\n",
     "You're usually meant to use them this way:\n",

docs/docs/integrations/chat/huggingface.ipynb

@@ -1,29 +1,15 @@
 {
  "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "---\n",
-    "sidebar_label: Hugging Face\n",
-    "---"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "# ChatHuggingFace\n",
     "\n",
+    "This will help you getting started with `langchain_huggingface` [chat models](/docs/concepts/#chat-models). For detailed documentation of all `ChatHuggingFace` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_huggingface.chat_models.huggingface.ChatHuggingFace.html). For a list of models supported by Hugging Face check out [this page](https://huggingface.co/models).\n",
+    "\n",
     "## Overview\n",
-    "\n",
-    "This notebook shows how to get started using Hugging Face LLMs as chat models.\n",
-    "\n",
-    "In particular, we will:\n",
-    "1. Utilize the [HuggingFaceEndpoint](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/llms/huggingface_endpoint.py) integrations to instantiate an LLM.\n",
-    "2. Utilize the `ChatHuggingFace` class to enable any of these LLMs to interface with LangChain's [Chat Messages](/docs/concepts/#message-types) abstraction.\n",
-    "3. Explore tool calling with the `ChatHuggingFace`.\n",
-    "4. Demonstrate how to use an open-source LLM to power an `ChatAgent` pipeline\n",
+    "### Integration details\n",
     "\n",
     "### Integration details\n",
     "\n",
@@ -64,7 +50,22 @@
    "source": [
     "### Installation\n",
     "\n",
-    "Below we install additional packages as well for demonstration purposes:"
+    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatHuggingFace](https://api.python.langchain.com/en/latest/chat_models/langchain_huggingface.chat_models.huggingface.ChatHuggingFace.html) | [langchain_huggingface](https://api.python.langchain.com/en/latest/huggingface_api_reference.html) | ✅ | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_huggingface?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_huggingface?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access `langchain_huggingface` models you'll need to create a/an `Hugging Face` account, get an API key, and install the `langchain_huggingface` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "You'll need to have a [Hugging Face Access Token](https://huggingface.co/docs/hub/security-tokens) saved as an environment variable: `HUGGINGFACEHUB_API_TOKEN`."
    ]
   },
   {
@@ -73,14 +74,41 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain-huggingface text-generation transformers google-search-results numexpr langchainhub sentencepiece jinja2"
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"HUGGINGFACEHUB_API_TOKEN\"] = getpass.getpass(\n",
+    "    \"Enter your Hugging Face API key: \"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.0\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.1.2\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install --upgrade --quiet  langchain-huggingface text-generation transformers google-search-results numexpr langchainhub sentencepiece jinja2 bitsandbytes accelerate"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Instantiation"
+    "## Instantiation\n",
+    "\n",
+    "You can instantiate a `ChatHuggingFace` model in two different ways, either from a `HuggingFaceEndpoint` or from a `HuggingFacePipeline`."
    ]
   },
   {
@@ -92,19 +120,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\n",
+      "Token is valid (permission: fineGrained).\n",
+      "Your token has been saved to /Users/isaachershenson/.cache/huggingface/token\n",
+      "Login successful\n"
+     ]
+    }
+   ],
    "source": [
-    "from langchain_huggingface import HuggingFaceEndpoint\n",
+    "from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint\n",
     "\n",
     "llm = HuggingFaceEndpoint(\n",
-    "    repo_id=\"meta-llama/Meta-Llama-3-70B-Instruct\",\n",
+    "    repo_id=\"HuggingFaceH4/zephyr-7b-beta\",\n",
     "    task=\"text-generation\",\n",
     "    max_new_tokens=512,\n",
     "    do_sample=False,\n",
     "    repetition_penalty=1.03,\n",
-    ")"
+    ")\n",
+    "\n",
+    "chat_model = ChatHuggingFace(llm=llm)"
    ]
   },
   {
@@ -116,11 +157,194 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 9,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "da32ae8ec8864ccfb480044fe2eec065",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "config.json:   0%|          | 0.00/638 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ee1891b7e5f64fba88ba35f444e598fb",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model.safetensors.index.json:   0%|          | 0.00/23.9k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9ff1ec7f575b42adb608c15955de7888",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading shards:   0%|          | 0/8 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5214696698814b919f561647a684d1e4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00001-of-00008.safetensors:   0%|          | 0.00/1.89G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9ac334c69a2048a0a77340cca44d8c80",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00002-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "465ad1a51d414e0daf1cd9308455be94",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00003-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a329c43c3d574df0afd38c7457cc639c",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00004-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a736a6c4023542af8c6ecc232b823d18",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00005-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "8bdee70b843d433e8236fff83ecda022",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00006-of-00008.safetensors:   0%|          | 0.00/1.95G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5ecb6103e0304ae188a14d598119a361",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00007-of-00008.safetensors:   0%|          | 0.00/1.98G [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "174e3cb487bd453c9c70d7614254a35e",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "model-00008-of-00008.safetensors:   0%|          | 0.00/816M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "28f8c233b04b45d7800e12c785a8c4bc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Loading checkpoint shards:   0%|          | 0/8 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "449dfa023dc8430fbcde94544ba01c4f",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "generation_config.json:   0%|          | 0.00/111 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
-    "from langchain_huggingface import HuggingFacePipeline\n",
+    "from langchain_huggingface import ChatHuggingFace, HuggingFacePipeline\n",
     "\n",
     "llm = HuggingFacePipeline.from_model_id(\n",
     "    model_id=\"HuggingFaceH4/zephyr-7b-beta\",\n",
@@ -129,8 +353,34 @@
     "        max_new_tokens=512,\n",
     "        do_sample=False,\n",
     "        repetition_penalty=1.03,\n",
-    "        return_full_text=False,\n",
     "    ),\n",
+    ")\n",
+    "\n",
+    "chat_model = ChatHuggingFace(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Instatiating with Quantization\n",
+    "\n",
+    "To run a quantized version of your model, you can specify a `bitsandbytes` quantization config as follows:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from transformers import BitsAndBytesConfig\n",
+    "\n",
+    "quantization_config = BitsAndBytesConfig(\n",
+    "    load_in_4bit=True,\n",
+    "    bnb_4bit_quant_type=\"nf4\",\n",
+    "    bnb_4bit_compute_dtype=\"float16\",\n",
+    "    bnb_4bit_use_double_quant=True,\n",
     ")"
    ]
   },
@@ -138,30 +388,27 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "To run a quantized version, you might specify a `bitsandbytes` quantization config as follows:\n",
-    "\n",
-    "```python\n",
-    "from transformers import BitsAndBytesConfig\n",
-    "\n",
-    "quantization_config = BitsAndBytesConfig(\n",
-    "    load_in_4bit=True,\n",
-    "    bnb_4bit_quant_type=\"nf4\",\n",
-    "    bnb_4bit_compute_dtype=\"float16\",\n",
-    "    bnb_4bit_use_double_quant=True\n",
-    ")\n",
-    "```\n",
-    "\n",
-    "and pass it to the `HuggingFacePipeline` as a part of its `model_kwargs`:\n",
-    "\n",
-    "```python\n",
-    "pipeline = HuggingFacePipeline(\n",
-    "    ...\n",
-    "\n",
+    "and pass it to the `HuggingFacePipeline` as a part of its `model_kwargs`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = HuggingFacePipeline.from_model_id(\n",
+    "    model_id=\"HuggingFaceH4/zephyr-7b-beta\",\n",
+    "    task=\"text-generation\",\n",
+    "    pipeline_kwargs=dict(\n",
+    "        max_new_tokens=512,\n",
+    "        do_sample=False,\n",
+    "        repetition_penalty=1.03,\n",
+    "    ),\n",
     "    model_kwargs={\"quantization_config\": quantization_config},\n",
-    "    \n",
-    "    ...\n",
     ")\n",
-    "```"
+    "\n",
+    "chat_model = ChatHuggingFace(llm=llm)"
    ]
   },
   {
@@ -171,34 +418,16 @@
     "## Invocation"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Instantiate the chat model and some messages to pass. \n",
-    "\n",
-    "**Note**: you need to pass the `model_id` explicitly if you are using self-hosted `text-generation-inference`"
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 11,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_core.messages import (\n",
     "    HumanMessage,\n",
     "    SystemMessage,\n",
     ")\n",
-    "from langchain_huggingface import ChatHuggingFace\n",
     "\n",
     "messages = [\n",
     "    SystemMessage(content=\"You're a helpful assistant\"),\n",
@@ -207,343 +436,35 @@
     "    ),\n",
     "]\n",
     "\n",
-    "chat_model = ChatHuggingFace(llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Check the `model_id`"
+    "ai_msg = chat_model.invoke(messages)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'meta-llama/Meta-Llama-3-70B-Instruct'"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chat_model.model_id"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Inspect how the chat messages are formatted for the LLM call."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\\n\\nYou're a helpful assistant<|eot_id|><|start_header_id|>user<|end_header_id|>\\n\\nWhat happens when an unstoppable force meets an immovable object?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\n\""
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chat_model._to_chat_prompt(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Call the model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "One of the classic thought experiments in physics!\n",
+      "According to the popular phrase and hypothetical scenario, when an unstoppable force meets an immovable object, a paradoxical situation arises as both forces are seemingly contradictory. On one hand, an unstoppable force is an entity that cannot be stopped or prevented from moving forward, while on the other hand, an immovable object is something that cannot be moved or displaced from its position. \n",
       "\n",
-      "The concept of an unstoppable force meeting an immovable object is a paradox that has puzzled philosophers and physicists for centuries. It's a mind-bending scenario that challenges our understanding of the fundamental laws of physics.\n",
-      "\n",
-      "In essence, an unstoppable force is something that cannot be halted or slowed down, while an immovable object is something that cannot be moved or displaced. If we assume that both entities exist in the same universe, we run into a logical contradiction.\n",
-      "\n",
-      "Here\n"
+      "In this scenario, it is un\n"
      ]
     }
    ],
    "source": [
-    "res = chat_model.invoke(messages)\n",
-    "print(res.content)"
+    "print(ai_msg.content)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Chaining\n",
+    "## API reference\n",
     "\n",
-    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = prompt | llm\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"German\",\n",
-    "        \"input\": \"I love programming.\",\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Tool calling with `ChatHuggingFace`\n",
-    "\n",
-    "`text-generation-inference` supports tool with open source LLMs starting from v2.0.1"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create a basic tool (`Calculator`):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
-    "\n",
-    "\n",
-    "class Calculator(BaseModel):\n",
-    "    \"\"\"Multiply two integers together.\"\"\"\n",
-    "\n",
-    "    a: int = Field(..., description=\"First integer\")\n",
-    "    b: int = Field(..., description=\"Second integer\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Bind the tool to the `chat_model` and give it a try:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Calculator(a=3, b=12)]"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.output_parsers.openai_tools import PydanticToolsParser\n",
-    "\n",
-    "llm_with_multiply = chat_model.bind_tools([Calculator], tool_choice=\"auto\")\n",
-    "parser = PydanticToolsParser(tools=[Calculator])\n",
-    "tool_chain = llm_with_multiply | parser\n",
-    "tool_chain.invoke(\"How much is 3 multiplied by 12?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Use with agents\n",
-    "\n",
-    "Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. \n",
-    "\n",
-    "The agent is based on the paper [ReAct: Synergizing Reasoning and Acting in Language Models](https://arxiv.org/abs/2210.03629)\n",
-    "\n",
-    "The example below is taken from [here](https://python.langchain.com/v0.1/docs/modules/agents/agent_types/react/#using-chat-models).\n",
-    "\n",
-    "> Note: To run this section, you'll need to have a [SerpAPI Token](https://serpapi.com/) saved as an environment variable: `SERPAPI_API_KEY`"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import AgentExecutor, load_tools\n",
-    "from langchain.agents.format_scratchpad import format_log_to_str\n",
-    "from langchain.agents.output_parsers import (\n",
-    "    ReActJsonSingleInputOutputParser,\n",
-    ")\n",
-    "from langchain.tools.render import render_text_description\n",
-    "from langchain_community.utilities import SerpAPIWrapper"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Configure the agent with a `react-json` style prompt and access to a search engine and calculator."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# setup tools\n",
-    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\n",
-    "\n",
-    "# setup ReAct style prompt\n",
-    "prompt = hub.pull(\"hwchase17/react-json\")\n",
-    "prompt = prompt.partial(\n",
-    "    tools=render_text_description(tools),\n",
-    "    tool_names=\", \".join([t.name for t in tools]),\n",
-    ")\n",
-    "\n",
-    "# define the agent\n",
-    "chat_model_with_stop = chat_model.bind(stop=[\"\\nObservation\"])\n",
-    "agent = (\n",
-    "    {\n",
-    "        \"input\": lambda x: x[\"input\"],\n",
-    "        \"agent_scratchpad\": lambda x: format_log_to_str(x[\"intermediate_steps\"]),\n",
-    "    }\n",
-    "    | prompt\n",
-    "    | chat_model_with_stop\n",
-    "    | ReActJsonSingleInputOutputParser()\n",
-    ")\n",
-    "\n",
-    "# instantiate AgentExecutor\n",
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mQuestion: Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\n",
-      "\n",
-      "Thought: I need to use the Search tool to find out who Leo DiCaprio's current girlfriend is. Then, I can use the Calculator tool to raise her current age to the power of 0.43.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Search\",\n",
-      "  \"action_input\": \"leo dicaprio girlfriend\"\n",
-      "}\n",
-      "```\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mLeonardo DiCaprio may have found The One in Vittoria Ceretti. “They are in love,” a source exclusively reveals in the latest issue of Us Weekly. “Leo was clearly very proud to be showing Vittoria off and letting everyone see how happy they are together.”\u001b[0m\u001b[32;1m\u001b[1;3mNow that we know Leo DiCaprio's current girlfriend is Vittoria Ceretti, let's find out her current age.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Search\",\n",
-      "  \"action_input\": \"vittoria ceretti age\"\n",
-      "}\n",
-      "```\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3m25 years\u001b[0m\u001b[32;1m\u001b[1;3mNow that we know Vittoria Ceretti's current age is 25, let's use the Calculator tool to raise it to the power of 0.43.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Calculator\",\n",
-      "  \"action_input\": \"25^0.43\"\n",
-      "}\n",
-      "```\n",
-      "\u001b[0m\u001b[33;1m\u001b[1;3mAnswer: 3.991298452658078\u001b[0m\u001b[32;1m\u001b[1;3mFinal Answer: Vittoria Ceretti, Leo DiCaprio's current girlfriend, when raised to the power of 0.43 is approximately 4.0 rounded to two decimal places. Her current age is 25 years old.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'input': \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\",\n",
-       " 'output': \"Vittoria Ceretti, Leo DiCaprio's current girlfriend, when raised to the power of 0.43 is approximately 4.0 rounded to two decimal places. Her current age is 25 years old.\"}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.invoke(\n",
-    "    {\n",
-    "        \"input\": \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Wahoo! Our open-source 7b parameter Zephyr model was able to:\n",
-    "\n",
-    "1. Plan out a series of actions: `I need to use the Search tool to find out who Leo DiCaprio's current girlfriend is. Then, I can use the Calculator tool to raise her current age to the power of 0.43.`\n",
-    "2. Then execute a search using the SerpAPI tool to find who Leo DiCaprio's current girlfriend is\n",
-    "3. Execute another search to find her age\n",
-    "4. And finally use a calculator tool to calculate her age raised to the power of 0.43\n",
-    "\n",
-    "It's exciting to see how far open-source LLM's can go as general purpose reasoning agents. Give it a try yourself!"
+    "For detailed documentation of all `ChatHuggingFace` features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_huggingface.chat_models.huggingface.ChatHuggingFace.html"
    ]
   },
   {
@@ -572,7 +493,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/index.mdx

@@ -0,0 +1,32 @@
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+keywords: [compatibility]
+---
+
+# Chat models
+
+[Chat models](/docs/concepts/#chat-models) are language models that use a sequence of [messages](/docs/concepts/#messages) as inputs and return messages as outputs (as opposed to using plain text). These are generally newer models.
+
+:::info
+
+If you'd like to write your own chat model, see [this how-to](/docs/how_to/custom_chat_model/).
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
+## Featured Providers
+
+:::info
+While all these LangChain classes support the indicated advanced feature, you may have
+to open the provider-specific documentation to learn which hosted models or backends support
+the feature.
+:::
+
+import { CategoryTable, IndexTable } from "@theme/FeatureTables";
+
+<CategoryTable category="chat" />
+
+## All chat models
+
+<IndexTable />

docs/docs/integrations/chat/kinetica.ipynb

@@ -13,7 +13,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Kinetica SqlAssist LLM Demo\n",
+    "# Kinetica Language To SQL Chat Model\n",
     "\n",
     "This notebook demonstrates how to use Kinetica to transform natural language into SQL\n",
     "and simplify the process of data retrieval. This demo is intended to show the mechanics\n",

docs/docs/integrations/chat/llamacpp.ipynb

@@ -4,9 +4,23 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# ChatLlamaCpp\n",
+    "# Llama.cpp\n",
     "\n",
-    "This notebook provides a quick overview for getting started with chat model intergrated with [llama cpp python](https://github.com/abetlen/llama-cpp-python)."
+    ">[llama.cpp python](https://github.com/abetlen/llama-cpp-python) library is a simple Python bindings for `@ggerganov`\n",
+    ">[llama.cpp](https://github.com/ggerganov/llama.cpp).\n",
+    ">\n",
+    ">This package provides:\n",
+    ">\n",
+    "> - Low-level access to C API via ctypes interface.\n",
+    "> - High-level Python API for text completion\n",
+    ">   - `OpenAI`-like API\n",
+    ">   - `LangChain` compatibility\n",
+    ">   - `LlamaIndex` compatibility\n",
+    "> - OpenAI compatible web server\n",
+    ">   - Local Copilot replacement\n",
+    ">   - Function Calling support\n",
+    ">   - Vision API support\n",
+    ">   - Multiple Models\n"
    ]
   },
   {
@@ -212,8 +226,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.tools import tool\n",
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "from langchain_core.tools import tool\n",
     "\n",
     "\n",
     "class WeatherInput(BaseModel):\n",
@@ -410,7 +424,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.8"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/mistralai.ipynb

@@ -12,12 +12,12 @@
   },
   {
    "cell_type": "markdown",
-   "id": "a14c83bf-af26-4f22-8c1a-d632c5795ecf",
+   "id": "d295c2a2",
    "metadata": {},
    "source": [
-    "# MistralAI\n",
+    "# ChatMistralAI\n",
     "\n",
-    "This will help you getting started with Mistral [chat models](/docs/concepts/#chat-models), accessed via their [API](https://docs.mistral.ai/api/). For detailed documentation of all ChatMistralAI features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html).\n",
+    "This will help you getting started with Mistral [chat models](/docs/concepts/#chat-models). For detailed documentation of all `ChatMistralAI` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html). The `ChatMistralAI` class is built on top of the [Mistral API](https://docs.mistral.ai/api/). For a list of all the models supported by Mistral, check out [this page](https://docs.mistral.ai/getting-started/models/).\n",
     "\n",
     "## Overview\n",
     "### Integration details\n",
@@ -29,36 +29,35 @@
     "### Model features\n",
     "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
     "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | \n",
+    "| ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | \n",
     "\n",
     "## Setup\n",
     "\n",
-    "To access Mistral models you'll need to create a Mistral account, get an API key, and install the `langchain-mistralai` integration package.\n",
+    "\n",
+    "To access `ChatMistralAI` models you'll need to create a Mistral account, get an API key, and install the `langchain_mistralai` integration package.\n",
     "\n",
     "### Credentials\n",
     "\n",
-    "A valid [API key](https://console.mistral.ai/users/api-keys/) is needed to communicate with the API. Once you've obtained an API key, store it in the `MISTRAL_API_KEY` environment variable:"
+    "\n",
+    "A valid [API key](https://console.mistral.ai/users/api-keys/) is needed to communicate with the API. Once you've done this set the MISTRAL_API_KEY environment variable:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9acd8340-09d4-4ece-871a-a35b0732c7d8",
+   "id": "2461605e",
    "metadata": {},
    "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
-    "    os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\n",
-    "        \"Enter your __ModuleName__ API key: \"\n",
-    "    )"
+    "os.environ[\"MISTRAL_API_KEY\"] = getpass.getpass(\"Enter your Mistral API key: \")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "42c979b1-df49-4f6c-9fe6-d9dbf3ea8c2a",
+   "id": "788f37ac",
    "metadata": {},
    "source": [
     "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
@@ -67,37 +66,37 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "cc4f11ec-5cb3-4caf-b3cd-7a20c41b0cfe",
+   "id": "007209d5",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "0fc42221-97b2-466b-95db-10368e17ca56",
+   "id": "0f5c74f9",
    "metadata": {},
    "source": [
     "### Installation\n",
     "\n",
-    "The LangChain MistralAI integration lives in the `langchain-mistralai` package:"
+    "The LangChain Mistral integration lives in the `langchain_mistralai` package:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "85cb1ab8-9f2c-4b93-8415-ad65819dcb38",
+   "id": "1ab11a65",
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain-mistralai"
+    "%pip install -qU langchain_mistralai"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "502127fd",
+   "id": "fb1a335e",
    "metadata": {},
    "source": [
     "## Instantiation\n",
@@ -107,19 +106,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "2dfa801a-d040-4c09-9634-58604e8eaf16",
+   "execution_count": 5,
+   "id": "e6c38580",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_mistralai.chat_models import ChatMistralAI\n",
+    "from langchain_mistralai import ChatMistralAI\n",
     "\n",
-    "llm = ChatMistralAI(model=\"mistral-large-latest\")"
+    "llm = ChatMistralAI(\n",
+    "    model=\"mistral-large-latest\",\n",
+    "    temperature=0,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "f668acff-eb14-4b3a-959a-df5bfc02968b",
+   "id": "aec79099",
    "metadata": {},
    "source": [
     "## Invocation"
@@ -127,17 +131,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "86e3f9e6-67ec-4fbf-8ff1-85331200f412",
+   "execution_count": 6,
+   "id": "8838c3cc",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'prompt_tokens': 27, 'total_tokens': 36, 'completion_tokens': 9}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-d6196c33-9410-413b-b454-4ed0bec1f0c7-0', usage_metadata={'input_tokens': 27, 'output_tokens': 9, 'total_tokens': 36})"
+       "AIMessage(content='Sure, I\\'d be happy to help you translate that sentence into French! The English sentence \"I love programming\" translates to \"J\\'aime programmer\" in French. Let me know if you have any other questions or need further assistance!', response_metadata={'token_usage': {'prompt_tokens': 32, 'total_tokens': 84, 'completion_tokens': 52}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-64bac156-7160-4b68-b67e-4161f63e021f-0', usage_metadata={'input_tokens': 32, 'output_tokens': 52, 'total_tokens': 84})"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -156,15 +160,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "8f8a24bc-b7f0-4d3a-b310-8a4e0ba125dd",
+   "execution_count": 7,
+   "id": "bbf6a048",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "J'adore la programmation.\n"
+      "Sure, I'd be happy to help you translate that sentence into French! The English sentence \"I love programming\" translates to \"J'aime programmer\" in French. Let me know if you have any other questions or need further assistance!\n"
      ]
     }
    ],
@@ -174,116 +178,27 @@
   },
   {
    "cell_type": "markdown",
-   "id": "c361ab1e-8c0c-4206-9e3c-9d1424a12b9c",
-   "metadata": {},
-   "source": [
-    "### Async"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=\"J'aime programmer.\", response_metadata={'token_usage': {'prompt_tokens': 27, 'total_tokens': 34, 'completion_tokens': 7}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-1873888a-186f-49a8-ab81-24335bd3099b-0', usage_metadata={'input_tokens': 27, 'output_tokens': 7, 'total_tokens': 34})"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "await llm.ainvoke(messages)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "86ccef97",
-   "metadata": {},
-   "source": [
-    "### Streaming\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "J'adore programmer."
-     ]
-    }
-   ],
-   "source": [
-    "for chunk in llm.stream(messages):\n",
-    "    print(chunk.content, end=\"\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f6189577",
-   "metadata": {},
-   "source": [
-    "### Batch"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "e63aebcb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'prompt_tokens': 27, 'total_tokens': 36, 'completion_tokens': 9}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-2aa2a189-c405-4cf5-bd31-e9025e4c8536-0', usage_metadata={'input_tokens': 27, 'output_tokens': 9, 'total_tokens': 36})]"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "llm.batch([messages])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "38e39e71",
+   "id": "32b87f87",
    "metadata": {},
    "source": [
     "## Chaining\n",
     "\n",
-    "You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/docs/concepts#langchain-expression-language-lcel)"
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "ee43a1ae",
+   "execution_count": 8,
+   "id": "24e2c51c",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Ich liebe Programmieren.', response_metadata={'token_usage': {'prompt_tokens': 21, 'total_tokens': 28, 'completion_tokens': 7}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-409ebc9a-b4a0-4734-ab6f-e11f6b4f808f-0', usage_metadata={'input_tokens': 21, 'output_tokens': 7, 'total_tokens': 28})"
+       "AIMessage(content='Ich liebe Programmierung. (German translation)', response_metadata={'token_usage': {'prompt_tokens': 26, 'total_tokens': 38, 'completion_tokens': 12}, 'model': 'mistral-small', 'finish_reason': 'stop'}, id='run-dfd4094f-e347-47b0-9056-8ebd7ea35fe7-0', usage_metadata={'input_tokens': 26, 'output_tokens': 12, 'total_tokens': 38})"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -291,7 +206,7 @@
    "source": [
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "prompt = ChatPromptTemplate(\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
     "        (\n",
     "            \"system\",\n",
@@ -313,12 +228,12 @@
   },
   {
    "cell_type": "markdown",
-   "id": "eb7e01fb-a433-48b1-a4c2-e6009523a896",
+   "id": "cb9b5834",
    "metadata": {},
    "source": [
     "## API reference\n",
     "\n",
-    "For detailed documentation of all ChatMistralAI features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html"
+    "Head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html) for detailed documentation of all attributes and methods."
    ]
   }
  ],
@@ -338,7 +253,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/octoai.ipynb

@@ -99,7 +99,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/docs/integrations/chat/openai.ipynb

@@ -56,23 +56,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "e817fe2e-4f1d-4533-b19e-2400b1cf6ce8",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdin",
-     "output_type": "stream",
-     "text": [
-      "Enter your OpenAI API key:  ········\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter your OpenAI API key: \")"
+    "if not os.environ.get(\"OPENAI_API_KEY\"):\n",
+    "    os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter your OpenAI API key: \")"
    ]
   },
   {
@@ -126,7 +119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "522686de",
    "metadata": {
     "tags": []
@@ -281,12 +274,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 4,
    "id": "b7ea7690-ec7a-4337-b392-e87d1f39a6ec",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
+    "from pydantic import BaseModel, Field\n",
     "\n",
     "\n",
     "class GetWeather(BaseModel):\n",
@@ -322,6 +315,47 @@
     "ai_msg"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "67b0f63d-15e6-45e0-9e86-2852ddcff54f",
+   "metadata": {},
+   "source": [
+    "### ``strict=True``\n",
+    "\n",
+    ":::info Requires ``langchain-openai>=0.1.21rc1``\n",
+    "\n",
+    ":::\n",
+    "\n",
+    "As of Aug 6, 2024, OpenAI supports a `strict` argument when calling tools that will enforce that the tool argument schema is respected by the model. See more here: https://platform.openai.com/docs/guides/function-calling\n",
+    "\n",
+    "**Note**: If ``strict=True`` the tool definition will also be validated, and a subset of JSON schema are accepted. Crucially, schema cannot have optional args (those with default values). Read the full docs on what types of schema are supported here: https://platform.openai.com/docs/guides/structured-outputs/supported-schemas. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "dc8ac4f1-4039-4392-90c1-2d8331cd6910",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_VYEfpPDh3npMQ95J9EWmWvSn', 'function': {'arguments': '{\"location\":\"San Francisco, CA\"}', 'name': 'GetWeather'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 68, 'total_tokens': 85}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_3aa7262c27', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a4c6749b-adbb-45c7-8b17-8d6835d5c443-0', tool_calls=[{'name': 'GetWeather', 'args': {'location': 'San Francisco, CA'}, 'id': 'call_VYEfpPDh3npMQ95J9EWmWvSn', 'type': 'tool_call'}], usage_metadata={'input_tokens': 68, 'output_tokens': 17, 'total_tokens': 85})"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_with_tools = llm.bind_tools([GetWeather], strict=True)\n",
+    "ai_msg = llm_with_tools.invoke(\n",
+    "    \"what is the weather like in San Francisco\",\n",
+    ")\n",
+    "ai_msg"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "768d1ae4-4b1a-48eb-a329-c8d5051067a3",
@@ -412,9 +446,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-2",
+   "display_name": "poetry-venv-311",
    "language": "python",
-   "name": "poetry-venv-2"
+   "name": "poetry-venv-311"
   },
   "language_info": {
    "codemirror_mode": {

docs/docs/integrations/chat/perplexity.ipynb

@@ -17,7 +17,7 @@
    "source": [
     "# ChatPerplexity\n",
     "\n",
-    "This notebook covers how to get started with Perplexity chat models."
+    "This notebook covers how to get started with `Perplexity` chat models."
    ]
   },
   {
@@ -37,17 +37,31 @@
     "from langchain_core.prompts import ChatPromptTemplate"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b26e2035-2f81-4451-ba44-fa2e2d5aeb62",
+   "metadata": {},
+   "source": [
+    "The code provided assumes that your PPLX_API_KEY is set in your environment variables. If you would like to manually specify your API key and also choose a different model, you can use the following code:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d986aac6-1bae-4608-8514-d3ba5b35b10e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatPerplexity(\n",
+    "    temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"llama-3-sonar-small-32k-online\"\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "97a8ce3a",
    "metadata": {},
    "source": [
-    "The code provided assumes that your PPLX_API_KEY is set in your environment variables. If you would like to manually specify your API key and also choose a different model, you can use the following code:\n",
-    "\n",
-    "```python\n",
-    "chat = ChatPerplexity(temperature=0, pplx_api_key=\"YOUR_API_KEY\", model=\"llama-3-sonar-small-32k-online\")\n",
-    "```\n",
-    "\n",
     "You can check a list of available models [here](https://docs.perplexity.ai/docs/model-cards). For reproducibility, we can set the API key dynamically by taking it as an input in this notebook."
    ]
   },
@@ -221,7 +235,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/apify_dataset.ipynb

@@ -13,7 +13,7 @@
     "\n",
     "## Prerequisites\n",
     "\n",
-    "You need to have an existing dataset on the Apify platform. If you don't have one, please first check out [this notebook](/docs/integrations/tools/apify) on how to use Apify to extract content from documentation, knowledge bases, help centers, or blogs. This example shows how to load a dataset produced by the [Website Content Crawler](https://apify.com/apify/website-content-crawler)."
+    "You need to have an existing dataset on the Apify platform. This example shows how to load a dataset produced by the [Website Content Crawler](https://apify.com/apify/website-content-crawler)."
    ]
   },
   {

docs/docs/integrations/document_loaders/github.ipynb

@@ -164,7 +164,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.document_loaders import GithubFileLoader"
+    "from langchain_community.document_loaders import GithubFileLoader"
    ]
   },
   {

docs/docs/integrations/document_loaders/index.mdx

@@ -0,0 +1,45 @@
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+---
+
+# Document loaders
+
+import { CategoryTable, IndexTable } from "@theme/FeatureTables";
+
+DocumentLoaders load data into the standard LangChain Document format.
+
+Each DocumentLoader has its own specific parameters, but they can all be invoked in the same way with the .load method.
+An example use case is as follows:
+
+```python
+from langchain_community.document_loaders.csv_loader import CSVLoader
+
+loader = CSVLoader(
+    ...  # <-- Integration specific parameters here
+)
+data = loader.load()
+```
+
+## Common File Types
+
+The below document loaders allow you to load data from common data formats.
+
+<CategoryTable category="common_loaders" />
+
+## PDFs
+
+The below document loaders allow you to load documents.
+
+<CategoryTable category="pdf_loaders" />
+
+## Webpages
+
+The below document loaders allow you to load webpages.
+
+<CategoryTable category="webpage_loaders" />
+
+
+## All document loaders
+
+<IndexTable />

docs/docs/integrations/document_loaders/pypdfloader.ipynb

@@ -0,0 +1,202 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# PyPDFLoader\n",
+    "\n",
+    "This notebook provides a quick overview for getting started with `PyPDF` [document loader](https://python.langchain.com/v0.2/docs/concepts/#document-loaders). For detailed documentation of all DocumentLoader features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.pdf.PyPDFLoader.html).\n",
+    "\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "\n",
+    "| Class | Package | Local | Serializable | JS support|\n",
+    "| :--- | :--- | :---: | :---: |  :---: |\n",
+    "| [PyPDFLoader](https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.pdf.PyPDFLoader.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ❌ | ❌ | \n",
+    "### Loader features\n",
+    "| Source | Document Lazy Loading | Native Async Support\n",
+    "| :---: | :---: | :---: | \n",
+    "| PyPDFLoader | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "No credentials are required to use `PyPDFLoader`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "To use `PyPDFLoader` you need to have the `langchain-community` python package downloaded:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain_community pypdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initialization\n",
+    "\n",
+    "Now we can instantiate our model object and load documents:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.document_loaders import PyPDFLoader\n",
+    "\n",
+    "loader = PyPDFLoader(\n",
+    "    \"./example_data/layout-parser-paper.pdf\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'page': 0}, page_content='LayoutParser : A Unified Toolkit for Deep\\nLearning Based Document Image Analysis\\nZejiang Shen1( \\x00), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain\\nLee4, Jacob Carlson3, and Weining Li5\\n1Allen Institute for AI\\nshannons@allenai.org\\n2Brown University\\nruochen zhang@brown.edu\\n3Harvard University\\n{melissadell,jacob carlson }@fas.harvard.edu\\n4University of Washington\\nbcgl@cs.washington.edu\\n5University of Waterloo\\nw422li@uwaterloo.ca\\nAbstract. Recent advances in document image analysis (DIA) have been\\nprimarily driven by the application of neural networks. Ideally, research\\noutcomes could be easily deployed in production and extended for further\\ninvestigation. However, various factors like loosely organized codebases\\nand sophisticated model configurations complicate the easy reuse of im-\\nportant innovations by a wide audience. Though there have been on-going\\nefforts to improve reusability and simplify deep learning (DL) model\\ndevelopment in disciplines like natural language processing and computer\\nvision, none of them are optimized for challenges in the domain of DIA.\\nThis represents a major gap in the existing toolkit, as DIA is central to\\nacademic research across a wide range of disciplines in the social sciences\\nand humanities. This paper introduces LayoutParser , an open-source\\nlibrary for streamlining the usage of DL in DIA research and applica-\\ntions. The core LayoutParser library comes with a set of simple and\\nintuitive interfaces for applying and customizing DL models for layout de-\\ntection, character recognition, and many other document processing tasks.\\nTo promote extensibility, LayoutParser also incorporates a community\\nplatform for sharing both pre-trained models and full document digiti-\\nzation pipelines. We demonstrate that LayoutParser is helpful for both\\nlightweight and large-scale digitization pipelines in real-word use cases.\\nThe library is publicly available at https://layout-parser.github.io .\\nKeywords: Document Image Analysis ·Deep Learning ·Layout Analysis\\n·Character Recognition ·Open Source library ·Toolkit.\\n1 Introduction\\nDeep Learning(DL)-based approaches are the state-of-the-art for a wide range of\\ndocument image analysis (DIA) tasks including document image classification [ 11,arXiv:2103.15348v2  [cs.CV]  21 Jun 2021')"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs = loader.load()\n",
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'source': './example_data/layout-parser-paper.pdf', 'page': 0}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Lazy Load\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "6"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pages = []\n",
+    "for doc in loader.lazy_load():\n",
+    "    pages.append(doc)\n",
+    "    if len(pages) >= 10:\n",
+    "        # do some paged operation, e.g.\n",
+    "        # index.upsert(page)\n",
+    "\n",
+    "        pages = []\n",
+    "len(pages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "LayoutParser : A Unified Toolkit for DL-Based DIA 11\n",
+      "focuses on precision, efficiency, and robustness. \n",
+      "{'source': './example_data/layout-parser-paper.pdf', 'page': 10}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(pages[0].page_content[:100])\n",
+    "print(pages[0].metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `PyPDFLoader` features and configurations head to the API reference: https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.pdf.PyPDFLoader.html"
+   ]
+  }
+ ],
+ "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": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/document_loaders/recursive_url.ipynb

@@ -7,7 +7,18 @@
    "source": [
     "# Recursive URL\n",
     "\n",
-    "The `RecursiveUrlLoader` lets you recursively scrape all child links from a root URL and parse them into Documents."
+    "The `RecursiveUrlLoader` lets you recursively scrape all child links from a root URL and parse them into Documents.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/document_loaders/web_loaders/recursive_url_loader/)|\n",
+    "| :--- | :--- | :---: | :---: |  :---: |\n",
+    "| [RecursiveUrlLoader](https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.recursive_url_loader.RecursiveUrlLoader.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ❌ | ✅ | \n",
+    "### Loader features\n",
+    "| Source | Document Lazy Loading | Native Async Support\n",
+    "| :---: | :---: | :---: | \n",
+    "| RecursiveUrlLoader | ✅ | ❌ | \n"
    ]
   },
   {
@@ -17,6 +28,12 @@
    "source": [
     "## Setup\n",
     "\n",
+    "### Credentials\n",
+    "\n",
+    "No credentials are required to use the `RecursiveUrlLoader`.\n",
+    "\n",
+    "### Installation\n",
+    "\n",
     "The `RecursiveUrlLoader` lives in the `langchain-community` package. There's no other required packages, though you will get richer default Document metadata if you have ``beautifulsoup4` installed as well."
    ]
   },
@@ -186,6 +203,50 @@
     "That certainly looks like HTML that comes from the url https://docs.python.org/3.9/, which is what we expected. Let's now look at some variations we can make to our basic example that can be helpful in different situations. "
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b17b7202",
+   "metadata": {},
+   "source": [
+    "## Lazy loading\n",
+    "\n",
+    "If we're loading a  large number of Documents and our downstream operations can be done over subsets of all loaded Documents, we can lazily load our Documents one at a time to minimize our memory footprint:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4b13e4d1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/var/folders/4j/2rz3865x6qg07tx43146py8h0000gn/T/ipykernel_73962/2110507528.py:6: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features=\"xml\"` into the BeautifulSoup constructor.\n",
+      "  soup = BeautifulSoup(html, \"lxml\")\n"
+     ]
+    }
+   ],
+   "source": [
+    "pages = []\n",
+    "for doc in loader.lazy_load():\n",
+    "    pages.append(doc)\n",
+    "    if len(pages) >= 10:\n",
+    "        # do some paged operation, e.g.\n",
+    "        # index.upsert(page)\n",
+    "\n",
+    "        pages = []"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fb039682",
+   "metadata": {},
+   "source": [
+    "In this example we never have more than 10 Documents loaded into memory at a time."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "8f41cc89",
@@ -256,50 +317,6 @@
     "You can similarly pass in a `metadata_extractor` to customize how Document metadata is extracted from the HTTP response. See the [API reference](https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.recursive_url_loader.RecursiveUrlLoader.html) for more on this."
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "1dddbc94",
-   "metadata": {},
-   "source": [
-    "## Lazy loading\n",
-    "\n",
-    "If we're loading a  large number of Documents and our downstream operations can be done over subsets of all loaded Documents, we can lazily load our Documents one at a time to minimize our memory footprint:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "7d0114fc",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/var/folders/4j/2rz3865x6qg07tx43146py8h0000gn/T/ipykernel_73962/2110507528.py:6: XMLParsedAsHTMLWarning: It looks like you're parsing an XML document using an HTML parser. If this really is an HTML document (maybe it's XHTML?), you can ignore or filter this warning. If it's XML, you should know that using an XML parser will be more reliable. To parse this document as XML, make sure you have the lxml package installed, and pass the keyword argument `features=\"xml\"` into the BeautifulSoup constructor.\n",
-      "  soup = BeautifulSoup(html, \"lxml\")\n"
-     ]
-    }
-   ],
-   "source": [
-    "page = []\n",
-    "for doc in loader.lazy_load():\n",
-    "    page.append(doc)\n",
-    "    if len(page) >= 10:\n",
-    "        # do some paged operation, e.g.\n",
-    "        # index.upsert(page)\n",
-    "\n",
-    "        page = []"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f88a7c2f-35df-4c3a-b238-f91be2674b96",
-   "metadata": {},
-   "source": [
-    "In this example we never have more than 10 Documents loaded into memory at a time."
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "3e4d1c8f",

docs/docs/integrations/document_loaders/sitemap.ipynb

@@ -6,9 +6,35 @@
    "source": [
     "# Sitemap\n",
     "\n",
-    "Extends from the `WebBaseLoader`, `SitemapLoader` loads a sitemap from a given URL, and then scrape and load all pages in the sitemap, returning each page as a Document.\n",
+    "Extends from the `WebBaseLoader`, `SitemapLoader` loads a sitemap from a given URL, and then scrapes and loads all pages in the sitemap, returning each page as a Document.\n",
     "\n",
-    "The scraping is done concurrently.  There are reasonable limits to concurrent requests, defaulting to 2 per second.  If you aren't concerned about being a good citizen, or you control the scrapped server, or don't care about load. Note, while this will speed up the scraping process, but it may cause the server to block you.  Be careful!"
+    "The scraping is done concurrently. There are reasonable limits to concurrent requests, defaulting to 2 per second.  If you aren't concerned about being a good citizen, or you control the scrapped server, or don't care about load you can increase this limit. Note, while this will speed up the scraping process, it may cause the server to block you. Be careful!\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/document_loaders/web_loaders/sitemap/)|\n",
+    "| :--- | :--- | :---: | :---: |  :---: |\n",
+    "| [SiteMapLoader](https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.sitemap.SitemapLoader.html#langchain_community.document_loaders.sitemap.SitemapLoader) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ❌ | ✅ | \n",
+    "### Loader features\n",
+    "| Source | Document Lazy Loading | Native Async Support\n",
+    "| :---: | :---: | :---: | \n",
+    "| SiteMapLoader | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access SiteMap document loader you'll need to install the `langchain-community` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "No credentials are needed to run this."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you want to get automated best in-class tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
    ]
   },
   {
@@ -17,21 +43,55 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  nest_asyncio"
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "Install **langchain_community**."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Fix notebook asyncio bug"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# fixes a bug with asyncio and jupyter\n",
     "import nest_asyncio\n",
     "\n",
     "nest_asyncio.apply()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initialization\n",
+    "\n",
+    "Now we can instantiate our model object and load documents:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -43,13 +103,63 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
-    "sitemap_loader = SitemapLoader(web_path=\"https://api.python.langchain.com/sitemap.xml\")\n",
-    "\n",
-    "docs = sitemap_loader.load()"
+    "sitemap_loader = SitemapLoader(web_path=\"https://api.python.langchain.com/sitemap.xml\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Fetching pages: 100%|##########| 28/28 [00:04<00:00,  6.83it/s]\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': 'https://api.python.langchain.com/en/stable/', 'loc': 'https://api.python.langchain.com/en/stable/', 'lastmod': '2024-05-15T00:29:42.163001+00:00', 'changefreq': 'weekly', 'priority': '1'}, page_content='\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nLangChain Python API Reference Documentation.\\n\\n\\nYou will be automatically redirected to the new location of this page.\\n\\n')"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs = sitemap_loader.load()\n",
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'source': 'https://api.python.langchain.com/en/stable/', 'loc': 'https://api.python.langchain.com/en/stable/', 'lastmod': '2024-05-15T00:29:42.163001+00:00', 'changefreq': 'weekly', 'priority': '1'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[0].metadata)"
    ]
   },
   {
@@ -71,24 +181,37 @@
     "sitemap_loader.requests_kwargs = {\"verify\": False}"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Lazy Load\n",
+    "\n",
+    "You can also load the pages lazily in order to minimize the memory load."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "Document(page_content='\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nLangChain Python API Reference Documentation.\\n\\n\\nYou will be automatically redirected to the new location of this page.\\n\\n', metadata={'source': 'https://api.python.langchain.com/en/stable/', 'loc': 'https://api.python.langchain.com/en/stable/', 'lastmod': '2024-02-09T01:10:49.422114+00:00', 'changefreq': 'weekly', 'priority': '1'})"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Fetching pages: 100%|##########| 28/28 [00:01<00:00, 19.06it/s]\n"
+     ]
     }
    ],
    "source": [
-    "docs[0]"
+    "page = []\n",
+    "for doc in sitemap_loader.lazy_load():\n",
+    "    page.append(doc)\n",
+    "    if len(page) >= 10:\n",
+    "        # do some paged operation, e.g.\n",
+    "        # index.upsert(page)\n",
+    "\n",
+    "        page = []"
    ]
   },
   {
@@ -224,11 +347,13 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all SiteMapLoader features and configurations head to the API reference: https://api.python.langchain.com/en/latest/document_loaders/langchain_community.document_loaders.sitemap.SitemapLoader.html#langchain_community.document_loaders.sitemap.SitemapLoader"
+   ]
   }
  ],
  "metadata": {
@@ -247,7 +372,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/unstructured_file.ipynb

@@ -7,20 +7,41 @@
    "source": [
     "# Unstructured\n",
     "\n",
-    "This notebook covers how to use `Unstructured` package to load files of many types. `Unstructured` currently supports loading of text files, powerpoints, html, pdfs, images, and more.\n",
+    "This notebook covers how to use `Unstructured` [document loader](https://python.langchain.com/v0.2/docs/concepts/#document-loaders) to load files of many types. `Unstructured` currently supports loading of text files, powerpoints, html, pdfs, images, and more.\n",
     "\n",
-    "Please see [this guide](/docs/integrations/providers/unstructured/) for more instructions on setting up Unstructured locally, including setting up required system dependencies."
+    "Please see [this guide](../../integrations/providers/unstructured.mdx) for more instructions on setting up Unstructured locally, including setting up required system dependencies.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/document_loaders/file_loaders/unstructured/)|\n",
+    "| :--- | :--- | :---: | :---: |  :---: |\n",
+    "| [UnstructuredLoader](https://api.python.langchain.com/en/latest/document_loaders/langchain_unstructured.document_loaders.UnstructuredLoader.html) | [langchain_community](https://api.python.langchain.com/en/latest/unstructured_api_reference.html) | ✅ | ❌ | ✅ | \n",
+    "### Loader features\n",
+    "| Source | Document Lazy Loading | Native Async Support\n",
+    "| :---: | :---: | :---: | \n",
+    "| UnstructuredLoader | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "By default, `langchain-unstructured` installs a smaller footprint that requires offloading of the partitioning logic to the Unstructured API, which requires an API key. If you use the local installation, you do not need an API key. To get your API key, head over to [this site](https://unstructured.io) and get an API key, and then set it in the cell below:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "2886982e",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Install package, compatible with API partitioning\n",
-    "%pip install --upgrade --quiet \"langchain-unstructured\""
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"UNSTRUCTURED_API_KEY\"] = getpass.getpass(\n",
+    "    \"Enter your Unstructured API key: \"\n",
+    ")"
    ]
   },
   {
@@ -28,15 +49,32 @@
    "id": "e75e2a6d",
    "metadata": {},
    "source": [
-    "### Local Partitioning (Optional)\n",
+    "### Installation\n",
     "\n",
-    "By default, `langchain-unstructured` installs a smaller footprint that requires\n",
-    "offloading of the partitioning logic to the Unstructured API, which requires an `api_key`. For\n",
-    "partitioning using the API, refer to the Unstructured API section below.\n",
+    "#### Normal Installation\n",
     "\n",
-    "If you would like to run the partitioning logic locally, you will need to install\n",
-    "a combination of system dependencies, as outlined in the \n",
-    "[Unstructured documentation here](https://docs.unstructured.io/open-source/installation/full-installation).\n",
+    "The following packages are required to run the rest of this notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d9de83b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Install package, compatible with API partitioning\n",
+    "%pip install --upgrade --quiet langchain-unstructured unstructured-client unstructured \"unstructured[pdf]\" python-magic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "637eda35",
+   "metadata": {},
+   "source": [
+    "#### Installation for Local\n",
+    "\n",
+    "If you would like to run the partitioning logic locally, you will need to install a combination of system dependencies, as outlined in the [Unstructured documentation here](https://docs.unstructured.io/open-source/installation/full-installation).\n",
     "\n",
     "For example, on Macs you can install the required dependencies with:\n",
     "\n",
@@ -48,7 +86,7 @@
     "brew install libxml2 libxslt\n",
     "```\n",
     "\n",
-    "You can install the required `pip` dependencies with:\n",
+    "You can install the required `pip` dependencies needed for local with:\n",
     "\n",
     "```bash\n",
     "pip install \"langchain-unstructured[local]\"\n",
@@ -60,120 +98,117 @@
    "id": "a9c1c775",
    "metadata": {},
    "source": [
-    "### Quickstart\n",
+    "## Initialization\n",
     "\n",
-    "To simply load a file as a document, you can use the LangChain `DocumentLoader.load` \n",
-    "interface:"
+    "The `UnstructuredLoader` allows loading from a variety of different file types. To read all about the `unstructured` package please refer to their [documentation](https://docs.unstructured.io/open-source/introduction/overview)/. In this example, we show loading from both a text file and a PDF file."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "79d3e549",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_unstructured import UnstructuredLoader\n",
     "\n",
-    "loader = UnstructuredLoader(\"./example_data/state_of_the_union.txt\")\n",
+    "file_paths = [\n",
+    "    \"./example_data/layout-parser-paper.pdf\",\n",
+    "    \"./example_data/state_of_the_union.txt\",\n",
+    "]\n",
     "\n",
-    "docs = loader.load()"
+    "\n",
+    "loader = UnstructuredLoader(file_paths)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "b4ab0a79",
+   "id": "8b68dcab",
    "metadata": {},
    "source": [
-    "### Load list of files"
+    "## Load"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "092d9a0b",
+   "execution_count": 2,
+   "id": "8da59ef8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "INFO: NumExpr defaulting to 12 threads.\n",
+      "INFO: pikepdf C++ to Python logger bridge initialized\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-07-25T21:28:58', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'd3ce55f220dfb75891b4394a18bcb973'}, page_content='1 2 0 2')"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs = loader.load()\n",
+    "\n",
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "97f7aa1f",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "whatsapp_chat.txt :  1/22/23, 6:30 PM - User 1: Hi! Im interested in your bag. Im offering $50. Let me know if you are in\n",
-      "state_of_the_union.txt :  May God bless you all. May God protect our troops.\n"
+      "{'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-07-25T21:28:58', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'd3ce55f220dfb75891b4394a18bcb973'}\n"
      ]
     }
    ],
    "source": [
-    "file_paths = [\n",
-    "    \"./example_data/whatsapp_chat.txt\",\n",
-    "    \"./example_data/state_of_the_union.txt\",\n",
-    "]\n",
-    "\n",
-    "loader = UnstructuredLoader(file_paths)\n",
-    "\n",
-    "docs = loader.load()\n",
-    "\n",
-    "print(docs[0].metadata.get(\"filename\"), \": \", docs[0].page_content[:100])\n",
-    "print(docs[-1].metadata.get(\"filename\"), \": \", docs[-1].page_content[:100])"
+    "print(docs[0].metadata)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "8de9ef16",
+   "id": "0d7f991b",
    "metadata": {},
    "source": [
-    "## PDF Example\n",
-    "\n",
-    "Processing PDF documents works exactly the same way. Unstructured detects the file type and extracts the same types of elements."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "672733fd",
-   "metadata": {},
-   "source": [
-    "### Define a Partitioning Strategy\n",
-    "\n",
-    "Unstructured document loader allow users to pass in a `strategy` parameter that lets Unstructured\n",
-    "know how to partition pdf and other OCR'd documents. Currently supported strategies are `\"auto\"`,\n",
-    "`\"hi_res\"`, `\"ocr_only\"`, and `\"fast\"`. Learn more about the different strategies\n",
-    "[here](https://docs.unstructured.io/open-source/core-functionality/partitioning#partition-pdf). \n",
-    "\n",
-    "Not all document types have separate hi res and fast partitioning strategies. For those document types, the `strategy` kwarg is\n",
-    "ignored. In some cases, the high res strategy will fallback to fast if there is a dependency missing\n",
-    "(i.e. a model for document partitioning). You can see how to apply a strategy to an\n",
-    "`UnstructuredLoader` below."
+    "## Lazy Load"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "60685353",
+   "execution_count": 4,
+   "id": "b05604d2",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 393.9), (16.34, 560.0), (36.34, 560.0), (36.34, 393.9)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'parent_id': '89565df026a24279aaea20dc08cedbec', 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'e9fa370aef7ee5c05744eb7bb7d9981b'}, page_content='2 v 8 4 3 5 1 . 3 0 1 2 : v i X r a'),\n",
-       " Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((157.62199999999999, 114.23496279999995), (157.62199999999999, 146.5141628), (457.7358962799999, 146.5141628), (457.7358962799999, 114.23496279999995)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'Title', 'element_id': 'bde0b230a1aa488e3ce837d33015181b'}, page_content='LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis'),\n",
-       " Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((134.809, 168.64029940800003), (134.809, 192.2517444), (480.5464199080001, 192.2517444), (480.5464199080001, 168.64029940800003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': '54700f902899f0c8c90488fa8d825bce'}, page_content='Zejiang Shen1 ((cid:0)), Ruochen Zhang2, Melissa Dell3, Benjamin Charles Germain Lee4, Jacob Carlson3, and Weining Li5'),\n",
-       " Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((207.23000000000002, 202.57205439999996), (207.23000000000002, 311.8195408), (408.12676, 311.8195408), (408.12676, 202.57205439999996)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'b650f5867bad9bb4e30384282c79bcfe'}, page_content='1 Allen Institute for AI shannons@allenai.org 2 Brown University ruochen zhang@brown.edu 3 Harvard University {melissadell,jacob carlson}@fas.harvard.edu 4 University of Washington bcgl@cs.washington.edu 5 University of Waterloo w422li@uwaterloo.ca'),\n",
-       " Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((162.779, 338.45008160000003), (162.779, 566.8455408), (454.0372021523199, 566.8455408), (454.0372021523199, 338.45008160000003)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-02-27T15:49:27', 'links': [{'text': ':// layout - parser . github . io', 'url': 'https://layout-parser.github.io', 'start_index': 1477}], 'page_number': 1, 'parent_id': 'bde0b230a1aa488e3ce837d33015181b', 'filetype': 'application/pdf', 'category': 'NarrativeText', 'element_id': 'cfc957c94fe63c8fd7c7f4bcb56e75a7'}, page_content='Abstract. Recent advances in document image analysis (DIA) have been primarily driven by the application of neural networks. Ideally, research outcomes could be easily deployed in production and extended for further investigation. However, various factors like loosely organized codebases and sophisticated model configurations complicate the easy reuse of im- portant innovations by a wide audience. Though there have been on-going efforts to improve reusability and simplify deep learning (DL) model development in disciplines like natural language processing and computer vision, none of them are optimized for challenges in the domain of DIA. This represents a major gap in the existing toolkit, as DIA is central to academic research across a wide range of disciplines in the social sciences and humanities. This paper introduces LayoutParser, an open-source library for streamlining the usage of DL in DIA research and applica- tions. The core LayoutParser library comes with a set of simple and intuitive interfaces for applying and customizing DL models for layout de- tection, character recognition, and many other document processing tasks. To promote extensibility, LayoutParser also incorporates a community platform for sharing both pre-trained models and full document digiti- zation pipelines. We demonstrate that LayoutParser is helpful for both lightweight and large-scale digitization pipelines in real-word use cases. The library is publicly available at https://layout-parser.github.io.')]"
+       "Document(metadata={'source': './example_data/layout-parser-paper.pdf', 'coordinates': {'points': ((16.34, 213.36), (16.34, 253.36), (36.34, 253.36), (36.34, 213.36)), 'system': 'PixelSpace', 'layout_width': 612, 'layout_height': 792}, 'file_directory': './example_data', 'filename': 'layout-parser-paper.pdf', 'languages': ['eng'], 'last_modified': '2024-07-25T21:28:58', 'page_number': 1, 'filetype': 'application/pdf', 'category': 'UncategorizedText', 'element_id': 'd3ce55f220dfb75891b4394a18bcb973'}, page_content='1 2 0 2')"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_unstructured import UnstructuredLoader\n",
+    "pages = []\n",
+    "for doc in loader.lazy_load():\n",
+    "    pages.append(doc)\n",
     "\n",
-    "loader = UnstructuredLoader(\"./example_data/layout-parser-paper.pdf\", strategy=\"fast\")\n",
-    "\n",
-    "docs = loader.load()\n",
-    "\n",
-    "docs[5:10]"
+    "pages[0]"
    ]
   },
   {
@@ -242,23 +277,6 @@
     "if you’d like to self-host the Unstructured API or run it locally."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "6e5fde16",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Install package\n",
-    "%pip install \"langchain-unstructured\"\n",
-    "%pip install \"unstructured-client\"\n",
-    "\n",
-    "# Set API key\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"UNSTRUCTURED_API_KEY\"] = \"FAKE_API_KEY\""
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 9,
@@ -496,6 +514,16 @@
     "print(\"Number of LangChain documents:\", len(docs))\n",
     "print(\"Length of text in the document:\", len(docs[0].page_content))"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ce01aa40",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `UnstructuredLoader` features and configurations head to the API reference: https://api.python.langchain.com/en/latest/document_loaders/langchain_unstructured.document_loaders.UnstructuredLoader.html"
+   ]
   }
  ],
  "metadata": {
@@ -514,7 +542,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/url.ipynb

@@ -138,6 +138,8 @@
    "source": [
     "## Playwright URL Loader\n",
     "\n",
+    ">[Playwright](https://github.com/microsoft/playwright) is an open-source automation tool developed by `Microsoft` that allows you to programmatically control and automate web browsers. It is designed for end-to-end testing, scraping, and automating tasks across various web browsers such as `Chromium`, `Firefox`, and `WebKit`.\n",
+    "\n",
     "This covers how to load HTML documents from a list of URLs using the `PlaywrightURLLoader`.\n",
     "\n",
     "[Playwright](https://playwright.dev/) enables reliable end-to-end testing for modern web apps.\n",
@@ -224,7 +226,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/youtube_transcript.ipynb

@@ -15,45 +15,47 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "427d5745",
    "metadata": {},
-   "source": "from langchain_community.document_loaders import YoutubeLoader",
    "outputs": [],
-   "execution_count": null
+   "source": [
+    "from langchain_community.document_loaders import YoutubeLoader"
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "34a25b57",
    "metadata": {
     "scrolled": true
    },
+   "outputs": [],
    "source": [
     "%pip install --upgrade --quiet  youtube-transcript-api"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "bc8b308a",
    "metadata": {},
+   "outputs": [],
    "source": [
     "loader = YoutubeLoader.from_youtube_url(\n",
     "    \"https://www.youtube.com/watch?v=QsYGlZkevEg\", add_video_info=False\n",
     ")"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "d073dd36",
    "metadata": {},
+   "outputs": [],
    "source": [
     "loader.load()"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "attachments": {},
@@ -66,26 +68,26 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "ba28af69",
    "metadata": {},
+   "outputs": [],
    "source": [
     "%pip install --upgrade --quiet  pytube"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "9b8ea390",
    "metadata": {},
+   "outputs": [],
    "source": [
     "loader = YoutubeLoader.from_youtube_url(\n",
     "    \"https://www.youtube.com/watch?v=QsYGlZkevEg\", add_video_info=True\n",
     ")\n",
     "loader.load()"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "attachments": {},
@@ -102,8 +104,10 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "08510625",
    "metadata": {},
+   "outputs": [],
    "source": [
     "loader = YoutubeLoader.from_youtube_url(\n",
     "    \"https://www.youtube.com/watch?v=QsYGlZkevEg\",\n",
@@ -112,13 +116,12 @@
     "    translation=\"en\",\n",
     ")\n",
     "loader.load()"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "markdown",
+   "id": "69f4e399a9764d73",
+   "metadata": {},
    "source": [
     "### Get transcripts as timestamped chunks\n",
     "\n",
@@ -127,12 +130,14 @@
     "`transcript_format` param:  One of the `langchain_community.document_loaders.youtube.TranscriptFormat` values.  In this case, `TranscriptFormat.CHUNKS`.\n",
     "\n",
     "`chunk_size_seconds` param:  An integer number of video seconds to be represented by each chunk of transcript data.  Default is 120 seconds."
-   ],
-   "id": "69f4e399a9764d73"
+   ]
   },
   {
-   "metadata": {},
    "cell_type": "code",
+   "execution_count": null,
+   "id": "540bbf19182f38bc",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from langchain_community.document_loaders.youtube import TranscriptFormat\n",
     "\n",
@@ -143,10 +148,7 @@
     "    chunk_size_seconds=30,\n",
     ")\n",
     "print(\"\\n\\n\".join(map(repr, loader.load())))"
-   ],
-   "id": "540bbf19182f38bc",
-   "outputs": [],
-   "execution_count": null
+   ]
   },
   {
    "attachments": {},
@@ -172,8 +174,10 @@
   },
   {
    "cell_type": "code",
+   "execution_count": null,
    "id": "c345bc43",
    "metadata": {},
+   "outputs": [],
    "source": [
     "# Init the GoogleApiClient\n",
     "from pathlib import Path\n",
@@ -198,9 +202,7 @@
     "\n",
     "# returns a list of Documents\n",
     "youtube_loader_channel.load()"
-   ],
-   "outputs": [],
-   "execution_count": null
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/document_transformers/openvino_rerank.ipynb

@@ -331,8 +331,8 @@
     }
    ],
    "source": [
-    "from langchain.embeddings import OpenVINOEmbeddings\n",
     "from langchain_community.document_loaders import TextLoader\n",
+    "from langchain_community.embeddings import OpenVINOEmbeddings\n",
     "from langchain_community.vectorstores import FAISS\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",

docs/docs/integrations/graphs/amazon_neptune_sparql.ipynb

@@ -245,8 +245,8 @@
    "outputs": [],
    "source": [
     "import boto3\n",
-    "from langchain.chains.graph_qa.neptune_sparql import NeptuneSparqlQAChain\n",
     "from langchain_aws import ChatBedrock\n",
+    "from langchain_community.chains.graph_qa.neptune_sparql import NeptuneSparqlQAChain\n",
     "from langchain_community.graphs import NeptuneRdfGraph\n",
     "\n",
     "host = \"<your host>\"\n",

docs/docs/integrations/graphs/azure_cosmosdb_gremlin.ipynb

@@ -65,7 +65,7 @@
    "outputs": [],
    "source": [
     "import nest_asyncio\n",
-    "from langchain.chains.graph_qa.gremlin import GremlinQAChain\n",
+    "from langchain_community.chains.graph_qa.gremlin import GremlinQAChain\n",
     "from langchain_community.graphs import GremlinGraph\n",
     "from langchain_community.graphs.graph_document import GraphDocument, Node, Relationship\n",
     "from langchain_core.documents import Document\n",

docs/docs/integrations/graphs/networkx.ipynb

@@ -49,7 +49,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.indexes import GraphIndexCreator\n",
+    "from langchain_community.graphs.index_creator import GraphIndexCreator\n",
     "from langchain_openai import OpenAI"
    ]
   },
@@ -252,7 +252,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.indexes.graph import NetworkxEntityGraph"
+    "from langchain_community.graphs import NetworkxEntityGraph"
    ]
   },
   {

docs/docs/integrations/llm_caching.ipynb

@@ -334,6 +334,121 @@
     "llm.invoke(\"Tell me a joke\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b29dd776",
+   "metadata": {},
+   "source": [
+    "### Semantic Cache\n",
+    "Use [Upstash Vector](https://upstash.com/docs/vector/overall/whatisvector) to do a semantic similarity search and cache the most similar response in the database. The vectorization is automatically done by the selected embedding model while creating Upstash Vector database. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b37fb3c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install upstash-semantic-cache"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "8470eedc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.globals import set_llm_cache\n",
+    "from upstash_semantic_cache import SemanticCache"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "16b9fb03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "UPSTASH_VECTOR_REST_URL = \"<UPSTASH_VECTOR_REST_URL>\"\n",
+    "UPSTASH_VECTOR_REST_TOKEN = \"<UPSTASH_VECTOR_REST_TOKEN>\"\n",
+    "\n",
+    "cache = SemanticCache(\n",
+    "    url=UPSTASH_VECTOR_REST_URL, token=UPSTASH_VECTOR_REST_TOKEN, min_proximity=0.7\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "8d37104b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "set_llm_cache(cache)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "926a08b3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 28.4 ms, sys: 3.93 ms, total: 32.3 ms\n",
+      "Wall time: 1.89 s\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nNew York City is the most crowded city in the USA.'"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "llm.invoke(\"Which city is the most crowded city in the USA?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "0ce37d57",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3.22 ms, sys: 940 μs, total: 4.16 ms\n",
+      "Wall time: 97.7 ms\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nNew York City is the most crowded city in the USA.'"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "llm.invoke(\"Which city has the highest population in the USA?\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "278ad7ae",
@@ -2684,7 +2799,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.12.3"
   }
  },
  "nbformat": 4,

docs/docs/integrations/llms/anthropic.ipynb

@@ -23,7 +23,7 @@
     "# AnthropicLLM\n",
     "\n",
     ":::caution\n",
-    "You are currently on a page documenting the use of Anthropic legacy Claude 2 models as [text completion models](/docs/concepts/#llms). The latest and most popular Anthropic models are [chat completion models](/docs/concepts/#chat-models).\n",
+    "You are currently on a page documenting the use of Anthropic legacy Claude 2 models as [text completion models](/docs/concepts/#llms). The latest and most popular Anthropic models are [chat completion models](/docs/concepts/#chat-models), and the text completion models have been deprecated.\n",
     "\n",
     "You are probably looking for [this page instead](/docs/integrations/chat/anthropic/).\n",
     ":::\n",
@@ -115,14 +115,6 @@
     "\n",
     "chain.invoke({\"question\": \"What is LangChain?\"})"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "a52f765c",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {

docs/docs/integrations/llms/clarifai.ipynb

@@ -226,7 +226,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Intialize the parameters as dict.\n",
+    "# Initialize the parameters as dict.\n",
     "params = dict(temperature=str(0.3), max_tokens=100)"
    ]
   },

docs/docs/integrations/llms/cohere.ipynb

@@ -15,7 +15,14 @@
     "\n",
     ">[Cohere](https://cohere.ai/about) is a Canadian startup that provides natural language processing models that help companies improve human-machine interactions.\n",
     "\n",
-    "Head to the [API reference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html) for detailed documentation of all attributes and methods."
+    "Head to the [API reference](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html) for detailed documentation of all attributes and methods.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/llms/cohere/) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [Cohere](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n"
    ]
   },
   {
@@ -29,34 +36,43 @@
     "\n",
     "The integration lives in the `langchain-community` package. We also need to install the `cohere` package itself. We can install these with:\n",
     "\n",
-    "```bash\n",
-    "pip install -U langchain-community langchain-cohere\n",
-    "```\n",
+    "### Credentials\n",
     "\n",
-    "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
+    "We'll need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "3f5dc9d7-65e3-4b5b-9086-3327d016cfe0",
    "metadata": {
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " ········\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
+    "if \"COHERE_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ff211537",
+   "metadata": {},
+   "source": [
+    "### Installation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "318454f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pip install -U langchain-community langchain-cohere"
    ]
   },
   {
@@ -83,7 +99,7 @@
    "id": "0b4e02bf-5beb-48af-a2a2-52cbcd8ebed6",
    "metadata": {},
    "source": [
-    "## Usage\n",
+    "## Invocation\n",
     "\n",
     "Cohere supports all [LLM](/docs/how_to#llms) functionality:"
    ]
@@ -199,6 +215,8 @@
    "id": "39198f7d-6fc8-4662-954a-37ad38c4bec4",
    "metadata": {},
    "source": [
+    "## Chaining\n",
+    "\n",
     "You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/docs/concepts#langchain-expression-language-lcel)"
    ]
   },
@@ -237,12 +255,14 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4797d719",
+   "cell_type": "markdown",
+   "id": "ac5fcbed",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `Cohere` llm features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_community.llms.cohere.Cohere.html"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/llms/fireworks.ipynb

@@ -15,7 +15,14 @@
     "\n",
     ">[Fireworks](https://app.fireworks.ai/) accelerates product development on generative AI by creating an innovative AI experiment and production platform. \n",
     "\n",
-    "This example goes over how to use LangChain to interact with `Fireworks` models."
+    "This example goes over how to use LangChain to interact with `Fireworks` models.\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.1/docs/integrations/llms/fireworks/) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [Fireworks](https://api.python.langchain.com/en/latest/llms/langchain_fireworks.llms.Fireworks.html#langchain_fireworks.llms.Fireworks) | [langchain_fireworks](https://api.python.langchain.com/en/latest/fireworks_api_reference.html) | ❌ | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_fireworks?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_fireworks?style=flat-square&label=%20) |"
    ]
   },
   {
@@ -24,29 +31,18 @@
    "id": "fb345268",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "%pip install -qU langchain-fireworks"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "60b6dbb2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_fireworks import Fireworks"
-   ]
+   "source": []
   },
   {
    "cell_type": "markdown",
    "id": "ccff689e",
    "metadata": {},
    "source": [
-    "# Setup\n",
+    "## Setup\n",
     "\n",
-    "1. Make sure the `langchain-fireworks` package is installed in your environment.\n",
-    "2. Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
+    "### Credentials \n",
+    "\n",
+    "Sign in to [Fireworks AI](http://fireworks.ai) for the an API Key to access our models, and make sure it is set as the `FIREWORKS_API_KEY` environment variable.\n",
     "3. Set up your model using a model id. If the model is not set, the default model is fireworks-llama-v2-7b-chat. See the full, most up-to-date model list on [fireworks.ai](https://fireworks.ai)."
    ]
   },
@@ -60,10 +56,46 @@
     "import getpass\n",
     "import os\n",
     "\n",
-    "from langchain_fireworks import Fireworks\n",
-    "\n",
     "if \"FIREWORKS_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")\n",
+    "    os.environ[\"FIREWORKS_API_KEY\"] = getpass.getpass(\"Fireworks API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e42ced7e",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "You need to install the `langchain_fireworks` python package for the rest of the notebook to work."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ca824723",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-fireworks"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "acc24d0c",
+   "metadata": {},
+   "source": [
+    "## Instantiation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d285fd7f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_fireworks import Fireworks\n",
     "\n",
     "# Initialize a Fireworks model\n",
     "llm = Fireworks(\n",
@@ -74,10 +106,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "acc24d0c",
+   "id": "a4c29f7b",
    "metadata": {},
    "source": [
-    "# Calling the Model Directly\n",
+    "## Invocation\n",
     "\n",
     "You can call the model directly with string prompts to get completions."
    ]
@@ -98,11 +130,18 @@
     }
    ],
    "source": [
-    "# Single prompt\n",
     "output = llm.invoke(\"Who's the best quarterback in the NFL?\")\n",
     "print(output)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b0283343",
+   "metadata": {},
+   "source": [
+    "### Invoking with multiple prompts"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 5,
@@ -128,6 +167,14 @@
     "print(output.generations)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f18f5717",
+   "metadata": {},
+   "source": [
+    "### Invoking with additional parameters"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 7,
@@ -158,7 +205,7 @@
    "id": "137662a6",
    "metadata": {},
    "source": [
-    "# Simple Chain with Non-Chat Model"
+    "## Chaining"
    ]
   },
   {
@@ -206,6 +253,8 @@
    "id": "d0a29826",
    "metadata": {},
    "source": [
+    "## Streaming\n",
+    "\n",
     "You can stream the output, if you want."
    ]
   },
@@ -233,12 +282,14 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "fcc0eecb",
+   "cell_type": "markdown",
+   "id": "692c5e76",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `Fireworks` LLM features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_fireworks.llms.Fireworks.html#langchain_fireworks.llms.Fireworks"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/llms/index.mdx

@@ -0,0 +1,30 @@
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+keywords: [compatibility]
+---
+
+# LLMs
+
+:::caution
+You are currently on a page documenting the use of [text completion models](/docs/concepts/#llms). Many of the latest and most popular models are [chat completion models](/docs/concepts/#chat-models).
+
+Unless you are specifically using more advanced prompting techniques, you are probably looking for [this page instead](/docs/integrations/chat/).
+:::
+
+[LLMs](docs/concepts/#llms) are language models that take a string as input and return a string as output.
+
+:::info
+
+If you'd like to write your own LLM, see [this how-to](/docs/how_to/custom_llm/).
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
+import { CategoryTable, IndexTable } from "@theme/FeatureTables";
+
+<CategoryTable category="llms" />
+
+## All LLMs
+
+<IndexTable />

docs/docs/integrations/llms/konko.ipynb

@@ -74,7 +74,7 @@
     }
    ],
    "source": [
-    "from langchain.llms import Konko\n",
+    "from langchain_community.llms import Konko\n",
     "\n",
     "llm = Konko(model=\"mistralai/mistral-7b-v0.1\", temperature=0.1, max_tokens=128)\n",
     "\n",

docs/docs/integrations/llms/openai.ipynb

@@ -19,33 +19,86 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "5d71df86-8a17-4283-83d7-4e46e7c06c44",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
+   "cell_type": "markdown",
+   "id": "74312161",
+   "metadata": {},
    "source": [
-    "# get a token: https://platform.openai.com/account/api-keys\n",
+    "## Overview\n",
     "\n",
-    "from getpass import getpass\n",
+    "### Integration details\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/openai) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatOpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html) | [langchain-openai](https://api.python.langchain.com/en/latest/openai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-openai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-openai?style=flat-square&label=%20) |\n",
     "\n",
-    "OPENAI_API_KEY = getpass()"
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access OpenAI models you'll need to create an OpenAI account, get an API key, and install the `langchain-openai` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to https://platform.openai.com to sign up to OpenAI and generate an API key. Once you've done this set the OPENAI_API_KEY environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "5472a7cd-af26-48ca-ae9b-5f6ae73c74d2",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
+   "execution_count": null,
+   "id": "efcdb2b6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Enter your OpenAI API key:  ········\n"
+     ]
+    }
+   ],
    "source": [
+    "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
+    "if \"OPENAI_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"Enter your OpenAI API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f5d528fa",
+   "metadata": {},
+   "source": [
+    "If you want to get automated best in-class tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "52fa46e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0fad78d8",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain OpenAI integration lives in the `langchain-openai` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e300149",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-openai"
    ]
   },
   {
@@ -60,7 +113,11 @@
     "OPENAI_ORGANIZATION = getpass()\n",
     "\n",
     "os.environ[\"OPENAI_ORGANIZATION\"] = OPENAI_ORGANIZATION\n",
-    "```"
+    "```\n",
+    "\n",
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
    ]
   },
   {
@@ -72,74 +129,29 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_core.prompts import PromptTemplate\n",
-    "from langchain_openai import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "035dea0f",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Question: {question}\n",
+    "from langchain_openai import OpenAI\n",
     "\n",
-    "Answer: Let's think step by step.\"\"\"\n",
-    "\n",
-    "prompt = PromptTemplate.from_template(template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "3f3458d9",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
     "llm = OpenAI()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "4fc152cd",
+   "id": "464003c1",
    "metadata": {},
    "source": [
-    "If you manually want to specify your OpenAI API key and/or organization ID, you can use the following:\n",
-    "```python\n",
-    "llm = OpenAI(openai_api_key=\"YOUR_API_KEY\", openai_organization=\"YOUR_ORGANIZATION_ID\")\n",
-    "```\n",
-    "Remove the openai_organization parameter should it not apply to you."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "a641dbd9",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "llm_chain = prompt | llm"
+    "## Invocation"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "9f844993",
-   "metadata": {
-    "tags": []
-   },
+   "id": "85b49da0",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "' Justin Bieber was born on March 1, 1994. The Super Bowl is typically played in late January or early February. So, we need to look at the Super Bowl from 1994. In 1994, the Super Bowl was Super Bowl XXVIII, played on January 30, 1994. The winning team of that Super Bowl was the Dallas Cowboys.'"
+       "\"\\n\\nI'm an AI language model created by OpenAI, so I don't have feelings or emotions. But thank you for asking! How can I assist you today?\""
       ]
      },
      "execution_count": 5,
@@ -148,9 +160,37 @@
     }
    ],
    "source": [
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "llm.invoke(\"Hello how are you?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b7e0dfc",
+   "metadata": {},
+   "source": [
+    "## Chaining"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a641dbd9",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import PromptTemplate\n",
     "\n",
-    "llm_chain.invoke(question)"
+    "prompt = PromptTemplate(\"How to say {input} in {output_language}:\\n\")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
    ]
   },
   {
@@ -158,6 +198,8 @@
    "id": "58a9ddb1",
    "metadata": {},
    "source": [
+    "## Using a proxy\n",
+    "\n",
     "If you are behind an explicit proxy, you can specify the http_client to pass through"
    ]
   },
@@ -168,11 +210,24 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pip install httpx\n",
+    "%pip install httpx\n",
     "\n",
     "import httpx\n",
     "\n",
-    "openai = OpenAI(model_name=\"gpt-3.5-turbo-instruct\", http_client=httpx.Client(proxies=\"http://proxy.yourcompany.com:8080\"))"
+    "openai = OpenAI(\n",
+    "    model_name=\"gpt-3.5-turbo-instruct\",\n",
+    "    http_client=httpx.Client(proxies=\"http://proxy.yourcompany.com:8080\"),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "73e207dd",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `OpenAI` llm features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/langchain_openai.llms.base.OpenAI.html"
    ]
   }
  ],
@@ -192,7 +247,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.11.9"
   },
   "vscode": {
    "interpreter": {

docs/docs/integrations/llms/runhouse.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Runhouse\n",
     "\n",
-    "The [Runhouse](https://github.com/run-house/runhouse) allows remote compute and data across environments and users. See the [Runhouse docs](https://runhouse-docs.readthedocs-hosted.com/en/latest/).\n",
+    "[Runhouse](https://github.com/run-house/runhouse) allows remote compute and data across environments and users. See the [Runhouse docs](https://www.run.house/docs).\n",
     "\n",
     "This example goes over how to use LangChain and [Runhouse](https://github.com/run-house/runhouse) to interact with models hosted on your own GPU, or on-demand GPUs on AWS, GCP, AWS, or Lambda.\n",
     "\n",

docs/docs/integrations/memory/motorhead_memory.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.memory.motorhead_memory import MotorheadMemory"
+    "from langchain_community.memory.motorhead_memory import MotorheadMemory"
    ]
   },
   {

docs/docs/integrations/memory/zep_memory.ipynb

@@ -48,7 +48,7 @@
     "from uuid import uuid4\n",
     "\n",
     "from langchain.agents import AgentType, initialize_agent\n",
-    "from langchain.memory import ZepMemory\n",
+    "from langchain_community.memory.zep_memory import ZepMemory\n",
     "from langchain_community.retrievers import ZepRetriever\n",
     "from langchain_community.utilities import WikipediaAPIWrapper\n",
     "from langchain_core.messages import AIMessage, HumanMessage\n",

docs/docs/integrations/memory/zep_memory_cloud.ipynb

@@ -69,11 +69,12 @@
    "source": [
     "from uuid import uuid4\n",
     "\n",
-    "from langchain.agents import AgentType, Tool, initialize_agent\n",
+    "from langchain.agents import AgentType, initialize_agent\n",
     "from langchain_community.memory.zep_cloud_memory import ZepCloudMemory\n",
     "from langchain_community.retrievers import ZepCloudRetriever\n",
     "from langchain_community.utilities import WikipediaAPIWrapper\n",
     "from langchain_core.messages import AIMessage, HumanMessage\n",
+    "from langchain_core.tools import Tool\n",
     "from langchain_openai import OpenAI\n",
     "\n",
     "session_id = str(uuid4())  # This is a unique identifier for the session"

docs/docs/integrations/platforms/aws.mdx

@@ -308,7 +308,7 @@ See a [usage example](/docs/integrations/graphs/amazon_neptune_open_cypher).
 ```python
 from langchain_community.graphs import NeptuneGraph
 from langchain_community.graphs import NeptuneAnalyticsGraph
-from langchain.chains import NeptuneOpenCypherQAChain
+from langchain_community.chains.graph_qa.neptune_cypher import NeptuneOpenCypherQAChain
 ```
 
 ### Amazon Neptune with SPARQL
@@ -317,7 +317,7 @@ See a [usage example](/docs/integrations/graphs/amazon_neptune_sparql).
 
 ```python
 from langchain_community.graphs import NeptuneRdfGraph
-from langchain.chains.graph_qa.neptune_sparql import NeptuneSparqlQAChain
+from langchain_community.chains.graph_qa.neptune_sparql import NeptuneSparqlQAChain
 ```
 
 

docs/docs/integrations/platforms/google.mdx

@@ -787,7 +787,7 @@ We need to install `langchain-google-community` with required dependencies:
 pip install langchain-google-community[gmail]
 ```
 
-See a [usage example and authorization instructions](/docs/integrations/toolkits/gmail).
+See a [usage example and authorization instructions](/docs/integrations/tools/gmail).
 
 ```python
 from langchain_google_community import GmailToolkit

docs/docs/integrations/platforms/huggingface.mdx

@@ -122,5 +122,5 @@ pip install transformers huggingface_hub
 See a [usage example](/docs/integrations/tools/huggingface_tools).
 
 ```python
-from langchain.agents import load_huggingface_tool
+from langchain_community.agent_toolkits.load_tools import load_huggingface_tool
 ```

docs/docs/integrations/platforms/microsoft.mdx

@@ -237,6 +237,26 @@ See a [usage example](/docs/integrations/document_loaders/microsoft_onenote).
 from langchain_community.document_loaders.onenote import OneNoteLoader
 ```
 
+### Playwright URL Loader
+
+>[Playwright](https://github.com/microsoft/playwright) is an open-source automation tool 
+> developed by `Microsoft` that allows you to programmatically control and automate 
+> web browsers. It is designed for end-to-end testing, scraping, and automating 
+> tasks across various web browsers such as `Chromium`, `Firefox`, and `WebKit`.
+
+
+First, let's install dependencies:
+
+```bash
+pip install playwright unstructured
+```
+
+See a [usage example](/docs/integrations/document_loaders/url/#playwright-url-loader).
+
+```python
+from langchain_community.document_loaders.onenote import OneNoteLoader
+```
+
 ## AI Agent Memory System
 
 [AI agent](https://learn.microsoft.com/en-us/azure/cosmos-db/ai-agents) needs robust memory systems that support multi-modality, offer strong operational performance, and enable agent memory sharing as well as separation.
@@ -370,7 +390,7 @@ We need to install several python packages.
 pip install azure-ai-formrecognizer azure-cognitiveservices-speech azure-ai-vision-imageanalysis
 ```
 
-See a [usage example](/docs/integrations/toolkits/azure_ai_services).
+See a [usage example](/docs/integrations/tools/azure_ai_services).
 
 ```python
 from langchain_community.agent_toolkits import azure_ai_services
@@ -385,7 +405,7 @@ pip install O365
 ```
 
 
-See a [usage example](/docs/integrations/toolkits/office365).
+See a [usage example](/docs/integrations/tools/office365).
 
 ```python
 from langchain_community.agent_toolkits import O365Toolkit
@@ -399,13 +419,31 @@ We need to install `azure-identity` python package.
 pip install azure-identity
 ```
 
-See a [usage example](/docs/integrations/toolkits/powerbi).
+See a [usage example](/docs/integrations/tools/powerbi).
 
 ```python
 from langchain_community.agent_toolkits import PowerBIToolkit
 from langchain_community.utilities.powerbi import PowerBIDataset
 ```
 
+### PlayWright Browser Toolkit
+
+>[Playwright](https://github.com/microsoft/playwright) is an open-source automation tool 
+> developed by `Microsoft` that allows you to programmatically control and automate 
+> web browsers. It is designed for end-to-end testing, scraping, and automating 
+> tasks across various web browsers such as `Chromium`, `Firefox`, and `WebKit`.
+
+We need to install several python packages.
+
+```bash
+pip install playwright lxml
+```
+
+See a [usage example](/docs/integrations/tools/playwright).
+
+```python
+from langchain_community.agent_toolkits import PlayWrightBrowserToolkit
+```
 
 ## Graphs
 

docs/docs/integrations/providers/ainetwork.mdx

@@ -15,7 +15,7 @@ pip install ain-py
 You need to set the `AIN_BLOCKCHAIN_ACCOUNT_PRIVATE_KEY` environmental variable to your AIN Blockchain Account Private Key.
 ## Toolkit
 
-See a [usage example](/docs/integrations/toolkits/ainetwork).
+See a [usage example](/docs/integrations/tools/ainetwork).
 
 ```python
 from langchain_community.agent_toolkits.ainetwork.toolkit import AINetworkToolkit

docs/docs/integrations/providers/apify.mdx

@@ -27,7 +27,7 @@ You can use the `ApifyWrapper` to run Actors on the Apify platform.
 from langchain_community.utilities import ApifyWrapper
 ```
 
-For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integrations/tools/apify).
+For more information on this wrapper, see [the API reference](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.apify.ApifyWrapper.html).
 
 
 ## Document loader

docs/docs/integrations/providers/cassandra.mdx

@@ -80,6 +80,6 @@ from langchain_community.agent_toolkits.cassandra_database.toolkit import (
 )
 ```
 
-Learn more in the [example notebook](/docs/integrations/toolkits/cassandra_database).
+Learn more in the [example notebook](/docs/integrations/tools/cassandra_database).
 
 

docs/docs/integrations/providers/github.mdx

@@ -18,6 +18,5 @@ There are two document loaders available for GitHub.
 See a [usage example](/docs/integrations/document_loaders/github).
 
 ```python
-from langchain_community.document_loaders import GitHubIssuesLoader
-from langchain.document_loaders import GithubFileLoader
+from langchain_community.document_loaders import GitHubIssuesLoader, GithubFileLoader
 ```

docs/docs/integrations/providers/ieit_systems.mdx

@@ -0,0 +1,31 @@
+# IEIT Systems
+
+>[IEIT Systems](https://en.ieisystem.com/) is a Chinese information technology company 
+> established in 1999. It provides the IT infrastructure products, solutions, 
+> and services, innovative IT products and solutions across cloud computing, 
+> big data, and artificial intelligence.
+
+
+## LLMs
+
+See a [usage example](/docs/integrations/llms/yuan2).
+
+```python
+from langchain_community.llms.yuan2 import Yuan2
+```
+
+## Chat models
+
+See the [installation instructions](/docs/integrations/chat/yuan2/#setting-up-your-api-server).
+
+Yuan2.0 provided an OpenAI compatible API, and ChatYuan2 is integrated into langchain by using `OpenAI client`. 
+Therefore, ensure the `openai` package is installed.
+
+```bash
+pip install openai
+```
+See a [usage example](/docs/integrations/chat/yuan2).
+
+```python
+from langchain_community.chat_models import ChatYuan2
+```

docs/docs/integrations/providers/iflytek.mdx

@@ -0,0 +1,38 @@
+# iFlytek
+
+>[iFlytek](https://www.iflytek.com) is a Chinese information technology company 
+> established in 1999. It creates voice recognition software and 
+> voice-based internet/mobile products covering education, communication, 
+> music, intelligent toys industries.
+
+
+## Installation and Setup
+
+- Get `SparkLLM` app_id, api_key and api_secret from [iFlyTek SparkLLM API Console](https://console.xfyun.cn/services/bm3) (for more info, see [iFlyTek SparkLLM Intro](https://xinghuo.xfyun.cn/sparkapi)).
+- Install the Python package (not for the embedding models):
+
+```bash
+pip install websocket-client
+```
+
+## LLMs
+
+See a [usage example](/docs/integrations/llms/sparkllm).
+
+```python
+from langchain_community.llms import SparkLLM
+```
+
+## Chat models
+
+See a [usage example](/docs/integrations/chat/sparkllm).
+
+```python
+from langchain_community.chat_models import ChatSparkLLM
+```
+
+## Embedding models
+
+```python
+from langchain_community.embeddings import SparkLLMTextEmbeddings
+```

docs/docs/integrations/providers/kinetica.mdx

@@ -9,7 +9,7 @@ The Kinetica LLM wrapper uses the [Kinetica SqlAssist
 LLM](https://docs.kinetica.com/7.2/sql-gpt/concepts/) to transform natural language into
 SQL to simplify the process of data retrieval.
 
-See [Kinetica SqlAssist LLM Demo](/docs/integrations/chat/kinetica) for usage.
+See [Kinetica Language To SQL Chat Model](/docs/integrations/chat/kinetica) for usage.
 
 ```python
 from langchain_community.chat_models.kinetica import ChatKinetica

docs/docs/integrations/providers/konko.mdx

@@ -41,7 +41,7 @@ See a usage [example](/docs/integrations/llms/konko).
 - **Completion with mistralai/Mistral-7B-v0.1:**
 
   ```python
-  from langchain.llms import Konko
+  from langchain_community.llms import Konko
   llm = Konko(max_tokens=800, model='mistralai/Mistral-7B-v0.1')
   prompt = "Generate a Product Description for Apple Iphone 15"
   response = llm.invoke(prompt)