chore(v0.4): merge master (#31963)

See [flake8-boolean-trap
(FBT)](https://docs.astral.sh/ruff/rules/#flake8-boolean-trap-fbt)

.github/CODEOWNERS

@@ -0,0 +1,3 @@
+/.github/   @baskaryan @ccurme @eyurtsev
+/libs/core/ @eyurtsev
+/libs/packages.yml   @ccurme

.github/DISCUSSION_TEMPLATE/q-a.yml

@@ -22,7 +22,7 @@ body:
         if there's another way to solve your problem:
         
         [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        [API Reference](https://api.python.langchain.com/en/stable/),
+        [API Reference](https://python.langchain.com/api_reference/),
         [GitHub search](https://github.com/langchain-ai/langchain),
         [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
         [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -16,7 +16,7 @@ body:
         if there's another way to solve your problem:
         
         [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        [API Reference](https://api.python.langchain.com/en/stable/),
+        [API Reference](https://python.langchain.com/api_reference/),
         [GitHub search](https://github.com/langchain-ai/langchain),
         [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
         [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
@@ -29,14 +29,14 @@ body:
       options:
         - label: I added a very descriptive title to this issue.
           required: true
-        - label: I searched the LangChain documentation with the integrated search.
-          required: true
         - label: I used the GitHub search to find a similar question and didn't find it.
           required: true
         - label: I am sure that this is a bug in LangChain rather than my code.
           required: true
         - label: The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
           required: true
+        - label: I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
+          required: true
   - type: textarea
     id: reproduction
     validations:
@@ -96,25 +96,21 @@ body:
     attributes:
       label: System Info
       description: |
-        Please share your system info with us. 
+        Please share your system info with us. Do NOT skip this step and please don't trim
+        the output. Most users don't include enough information here and it makes it harder
+        for us to help you.
         
-        "pip freeze | grep langchain" 
-        platform (windows / linux / mac)
-        python version
-        
-        OR if you're on a recent version of langchain-core you can paste the output of:
+        Run the following command in your terminal and paste the output here:
         
         python -m langchain_core.sys_info
+        
+        or if you have an existing python interpreter running:
+        
+        from langchain_core import sys_info
+        sys_info.print_sys_info()
+        
+        alternatively, put the entire output of `pip freeze` here.
       placeholder: |
-        "pip freeze | grep langchain"
-        platform
-        python version
-        
-        Alternatively, if you're on a recent version of langchain-core you can paste the output of:
-        
         python -m langchain_core.sys_info
-        
-        These will only surface LangChain packages, don't forget to include any other relevant
-        packages you're using (if you're not sure what's relevant, you can paste the entire output of `pip freeze`).
     validations:
       required: true

.github/ISSUE_TEMPLATE/config.yml

@@ -1,9 +1,9 @@
 blank_issues_enabled: false
 version: 2.1
 contact_links:
-  - name: 🤔 Question or Problem
-    about: Ask a question or ask about a problem in GitHub Discussions.
-    url: https://www.github.com/langchain-ai/langchain/discussions/categories/q-a
+  - name: 🤔 Question
+    about: Ask a question in the LangChain forums
+    url: https://forum.langchain.com/c/help/langchain/14
   - name: Feature Request
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
     about: Suggest a feature or an idea

.github/ISSUE_TEMPLATE/documentation.yml

@@ -21,7 +21,7 @@ body:
       place to ask your question:
       
       [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-      [API Reference](https://api.python.langchain.com/en/stable/),
+      [API Reference](https://python.langchain.com/api_reference/),
       [GitHub search](https://github.com/langchain-ai/langchain),
       [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
       [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,8 +1,8 @@
 Thank you for contributing to LangChain!
 
 - [ ] **PR title**: "package: description"
-  - Where "package" is whichever of langchain, community, core, experimental, etc. is being modified. Use "docs: ..." for purely docs changes, "templates: ..." for template changes, "infra: ..." for CI changes.
-  - Example: "community: add foobar LLM"
+  - Where "package" is whichever of langchain, core, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes.
+  - Example: "core: add foobar LLM"
 
 
 - [ ] **PR message**: ***Delete this entire checklist*** and replace with
@@ -24,6 +24,5 @@ Additional guidelines:
 - Please do not add dependencies to pyproject.toml files (even optional ones) unless they are required for unit tests.
 - Most PRs should not touch more than one package.
 - Changes should be backwards compatible.
-- If you are adding something to community, do not re-import it in langchain.
 
-If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.
+If no one reviews your PR within a few days, please @-mention one of baskaryan, eyurtsev, ccurme, vbarda, hwchase17.

.github/actions/uv_setup/action.yml

@@ -0,0 +1,21 @@
+# TODO: https://docs.astral.sh/uv/guides/integration/github/#caching
+
+name: uv-install
+description: Set up Python and uv
+
+inputs:
+  python-version:
+    description: Python version, supporting MAJOR.MINOR only
+    required: true
+
+env:
+  UV_VERSION: "0.5.25"
+
+runs:
+  using: composite
+  steps:
+    - name: Install uv and set the python version
+      uses: astral-sh/setup-uv@v5
+      with:
+        version: ${{ env.UV_VERSION }}
+        python-version: ${{ inputs.python-version }}

.github/dependabot.yml

@@ -0,0 +1,11 @@
+# Please see the documentation for all configuration options:
+# https://docs.github.com/github/administering-a-repository/configuration-options-for-dependency-updates
+# and
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

.github/scripts/check_diff.py

@@ -1,20 +1,43 @@
 import glob
 import json
 import os
-import re
 import sys
-import tomllib
 from collections import defaultdict
 from typing import Dict, List, Set
 from pathlib import Path
+import tomllib
+
+from packaging.requirements import Requirement
+
+from get_min_versions import get_min_version_from_toml
 
 
 LANGCHAIN_DIRS = [
     "libs/core",
     "libs/text-splitters",
     "libs/langchain",
-    "libs/community",
-    "libs/experimental",
+]
+
+# when set to True, we are ignoring core dependents
+# in order to be able to get CI to pass for each individual
+# package that depends on core
+# e.g. if you touch core, we don't then add textsplitters/etc to CI
+IGNORE_CORE_DEPENDENTS = False
+
+# ignored partners are removed from dependents
+# but still run if directly edited
+IGNORED_PARTNERS = [
+    # remove huggingface from dependents because of CI instability
+    # specifically in huggingface jobs
+    # https://github.com/langchain-ai/langchain/issues/25558
+    "huggingface",
+    # prompty exhibiting issues with numpy for Python 3.13
+    # https://github.com/langchain-ai/langchain/actions/runs/12651104685/job/35251034969?pr=29065
+    "prompty",
+]
+
+PY_312_MAX_PACKAGES = [
+    "libs/partners/chroma", # https://github.com/chroma-core/chroma/issues/4382
 ]
 
 
@@ -39,15 +62,17 @@ def dependents_graph() -> dict:
 
         # load regular and test deps from pyproject.toml
         with open(path, "rb") as f:
-            pyproject = tomllib.load(f)["tool"]["poetry"]
+            pyproject = tomllib.load(f)
 
         pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
         for dep in [
-            *pyproject["dependencies"].keys(),
-            *pyproject["group"]["test"]["dependencies"].keys(),
+            *pyproject["project"]["dependencies"],
+            *pyproject["dependency-groups"]["test"],
         ]:
+            requirement = Requirement(dep)
+            package_name = requirement.name
             if "langchain" in dep:
-                dependents[dep].add(pkg_dir)
+                dependents[package_name].add(pkg_dir)
                 continue
 
         # load extended deps from extended_testing_deps.txt
@@ -69,6 +94,11 @@ def dependents_graph() -> dict:
 
                     if "langchain" in dep:
                         dependents[dep].add(pkg_dir)
+
+    for k in dependents:
+        for partner in IGNORED_PARTNERS:
+            if f"libs/partners/{partner}" in dependents[k]:
+                dependents[k].remove(f"libs/partners/{partner}")
     return dependents
 
 
@@ -86,35 +116,104 @@ def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
 
 
 def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
-    min_python = "3.8"
-    max_python = "3.12"
+    if job == "test-pydantic":
+        return _get_pydantic_test_configs(dir_)
 
+    if job == "codspeed":
+        py_versions = ["3.12"]  # 3.13 is not yet supported
+    elif dir_ == "libs/core":
+        py_versions = ["3.9", "3.10", "3.11", "3.12", "3.13"]
     # custom logic for specific directories
-    if dir_ == "libs/partners/milvus":
-        # milvus poetry doesn't allow 3.12 because they
-        # declare deps in funny way
-        max_python = "3.11"
+    elif dir_ == "libs/partners/milvus":
+        # milvus doesn't allow 3.12 because they declare deps in funny way
+        py_versions = ["3.9", "3.11"]
 
-    return [
-        {"working-directory": dir_, "python-version": min_python},
-        {"working-directory": dir_, "python-version": max_python},
+    elif dir_ in PY_312_MAX_PACKAGES:
+        py_versions = ["3.9", "3.12"]
+
+    elif dir_ == "libs/langchain" and job == "extended-tests":
+        py_versions = ["3.9", "3.13"]
+
+    elif dir_ == ".":
+        # unable to install with 3.13 because tokenizers doesn't support 3.13 yet
+        py_versions = ["3.9", "3.12"]
+    else:
+        py_versions = ["3.9", "3.13"]
+
+    return [{"working-directory": dir_, "python-version": py_v} for py_v in py_versions]
+
+
+def _get_pydantic_test_configs(
+    dir_: str, *, python_version: str = "3.11"
+) -> List[Dict[str, str]]:
+    with open("./libs/core/uv.lock", "rb") as f:
+        core_uv_lock_data = tomllib.load(f)
+    for package in core_uv_lock_data["package"]:
+        if package["name"] == "pydantic":
+            core_max_pydantic_minor = package["version"].split(".")[1]
+            break
+
+    with open(f"./{dir_}/uv.lock", "rb") as f:
+        dir_uv_lock_data = tomllib.load(f)
+
+    for package in dir_uv_lock_data["package"]:
+        if package["name"] == "pydantic":
+            dir_max_pydantic_minor = package["version"].split(".")[1]
+            break
+
+    core_min_pydantic_version = get_min_version_from_toml(
+        "./libs/core/pyproject.toml", "release", python_version, include=["pydantic"]
+    )["pydantic"]
+    core_min_pydantic_minor = (
+        core_min_pydantic_version.split(".")[1]
+        if "." in core_min_pydantic_version
+        else "0"
+    )
+    dir_min_pydantic_version = get_min_version_from_toml(
+        f"./{dir_}/pyproject.toml", "release", python_version, include=["pydantic"]
+    ).get("pydantic", "0.0.0")
+    dir_min_pydantic_minor = (
+        dir_min_pydantic_version.split(".")[1]
+        if "." in dir_min_pydantic_version
+        else "0"
+    )
+
+    max_pydantic_minor = min(
+        int(dir_max_pydantic_minor),
+        int(core_max_pydantic_minor),
+    )
+    min_pydantic_minor = max(
+        int(dir_min_pydantic_minor),
+        int(core_min_pydantic_minor),
+    )
+
+    configs = [
+        {
+            "working-directory": dir_,
+            "pydantic-version": f"2.{v}.0",
+            "python-version": python_version,
+        }
+        for v in range(min_pydantic_minor, max_pydantic_minor + 1)
     ]
+    return configs
 
 
 def _get_configs_for_multi_dirs(
-    job: str, dirs_to_run: List[str], dependents: dict
+    job: str, dirs_to_run: Dict[str, Set[str]], dependents: dict
 ) -> List[Dict[str, str]]:
     if job == "lint":
         dirs = add_dependents(
             dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
             dependents,
         )
-    elif job in ["test", "compile-integration-tests", "dependencies"]:
+    elif job in ["test", "compile-integration-tests", "dependencies", "test-pydantic"]:
         dirs = add_dependents(
             dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
         )
     elif job == "extended-tests":
         dirs = list(dirs_to_run["extended-test"])
+    elif job == "codspeed":
+        dirs = list(dirs_to_run["codspeed"])
     else:
         raise ValueError(f"Unknown job: {job}")
 
@@ -130,6 +229,7 @@ if __name__ == "__main__":
         "lint": set(),
         "test": set(),
         "extended-test": set(),
+        "codspeed": set(),
     }
     docs_edited = False
 
@@ -138,6 +238,7 @@ if __name__ == "__main__":
         dirs_to_run["lint"] = all_package_dirs()
         dirs_to_run["test"] = all_package_dirs()
         dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
+
     for file in files:
         if any(
             file.startswith(dir_)
@@ -152,11 +253,17 @@ if __name__ == "__main__":
             dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
             dirs_to_run["lint"].add(".")
 
+        if file.startswith("libs/core"):
+            dirs_to_run["codspeed"].add(f"libs/core")
         if any(file.startswith(dir_) for dir_ in LANGCHAIN_DIRS):
             # add that dir and all dirs after in LANGCHAIN_DIRS
             # for extended testing
+
             found = False
             for dir_ in LANGCHAIN_DIRS:
+                if dir_ == "libs/core" and IGNORE_CORE_DEPENDENTS:
+                    dirs_to_run["extended-test"].add(dir_)
+                    continue
                 if file.startswith(dir_):
                     found = True
                 if found:
@@ -165,16 +272,19 @@ if __name__ == "__main__":
             # TODO: update to include all packages that rely on standard-tests (all partner packages)
             # note: won't run on external repo partners
             dirs_to_run["lint"].add("libs/standard-tests")
+            dirs_to_run["test"].add("libs/standard-tests")
+            dirs_to_run["lint"].add("libs/cli")
+            dirs_to_run["test"].add("libs/cli")
             dirs_to_run["test"].add("libs/partners/mistralai")
             dirs_to_run["test"].add("libs/partners/openai")
             dirs_to_run["test"].add("libs/partners/anthropic")
-            dirs_to_run["test"].add("libs/partners/ai21")
             dirs_to_run["test"].add("libs/partners/fireworks")
             dirs_to_run["test"].add("libs/partners/groq")
 
         elif file.startswith("libs/cli"):
-            # todo: add cli makefile
-            pass
+            dirs_to_run["lint"].add("libs/cli")
+            dirs_to_run["test"].add("libs/cli")
+            
         elif file.startswith("libs/partners"):
             partner_dir = file.split("/")[2]
             if os.path.isdir(f"libs/partners/{partner_dir}") and [
@@ -183,22 +293,23 @@ if __name__ == "__main__":
                 if not filename.startswith(".")
             ] != ["README.md"]:
                 dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
+                dirs_to_run["codspeed"].add(f"libs/partners/{partner_dir}")
             # Skip if the directory was deleted or is just a tombstone readme
+        elif file == "libs/packages.yml":
+            continue
         elif file.startswith("libs/"):
             raise ValueError(
                 f"Unknown lib: {file}. check_diff.py likely needs "
                 "an update for this new library!"
             )
-        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
-            if file.startswith("docs/"):
-                docs_edited = True
+        elif file.startswith("docs/") or file in ["pyproject.toml", "uv.lock"]: # docs or root uv files
+            docs_edited = True
             dirs_to_run["lint"].add(".")
 
     dependents = dependents_graph()
 
     # we now have dirs_by_job
     # todo: clean this up
-
     map_job_to_configs = {
         job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
         for job in [
@@ -207,6 +318,8 @@ if __name__ == "__main__":
             "extended-tests",
             "compile-integration-tests",
             "dependencies",
+            "test-pydantic",
+            "codspeed",
         ]
     }
     map_job_to_configs["test-doc-imports"] = (

.github/scripts/check_prerelease_dependencies.py

@@ -10,26 +10,25 @@ if __name__ == "__main__":
         toml_data = tomllib.load(file)
 
     # see if we're releasing an rc
-    version = toml_data["tool"]["poetry"]["version"]
-    releasing_rc = "rc" in version
+    version = toml_data["project"]["version"]
+    releasing_rc = "rc" in version or "dev" in version
 
     # if not, iterate through dependencies and make sure none allow prereleases
     if not releasing_rc:
-        dependencies = toml_data["tool"]["poetry"]["dependencies"]
-        for lib in dependencies:
-            dep_version = dependencies[lib]
+        dependencies = toml_data["project"]["dependencies"]
+        for dep_version in dependencies:
             dep_version_string = (
                 dep_version["version"] if isinstance(dep_version, dict) else dep_version
             )
 
             if "rc" in dep_version_string:
                 raise ValueError(
-                    f"Dependency {lib} has a prerelease version. Please remove this."
+                    f"Dependency {dep_version} has a prerelease version. Please remove this."
                 )
 
             if isinstance(dep_version, dict) and dep_version.get(
                 "allow-prereleases", False
             ):
                 raise ValueError(
-                    f"Dependency {lib} has allow-prereleases set to true. Please remove this."
+                    f"Dependency {dep_version} has allow-prereleases set to true. Please remove this."
                 )

.github/scripts/get_min_versions.py

@@ -1,4 +1,6 @@
+from collections import defaultdict
 import sys
+from typing import Optional
 
 if sys.version_info >= (3, 11):
     import tomllib
@@ -6,72 +8,146 @@ else:
     # for python 3.10 and below, which doesnt have stdlib tomllib
     import tomli as tomllib
 
-from packaging.version import parse as parse_version
+from packaging.requirements import Requirement
+from packaging.specifiers import SpecifierSet
+from packaging.version import Version
+
+
+import requests
+from packaging.version import parse
+from typing import List
+
 import re
 
+
 MIN_VERSION_LIBS = [
     "langchain-core",
-    "langchain-community",
     "langchain",
     "langchain-text-splitters",
+    "numpy",
     "SQLAlchemy",
 ]
 
-SKIP_IF_PULL_REQUEST = ["langchain-core"]
+# some libs only get checked on release because of simultaneous changes in
+# multiple libs
+SKIP_IF_PULL_REQUEST = [
+    "langchain-core",
+    "langchain-text-splitters",
+    "langchain",
+]
 
 
-def get_min_version(version: str) -> str:
-    # base regex for x.x.x with cases for rc/post/etc
-    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
-    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
-    # case ^x.x.x
-    _match = re.match(f"^\\^({vstring})$", version)
-    if _match:
-        return _match.group(1)
+def get_pypi_versions(package_name: str) -> List[str]:
+    """
+    Fetch all available versions for a package from PyPI.
 
-    # case >=x.x.x,<y.y.y
-    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
-    if _match:
-        _min = _match.group(1)
-        _max = _match.group(2)
-        assert parse_version(_min) < parse_version(_max)
-        return _min
+    Args:
+        package_name (str): Name of the package
 
-    # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
-    if _match:
-        return _match.group(1)
+    Returns:
+        List[str]: List of all available versions
 
-    raise ValueError(f"Unrecognized version format: {version}")
+    Raises:
+        requests.exceptions.RequestException: If PyPI API request fails
+        KeyError: If package not found or response format unexpected
+    """
+    pypi_url = f"https://pypi.org/pypi/{package_name}/json"
+    response = requests.get(pypi_url)
+    response.raise_for_status()
+    return list(response.json()["releases"].keys())
 
 
-def get_min_version_from_toml(toml_path: str, versions_for: str):
+def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
+    """
+    Find the minimum published version that satisfies the given constraints.
+
+    Args:
+        package_name (str): Name of the package
+        spec_string (str): Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
+
+    Returns:
+        Optional[str]: Minimum compatible version or None if no compatible version found
+    """
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        spec_string = re.sub(rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}", spec_string)
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        spec_string = re.sub(
+            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x+1}", spec_string
+        )
+
+    spec_set = SpecifierSet(spec_string)
+    all_versions = get_pypi_versions(package_name)
+
+    valid_versions = []
+    for version_str in all_versions:
+        try:
+            version = parse(version_str)
+            if spec_set.contains(version):
+                valid_versions.append(version)
+        except ValueError:
+            continue
+
+    return str(min(valid_versions)) if valid_versions else None
+
+
+def _check_python_version_from_requirement(
+    requirement: Requirement, python_version: str
+) -> bool:
+    if not requirement.marker:
+        return True
+    else:
+        marker_str = str(requirement.marker)
+        if "python_version" or "python_full_version" in marker_str:
+            python_version_str = "".join(
+                char
+                for char in marker_str
+                if char.isdigit() or char in (".", "<", ">", "=", ",")
+            )
+            return check_python_version(python_version, python_version_str)
+        return True
+
+
+def get_min_version_from_toml(
+    toml_path: str,
+    versions_for: str,
+    python_version: str,
+    *,
+    include: Optional[list] = None,
+):
     # Parse the TOML file
     with open(toml_path, "rb") as file:
         toml_data = tomllib.load(file)
 
-    # Get the dependencies from tool.poetry.dependencies
-    dependencies = toml_data["tool"]["poetry"]["dependencies"]
+    dependencies = defaultdict(list)
+    for dep in toml_data["project"]["dependencies"]:
+        requirement = Requirement(dep)
+        dependencies[requirement.name].append(requirement)
 
     # Initialize a dictionary to store the minimum versions
     min_versions = {}
 
     # Iterate over the libs in MIN_VERSION_LIBS
-    for lib in MIN_VERSION_LIBS:
+    for lib in set(MIN_VERSION_LIBS + (include or [])):
         if versions_for == "pull_request" and lib in SKIP_IF_PULL_REQUEST:
             # some libs only get checked on release because of simultaneous
-            # changes
+            # changes in multiple libs
             continue
         # Check if the lib is present in the dependencies
         if lib in dependencies:
-            # Get the version string
-            version_string = dependencies[lib]
-
-            if isinstance(version_string, dict):
-                version_string = version_string["version"]
+            if include and lib not in include:
+                continue
+            requirements = dependencies[lib]
+            for requirement in requirements:
+                if _check_python_version_from_requirement(requirement, python_version):
+                    version_string = str(requirement.specifier)
+                    break
 
             # Use parse_version to get the minimum supported version from version_string
-            min_version = get_min_version(version_string)
+            min_version = get_minimum_version(lib, version_string)
 
             # Store the minimum version in the min_versions dictionary
             min_versions[lib] = min_version
@@ -79,13 +155,45 @@ def get_min_version_from_toml(toml_path: str, versions_for: str):
     return min_versions
 
 
+def check_python_version(version_string, constraint_string):
+    """
+    Check if the given Python version matches the given constraints.
+
+    :param version_string: A string representing the Python version (e.g. "3.8.5").
+    :param constraint_string: A string representing the package's Python version constraints (e.g. ">=3.6, <4.0").
+    :return: True if the version matches the constraints, False otherwise.
+    """
+
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}.0", constraint_string
+        )
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x+1}.0.0", constraint_string
+        )
+
+    try:
+        version = Version(version_string)
+        constraints = SpecifierSet(constraint_string)
+        return version in constraints
+    except Exception as e:
+        print(f"Error: {e}")
+        return False
+
+
 if __name__ == "__main__":
     # Get the TOML file path from the command line argument
     toml_file = sys.argv[1]
     versions_for = sys.argv[2]
+    python_version = sys.argv[3]
     assert versions_for in ["release", "pull_request"]
 
     # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file, versions_for)
+    min_versions = get_min_version_from_toml(toml_file, versions_for, python_version)
 
     print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))

.github/scripts/prep_api_docs_build.py

@@ -0,0 +1,101 @@
+#!/usr/bin/env python
+"""Script to sync libraries from various repositories into the main langchain repository."""
+
+import os
+import shutil
+import yaml
+from pathlib import Path
+from typing import Dict, Any
+
+
+def load_packages_yaml() -> Dict[str, Any]:
+    """Load and parse the packages.yml file."""
+    with open("langchain/libs/packages.yml", "r") as f:
+        return yaml.safe_load(f)
+
+
+def get_target_dir(package_name: str) -> Path:
+    """Get the target directory for a given package."""
+    package_name_short = package_name.replace("langchain-", "")
+    base_path = Path("langchain/libs")
+    if package_name_short == "experimental":
+        return base_path / "experimental"
+    if package_name_short == "community":
+        return base_path / "community"
+    return base_path / "partners" / package_name_short
+
+
+def clean_target_directories(packages: list) -> None:
+    """Remove old directories that will be replaced."""
+    for package in packages:
+
+        target_dir = get_target_dir(package["name"])
+        if target_dir.exists():
+            print(f"Removing {target_dir}")
+            shutil.rmtree(target_dir)
+
+
+def move_libraries(packages: list) -> None:
+    """Move libraries from their source locations to the target directories."""
+    for package in packages:
+
+        repo_name = package["repo"].split("/")[1]
+        source_path = package["path"]
+        target_dir = get_target_dir(package["name"])
+
+        # Handle root path case
+        if source_path == ".":
+            source_dir = repo_name
+        else:
+            source_dir = f"{repo_name}/{source_path}"
+
+        print(f"Moving {source_dir} to {target_dir}")
+
+        # Ensure target directory exists
+        os.makedirs(os.path.dirname(target_dir), exist_ok=True)
+
+        try:
+            # Move the directory
+            shutil.move(source_dir, target_dir)
+        except Exception as e:
+            print(f"Error moving {source_dir} to {target_dir}: {e}")
+
+
+def main():
+    """Main function to orchestrate the library sync process."""
+    try:
+        # Load packages configuration
+        package_yaml = load_packages_yaml()
+
+        # Clean target directories
+        clean_target_directories([
+            p
+            for p in package_yaml["packages"]
+            if (p["repo"].startswith("langchain-ai/") or p.get("include_in_api_ref"))
+            and p["repo"] != "langchain-ai/langchain"
+        ])
+
+        # Move libraries to their new locations
+        move_libraries([
+            p
+            for p in package_yaml["packages"]
+            if not p.get("disabled", False)
+            and (p["repo"].startswith("langchain-ai/") or p.get("include_in_api_ref"))
+            and p["repo"] != "langchain-ai/langchain"
+        ])
+
+        # Delete ones without a pyproject.toml
+        for partner in Path("langchain/libs/partners").iterdir():
+            if partner.is_dir() and not (partner / "pyproject.toml").exists():
+                print(f"Removing {partner} as it does not have a pyproject.toml")
+                shutil.rmtree(partner)
+
+        print("Library sync completed successfully!")
+
+    except Exception as e:
+        print(f"Error during library sync: {e}")
+        raise
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/.codespell-exclude

@@ -1,4 +1,3 @@
-libs/community/langchain_community/llms/yuan2.py
 "NotIn": "not in",
 - `/checkin`: Check-in
 docs/docs/integrations/providers/trulens.mdx

.github/workflows/_compile_integration_test.yml

@@ -12,8 +12,11 @@ on:
         type: string
         description: "Python version to use"
 
+permissions:
+  contents: read
+
 env:
-  POETRY_VERSION: "1.7.1"
+  UV_FROZEN: "true"
 
 jobs:
   build:
@@ -21,25 +24,23 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
+    timeout-minutes: 20
+    name: "uv run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python ${{ inputs.python-version }} + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ inputs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: compile-integration
 
       - name: Install integration dependencies
         shell: bash
-        run: poetry install --with=test_integration,test
+        run: uv sync --group test --group test_integration
 
       - name: Check integration tests compile
         shell: bash
-        run: poetry run pytest -m compile tests/integration_tests
+        run: uv run pytest -m compile tests/integration_tests
 
       - name: Ensure the tests did not create any additional files
         shell: bash

.github/workflows/_dependencies.yml

@@ -1,114 +0,0 @@
-name: dependencies
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-      langchain-location:
-        required: false
-        type: string
-        description: "Relative path to the langchain library folder"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-env:
-  POETRY_VERSION: "1.7.1"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    name: dependency checks ${{ inputs.python-version }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: pydantic-cross-compat
-
-      - name: Install dependencies
-        shell: bash
-        run: poetry install
-
-      - name: Check imports with base dependencies
-        shell: bash
-        run: poetry run make check_imports
-
-      - name: Install test dependencies
-        shell: bash
-        run: poetry install --with test
-
-      - name: Install langchain editable
-        working-directory: ${{ inputs.working-directory }}
-        if: ${{ inputs.langchain-location }}
-        env:
-          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
-        run: |
-          poetry run pip install -e "$LANGCHAIN_LOCATION"
-
-      - name: Install the opposite major version of pydantic
-        # If normal tests use pydantic v1, here we'll use v2, and vice versa.
-        shell: bash
-        # airbyte currently doesn't support pydantic v2
-        if: ${{ !startsWith(inputs.working-directory, 'libs/partners/airbyte') }}
-        run: |
-          # Determine the major part of pydantic version
-          REGULAR_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
-
-          if [[ "$REGULAR_VERSION" == "1" ]]; then
-            PYDANTIC_DEP=">=2.1,<3"
-            TEST_WITH_VERSION="2"
-          elif [[ "$REGULAR_VERSION" == "2" ]]; then
-            PYDANTIC_DEP="<2"
-            TEST_WITH_VERSION="1"
-          else
-            echo "Unexpected pydantic major version '$REGULAR_VERSION', cannot determine which version to use for cross-compatibility test."
-            exit 1
-          fi
-
-          # Install via `pip` instead of `poetry add` to avoid changing lockfile,
-          # which would prevent caching from working: the cache would get saved
-          # to a different key than where it gets loaded from.
-          poetry run pip install "pydantic${PYDANTIC_DEP}"
-
-          # Ensure that the correct pydantic is installed now.
-          echo "Checking pydantic version... Expecting ${TEST_WITH_VERSION}"
-
-          # Determine the major part of pydantic version
-          CURRENT_VERSION=$(poetry run python -c "import pydantic; print(pydantic.__version__)" | cut -d. -f1)
-
-          # Check that the major part of pydantic version is as expected, if not
-          # raise an error
-          if [[ "$CURRENT_VERSION" != "$TEST_WITH_VERSION" ]]; then
-            echo "Error: expected pydantic version ${CURRENT_VERSION} to have been installed, but found: ${TEST_WITH_VERSION}"
-            exit 1
-          fi
-          echo "Found pydantic version ${CURRENT_VERSION}, as expected"
-      - name: Run pydantic compatibility tests
-        # airbyte currently doesn't support pydantic v2
-        if: ${{ !startsWith(inputs.working-directory, 'libs/partners/airbyte') }}
-        shell: bash
-        run: make test
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_integration_test.yml

@@ -1,4 +1,4 @@
-name: Integration tests
+name: Integration Tests
 
 on:
   workflow_dispatch:
@@ -6,13 +6,17 @@ on:
       working-directory:
         required: true
         type: string
+        description: "From which folder this pipeline executes"
       python-version:
         required: true
         type: string
         description: "Python version to use"
 
+permissions:
+  contents: read
+
 env:
-  POETRY_VERSION: "1.7.1"
+  UV_FROZEN: "true"
 
 jobs:
   build:
@@ -24,28 +28,14 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python ${{ inputs.python-version }} + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ inputs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: core
 
       - name: Install dependencies
         shell: bash
-        run: poetry install --with test,test_integration
-
-      - name: Install deps outside pyproject
-        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
-        shell: bash
-        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
-
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+        run: uv sync --group test --group test_integration
 
       - name: Run integration tests
         shell: bash
@@ -54,10 +44,13 @@ jobs:
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
+          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
           AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
           AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
           AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
@@ -67,23 +60,22 @@ jobs:
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
           WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
-          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
           UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_lint.yml

@@ -7,48 +7,34 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      langchain-location:
-        required: false
-        type: string
-        description: "Relative path to the langchain library folder"
       python-version:
         required: true
         type: string
         description: "Python version to use"
 
+permissions:
+  contents: read
+
 env:
-  POETRY_VERSION: "1.7.1"
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 
   # This env var allows us to get inline annotations when ruff has complaints.
   RUFF_OUTPUT_FORMAT: github
 
+  UV_FROZEN: "true"
+
 jobs:
   build:
     name: "make lint #${{ inputs.python-version }}"
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python ${{ inputs.python-version }} + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ inputs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: lint-with-extras
-
-      - name: Check Poetry File
-        shell: bash
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry check
-
-      - name: Check lock file
-        shell: bash
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          poetry lock --check
 
       - name: Install dependencies
         # Also installs dev/lint/test/typing dependencies, to ensure we have
@@ -61,25 +47,7 @@ jobs:
         # It doesn't matter how you change it, any change will cause a cache-bust.
         working-directory: ${{ inputs.working-directory }}
         run: |
-          poetry install --with lint,typing
-
-      - name: Install langchain editable
-        working-directory: ${{ inputs.working-directory }}
-        if: ${{ inputs.langchain-location }}
-        env:
-          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
-        run: |
-          poetry run pip install -e "$LANGCHAIN_LOCATION"
-
-      - name: Get .mypy_cache to speed up mypy
-        uses: actions/cache@v4
-        env:
-          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
-        with:
-          path: |
-            ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
-
+          uv sync --group lint --group typing
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}
@@ -98,21 +66,12 @@ jobs:
         if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
-          poetry install --with test
+          uv sync --inexact --group test
       - name: Install unit+integration test dependencies
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
-          poetry install --with test,test_integration
-
-      - name: Get .mypy_cache_test to speed up mypy
-        uses: actions/cache@v4
-        env:
-          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
-        with:
-          path: |
-            ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          uv sync --inexact --group test --group test_integration
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_release.yml

@@ -1,4 +1,4 @@
-name: release
+name: Release
 run-name: Release ${{ inputs.working-directory }} by @${{ github.actor }}
 on:
   workflow_call:
@@ -12,6 +12,7 @@ on:
       working-directory:
         required: true
         type: string
+        description: "From which folder this pipeline executes"
         default: 'libs/langchain'
       dangerous-nonmaster-release:
         required: false
@@ -21,7 +22,8 @@ on:
 
 env:
   PYTHON_VERSION: "3.11"
-  POETRY_VERSION: "1.7.1"
+  UV_FROZEN: "true"
+  UV_NO_SYNC: "true"
 
 jobs:
   build:
@@ -36,13 +38,10 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: release
 
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
@@ -56,7 +55,7 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: poetry build
+        run: uv build
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
@@ -65,13 +64,20 @@ jobs:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
 
-      - name: Check Version
+      - name: Check version
         id: check-version
-        shell: bash
+        shell: python
         working-directory: ${{ inputs.working-directory }}
         run: |
-          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
-          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
+          import os
+          import tomllib
+          with open("pyproject.toml", "rb") as f:
+              data = tomllib.load(f)
+          pkg_name = data["project"]["name"]
+          version = data["project"]["version"]
+          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
+              f.write(f"pkg-name={pkg_name}\n")
+              f.write(f"version={version}\n")
   release-notes:
     needs:
       - build
@@ -85,9 +91,9 @@ jobs:
           path: langchain
           sparse-checkout: | # this only grabs files for relevant dir
             ${{ inputs.working-directory }}
-          ref: master # this scopes to just master branch
+          ref: ${{ github.ref }} # this scopes to just ref'd branch
           fetch-depth: 0 # this fetches entire commit history
-      - name: Check Tags
+      - name: Check tags
         id: check-tags
         shell: bash
         working-directory: langchain/${{ inputs.working-directory }}
@@ -95,9 +101,47 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-          echo $REGEX
-          PREV_TAG=$(git tag --sort=-creatordate | grep -P $REGEX || true | head -1)
+          # Handle regular versions and pre-release versions differently
+          if [[ "$VERSION" == *"-"* ]]; then
+            # This is a pre-release version (contains a hyphen)
+            # Extract the base version without the pre-release suffix
+            BASE_VERSION=${VERSION%%-*}
+            # Look for the latest release of the same base version
+            REGEX="^$PKG_NAME==$BASE_VERSION\$"
+            PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
+            
+            # If no exact base version match, look for the latest release of any kind
+            if [ -z "$PREV_TAG" ]; then
+              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
+              PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
+            fi
+          else
+            # Regular version handling
+            PREV_TAG="$PKG_NAME==${VERSION%.*}.$(( ${VERSION##*.} - 1 ))"; [[ "${VERSION##*.}" -eq 0 ]] && PREV_TAG=""
+
+            # backup case if releasing e.g. 0.3.0, looks up last release
+            # note if last release (chronologically) was e.g. 0.1.47 it will get 
+            # that instead of the last 0.2 release
+            if [ -z "$PREV_TAG" ]; then
+              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
+              echo $REGEX
+              PREV_TAG=$(git tag --sort=-creatordate | (grep -P $REGEX || true) | head -1)
+            fi
+          fi
+
+          # if PREV_TAG is empty, let it be empty
+          if [ -z "$PREV_TAG" ]; then
+            echo "No previous tag found - first release"
+          else
+            # confirm prev-tag actually exists in git repo with git tag
+            GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
+            if [ -z "$GIT_TAG_RESULT" ]; then
+              echo "Previous tag $PREV_TAG not found in git repo"
+              exit 1
+            fi
+          fi
+
+
           TAG="${PKG_NAME}==${VERSION}"
           if [ "$TAG" == "$PREV_TAG" ]; then
             echo "No new version to release"
@@ -146,6 +190,7 @@ jobs:
       - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
 
@@ -162,14 +207,18 @@ jobs:
       # - The package is published, and it breaks on the missing dependency when
       #   used in the real world.
 
-      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python + uv
+        uses: "./.github/actions/uv_setup"
+        id: setup-python
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
 
-      - name: Import published package
+      - uses: actions/download-artifact@v4
+        with:
+          name: dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Import dist package
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         env:
@@ -185,27 +234,21 @@ jobs:
         # - attempt install again after 5 seconds if it fails because there is
         #   sometimes a delay in availability on test pypi
         run: |
-          poetry run pip install \
-            --extra-index-url https://test.pypi.org/simple/ \
-            "$PKG_NAME==$VERSION" || \
-          ( \
-            sleep 15 && \
-            poetry run pip install \
-              --extra-index-url https://test.pypi.org/simple/ \
-              "$PKG_NAME==$VERSION" \
-          )
+          uv venv
+          VIRTUAL_ENV=.venv uv pip install dist/*.whl
 
           # Replace all dashes in the package name with underscores,
           # since that's how Python imports packages with dashes in the name.
-          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
+          # also remove _official suffix
+          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g | sed s/_official//g)"
 
-          poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
+          uv run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test
+        run: uv sync --group test
         working-directory: ${{ inputs.working-directory }}
 
-      # Overwrite the local version of the package with the test PyPI version.
+      # Overwrite the local version of the package with the built version
       - name: Import published package (again)
         working-directory: ${{ inputs.working-directory }}
         shell: bash
@@ -213,9 +256,7 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          poetry run pip install \
-            --extra-index-url https://test.pypi.org/simple/ \
-            "$PKG_NAME==$VERSION"
+          VIRTUAL_ENV=.venv uv pip install dist/*.whl
 
       - name: Run unit tests
         run: make tests
@@ -224,14 +265,15 @@ jobs:
       - name: Check for prerelease versions
         working-directory: ${{ inputs.working-directory }}
         run: |
-          poetry run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
+          uv run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
 
       - name: Get minimum versions
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         run: |
-          poetry run pip install packaging
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release)"
+          VIRTUAL_ENV=.venv uv pip install packaging requests
+          python_version="$(uv run python --version | awk '{print $2}')"
+          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release $python_version)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
           echo "min-versions=$min_versions"
 
@@ -240,18 +282,12 @@ jobs:
         env:
           MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
         run: |
-          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
+          VIRTUAL_ENV=.venv uv pip install --force-reinstall $MIN_VERSIONS --editable .
           make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
       - name: Import integration test dependencies
-        run: poetry install --with test,test_integration
+        run: uv sync --group test --group test_integration
         working-directory: ${{ inputs.working-directory }}
 
       - name: Run integration tests
@@ -267,38 +303,121 @@ jobs:
           AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
           AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
           WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
-          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
-          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
           UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
+          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
+  # Test select published packages against new core
+  test-prior-published-packages-against-new-core:
+    needs:
+      - build
+      - release-notes
+      - test-pypi-publish
+      - pre-release-checks
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        partner: [openai, anthropic]
+      fail-fast: false  # Continue testing other partners if one fails
+    env:
+      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+      ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
+      ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
+      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+      AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+      AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+      AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+      AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
+      AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
+      AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
+    steps:
+      - uses: actions/checkout@v4
+
+      # We implement this conditional as Github Actions does not have good support
+      # for conditionally needing steps. https://github.com/actions/runner/issues/491
+      - name: Check if libs/core
+        run: |
+          if [ "${{ startsWith(inputs.working-directory, 'libs/core') }}" != "true" ]; then
+            echo "Not in libs/core. Exiting successfully."
+            exit 0
+          fi
+
+      - name: Set up Python + uv
+        if: startsWith(inputs.working-directory, 'libs/core')
+        uses: "./.github/actions/uv_setup"
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - uses: actions/download-artifact@v4
+        if: startsWith(inputs.working-directory, 'libs/core')
+        with:
+          name: dist
+          path: ${{ inputs.working-directory }}/dist/
+
+      - name: Test against ${{ matrix.partner }}
+        if: startsWith(inputs.working-directory, 'libs/core')
+        run: |
+          # Identify latest tag
+          LATEST_PACKAGE_TAG="$(
+            git ls-remote --tags origin "langchain-${{ matrix.partner }}*" \
+            | awk '{print $2}' \
+            | sed 's|refs/tags/||' \
+            | sort -Vr \
+            | head -n 1
+          )"
+          echo "Latest package tag: $LATEST_PACKAGE_TAG"
+
+          # Shallow-fetch just that single tag
+          git fetch --depth=1 origin tag "$LATEST_PACKAGE_TAG"
+
+          # Checkout the latest package files
+          rm -rf $GITHUB_WORKSPACE/libs/partners/${{ matrix.partner }}/*
+          rm -rf $GITHUB_WORKSPACE/libs/standard-tests/*
+          cd $GITHUB_WORKSPACE/libs/
+          git checkout "$LATEST_PACKAGE_TAG" -- standard-tests/
+          git checkout "$LATEST_PACKAGE_TAG" -- partners/${{ matrix.partner }}/
+          cd partners/${{ matrix.partner }}
+
+          # Print as a sanity check
+          echo "Version number from pyproject.toml: "
+          cat pyproject.toml | grep "version = "
+
+          # Run tests
+          uv sync --group test --group test_integration
+          uv pip install ../../core/dist/*.whl
+          make integration_tests
+
   publish:
     needs:
       - build
       - release-notes
       - test-pypi-publish
       - pre-release-checks
+      - test-prior-published-packages-against-new-core
     runs-on: ubuntu-latest
     permissions:
       # This permission is used for trusted publishing:
@@ -315,13 +434,10 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: release
 
       - uses: actions/download-artifact@v4
         with:
@@ -334,6 +450,8 @@ jobs:
           packages-dir: ${{ inputs.working-directory }}/dist/
           verbose: true
           print-hash: true
+          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
+          attestations: false
 
   mark-release:
     needs:
@@ -355,13 +473,10 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: release
 
       - uses: actions/download-artifact@v4
         with:

.github/workflows/_release_docker.yml

@@ -1,62 +0,0 @@
-name: release_docker
-
-on:
-  workflow_call:
-    inputs:
-      dockerfile:
-        required: true
-        type: string
-        description: "Path to the Dockerfile to build"
-      image:
-        required: true
-        type: string
-        description: "Name of the image to build"
-
-env:
-  TEST_TAG: ${{ inputs.image }}:test
-  LATEST_TAG: ${{ inputs.image }}:latest
-
-jobs:
-  docker:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Get git tag
-        uses: actions-ecosystem/action-get-latest-tag@v1
-        id: get-latest-tag
-      - name: Set docker tag
-        env:
-          VERSION: ${{ steps.get-latest-tag.outputs.tag }}
-        run: |
-          echo "VERSION_TAG=${{ inputs.image }}:${VERSION#v}" >> $GITHUB_ENV
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-      - name: Build for Test
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          file: ${{ inputs.dockerfile }}
-          load: true
-          tags: ${{ env.TEST_TAG }}
-      - name: Test
-        run: |
-          docker run --rm ${{ env.TEST_TAG }} python -c "import langchain"
-      - name: Build and Push to Docker Hub
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          file: ${{ inputs.dockerfile }}
-          # We can only build for the intersection of platforms supported by
-          # QEMU and base python image, for now build only for
-          # linux/amd64 and linux/arm64
-          platforms: linux/amd64,linux/arm64
-          tags: ${{ env.LATEST_TAG }},${{ env.VERSION_TAG }}
-          push: true

.github/workflows/_test.yml

@@ -7,17 +7,17 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      langchain-location:
-        required: false
-        type: string
-        description: "Relative path to the langchain library folder"
       python-version:
         required: true
         type: string
         description: "Python version to use"
 
+permissions:
+  contents: read
+
 env:
-  POETRY_VERSION: "1.7.1"
+  UV_FROZEN: "true"
+  UV_NO_SYNC: "true"
 
 jobs:
   build:
@@ -25,35 +25,45 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     name: "make test #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python ${{ inputs.python-version }} + uv
+        uses: "./.github/actions/uv_setup"
+        id: setup-python
         with:
           python-version: ${{ inputs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: core
-
       - name: Install dependencies
         shell: bash
-        run: poetry install --with test
-
-      - name: Install langchain editable
-        working-directory: ${{ inputs.working-directory }}
-        if: ${{ inputs.langchain-location }}
-        env:
-          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
-        run: |
-          poetry run pip install -e "$LANGCHAIN_LOCATION"
+        run: uv sync --group test --dev
 
       - name: Run core tests
         shell: bash
         run: |
           make test
 
+      - name: Get minimum versions
+        working-directory: ${{ inputs.working-directory }}
+        id: min-version
+        shell: bash
+        run: |
+          VIRTUAL_ENV=.venv uv pip install packaging tomli requests
+          python_version="$(uv run python --version | awk '{print $2}')"
+          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
+          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
+          echo "min-versions=$min_versions"
+
+      - name: Run unit tests with minimum dependency versions
+        if: ${{ steps.min-version.outputs.min-versions != '' }}
+        env:
+          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
+        run: |
+          VIRTUAL_ENV=.venv uv pip install $MIN_VERSIONS
+          make tests
+        working-directory: ${{ inputs.working-directory }}
+
       - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
@@ -66,21 +76,3 @@ jobs:
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
           
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          poetry run pip install packaging tomli
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-# Temporarily disabled until we can get the minimum versions working
-#      - name: Run unit tests with minimum dependency versions
-#        if: ${{ steps.min-version.outputs.min-versions != '' }}
-#        env:
-#          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-#        run: |
-#          poetry run pip install --force-reinstall $MIN_VERSIONS --editable .
-#          make tests
-#        working-directory: ${{ inputs.working-directory }}

.github/workflows/_test_doc_imports.yml

@@ -8,35 +8,37 @@ on:
         type: string
         description: "Python version to use"
 
+permissions:
+  contents: read
+
 env:
-  POETRY_VERSION: "1.7.1"
+  UV_FROZEN: "true"
 
 jobs:
   build:
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     name: "check doc imports #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python ${{ inputs.python-version }} + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ inputs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          cache-key: core
 
       - name: Install dependencies
         shell: bash
-        run: poetry install --with test
+        run: uv sync --group test
 
       - name: Install langchain editable
         run: |
-          poetry run pip install -e libs/core libs/langchain libs/community libs/experimental
+          VIRTUAL_ENV=.venv uv pip install langchain-experimental langchain-community -e libs/core libs/langchain
 
       - name: Check doc imports
         shell: bash
         run: |
-          poetry run python docs/scripts/check_imports.py
+          uv run python docs/scripts/check_imports.py
 
       - name: Ensure the test did not create any additional files
         shell: bash

.github/workflows/_test_pydantic.yml

@@ -0,0 +1,66 @@
+name: test pydantic intermediate versions
+
+on:
+  workflow_call:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        description: "From which folder this pipeline executes"
+      python-version:
+        required: false
+        type: string
+        description: "Python version to use"
+        default: "3.11"
+      pydantic-version:
+        required: true
+        type: string
+        description: "Pydantic version to test."
+
+permissions:
+  contents: read
+
+env:
+  UV_FROZEN: "true"
+  UV_NO_SYNC: "true"
+
+jobs:
+  build:
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    name: "make test # pydantic: ~=${{ inputs.pydantic-version }}, python: ${{ inputs.python-version }}, "
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python ${{ inputs.python-version }} + uv
+        uses: "./.github/actions/uv_setup"
+        with:
+          python-version: ${{ inputs.python-version }}
+
+      - name: Install dependencies
+        shell: bash
+        run: uv sync --group test
+
+      - name: Overwrite pydantic version
+        shell: bash
+        run: VIRTUAL_ENV=.venv uv pip install pydantic~=${{ inputs.pydantic-version }}
+
+      - name: Run core tests
+        shell: bash
+        run: |
+          make test
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(git status)"
+          echo "$STATUS"
+
+          # grep will exit non-zero if the target message isn't found,
+          # and `set -e` above will cause the step to fail.
+          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_release.yml

@@ -14,8 +14,8 @@ on:
         description: "Release from a non-master branch (danger!)"
 
 env:
-  POETRY_VERSION: "1.7.1"
-  PYTHON_VERSION: "3.10"
+  PYTHON_VERSION: "3.11"
+  UV_FROZEN: "true"
 
 jobs:
   build:
@@ -29,13 +29,10 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ inputs.working-directory }}
-          cache-key: release
 
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
@@ -49,7 +46,7 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: poetry build
+        run: uv build
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
@@ -60,11 +57,18 @@ jobs:
 
       - name: Check Version
         id: check-version
-        shell: bash
+        shell: python
         working-directory: ${{ inputs.working-directory }}
         run: |
-          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
-          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
+          import os
+          import tomllib
+          with open("pyproject.toml", "rb") as f:
+              data = tomllib.load(f)
+          pkg_name = data["project"]["name"]
+          version = data["project"]["version"]
+          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
+              f.write(f"pkg-name={pkg_name}\n")
+              f.write(f"version={version}\n")
 
   publish:
     needs:
@@ -98,3 +102,5 @@ jobs:
           # This is *only for CI use* and is *extremely dangerous* otherwise!
           # https://github.com/pypa/gh-action-pypi-publish#tolerating-release-package-file-duplicates
           skip-existing: true
+          # Temp workaround since attestations are on by default as of gh-action-pypi-publish v1.11.0
+          attestations: false

.github/workflows/api_doc_build.yml

@@ -0,0 +1,107 @@
+name: API Docs Build
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 13 * * *'
+env:
+  PYTHON_VERSION: "3.11"
+
+jobs:
+  build:
+    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
+    runs-on: ubuntu-latest
+    permissions: write-all
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          path: langchain
+      - uses: actions/checkout@v4
+        with:
+          repository: langchain-ai/langchain-api-docs-html
+          path: langchain-api-docs-html
+          token: ${{ secrets.TOKEN_GITHUB_API_DOCS_HTML }}
+
+      - name: Get repos with yq
+        id: get-unsorted-repos
+        uses: mikefarah/yq@master
+        with:
+          cmd: |
+            yq '
+              .packages[]
+              | select(
+                  (
+                    (.repo | test("^langchain-ai/"))
+                    and
+                    (.repo != "langchain-ai/langchain")
+                  )
+                  or
+                  (.include_in_api_ref // false)
+                )
+              | .repo
+            ' langchain/libs/packages.yml
+
+      - name: Parse YAML and checkout repos
+        env:
+          REPOS_UNSORTED: ${{ steps.get-unsorted-repos.outputs.result }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Get unique repositories
+          REPOS=$(echo "$REPOS_UNSORTED" | sort -u)
+          
+          # Checkout each unique repository that is in langchain-ai org
+          for repo in $REPOS; do
+            REPO_NAME=$(echo $repo | cut -d'/' -f2)
+            echo "Checking out $repo to $REPO_NAME"
+            git clone --depth 1 https://github.com/$repo.git $REPO_NAME
+          done
+
+      - name: Setup Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@v5
+        id: setup-python
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Install initial py deps
+        working-directory: langchain
+        run: |
+          python -m pip install -U uv
+          python -m uv pip install --upgrade --no-cache-dir pip setuptools pyyaml
+
+      - name: Move libs
+        run: python langchain/.github/scripts/prep_api_docs_build.py
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Rm old html
+        run:
+          rm -rf langchain-api-docs-html/api_reference_build/html
+
+      - name: Install dependencies
+        working-directory: langchain
+        run: |
+          python -m uv pip install $(ls ./libs/partners | xargs -I {} echo "./libs/partners/{}") --overrides ./docs/vercel_overrides.txt
+          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
+          python -m uv pip install -r docs/api_reference/requirements.txt
+
+      - name: Set Git config
+        working-directory: langchain
+        run: |
+          git config --local user.email "actions@github.com"
+          git config --local user.name "Github Actions"
+
+      - name: Build docs
+        working-directory: langchain
+        run: |
+          python docs/api_reference/create_api_rst.py
+          python -m sphinx -T -E -b html -d ../langchain-api-docs-html/_build/doctrees -c docs/api_reference docs/api_reference ../langchain-api-docs-html/api_reference_build/html -j auto
+          python docs/api_reference/scripts/custom_formatter.py ../langchain-api-docs-html/api_reference_build/html
+          # Default index page is blank so we copy in the actual home page.
+          cp ../langchain-api-docs-html/api_reference_build/html/{reference,index}.html
+          rm -rf ../langchain-api-docs-html/_build/
+
+      # https://github.com/marketplace/actions/add-commit
+      - uses: EndBug/add-and-commit@v9
+        with:
+          cwd: langchain-api-docs-html
+          message: 'Update API docs build'

.github/workflows/check-broken-links.yml

@@ -5,14 +5,17 @@ on:
   schedule:
     - cron:  '0 13 * * *'
 
+permissions:
+  contents: read
+
 jobs:
   check-links:
-    if: github.repository_owner == 'langchain-ai'
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
       - name: Use Node.js 18.x
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 18.x
           cache: "yarn"

.github/workflows/check_core_versions.yml

@@ -0,0 +1,32 @@
+name: Check `core` Version Equality
+
+on:
+  pull_request:
+    paths:
+      - 'libs/core/pyproject.toml'
+      - 'libs/core/langchain_core/version.py'
+
+permissions:
+  contents: read
+
+jobs:
+  check_version_equality:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Check version equality
+        run: |
+          PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/core/pyproject.toml)
+          VERSION_PY_VERSION=$(grep -Po '(?<=^VERSION = ")[^"]*' libs/core/langchain_core/version.py)
+
+          # Compare the two versions
+          if [ "$PYPROJECT_VERSION" != "$VERSION_PY_VERSION" ]; then
+            echo "langchain-core versions in pyproject.toml and version.py do not match!"
+            echo "pyproject.toml version: $PYPROJECT_VERSION"
+            echo "version.py version: $VERSION_PY_VERSION"
+            exit 1
+          else
+            echo "Versions match: $PYPROJECT_VERSION"
+          fi

.github/workflows/check_diffs.yml

@@ -1,10 +1,10 @@
----
 name: CI
 
 on:
   push:
     branches: [master]
   pull_request:
+  merge_group:
 
 # If another push to the same PR or branch happens while this workflow is still running,
 # cancel the earlier run in favor of the next run.
@@ -16,8 +16,12 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 env:
-  POETRY_VERSION: "1.7.1"
+  UV_FROZEN: "true"
+  UV_NO_SYNC: "true"
 
 jobs:
   build:
@@ -28,9 +32,10 @@ jobs:
         with:
           python-version: '3.11'
       - id: files
-        uses: Ana06/get-changed-files@v2.2.0
+        uses: Ana06/get-changed-files@v2.3.0
       - id: set-matrix
         run: |
+          python -m pip install packaging requests
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
       lint: ${{ steps.set-matrix.outputs.lint }}
@@ -39,6 +44,7 @@ jobs:
       compile-integration-tests: ${{ steps.set-matrix.outputs.compile-integration-tests }}
       dependencies: ${{ steps.set-matrix.outputs.dependencies }}
       test-doc-imports: ${{ steps.set-matrix.outputs.test-doc-imports }}
+      test-pydantic: ${{ steps.set-matrix.outputs.test-pydantic }}
   lint:
     name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
@@ -46,6 +52,7 @@ jobs:
     strategy:
       matrix:
         job-configs: ${{ fromJson(needs.build.outputs.lint) }}
+      fail-fast: false
     uses: ./.github/workflows/_lint.yml
     with:
       working-directory: ${{ matrix.job-configs.working-directory }}
@@ -59,18 +66,34 @@ jobs:
     strategy:
       matrix:
         job-configs: ${{ fromJson(needs.build.outputs.test) }}
+      fail-fast: false
     uses: ./.github/workflows/_test.yml
     with:
       working-directory: ${{ matrix.job-configs.working-directory }}
       python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
+  test-pydantic:
+    name: cd ${{ matrix.job-configs.working-directory }}
+    needs: [ build ]
+    if: ${{ needs.build.outputs.test-pydantic != '[]' }}
+    strategy:
+      matrix:
+        job-configs: ${{ fromJson(needs.build.outputs.test-pydantic) }}
+      fail-fast: false
+    uses: ./.github/workflows/_test_pydantic.yml
+    with:
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      pydantic-version: ${{ matrix.job-configs.pydantic-version }}
+    secrets: inherit
+
   test-doc-imports:
     needs: [ build ]
     if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
     strategy:
       matrix:
         job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
+      fail-fast: false
     uses: ./.github/workflows/_test_doc_imports.yml
     secrets: inherit
     with:
@@ -83,25 +106,13 @@ jobs:
     strategy:
       matrix:
         job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
+      fail-fast: false
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
       working-directory: ${{ matrix.job-configs.working-directory }}
       python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
-  dependencies:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.dependencies != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.dependencies) }}
-    uses: ./.github/workflows/_dependencies.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
-    secrets: inherit
-
   extended-tests:
     name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
     needs: [ build ]
@@ -110,31 +121,28 @@ jobs:
       matrix:
         # note different variable for extended test dirs
         job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
+      fail-fast: false
     runs-on: ubuntu-latest
+    timeout-minutes: 20
     defaults:
       run:
         working-directory: ${{ matrix.job-configs.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
+      - name: Set up Python ${{ matrix.job-configs.python-version }} + uv
+        uses: "./.github/actions/uv_setup"
         with:
           python-version: ${{ matrix.job-configs.python-version }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.job-configs.working-directory }}
-          cache-key: extended
 
-      - name: Install dependencies
+      - name: Install dependencies and run extended tests
         shell: bash
         run: |
-          echo "Running extended tests, installing dependencies with poetry..."
-          poetry install --with test
-          poetry run pip install uv
-          poetry run uv pip install -r extended_testing_deps.txt
-
-      - name: Run extended tests
-        run: make extended_tests
+          echo "Running extended tests, installing dependencies with uv..."
+          uv venv
+          uv sync --group test
+          VIRTUAL_ENV=.venv uv pip install -r extended_testing_deps.txt
+          VIRTUAL_ENV=.venv make extended_tests
 
       - name: Ensure the tests did not create any additional files
         shell: bash
@@ -147,9 +155,10 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
+
   ci_success:
     name: "CI Success"
-    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests, test-doc-imports]
+    needs: [build, lint, test, compile-integration-tests, extended-tests, test-doc-imports, test-pydantic]
     if: |
       always()
     runs-on: ubuntu-latest

.github/workflows/check_new_docs.yml

@@ -1,5 +1,4 @@
----
-name: Integration docs lint
+name: Integration Docs Lint
 
 on:
   push:
@@ -16,6 +15,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   build:
     runs-on: ubuntu-latest
@@ -25,7 +27,7 @@ jobs:
         with:
           python-version: '3.10'
       - id: files
-        uses: Ana06/get-changed-files@v2.2.0
+        uses: Ana06/get-changed-files@v2.3.0
         with:
           filter: |
             *.ipynb

.github/workflows/codespell.yml

@@ -1,11 +1,9 @@
----
 name: CI / cd . / make spell_check
 
 on:
   push:
-    branches: [master, v0.1]
+    branches: [master, v0.1, v0.2]
   pull_request:
-    branches: [master, v0.1]
 
 permissions:
   contents: read

.github/workflows/codspeed.yml

@@ -0,0 +1,65 @@
+name: CodSpeed
+
+on:
+  push:
+    branches:
+        - master
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: foo
+  AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: foo
+  DEEPSEEK_API_KEY: foo
+  FIREWORKS_API_KEY: foo
+
+jobs:
+  codspeed:
+    name: Run benchmarks
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - working-directory: libs/core
+            mode: walltime
+          - working-directory: libs/partners/openai
+          - working-directory: libs/partners/anthropic
+          - working-directory: libs/partners/deepseek
+          - working-directory: libs/partners/fireworks
+          - working-directory: libs/partners/xai
+          - working-directory: libs/partners/mistralai
+          - working-directory: libs/partners/groq
+      fail-fast: false
+
+    steps:
+      - uses: actions/checkout@v4
+
+      # We have to use 3.12 as 3.13 is not yet supported
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          python-version: "3.12"
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+
+      - name: Install dependencies
+        run: uv sync --group test
+        working-directory: ${{ matrix.working-directory }}
+
+      - name: Run benchmarks ${{ matrix.working-directory }}
+        uses: CodSpeedHQ/action@v3
+        with:
+          token: ${{ secrets.CODSPEED_TOKEN }}
+          run: |
+            cd ${{ matrix.working-directory }}
+            if [ "${{ matrix.working-directory }}" = "libs/core" ]; then
+              uv run --no-sync pytest ./tests/benchmarks --codspeed
+            else
+              uv run --no-sync pytest ./tests/ --codspeed
+            fi
+          mode: ${{ matrix.mode || 'instrumentation' }}

.github/workflows/langchain_release_docker.yml

@@ -1,14 +0,0 @@
----
-name: docker/langchain/langchain Release
-
-on:
-  workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
-  workflow_call: # Allows triggering from another workflow
-
-jobs:
-  release:
-    uses: ./.github/workflows/_release_docker.yml
-    with:
-      dockerfile: docker/Dockerfile.base
-      image: langchain/langchain
-    secrets: inherit

.github/workflows/people.yml

@@ -6,17 +6,13 @@ on:
   push:
     branches: [jacob/people]
   workflow_dispatch:
-    inputs:
-      debug_enabled:
-        description: 'Run the build with tmate debugging enabled (https://github.com/marketplace/actions/debugging-with-tmate)'
-        required: false
-        default: 'false'
 
 jobs:
   langchain-people:
-    if: github.repository_owner == 'langchain-ai'
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
     runs-on: ubuntu-latest
-    permissions: write-all
+    permissions:
+      contents: write
     steps:
       - name: Dump GitHub context
         env:
@@ -26,12 +22,6 @@ jobs:
       # Ref: https://github.com/actions/runner/issues/2033
       - name: Fix git safe.directory in container
         run: mkdir -p /home/runner/work/_temp/_github_home && printf "[safe]\n\tdirectory = /github/workspace" > /home/runner/work/_temp/_github_home/.gitconfig
-      # Allow debugging with tmate
-      - name: Setup tmate session
-        uses: mxschmitt/action-tmate@v3
-        if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.debug_enabled == 'true' }}
-        with:
-          limit-access-to-actor: true
       - uses: ./.github/actions/people
         with:
-          token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}
+          token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}

.github/workflows/pr_lint.yml

@@ -0,0 +1,111 @@
+# -----------------------------------------------------------------------------
+# PR Title Lint Workflow
+#
+# Purpose:
+#   Enforces Conventional Commits format for pull request titles to maintain a
+#   clear, consistent, and machine-readable change history across our repository.
+#
+# Enforced Commit Message Format (Conventional Commits 1.0.0):
+#   <type>[optional scope]: <description>
+#   [optional body]
+#   [optional footer(s)]
+#
+# Allowed Types:
+#   • feat       — a new feature (MINOR bump)
+#   • fix        — a bug fix (PATCH bump)
+#   • docs       — documentation only changes
+#   • style      — formatting, missing semi-colons, etc.; no code change
+#   • refactor   — code change that neither fixes a bug nor adds a feature
+#   • perf       — code change that improves performance
+#   • test       — adding missing tests or correcting existing tests
+#   • build      — changes that affect the build system or external dependencies
+#   • ci         — continuous integration/configuration changes
+#   • chore      — other changes that don't modify src or test files
+#   • revert     — reverts a previous commit
+#   • release    — prepare a new release
+#
+# Allowed Scopes (optional):
+#   core, cli, langchain, standard-tests, docs, anthropic, chroma, deepseek,
+#   exa, fireworks, groq, huggingface, mistralai, nomic, ollama, openai,
+#   perplexity, prompty, qdrant, xai
+#
+# Rules & Tips for New Committers:
+#   1. Subject (type) must start with a lowercase letter and, if possible, be
+#      followed by a scope wrapped in parenthesis `(scope)`
+#   2. Breaking changes:
+#        – Append "!" after type/scope (e.g., feat!: drop Node 12 support)
+#        – Or include a footer "BREAKING CHANGE: <details>"
+#   3. Example PR titles:
+#        feat(core): add multi‐tenant support
+#        fix(cli): resolve flag parsing error
+#        docs: update API usage examples
+#        docs(openai): update API usage examples
+#
+# Resources:
+#   • Conventional Commits spec: https://www.conventionalcommits.org/en/v1.0.0/
+# -----------------------------------------------------------------------------
+
+name: PR Title Lint
+
+permissions:
+  pull-requests: read
+
+on:
+  pull_request:
+    types: [opened, edited, synchronize]
+
+jobs:
+  lint-pr-title:
+    name: Validate PR Title
+    runs-on: ubuntu-latest
+    steps:
+      - name: Validate PR Title
+        uses: amannn/action-semantic-pull-request@v5
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        with:
+          types: |
+            feat
+            fix
+            docs
+            style
+            refactor
+            perf
+            test
+            build
+            ci
+            chore
+            revert
+            release
+          scopes: |
+            core
+            cli
+            langchain
+            standard-tests
+            docs
+            anthropic
+            chroma
+            deepseek
+            exa
+            fireworks
+            groq
+            huggingface
+            mistralai
+            nomic
+            ollama
+            openai
+            perplexity
+            prompty
+            qdrant
+            xai
+          requireScope: false
+          disallowScopes: |
+            release
+            [A-Z]+
+          subjectPattern: ^(?![A-Z]).+$
+          subjectPatternError: |
+            The subject "{subject}" found in the pull request title "{title}"
+            didn't match the configured pattern. Please ensure that the subject
+            doesn't start with an uppercase character.
+          ignoreLabels: |
+            ignore-lint-pr-title

.github/workflows/run_notebooks.yml

@@ -0,0 +1,75 @@
+name: Run Notebooks
+
+on:
+  workflow_dispatch:
+    inputs:
+      python_version:
+        description: 'Python version'
+        required: false
+        default: '3.11'
+      working-directory:
+        description: 'Working directory or subset (e.g., docs/docs/tutorials/llm_chain.ipynb or docs/docs/how_to)'
+        required: false
+        default: 'all'
+  schedule:
+    - cron: '0 13 * * *'
+
+permissions:
+  contents: read
+
+env:
+  UV_FROZEN: "true"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
+    name: "Test docs"
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python + uv
+        uses: "./.github/actions/uv_setup"
+        with:
+          python-version: ${{ github.event.inputs.python_version || '3.11' }}
+
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
+      - name: Configure AWS Credentials
+        uses: aws-actions/configure-aws-credentials@v4
+        with:
+          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
+          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
+          aws-region: ${{ secrets.AWS_REGION }}
+
+      - name: Install dependencies
+        run: |
+          uv sync --group dev --group test
+
+      - name: Pre-download files
+        run: |
+          uv run python docs/scripts/cache_data.py
+          curl -s https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql | sqlite3 docs/docs/how_to/Chinook.db
+          cp docs/docs/how_to/Chinook.db docs/docs/tutorials/Chinook.db
+
+      - name: Prepare notebooks
+        run: |
+          uv run python docs/scripts/prepare_notebooks_for_ci.py --comment-install-cells --working-directory ${{ github.event.inputs.working-directory || 'all' }}
+
+      - name: Run notebooks
+        env:
+          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+          WORKING_DIRECTORY: ${{ github.event.inputs.working-directory || 'all' }}
+        run: |
+          ./docs/scripts/execute_notebooks.sh $WORKING_DIRECTORY

.github/workflows/scheduled_test.yml

@@ -1,35 +1,66 @@
-name: Scheduled tests
+name: Scheduled Tests
 
 on:
   workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+    inputs:
+      working-directory-force:
+        type: string
+        description: "From which folder this pipeline executes - defaults to all in matrix - example value: libs/partners/anthropic"
+      python-version-force:
+        type: string
+        description: "Python version to use - defaults to 3.9 and 3.11 in matrix - example value: 3.9"
   schedule:
     - cron:  '0 13 * * *'
 
+permissions:
+  contents: read
+
 env:
-  POETRY_VERSION: "1.7.1"
+  POETRY_VERSION: "1.8.4"
+  UV_FROZEN: "true"
+  DEFAULT_LIBS: '["libs/partners/openai", "libs/partners/anthropic", "libs/partners/fireworks", "libs/partners/groq", "libs/partners/mistralai", "libs/partners/xai", "libs/partners/google-vertexai", "libs/partners/google-genai", "libs/partners/aws"]'
+  POETRY_LIBS: ("libs/partners/google-vertexai" "libs/partners/google-genai" "libs/partners/aws")
 
 jobs:
+  compute-matrix:
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
+    runs-on: ubuntu-latest
+    name: Compute matrix
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - name: Set matrix
+        id: set-matrix
+        env:
+          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
+          WORKING_DIRECTORY_FORCE: ${{ github.event.inputs.working-directory-force || '' }}
+          PYTHON_VERSION_FORCE: ${{ github.event.inputs.python-version-force || '' }}
+        run: |
+          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
+          # python-version should default to 3.9 and 3.11, but is overridden to [PYTHON_VERSION_FORCE] if set
+          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
+          python_version='["3.9", "3.11"]'
+          working_directory="$DEFAULT_LIBS"
+          if [ -n "$PYTHON_VERSION_FORCE" ]; then
+            python_version="[\"$PYTHON_VERSION_FORCE\"]"
+          fi
+          if [ -n "$WORKING_DIRECTORY_FORCE" ]; then
+            working_directory="[\"$WORKING_DIRECTORY_FORCE\"]"
+          fi
+          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
+          echo $matrix
+          echo "matrix=$matrix" >> $GITHUB_OUTPUT
   build:
-    if: github.repository_owner == 'langchain-ai'
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
     name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     runs-on: ubuntu-latest
+    needs: [compute-matrix]
+    timeout-minutes: 20
     strategy:
       fail-fast: false
       matrix:
-        python-version:
-          - "3.8"
-          - "3.11"
-        working-directory:
-          - "libs/partners/openai"
-          - "libs/partners/anthropic"
-          - "libs/partners/ai21"
-          - "libs/partners/fireworks"
-          - "libs/partners/groq"
-          - "libs/partners/mistralai"
-          - "libs/partners/together"
-          - "libs/partners/google-vertexai"
-          - "libs/partners/google-genai"
-          - "libs/partners/aws"
+        python-version: ${{ fromJSON(needs.compute-matrix.outputs.matrix).python-version }}
+        working-directory: ${{ fromJSON(needs.compute-matrix.outputs.matrix).working-directory }}
 
     steps:
       - uses: actions/checkout@v4
@@ -53,7 +84,8 @@ jobs:
           mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
           mv langchain-aws/libs/aws langchain/libs/partners/aws
 
-      - name: Set up Python ${{ matrix.python-version }}
+      - name: Set up Python ${{ matrix.python-version }} with poetry
+        if: contains(env.POETRY_LIBS, matrix.working-directory)
         uses: "./langchain/.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
@@ -61,6 +93,12 @@ jobs:
           working-directory: langchain/${{ matrix.working-directory }}
           cache-key: scheduled
 
+      - name: Set up Python ${{ matrix.python-version }} + uv
+        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
+        uses: "./langchain/.github/actions/uv_setup"
+        with:
+          python-version: ${{ matrix.python-version }}
+
       - name: 'Authenticate to Google Cloud'
         id: 'auth'
         uses: google-github-actions/auth@v2
@@ -74,32 +112,45 @@ jobs:
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           aws-region: ${{ secrets.AWS_REGION }}
 
-      - name: Install dependencies
+      - name: Install dependencies (poetry)
+        if: contains(env.POETRY_LIBS, matrix.working-directory)
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
           cd langchain/${{ matrix.working-directory }}
           poetry install --with=test_integration,test
 
+      - name: Install dependencies (uv)
+        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
+        run: |
+          echo "Running scheduled tests, installing dependencies with uv..."
+          cd langchain/${{ matrix.working-directory }}
+          uv sync --group test --group test_integration
+
       - name: Run integration tests
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          ANTHROPIC_FILES_API_IMAGE_ID: ${{ secrets.ANTHROPIC_FILES_API_IMAGE_ID }}
+          ANTHROPIC_FILES_API_PDF_ID: ${{ secrets.ANTHROPIC_FILES_API_PDF_ID }}
           AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
           AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
           AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
+          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
+          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
           cd langchain/${{ matrix.working-directory }}
           make integration_tests
@@ -111,7 +162,7 @@ jobs:
             langchain/libs/partners/google-vertexai \
             langchain/libs/partners/aws
 
-      - name: Ensure the tests did not create any additional files
+      - name: Ensure tests did not create additional files
         working-directory: langchain
         run: |
           set -eu

.gitignore

@@ -59,6 +59,7 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
+.codspeed/
 
 # Translations
 *.mo
@@ -167,11 +168,14 @@ docs/.docusaurus/
 docs/.cache-loader/
 docs/_dist
 docs/api_reference/*api_reference.rst
+docs/api_reference/*.md
 docs/api_reference/_build
 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

.pre-commit-config.yaml

@@ -0,0 +1,111 @@
+repos:
+- repo: local
+  hooks:
+    - id: core
+      name: format core
+      language: system
+      entry: make -C libs/core format
+      files: ^libs/core/
+      pass_filenames: false
+    - id: langchain
+      name: format langchain
+      language: system
+      entry: make -C libs/langchain format
+      files: ^libs/langchain/
+      pass_filenames: false
+    - id: standard-tests
+      name: format standard-tests
+      language: system
+      entry: make -C libs/standard-tests format
+      files: ^libs/standard-tests/
+      pass_filenames: false
+    - id: text-splitters
+      name: format text-splitters
+      language: system
+      entry: make -C libs/text-splitters format
+      files: ^libs/text-splitters/
+      pass_filenames: false
+    - id: anthropic
+      name: format partners/anthropic
+      language: system
+      entry: make -C libs/partners/anthropic format
+      files: ^libs/partners/anthropic/
+      pass_filenames: false
+    - id: chroma
+      name: format partners/chroma
+      language: system
+      entry: make -C libs/partners/chroma format
+      files: ^libs/partners/chroma/
+      pass_filenames: false
+    - id: couchbase
+      name: format partners/couchbase
+      language: system
+      entry: make -C libs/partners/couchbase format
+      files: ^libs/partners/couchbase/
+      pass_filenames: false
+    - id: exa
+      name: format partners/exa
+      language: system
+      entry: make -C libs/partners/exa format
+      files: ^libs/partners/exa/
+      pass_filenames: false
+    - id: fireworks
+      name: format partners/fireworks
+      language: system
+      entry: make -C libs/partners/fireworks format
+      files: ^libs/partners/fireworks/
+      pass_filenames: false
+    - id: groq
+      name: format partners/groq
+      language: system
+      entry: make -C libs/partners/groq format
+      files: ^libs/partners/groq/
+      pass_filenames: false
+    - id: huggingface
+      name: format partners/huggingface
+      language: system
+      entry: make -C libs/partners/huggingface format
+      files: ^libs/partners/huggingface/
+      pass_filenames: false
+    - id: mistralai
+      name: format partners/mistralai
+      language: system
+      entry: make -C libs/partners/mistralai format
+      files: ^libs/partners/mistralai/
+      pass_filenames: false
+    - id: nomic
+      name: format partners/nomic
+      language: system
+      entry: make -C libs/partners/nomic format
+      files: ^libs/partners/nomic/
+      pass_filenames: false
+    - id: ollama
+      name: format partners/ollama
+      language: system
+      entry: make -C libs/partners/ollama format
+      files: ^libs/partners/ollama/
+      pass_filenames: false
+    - id: openai
+      name: format partners/openai
+      language: system
+      entry: make -C libs/partners/openai format
+      files: ^libs/partners/openai/
+      pass_filenames: false
+    - id: prompty
+      name: format partners/prompty
+      language: system
+      entry: make -C libs/partners/prompty format
+      files: ^libs/partners/prompty/
+      pass_filenames: false
+    - id: qdrant
+      name: format partners/qdrant
+      language: system
+      entry: make -C libs/partners/qdrant format
+      files: ^libs/partners/qdrant/
+      pass_filenames: false
+    - id: root
+      name: format docs, cookbook
+      language: system
+      entry: make format
+      files: ^(docs|cookbook)/
+      pass_filenames: false

.readthedocs.yaml

@@ -1,12 +1,7 @@
 # Read the Docs configuration file
 # See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
-
-# Required
 version: 2
 
-formats:
-  - pdf
-
 # Set the version of Python and other tools you might need
 build:
   os: ubuntu-22.04
@@ -15,15 +10,16 @@ build:
   commands:
     - mkdir -p $READTHEDOCS_OUTPUT
     - cp -r api_reference_build/* $READTHEDOCS_OUTPUT
+
 # Build documentation in the docs/ directory with Sphinx
 sphinx:
    configuration: docs/api_reference/conf.py
 
 # If using Sphinx, optionally build your docs in additional formats such as PDF
-# formats:
-#    - pdf
+formats:
+  - pdf
 
 # Optionally declare the Python requirements required to build your docs
 python:
    install:
-   - requirements: docs/api_reference/requirements.txt
+     - requirements: docs/api_reference/requirements.txt

MIGRATE.md

@@ -1,70 +1,11 @@
 # Migrating
 
-## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
+Please see the following guides for migrating LangChain code:
 
-In an effort to make `langchain` leaner and safer, we are moving select chains to `langchain_experimental`.
-This migration has already started, but we are remaining backwards compatible until 7/28.
-On that date, we will remove functionality from `langchain`.
-Read more about the motivation and the progress [here](https://github.com/langchain-ai/langchain/discussions/8043).
+* Migrate to [LangChain v0.3](https://python.langchain.com/docs/versions/v0_3/)
+* Migrate to [LangChain v0.2](https://python.langchain.com/docs/versions/v0_2/)
+* Migrating from [LangChain 0.0.x Chains](https://python.langchain.com/docs/versions/migrating_chains/)
+* Upgrade to [LangGraph Memory](https://python.langchain.com/docs/versions/migrating_memory/)
 
-### Migrating to `langchain_experimental`
-
-We are moving any experimental components of LangChain, or components with vulnerability issues, into `langchain_experimental`.
-This guide covers how to migrate.
-
-### Installation
-
-Previously:
-
-`pip install -U langchain`
-
-Now (only if you want to access things in experimental):
-
-`pip install -U langchain langchain_experimental`
-
-### Things in `langchain.experimental`
-
-Previously:
-
-`from langchain.experimental import ...`
-
-Now:
-
-`from langchain_experimental import ...`
-
-### PALChain
-
-Previously:
-
-`from langchain.chains import PALChain`
-
-Now:
-
-`from langchain_experimental.pal_chain import PALChain`
-
-### SQLDatabaseChain
-
-Previously:
-
-`from langchain.chains import SQLDatabaseChain`
-
-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)
-
-`from langchain.chains import create_sql_query_chain`
-
-### `load_prompt` for Python files
-
-Note: this only applies if you want to load Python files as prompts.
-If you want to load json/yaml files, no change is needed.
-
-Previously:
-
-`from langchain.prompts import load_prompt`
-
-Now:
-
-`from langchain_experimental.prompts import load_prompt`
+The [LangChain CLI](https://python.langchain.com/docs/versions/v0_3/#migrate-using-langchain-cli) can help you automatically upgrade your code to use non-deprecated imports. 
+This will be especially helpful if you're still on either version 0.0.x or 0.1.x of LangChain.

Makefile

@@ -1,5 +1,8 @@
 .PHONY: all clean help docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck spell_check spell_fix lint lint_package lint_tests format format_diff
 
+.EXPORT_ALL_VARIABLES:
+UV_FROZEN = true
+
 ## help: Show this help info.
 help: Makefile
 	@printf "\n\033[1mUsage: make <TARGETS> ...\033[0m\n\n\033[1mTargets:\033[0m\n\n"
@@ -25,38 +28,40 @@ docs_clean:
 
 ## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
-	poetry run linkchecker _dist/docs/ --ignore-url node_modules
+	uv run --no-group test linkchecker _dist/docs/ --ignore-url node_modules
 
 ## api_docs_build: Build the API Reference documentation.
 api_docs_build:
-	poetry run python docs/api_reference/create_api_rst.py
-	cd docs/api_reference && poetry run make html
+	uv run --no-group test python docs/api_reference/create_api_rst.py
+	cd docs/api_reference && uv run --no-group test make html
+	uv run --no-group test python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
 
 API_PKG ?= text-splitters
 
 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
+	uv run --no-group test python docs/api_reference/create_api_rst.py $(API_PKG)
+	cd docs/api_reference && uv run make html
+	uv run --no-group test 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 -f docs/api_reference/index.md
 	
 
 ## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
-	poetry run linkchecker docs/api_reference/_build/html/index.html
+	uv run --no-group test linkchecker docs/api_reference/_build/html/index.html
 
 ## spell_check: Run codespell on the project.
 spell_check:
-	poetry run codespell --toml pyproject.toml
+	uv run --no-group test codespell --toml pyproject.toml
 
 ## spell_fix: Run codespell on the project and fix the errors.
 spell_fix:
-	poetry run codespell --toml pyproject.toml -w
+	uv run --no-group test codespell --toml pyproject.toml -w
 
 ######################
 # LINTING AND FORMATTING
@@ -64,12 +69,18 @@ spell_fix:
 
 ## lint: Run linting on the project.
 lint lint_package lint_tests:
-	poetry run ruff check docs templates cookbook
-	poetry run ruff format docs templates cookbook --diff
-	poetry run ruff check --select I docs templates cookbook
-	git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+	uv run --group lint ruff check docs cookbook
+	uv run --group lint ruff format docs cookbook cookbook --diff
+	git --no-pager grep 'from langchain import' docs cookbook | grep -vE 'from langchain import (hub)' && echo "Error: no importing langchain from root in docs, except for hub" && exit 1 || exit 0
+	
+	git --no-pager grep 'api.python.langchain.com' -- docs/docs ':!docs/docs/additional_resources/arxiv_references.mdx' ':!docs/docs/integrations/document_loaders/sitemap.ipynb' || exit 0 && \
+	echo "Error: you should link python.langchain.com/api_reference, not api.python.langchain.com in the docs" && \
+	exit 1
 
 ## format: Format the project files.
 format format_diff:
-	poetry run ruff format docs templates cookbook
-	poetry run ruff check --select I --fix docs templates cookbook
+	uv run --group lint ruff format docs cookbook
+	uv run --group lint ruff check --fix docs cookbook
+
+update-package-downloads:
+	uv run python docs/scripts/packages_yml_get_downloads.py

README.md

@@ -1,136 +1,83 @@
-# 🦜️🔗 LangChain
+<picture>
+  <source media="(prefers-color-scheme: light)" srcset="docs/static/img/logo-dark.svg">
+  <source media="(prefers-color-scheme: dark)" srcset="docs/static/img/logo-light.svg">
+  <img alt="LangChain Logo" src="docs/static/img/logo-dark.svg" width="80%">
+</picture>
 
-⚡ Build context-aware reasoning applications ⚡
+<div>
+<br>
+</div>
 
 [![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/releases)
 [![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
 [![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-core?style=flat-square)](https://pypistats.org/packages/langchain-core)
 [![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
-[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain?style=flat-square)](https://libraries.io/github/langchain-ai/langchain)
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/issues)
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
-[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)
+[<img src="https://github.com/codespaces/badge.svg" title="Open in Github Codespace" width="150" height="20">](https://codespaces.new/langchain-ai/langchain)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+[![CodSpeed Badge](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/langchain-ai/langchain)
 
-Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
+> [!NOTE]
+> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
-[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
-Fill out [this form](https://www.langchain.com/contact-sales) to speak with our sales team.
+LangChain is a framework for building LLM-powered applications. It helps you chain
+together interoperable components and third-party integrations to simplify AI
+application development —  all while future-proofing decisions as the underlying
+technology evolves.
 
-## Quick Install
-
-With pip:
 ```bash
-pip install langchain
+pip install -U langchain
 ```
 
-With conda:
-```bash
-conda install langchain -c conda-forge
-```
+To learn more about LangChain, check out
+[the docs](https://python.langchain.com/docs/introduction/). If you’re looking for more
+advanced customization or agent orchestration, check out
+[LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building
+controllable agent workflows.
 
-## 🤔 What is LangChain?
+## Why use LangChain?
 
-**LangChain** is a framework for developing applications powered by large language models (LLMs).
+LangChain helps developers build applications powered by LLMs through a standard
+interface for models, embeddings, vector stores, and more. 
 
-For these applications, LangChain simplifies the entire application lifecycle:
+Use LangChain for:
+- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and
+external / internal systems, drawing from LangChain’s vast library of integrations with
+model providers, tools, vector stores, retrievers, and more.
+- **Model interoperability**. Swap models in and out as your engineering team
+experiments to find the best choice for your application’s needs. As the industry
+frontier evolves, adapt quickly — LangChain’s abstractions keep you moving without
+losing momentum.
 
-- **Open-source libraries**:  Build your applications using LangChain's open-source [building blocks](https://python.langchain.com/v0.2/docs/concepts#langchain-expression-language-lcel), [components](https://python.langchain.com/v0.2/docs/concepts), and [third-party integrations](https://python.langchain.com/v0.2/docs/integrations/platforms/).
-Use [LangGraph](/docs/concepts/#langgraph) to build stateful agents with first-class streaming and human-in-the-loop support.
-- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://docs.smith.langchain.com/) so that you can constantly optimize and deploy with confidence.
-- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
+## LangChain’s ecosystem
+While the LangChain framework can be used standalone, it also integrates seamlessly
+with any LangChain product, giving developers a full suite of tools when building LLM
+applications. 
 
-### Open-source libraries
-- **`langchain-core`**: Base abstractions and LangChain Expression Language.
-- **`langchain-community`**: Third party integrations.
-  - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
-- **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
-- **[`LangGraph`](https://langchain-ai.github.io/langgraph/)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph. Integrates smoothly with LangChain, but can be used without it.
+To improve your LLM application development, pair LangChain with:
 
-### Productionization:
-- **[LangSmith](https://docs.smith.langchain.com/)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
+- [LangSmith](http://www.langchain.com/langsmith) - Helpful for agent evals and
+observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain
+visibility in production, and improve performance over time.
+- [LangGraph](https://langchain-ai.github.io/langgraph/) - Build agents that can
+reliably handle complex tasks with LangGraph, our low-level agent orchestration
+framework. LangGraph offers customizable architecture, long-term memory, and
+human-in-the-loop workflows — and is trusted in production by companies like LinkedIn,
+Uber, Klarna, and GitLab.
+- [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/langgraph_platform/) - Deploy
+and scale agents effortlessly with a purpose-built deployment platform for long
+running, stateful workflows. Discover, reuse, configure, and share agents across
+teams — and iterate quickly with visual prototyping in
+[LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
 
-### Deployment:
-- **[LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/)**: Turn your LangGraph applications into production-ready APIs and Assistants.
-
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_062024.svg "LangChain Architecture Overview")
-
-## 🧱 What can you build with LangChain?
-
-**❓ Question answering with RAG**
-
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/rag/)
-- End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
-
-**🧱 Extracting structured output**
-
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/extraction/)
-- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
-
-**🤖 Chatbots**
-
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/chatbot/)
-- End-to-end Example: [Web LangChain (web researcher chatbot)](https://weblangchain.vercel.app) and [repo](https://github.com/langchain-ai/weblangchain)
-
-And much more! Head to the [Tutorials](https://python.langchain.com/v0.2/docs/tutorials/) section of the docs for more.
-
-## 🚀 How does LangChain help?
-The main value props of the LangChain libraries are:
-1. **Components**: composable building blocks, tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
-2. **Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
-
-Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones. 
-
-## LangChain Expression Language (LCEL)
-
-LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
-
-- **[Overview](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
-- **[Interface](https://python.langchain.com/v0.2/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
-- **[Primitives](https://python.langchain.com/v0.2/docs/how_to/#langchain-expression-language-lcel)**: More on the primitives LCEL includes
-- **[Cheatsheet](https://python.langchain.com/v0.2/docs/how_to/lcel_cheatsheet/)**: Quick overview of the most common usage patterns
-
-## Components
-
-Components fall into the following **modules**:
-
-**📃 Model I/O**
-
-This includes [prompt management](https://python.langchain.com/v0.2/docs/concepts/#prompt-templates), [prompt optimization](https://python.langchain.com/v0.2/docs/concepts/#example-selectors), a generic interface for [chat models](https://python.langchain.com/v0.2/docs/concepts/#chat-models) and [LLMs](https://python.langchain.com/v0.2/docs/concepts/#llms), and common utilities for working with [model outputs](https://python.langchain.com/v0.2/docs/concepts/#output-parsers).
-
-**📚 Retrieval**
-
-Retrieval Augmented Generation involves [loading data](https://python.langchain.com/v0.2/docs/concepts/#document-loaders) from a variety of sources, [preparing it](https://python.langchain.com/v0.2/docs/concepts/#text-splitters), then [searching over (a.k.a. retrieving from)](https://python.langchain.com/v0.2/docs/concepts/#retrievers) it for use in the generation step.
-
-**🤖 Agents**
-
-Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents), along with [LangGraph](https://github.com/langchain-ai/langgraph) for building custom agents.
-
-## 📖 Documentation
-
-Please see [here](https://python.langchain.com) for full documentation, which includes:
-
-- [Introduction](https://python.langchain.com/v0.2/docs/introduction/): Overview of the framework and the structure of the docs.
-- [Tutorials](https://python.langchain.com/docs/use_cases/): If you're looking to build something specific or are more of a hands-on learner, check out our tutorials. This is the best place to get started.
-- [How-to guides](https://python.langchain.com/v0.2/docs/how_to/): Answers to “How do I….?” type questions. These guides are goal-oriented and concrete; they're meant to help you complete a specific task.
-- [Conceptual guide](https://python.langchain.com/v0.2/docs/concepts/): Conceptual explanations of the key parts of the framework.
-- [API Reference](https://api.python.langchain.com): Thorough documentation of every class and method.
-
-## 🌐 Ecosystem
-
-- [🦜🛠️ LangSmith](https://docs.smith.langchain.com/): Trace and evaluate your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Create stateful, multi-actor applications with LLMs. Integrates smoothly with LangChain, but can be used without it.
-- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploy LangChain runnables and chains as REST APIs.
-
-
-## 💁 Contributing
-
-As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.
-
-For detailed information on how to contribute, see [here](https://python.langchain.com/v0.2/docs/contributing/).
-
-## 🌟 Contributors
-
-[![langchain contributors](https://contrib.rocks/image?repo=langchain-ai/langchain&max=2000)](https://github.com/langchain-ai/langchain/graphs/contributors)
+## Additional resources
+- [Tutorials](https://python.langchain.com/docs/tutorials/): Simple walkthroughs with
+guided examples on getting started with LangChain.
+- [How-to Guides](https://python.langchain.com/docs/how_to/): Quick, actionable code
+snippets for topics such as tool calling, RAG use cases, and more.
+- [Conceptual Guides](https://python.langchain.com/docs/concepts/): Explanations of key
+concepts behind the LangChain framework.
+- [API Reference](https://python.langchain.com/api_reference/): Detailed reference on
+navigating base packages and integrations for LangChain.

SECURITY.md

@@ -1,5 +1,30 @@
 # Security Policy
 
+LangChain has a large ecosystem of integrations with various external resources like local and remote file systems, APIs and databases. These integrations allow developers to create versatile applications that combine the power of LLMs with the ability to access, interact with and manipulate external resources.
+
+## Best practices
+
+When building such applications developers should remember to follow good security practices:
+
+* [**Limit Permissions**](https://en.wikipedia.org/wiki/Principle_of_least_privilege): Scope permissions specifically to the application's need. Granting broad or excessive permissions can introduce significant security vulnerabilities. To avoid such vulnerabilities, consider using read-only credentials, disallowing access to sensitive resources, using sandboxing techniques (such as running inside a container), specifying proxy configurations to control external requests, etc. as appropriate for your application.
+* **Anticipate Potential Misuse**: Just as humans can err, so can Large Language Models (LLMs). Always assume that any system access or credentials may be used in any way allowed by the permissions they are assigned. For example, if a pair of database credentials allows deleting data, it's safest to assume that any LLM able to use those credentials may in fact delete data.
+* [**Defense in Depth**](https://en.wikipedia.org/wiki/Defense_in_depth_(computing)): No security technique is perfect. Fine-tuning and good chain design can reduce, but not eliminate, the odds that a Large Language Model (LLM) may make a mistake. It's best to combine multiple layered security approaches rather than relying on any single layer of defense to ensure security. For example: use both read-only permissions and sandboxing to ensure that LLMs are only able to access data that is explicitly meant for them to use.
+
+Risks of not doing so include, but are not limited to:
+* Data corruption or loss.
+* Unauthorized access to confidential information.
+* Compromised performance or availability of critical resources.
+
+Example scenarios with mitigation strategies:
+
+* A user may ask an agent with access to the file system to delete files that should not be deleted or read the content of files that contain sensitive information. To mitigate, limit the agent to only use a specific directory and only allow it to read or write files that are safe to read or write. Consider further sandboxing the agent by running it in a container.
+* A user may ask an agent with write access to an external API to write malicious data to the API, or delete data from that API. To mitigate, give the agent read-only API keys, or limit it to only use endpoints that are already resistant to such misuse.
+* A user may ask an agent with access to a database to drop a table or mutate the schema. To mitigate, scope the credentials to only the tables that the agent needs to access and consider issuing READ-ONLY credentials.
+
+If you're building applications that access external resources like file systems, APIs
+or databases, consider speaking with your company's security team to determine how to best
+design and secure your applications.
+
 ## Reporting OSS Vulnerabilities
 
 LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide 
@@ -14,7 +39,7 @@ Before reporting a vulnerability, please review:
 
 1) In-Scope Targets and Out-of-Scope Targets below.
 2) The [langchain-ai/langchain](https://python.langchain.com/docs/contributing/repo_structure) monorepo structure.
-3) LangChain [security guidelines](https://python.langchain.com/docs/security) to
+3) The [Best practices](#best-practices) above to
    understand what we consider to be a security vulnerability vs. developer
    responsibility.
 
@@ -33,13 +58,13 @@ The following packages and repositories are eligible for bug bounties:
 All out of scope targets defined by huntr as well as:
 
 - **langchain-experimental**: This repository is for experimental code and is not
-  eligible for bug bounties, bug reports to it will be marked as interesting or waste of
+  eligible for bug bounties (see [package warning](https://pypi.org/project/langchain-experimental/)), bug reports to it will be marked as interesting or waste of
   time and published with no bounty attached.
 - **tools**: Tools in either langchain or langchain-community are not eligible for bug
   bounties. This includes the following directories
-  - langchain/tools
-  - langchain-community/tools
-  - Please review our [security guidelines](https://python.langchain.com/docs/security)
+  - libs/langchain/langchain/tools
+  - libs/community/langchain_community/tools
+  - Please review the [best practices](#best-practices)
     for more details, but generally tools interact with the real world. Developers are
     expected to understand the security implications of their code and are responsible
     for the security of their tools.
@@ -47,7 +72,7 @@ All out of scope targets defined by huntr as well as:
   case basis, but likely will not be eligible for a bounty as the code is already
   documented with guidelines for developers that should be followed for making their
   application secure.
-- Any LangSmith related repositories or APIs see below.
+- Any LangSmith related repositories or APIs (see [Reporting LangSmith Vulnerabilities](#reporting-langsmith-vulnerabilities)).
 
 ## Reporting LangSmith Vulnerabilities
 

cookbook/Gemma_LangChain.ipynb

@@ -60,7 +60,7 @@
     "id": "CI8Elyc5gBQF"
    },
    "source": [
-    "Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint it ready, you need to copy its number."
+    "Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint is ready, you need to copy its number."
    ]
   },
   {

cookbook/LLaMA2_sql_chat.ipynb

@@ -47,7 +47,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "6a75a5c6-34ee-4ab9-a664-d9b432d812ee",
    "metadata": {},
    "outputs": [
@@ -61,7 +61,7 @@
    ],
    "source": [
     "# Local\n",
-    "from langchain_community.chat_models import ChatOllama\n",
+    "from langchain_ollama import ChatOllama\n",
     "\n",
     "llama2_chat = ChatOllama(model=\"llama2:13b-chat\")\n",
     "llama2_code = ChatOllama(model=\"codellama:7b-instruct\")\n",

cookbook/Multi_modal_RAG_google.ipynb

@@ -185,7 +185,7 @@
     "    )\n",
     "    # Text summary chain\n",
     "    model = VertexAI(\n",
-    "        temperature=0, model_name=\"gemini-pro\", max_tokens=1024\n",
+    "        temperature=0, model_name=\"gemini-2.0-flash-lite-001\", max_tokens=1024\n",
     "    ).with_fallbacks([empty_response])\n",
     "    summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
     "\n",
@@ -254,7 +254,7 @@
     "\n",
     "def image_summarize(img_base64, prompt):\n",
     "    \"\"\"Make image summary\"\"\"\n",
-    "    model = ChatVertexAI(model=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(model=\"gemini-2.0-flash\", max_tokens=1024)\n",
     "\n",
     "    msg = model.invoke(\n",
     "        [\n",
@@ -394,7 +394,7 @@
     "# The vectorstore to use to index the summaries\n",
     "vectorstore = Chroma(\n",
     "    collection_name=\"mm_rag_cj_blog\",\n",
-    "    embedding_function=VertexAIEmbeddings(model_name=\"textembedding-gecko@latest\"),\n",
+    "    embedding_function=VertexAIEmbeddings(model_name=\"text-embedding-005\"),\n",
     ")\n",
     "\n",
     "# Create retriever\n",
@@ -445,7 +445,7 @@
     "\n",
     "\n",
     "def plt_img_base64(img_base64):\n",
-    "    \"\"\"Disply base64 encoded string as image\"\"\"\n",
+    "    \"\"\"Display base64 encoded string as image\"\"\"\n",
     "    # Create an HTML img tag with the base64 string as the source\n",
     "    image_html = f'<img src=\"data:image/jpeg;base64,{img_base64}\" />'\n",
     "    # Display the image by rendering the HTML\n",
@@ -553,7 +553,7 @@
     "    \"\"\"\n",
     "\n",
     "    # Multi-modal LLM\n",
-    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-2.0-flash\", max_tokens=1024)\n",
     "\n",
     "    # RAG pipeline\n",
     "    chain = (\n",

cookbook/README.md

@@ -4,6 +4,8 @@ Example code for building applications with LangChain, with an emphasis on more
 
 Notebook | Description
 :- | :-
+[agent_fireworks_ai_langchain_mongodb.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/agent_fireworks_ai_langchain_mongodb.ipynb) | Build an AI Agent With Memory Using MongoDB, LangChain and FireWorksAI.
+[mongodb-langchain-cache-memory.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/mongodb-langchain-cache-memory.ipynb) | Build a RAG Application with Semantic Cache Using MongoDB and LangChain.
 [LLaMA2_sql_chat.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/LLaMA2_sql_chat.ipynb) | Build a chat application that interacts with a SQL database using an open source llm (llama2), specifically demonstrated on an SQLite database containing rosters.
 [Semi_Structured_RAG.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_Structured_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data, including text and tables, using unstructured for parsing, multi-vector retriever for storing, and lcel for implementing chains.
 [Semi_structured_and_multi_moda...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_and_multi_modal_RAG.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using unstructured for parsing, multi-vector retriever for storage and retrieval, and lcel for implementing chains.
@@ -19,7 +21,6 @@ Notebook | Description
 [code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.
 [custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.
 [custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.
-[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.
 [deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.
 [elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl API.
 [extraction_openai_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/extraction_openai_tools.ipynb) | Structured Data Extraction with OpenAI Tools
@@ -36,6 +37,7 @@ Notebook | Description
 [llm_symbolic_math.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/llm_symbolic_math.ipynb) | Solve algebraic equations with the help of llms (language learning models) and sympy, a python library for symbolic mathematics.
 [meta_prompt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/meta_prompt.ipynb) | Implement the meta-prompt concept, which is a method for building self-improving agents that reflect on their own performance and modify their instructions accordingly.
 [multi_modal_output_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_output_agent.ipynb) | Generate multi-modal outputs, specifically images and text.
+[multi_modal_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_modal_RAG_vdms.ipynb) | Perform retrieval-augmented generation (rag) on documents including text and images, using unstructured for parsing, Intel's Visual Data Management System (VDMS) as the vectorstore, and chains.
 [multi_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multi_player_dnd.ipynb) | Simulate multi-player dungeons & dragons games, with a custom function determining the speaking schedule of the agents.
 [multiagent_authoritarian.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_authoritarian.ipynb) | Implement a multi-agent simulation where a privileged agent controls the conversation, including deciding who speaks and when the conversation ends, in the context of a simulated news network.
 [multiagent_bidding.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/multiagent_bidding.ipynb) | Implement a multi-agent simulation where agents bid to speak, with the highest bidder speaking next, demonstrated through a fictitious presidential debate example.
@@ -47,7 +49,7 @@ Notebook | Description
 [press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
 [program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
 [qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_layout_analysis_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb) | End-to-end RAG example using Upstage Layout Analysis and Groundedness Check.
+[rag_upstage_document_parse_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_document_parse_groundedness_check.ipynb) | End-to-end RAG example using Upstage Document Parse and Groundedness Check.
 [retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
 [self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
@@ -59,4 +61,6 @@ Notebook | Description
 [wikibase_agent.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/wikibase_agent.ipynb) | Create a simple wikibase agent that utilizes sparql generation, with testing done on http://wikidata.org.
 [oracleai_demo.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/oracleai_demo.ipynb) | This guide outlines how to utilize Oracle AI Vector Search alongside Langchain for an end-to-end RAG pipeline, providing step-by-step examples. The process includes loading documents from various sources using OracleDocLoader, summarizing them either within or outside the database with OracleSummary, and generating embeddings similarly through OracleEmbeddings. It also covers chunking documents according to specific requirements using Advanced Oracle Capabilities from OracleTextSplitter, and finally, storing and indexing these documents in a Vector Store for querying with OracleVS.
 [rag-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag-locally-on-intel-cpu.ipynb) | Perform Retrieval-Augmented-Generation (RAG) on locally downloaded open-source models using langchain and open source tools and execute it on Intel Xeon CPU. We showed an example of how to apply RAG on Llama 2 model and enable it to answer the queries related to Intel Q1 2024 earnings release.
-[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
+[visual_RAG_vdms.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/visual_RAG_vdms.ipynb) | Performs Visual Retrieval-Augmented-Generation (RAG) using videos and scene descriptions generated by open source models.
+[contextual_rag.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/contextual_rag.ipynb) | Performs contextual retrieval-augmented generation (RAG) prepending chunk-specific explanatory context to each chunk before embedding.
+[rag-agents-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/local_rag_agents_intel_cpu.ipynb) | Build a RAG agent locally with open source models that routes questions through one of two paths to find answers. The agent generates answers based on documents retrieved from either the vector database or retrieved from web search. If the vector database lacks relevant information, the agent opts for web search. Open-source models for LLM and embeddings are used locally on an Intel Xeon CPU to execute this pipeline.

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"
    ]
   },
   {
@@ -204,14 +204,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "523e6ed2-2132-4748-bdb7-db765f20648d",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.chat_models import ChatOllama\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate"
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_ollama import ChatOllama"
    ]
   },
   {

cookbook/advanced_rag_eval.ipynb

@@ -30,7 +30,7 @@
    "outputs": [],
    "source": [
     "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken open_clip_torch torch"
+    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml matplotlib tiktoken open_clip_torch torch"
    ]
   },
   {
@@ -409,7 +409,7 @@
     "    table_summaries,\n",
     "    tables,\n",
     "    image_summaries,\n",
-    "    image_summaries,\n",
+    "    img_base64_list,\n",
     ")"
    ]
   },

cookbook/agent_vectorstore.ipynb

@@ -22,7 +22,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 1,
+   "id": "e8d63d14-138d-4aa5-a741-7fd3537d00aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
    "id": "2e87c10a",
    "metadata": {},
    "outputs": [],
@@ -37,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 3,
    "id": "0b7b772b",
    "metadata": {},
    "outputs": [],
@@ -54,19 +66,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 4,
    "id": "f2675861",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Running Chroma using direct local API.\n",
-      "Using DuckDB in-memory for database. Data will be transient.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.document_loaders import TextLoader\n",
     "\n",
@@ -81,7 +84,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "bc5403d4",
    "metadata": {},
    "outputs": [],
@@ -93,17 +96,25 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "1431cded",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "USER_AGENT environment variable not set, consider setting it to identify your requests.\n"
+     ]
+    }
+   ],
    "source": [
     "from langchain_community.document_loaders import WebBaseLoader"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "915d3ff3",
    "metadata": {},
    "outputs": [],
@@ -113,16 +124,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "96a2edf8",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
+     "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Running Chroma using direct local API.\n",
-      "Using DuckDB in-memory for database. Data will be transient.\n"
+      "Created a chunk of size 2122, which is longer than the specified 1000\n",
+      "Created a chunk of size 3187, which is longer than the specified 1000\n",
+      "Created a chunk of size 1017, which is longer than the specified 1000\n",
+      "Created a chunk of size 1049, which is longer than the specified 1000\n",
+      "Created a chunk of size 1256, which is longer than the specified 1000\n",
+      "Created a chunk of size 2321, which is longer than the specified 1000\n"
      ]
     }
    ],
@@ -135,14 +150,6 @@
     ")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "71ecef90",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  },
   {
    "cell_type": "markdown",
    "id": "c0a6c031",
@@ -153,31 +160,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 9,
    "id": "eb142786",
    "metadata": {},
    "outputs": [],
    "source": [
     "# Import things that are needed generically\n",
-    "from langchain.agents import AgentType, Tool, initialize_agent\n",
-    "from langchain_openai import OpenAI"
+    "from langchain.agents import Tool"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 10,
    "id": "850bc4e9",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"State of Union QA System\",\n",
+    "        name=\"state_of_union_qa_system\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"Ruff QA System\",\n",
+    "        name=\"ruff_qa_system\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
     "    ),\n",
@@ -186,94 +192,116 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
-   "id": "fc47f230",
+   "execution_count": 11,
+   "id": "70c461d8-aaca-4f2a-9a93-bf35841cc615",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Construct the agent. We will use the default agent type here.\n",
-    "# See documentation for a full list of options.\n",
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
-   "id": "10ca2db8",
+   "execution_count": 12,
+   "id": "a6d2b911-3044-4430-a35b-75832bb45334",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "What did biden say about ketanji brown jackson in the state of the union address?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  state_of_union_qa_system (call_26QlRdsptjEJJZjFsAUjEbaH)\n",
+      " Call ID: call_26QlRdsptjEJJZjFsAUjEbaH\n",
+      "  Args:\n",
+      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: state_of_union_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
-      "Action: State of Union QA System\n",
-      "Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
+      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "In the State of the Union address, Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
-      ]
-     },
-     "execution_count": 46,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\n",
-    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
-    ")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
-   "id": "4e91b811",
+   "execution_count": 13,
+   "id": "e836b4cd-abf7-49eb-be0e-b9ad501213f3",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "Why use ruff over flake8?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  ruff_qa_system (call_KqDoWeO9bo9OAXdxOsCb6msC)\n",
+      " Call ID: call_KqDoWeO9bo9OAXdxOsCb6msC\n",
+      "  Args:\n",
+      "    __arg1: Why use ruff over flake8?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: ruff_qa_system\n",
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
-      "Action: Ruff QA System\n",
-      "Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
+      "There are a few reasons why someone might choose to use Ruff over Flake8:\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "1. Larger rule set: Ruff implements over 800 rules, while Flake8 only implements around 200. This means that Ruff can catch more potential issues in your code.\n",
+      "\n",
+      "2. Better compatibility with other tools: Ruff is designed to work well with other tools like Black, isort, and type checkers like Mypy. This means that you can use Ruff alongside these tools to get more comprehensive feedback on your code.\n",
+      "\n",
+      "3. Automatic fixing of lint violations: Unlike Flake8, Ruff is capable of automatically fixing its own lint violations. This can save you time and effort when fixing issues in your code.\n",
+      "\n",
+      "4. Native implementation of popular Flake8 plugins: Ruff re-implements some of the most popular Flake8 plugins natively, which means you don't have to install and configure multiple plugins to get the same functionality.\n",
+      "\n",
+      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8, making it a popular choice for many developers.\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "You might choose to use Ruff over Flake8 for several reasons:\n",
+      "\n",
+      "1. Ruff has a much larger rule set, implementing over 800 rules compared to Flake8's roughly 200, so it can catch more potential issues.\n",
+      "2. Ruff is designed to work better with other tools like Black, isort, and type checkers like Mypy, providing more comprehensive code feedback.\n",
+      "3. Ruff can automatically fix its own lint violations, which Flake8 cannot, saving time and effort.\n",
+      "4. Ruff natively implements some popular Flake8 plugins, so you don't need to install and configure multiple plugins separately.\n",
+      "\n",
+      "Overall, Ruff offers a more comprehensive and user-friendly experience compared to Flake8.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
-      ]
-     },
-     "execution_count": 47,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\"Why use ruff over flake8?\")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"Why use ruff over flake8?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -296,20 +324,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 14,
    "id": "f59b377e",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"State of Union QA System\",\n",
+    "        name=\"state_of_union_qa_system\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\",\n",
     "        return_direct=True,\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"Ruff QA System\",\n",
+    "        name=\"ruff_qa_system\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question.\",\n",
     "        return_direct=True,\n",
@@ -319,90 +347,92 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
-   "id": "8615707a",
+   "execution_count": 15,
+   "id": "06f69c0f-c83d-4b7f-a1c8-7614aced3bae",
    "metadata": {},
    "outputs": [],
    "source": [
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
-   "id": "36e718a9",
+   "execution_count": 16,
+   "id": "a6b38c12-ac25-43c0-b9c2-2b1985ab4825",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "What did biden say about ketanji brown jackson in the state of the union address?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  state_of_union_qa_system (call_yjxh11OnZiauoyTAn9npWdxj)\n",
+      " Call ID: call_yjxh11OnZiauoyTAn9npWdxj\n",
+      "  Args:\n",
+      "    __arg1: What did Biden say about Ketanji Brown Jackson in the state of the union address?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: state_of_union_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out what Biden said about Ketanji Brown Jackson in the State of the Union address.\n",
-      "Action: State of Union QA System\n",
-      "Action Input: What did Biden say about Ketanji Brown Jackson in the State of the Union address?\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      " Biden said that he nominated Ketanji Brown Jackson for the United States Supreme Court and praised her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\" Biden said that Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
-      ]
-     },
-     "execution_count": 50,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\n",
-    "    \"What did biden say about ketanji brown jackson in the state of the union address?\"\n",
-    ")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"What did biden say about ketanji brown jackson in the state of the union address?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
-   "id": "edfd0a1a",
+   "execution_count": 17,
+   "id": "88f08d86-7972-4148-8128-3ac8898ad68a",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "Why use ruff over flake8?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  ruff_qa_system (call_GiWWfwF6wbbRFQrHlHbhRtGW)\n",
+      " Call ID: call_GiWWfwF6wbbRFQrHlHbhRtGW\n",
+      "  Args:\n",
+      "    __arg1: What are the advantages of using ruff over flake8 for Python linting?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: ruff_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out the advantages of using ruff over flake8\n",
-      "Action: Ruff QA System\n",
-      "Action Input: What are the advantages of using ruff over flake8?\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      " Ruff has a larger rule set, supports automatic fixing of lint violations, and does not require the installation of additional plugins. It also has better compatibility with Black and can be used alongside a type checker for more comprehensive code analysis.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "' Ruff can be used as a drop-in replacement for Flake8 when used (1) without or with a small number of plugins, (2) alongside Black, and (3) on Python 3 code. It also re-implements some of the most popular Flake8 plugins and related code quality tools natively, including isort, yesqa, eradicate, and most of the rules implemented in pyupgrade. Ruff also supports automatically fixing its own lint violations, which Flake8 does not.'"
-      ]
-     },
-     "execution_count": 51,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\"Why use ruff over flake8?\")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"Why use ruff over flake8?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -417,19 +447,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 57,
+   "execution_count": 18,
    "id": "d397a233",
    "metadata": {},
    "outputs": [],
    "source": [
     "tools = [\n",
     "    Tool(\n",
-    "        name=\"State of Union QA System\",\n",
+    "        name=\"state_of_union_qa_system\",\n",
     "        func=state_of_union.run,\n",
     "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
     "    ),\n",
     "    Tool(\n",
-    "        name=\"Ruff QA System\",\n",
+    "        name=\"ruff_qa_system\",\n",
     "        func=ruff.run,\n",
     "        description=\"useful for when you need to answer questions about ruff (a python linter). Input should be a fully formed question, not referencing any obscure pronouns from the conversation before.\",\n",
     "    ),\n",
@@ -438,60 +468,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
-   "id": "06157240",
+   "execution_count": 19,
+   "id": "41743f29-150d-40ba-aa8e-3a63c32216aa",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Construct the agent. We will use the default agent type here.\n",
-    "# See documentation for a full list of options.\n",
-    "agent = initialize_agent(\n",
-    "    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\n",
-    ")"
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent = create_react_agent(\"openai:gpt-4.1-mini\", tools)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
-   "id": "b492b520",
+   "execution_count": 20,
+   "id": "e20e81dd-284a-4d07-9160-63a84b65cba8",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
       "\n",
+      "What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  ruff_qa_system (call_VOnxiOEehauQyVOTjDJkR5L2)\n",
+      " Call ID: call_VOnxiOEehauQyVOTjDJkR5L2\n",
+      "  Args:\n",
+      "    __arg1: What tool does ruff use to run over Jupyter Notebooks?\n",
+      "  state_of_union_qa_system (call_AbSsXAxwe4JtCRhga926SxOZ)\n",
+      " Call ID: call_AbSsXAxwe4JtCRhga926SxOZ\n",
+      "  Args:\n",
+      "    __arg1: Did the president mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union?\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: state_of_union_qa_system\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m I need to find out what tool ruff uses to run over Jupyter Notebooks, and if the president mentioned it in the state of the union.\n",
-      "Action: Ruff QA System\n",
-      "Action Input: What tool does ruff use to run over Jupyter Notebooks?\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m Ruff is integrated into nbQA, a tool for running linters and code formatters over Jupyter Notebooks. After installing ruff and nbqa, you can run Ruff over a notebook like so: > nbqa ruff Untitled.html\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now need to find out if the president mentioned this tool in the state of the union.\n",
-      "Action: State of Union QA System\n",
-      "Action Input: Did the president mention nbQA in the state of the union?\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: No, the president did not mention nbQA in the state of the union.\u001b[0m\n",
+      " No, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "Ruff does not support source.organizeImports and source.fixAll code actions in Jupyter Notebooks. Additionally, the president did not mention the tool that ruff uses to run over Jupyter Notebooks in the state of the union.\n"
      ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'No, the president did not mention nbQA in the state of the union.'"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent.run(\n",
-    "    \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\"\n",
-    ")"
+    "input_message = {\n",
+    "    \"role\": \"user\",\n",
+    "    \"content\": \"What tool does ruff use to run over Jupyter Notebooks? Did the president mention that tool in the state of the union?\",\n",
+    "}\n",
+    "\n",
+    "for step in agent.stream(\n",
+    "    {\"messages\": [input_message]},\n",
+    "    stream_mode=\"values\",\n",
+    "):\n",
+    "    step[\"messages\"][-1].pretty_print()"
    ]
   },
   {
@@ -519,7 +549,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,

cookbook/anthropic_structured_outputs.ipynb

@@ -31,8 +31,8 @@
    "source": [
     "# Optional\n",
     "import os\n",
-    "# os.environ['LANGCHAIN_TRACING_V2'] = 'true' # enables tracing\n",
-    "# os.environ['LANGCHAIN_API_KEY'] = <your-api-key>"
+    "# os.environ['LANGSMITH_TRACING'] = 'true' # enables tracing\n",
+    "# os.environ['LANGSMITH_API_KEY'] = <your-api-key>"
    ]
   },
   {

cookbook/azure_container_apps_dynamic_sessions_data_analyst.ipynb

@@ -135,7 +135,7 @@
    "source": [
     "## Instantiate model, DB, code interpreter\n",
     "\n",
-    "We'll use the LangChain [SQLDatabase](https://api.python.langchain.com/en/latest/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase) interface to connect to our DB and query it. This works with any SQL database supported by [SQLAlchemy](https://www.sqlalchemy.org/)."
+    "We'll use the LangChain [SQLDatabase](https://python.langchain.com/v0.2/api_reference/community/utilities/langchain_community.utilities.sql_database.SQLDatabase.html#langchain_community.utilities.sql_database.SQLDatabase) interface to connect to our DB and query it. This works with any SQL database supported by [SQLAlchemy](https://www.sqlalchemy.org/)."
    ]
   },
   {

cookbook/code-analysis-deeplake.ipynb

@@ -66,7 +66,7 @@
    },
    "outputs": [],
    "source": [
-    "#!python3 -m pip install --upgrade langchain deeplake openai"
+    "#!python3 -m pip install --upgrade langchain langchain-deeplake openai"
    ]
   },
   {
@@ -90,7 +90,8 @@
     "import os\n",
     "from getpass import getpass\n",
     "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "if \"OPENAI_API_KEY\" not in os.environ:\n",
+    "    os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
     "# Please manually enter OpenAI Key"
    ]
   },
@@ -665,89 +666,26 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Your Deep Lake dataset has been successfully created!\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      " \r"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Dataset(path='hub://adilkhan/langchain-code', tensors=['embedding', 'id', 'metadata', 'text'])\n",
-      "\n",
-      "  tensor      htype       shape       dtype  compression\n",
-      "  -------    -------     -------     -------  ------- \n",
-      " embedding  embedding  (8244, 1536)  float32   None   \n",
-      "    id        text      (8244, 1)      str     None   \n",
-      " metadata     json      (8244, 1)      str     None   \n",
-      "   text       text      (8244, 1)      str     None   \n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": []
-    },
-    {
-     "data": {
-      "text/plain": [
-       "<langchain_community.vectorstores.deeplake.DeepLake at 0x7fe1b67d7a30>"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import DeepLake\n",
+    "from langchain_deeplake.vectorstores import DeeplakeVectorStore\n",
     "\n",
     "username = \"<USERNAME_OR_ORG>\"\n",
     "\n",
     "\n",
-    "db = DeepLake.from_documents(\n",
-    "    texts, embeddings, dataset_path=f\"hub://{username}/langchain-code\", overwrite=True\n",
+    "db = DeeplakeVectorStore.from_documents(\n",
+    "    documents=texts,\n",
+    "    embedding=embeddings,\n",
+    "    dataset_path=f\"hub://{username}/langchain-code\",\n",
+    "    overwrite=True,\n",
     ")\n",
     "db"
    ]
   },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# from langchain_community.vectorstores import DeepLake\n",
-    "\n",
-    "# db = DeepLake.from_documents(\n",
-    "#     texts, embeddings, dataset_path=f\"hub://{<org_id>}/langchain-code\", runtime={\"tensor_db\": True}\n",
-    "# )\n",
-    "# db"
-   ]
-  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -759,24 +697,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Deep Lake Dataset in hub://adilkhan/langchain-code already exists, loading from the storage\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "db = DeepLake(\n",
+    "db = DeeplakeVectorStore(\n",
     "    dataset_path=f\"hub://{username}/langchain-code\",\n",
     "    read_only=True,\n",
-    "    embedding=embeddings,\n",
+    "    embedding_function=embeddings,\n",
     ")"
    ]
   },
@@ -795,36 +725,6 @@
     "retriever.search_kwargs[\"k\"] = 20"
    ]
   },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can also specify user defined functions using [Deep Lake filters](https://docs.deeplake.ai/en/latest/deeplake.core.dataset.html#deeplake.core.dataset.Dataset.filter)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "def filter(x):\n",
-    "    # filter based on source code\n",
-    "    if \"something\" in x[\"text\"].data()[\"value\"]:\n",
-    "        return False\n",
-    "\n",
-    "    # filter based on path e.g. extension\n",
-    "    metadata = x[\"metadata\"].data()[\"value\"]\n",
-    "    return \"only_this\" in metadata[\"source\"] or \"also_that\" in metadata[\"source\"]\n",
-    "\n",
-    "\n",
-    "### turn on below for custom filtering\n",
-    "# retriever.search_kwargs['filter'] = filter"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 20,
@@ -836,10 +736,8 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(\n",
-    "    model_name=\"gpt-3.5-turbo-0613\"\n",
-    ")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
-    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0613\")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
+    "qa = RetrievalQA.from_llm(model, retriever=retriever)"
    ]
   },
   {

cookbook/cql_agent.ipynb

@@ -38,7 +38,7 @@
    "source": [
     "Connection is via `cassio` using `auto=True` parameter, and the notebook uses OpenAI. You should create a `.env` file accordingly.\n",
     "\n",
-    "For Casssandra, set:\n",
+    "For Cassandra, set:\n",
     "```bash\n",
     "CASSANDRA_CONTACT_POINTS\n",
     "CASSANDRA_USERNAME\n",

cookbook/databricks_sql_db.ipynb

@@ -1,273 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "707d13a7",
-   "metadata": {},
-   "source": [
-    "# Databricks\n",
-    "\n",
-    "This notebook covers how to connect to the [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.\n",
-    "It is broken into 3 parts: installation and setup, connecting to Databricks, and examples."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0076d072",
-   "metadata": {},
-   "source": [
-    "## Installation and Setup"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "739b489b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "!pip install databricks-sql-connector"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "73113163",
-   "metadata": {},
-   "source": [
-    "## Connecting to Databricks\n",
-    "\n",
-    "You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the `SQLDatabase.from_databricks()` method.\n",
-    "\n",
-    "### Syntax\n",
-    "```python\n",
-    "SQLDatabase.from_databricks(\n",
-    "    catalog: str,\n",
-    "    schema: str,\n",
-    "    host: Optional[str] = None,\n",
-    "    api_token: Optional[str] = None,\n",
-    "    warehouse_id: Optional[str] = None,\n",
-    "    cluster_id: Optional[str] = None,\n",
-    "    engine_args: Optional[dict] = None,\n",
-    "    **kwargs: Any)\n",
-    "```\n",
-    "### Required Parameters\n",
-    "* `catalog`: The catalog name in the Databricks database.\n",
-    "* `schema`: The schema name in the catalog.\n",
-    "\n",
-    "### Optional Parameters\n",
-    "There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.\n",
-    "* `host`: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.\n",
-    "* `api_token`: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.\n",
-    "* `warehouse_id`: The warehouse ID in the Databricks SQL.\n",
-    "* `cluster_id`: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.\n",
-    "* `engine_args`: The arguments to be used when connecting Databricks.\n",
-    "* `**kwargs`: Additional keyword arguments for the `SQLDatabase.from_uri` method."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b11c7e48",
-   "metadata": {},
-   "source": [
-    "## Examples"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "8102bca0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Connecting to Databricks with SQLDatabase wrapper\n",
-    "from langchain_community.utilities import SQLDatabase\n",
-    "\n",
-    "db = SQLDatabase.from_databricks(catalog=\"samples\", schema=\"nyctaxi\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "9dd36f58",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Creating a OpenAI Chat LLM wrapper\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5b5c5f1a",
-   "metadata": {},
-   "source": [
-    "### SQL Chain example\n",
-    "\n",
-    "This example demonstrates the use of the [SQL Chain](https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html) for answering a question over a Databricks database."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "36f2270b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.utilities import SQLDatabaseChain\n",
-    "\n",
-    "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "4e2b5f25",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
-      "What is the average duration of taxi rides that start between midnight and 6am?\n",
-      "SQLQuery:\u001b[32;1m\u001b[1;3mSELECT AVG(UNIX_TIMESTAMP(tpep_dropoff_datetime) - UNIX_TIMESTAMP(tpep_pickup_datetime)) as avg_duration\n",
-      "FROM trips\n",
-      "WHERE HOUR(tpep_pickup_datetime) >= 0 AND HOUR(tpep_pickup_datetime) < 6\u001b[0m\n",
-      "SQLResult: \u001b[33;1m\u001b[1;3m[(987.8122786304605,)]\u001b[0m\n",
-      "Answer:\u001b[32;1m\u001b[1;3mThe average duration of taxi rides that start between midnight and 6am is 987.81 seconds.\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "db_chain.run(\n",
-    "    \"What is the average duration of taxi rides that start between midnight and 6am?\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e496d5e5",
-   "metadata": {},
-   "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."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "9918e86a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import create_sql_agent\n",
-    "from langchain_community.agent_toolkits import SQLDatabaseToolkit\n",
-    "\n",
-    "toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
-    "agent = create_sql_agent(llm=llm, toolkit=toolkit, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "c484a76e",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
-      "Action Input: \u001b[0m\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3mtrips\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.\n",
-      "Action: schema_sql_db\n",
-      "Action Input: trips\u001b[0m\n",
-      "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "CREATE TABLE trips (\n",
-      "\ttpep_pickup_datetime TIMESTAMP, \n",
-      "\ttpep_dropoff_datetime TIMESTAMP, \n",
-      "\ttrip_distance FLOAT, \n",
-      "\tfare_amount FLOAT, \n",
-      "\tpickup_zip INT, \n",
-      "\tdropoff_zip INT\n",
-      ") USING DELTA\n",
-      "\n",
-      "/*\n",
-      "3 rows from trips table:\n",
-      "tpep_pickup_datetime\ttpep_dropoff_datetime\ttrip_distance\tfare_amount\tpickup_zip\tdropoff_zip\n",
-      "2016-02-14 16:52:13+00:00\t2016-02-14 17:16:04+00:00\t4.94\t19.0\t10282\t10171\n",
-      "2016-02-04 18:44:19+00:00\t2016-02-04 18:46:00+00:00\t0.28\t3.5\t10110\t10110\n",
-      "2016-02-17 17:13:57+00:00\t2016-02-17 17:17:55+00:00\t0.7\t5.0\t10103\t10023\n",
-      "*/\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.\n",
-      "Action: query_checker_sql_db\n",
-      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
-      "Observation: \u001b[31;1m\u001b[1;3mSELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe query is correct. I will now execute it to find the longest trip distance and its duration.\n",
-      "Action: query_sql_db\n",
-      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(30.6, '0 00:43:31.000000000')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
-      "Final Answer: The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent.run(\"What is the longest trip distance and how long did it take?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/elasticsearch_db_qa.ipynb

@@ -115,7 +115,7 @@
     "\n",
     "PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
     "\n",
-    "Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
+    "Unless told to do not query for all the columns from a specific index, only ask for a few relevant columns given the question.\n",
     "\n",
     "Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
     "\n",

cookbook/img-to_img-search_CLIP_ChromaDB.ipynb

@@ -358,7 +358,7 @@
    "id": "6e5cd014-db86-4d6b-8399-25cae3da5570",
    "metadata": {},
    "source": [
-    "## Helper function to plot retrived similar images"
+    "## Helper function to plot retrieved similar images"
    ]
   },
   {

cookbook/langgraph_self_rag.ipynb

@@ -336,7 +336,7 @@
     "    # Create a prompt template with format instructions and the query\n",
     "    prompt = PromptTemplate(\n",
     "        template=\"\"\"You are generating questions that is well optimized for retrieval. \\n \n",
-    "        Look at the input and try to reason about the underlying sematic intent / meaning. \\n \n",
+    "        Look at the input and try to reason about the underlying semantic intent / meaning. \\n \n",
     "        Here is the initial question:\n",
     "        \\n ------- \\n\n",
     "        {question} \n",
@@ -643,7 +643,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python 3.11.1 64-bit",
    "language": "python",
    "name": "python3"
   },
@@ -657,7 +657,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.11.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "1a1af0ee75eeea9e2e1ee996c87e7a2b11a0bebd85af04bb136d915cefc0abce"
+   }
   }
  },
  "nbformat": 4,

cookbook/mongodb-langchain-cache-memory.ipynb

@@ -124,8 +124,8 @@
     "# Optional-- If you want to enable Langsmith -- good for debugging\n",
     "import os\n",
     "\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+    "os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+    "os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass()"
    ]
   },
   {
@@ -156,7 +156,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Ensure you have an HF_TOKEN in your development enviornment:\n",
+    "# Ensure you have an HF_TOKEN in your development environment:\n",
     "# access tokens can be created or copied from the Hugging Face platform (https://huggingface.co/docs/hub/en/security-tokens)\n",
     "\n",
     "# Load MongoDB's embedded_movies dataset from Hugging Face\n",

cookbook/multi_modal_RAG_vdms.ipynb

@@ -18,9 +18,14 @@
     "* Use of multimodal embeddings (such as [CLIP](https://openai.com/research/clip)) to embed images and text\n",
     "* Use of [VDMS](https://github.com/IntelLabs/vdms/blob/master/README.md) as a vector store with support for multi-modal\n",
     "* Retrieval of both images and text using similarity search\n",
-    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis \n",
-    "\n",
-    "\n",
+    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2498a0a1",
+   "metadata": {},
+   "source": [
     "## Packages\n",
     "\n",
     "For `unstructured`, you will also need `poppler` ([installation instructions](https://pdf2image.readthedocs.io/en/latest/installation.html)) and `tesseract` ([installation instructions](https://tesseract-ocr.github.io/tessdoc/Installation.html)) in your system."
@@ -33,16 +38,26 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# (newest versions required for multi-modal)\n",
-    "! pip install --quiet -U vdms langchain-experimental\n",
+    "! pip install --quiet -U langchain-vdms langchain-experimental langchain-ollama\n",
     "\n",
     "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install --quiet pdf2image \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml open_clip_torch"
+    "! pip install --quiet pdf2image \"unstructured[all-docs]==0.10.19\" \"onnxruntime==1.17.0\" pillow pydantic lxml open_clip_torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "78ac6543",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from dotenv import load_dotenv, find_dotenv\n",
+    "# load_dotenv(find_dotenv(), override=True);"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "6a6b6e73",
+   "id": "e5c8916e",
    "metadata": {},
    "source": [
     "## Start VDMS Server\n",
@@ -54,15 +69,14 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "5f483872",
+   "id": "1e6e2c15",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "docker: Error response from daemon: Conflict. The container name \"/vdms_rag_nb\" is already in use by container \"0c19ed281463ac10d7efe07eb815643e3e534ddf24844357039453ad2b0c27e8\". You have to remove (or rename) that container to be able to reuse that name.\n",
-      "See 'docker run --help'.\n"
+      "a701e5ac3523006e9540b5355e2d872d5d78383eab61562a675d5b9ac21fde65\n"
      ]
     }
    ],
@@ -70,22 +84,11 @@
     "! docker run --rm -d -p 55559:55555 --name vdms_rag_nb intellabs/vdms:latest\n",
     "\n",
     "# Connect to VDMS Vector Store\n",
-    "from langchain_community.vectorstores.vdms import VDMS_Client\n",
+    "from langchain_vdms.vectorstores import VDMS_Client\n",
     "\n",
     "vdms_client = VDMS_Client(port=55559)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "78ac6543",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# from dotenv import load_dotenv, find_dotenv\n",
-    "# load_dotenv(find_dotenv(), override=True);"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "1e94b3fb-8e3e-4736-be0a-ad881626c7bd",
@@ -95,14 +98,9 @@
     "\n",
     "### Partition PDF text and images\n",
     "  \n",
-    "Let's look at an example pdf containing interesting images.\n",
+    "Let's use famous photographs from the PDF version of Library of Congress Magazine in this example.\n",
     "\n",
-    "Famous photographs from library of congress:\n",
-    "\n",
-    "* https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\n",
-    "* We'll use this as an example below\n",
-    "\n",
-    "We can use `partition_pdf` below from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
+    "We can use `partition_pdf` from [Unstructured](https://unstructured-io.github.io/unstructured/introduction.html#key-concepts) to extract text and images."
    ]
   },
   {
@@ -116,12 +114,13 @@
     "\n",
     "import requests\n",
     "\n",
-    "# Folder with pdf and extracted images\n",
-    "datapath = Path(\"./multimodal_files\").resolve()\n",
+    "# Folder to store pdf and extracted images\n",
+    "base_datapath = Path(\"./data/multimodal_files\").resolve()\n",
+    "datapath = base_datapath / \"images\"\n",
     "datapath.mkdir(parents=True, exist_ok=True)\n",
     "\n",
     "pdf_url = \"https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\"\n",
-    "pdf_path = str(datapath / pdf_url.split(\"/\")[-1])\n",
+    "pdf_path = str(base_datapath / pdf_url.split(\"/\")[-1])\n",
     "with open(pdf_path, \"wb\") as f:\n",
     "    f.write(requests.get(pdf_url).content)"
    ]
@@ -174,14 +173,8 @@
    "source": [
     "## Multi-modal embeddings with our document\n",
     "\n",
-    "We will use [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
-    "\n",
-    "We use a larger model for better performance (set in `langchain_experimental.open_clip.py`).\n",
-    "\n",
-    "```\n",
-    "model_name = \"ViT-g-14\"\n",
-    "checkpoint = \"laion2b_s34b_b88k\"\n",
-    "```"
+    "In this section, we initialize the VDMS vector store for both text and images. For better performance, we use model `ViT-g-14` from [OpenClip multimodal embeddings](https://python.langchain.com/docs/integrations/text_embedding/open_clip).\n",
+    "The images are stored as base64 encoded strings with `vectorstore.add_images`.\n"
    ]
   },
   {
@@ -193,16 +186,14 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain_community.vectorstores import VDMS\n",
     "from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
+    "from langchain_vdms import VDMS\n",
     "\n",
     "# Create VDMS\n",
     "vectorstore = VDMS(\n",
     "    client=vdms_client,\n",
     "    collection_name=\"mm_rag_clip_photos\",\n",
-    "    embedding_function=OpenCLIPEmbeddings(\n",
-    "        model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"\n",
-    "    ),\n",
+    "    embedding=OpenCLIPEmbeddings(model_name=\"ViT-g-14\", checkpoint=\"laion2b_s34b_b88k\"),\n",
     ")\n",
     "\n",
     "# Get image URIs with .jpg extension only\n",
@@ -233,7 +224,7 @@
    "source": [
     "## RAG\n",
     "\n",
-    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings."
+    "Here we define helper functions for image results."
    ]
   },
   {
@@ -322,10 +313,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.llms.ollama import Ollama\n",
-    "from langchain_core.messages import HumanMessage\n",
+    "from langchain_core.messages import HumanMessage, SystemMessage\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
+    "from langchain_ollama.llms import OllamaLLM\n",
     "\n",
     "\n",
     "def prompt_func(data_dict):\n",
@@ -350,8 +341,8 @@
     "            \"As an expert art critic and historian, your task is to analyze and interpret images, \"\n",
     "            \"considering their historical and cultural significance. Alongside the images, you will be \"\n",
     "            \"provided with related text to offer context. Both will be retrieved from a vectorstore based \"\n",
-    "            \"on user-input keywords. Please convert answers to english and use your extensive knowledge \"\n",
-    "            \"and analytical skills to provide a comprehensive summary that includes:\\n\"\n",
+    "            \"on user-input keywords. Please use your extensive knowledge and analytical skills to provide a \"\n",
+    "            \"comprehensive summary that includes:\\n\"\n",
     "            \"- A detailed description of the visual elements in the image.\\n\"\n",
     "            \"- The historical and cultural context of the image.\\n\"\n",
     "            \"- An interpretation of the image's symbolism and meaning.\\n\"\n",
@@ -369,7 +360,7 @@
     "    \"\"\"Multi-modal RAG chain\"\"\"\n",
     "\n",
     "    # Multi-modal LLM\n",
-    "    llm_model = Ollama(\n",
+    "    llm_model = OllamaLLM(\n",
     "        verbose=True, temperature=0.5, model=\"llava\", base_url=\"http://localhost:11434\"\n",
     "    )\n",
     "\n",
@@ -392,7 +383,8 @@
    "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
    "metadata": {},
    "source": [
-    "## Test retrieval and run RAG"
+    "## Test retrieval and run RAG\n",
+    "Now let's query for a `woman with children` and retrieve the top results."
    ]
   },
   {
@@ -428,6 +420,121 @@
      },
      "metadata": {},
      "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "© 2017 LARRY D. MOORE\n",
+      "\n",
+      "contemporary criticism of the less-than- thoughtful circumstances under which Lange photographed Thomson, the picture’s power to engage has not diminished. Artists in other countries have appropriated the image, changing the mother’s features into those of other ethnicities, but keeping her expression and the positions of her clinging children. Long after anyone could help the Thompson family, this picture has resonance in another time of national crisis, unemployment and food shortages.\n",
+      "\n",
+      "A striking, but very different picture is a 1900 portrait of the legendary Hin-mah-too-yah- lat-kekt (Chief Joseph) of the Nez Percé people. The Bureau of American Ethnology in Washington, D.C., regularly arranged for its photographer, De Lancey Gill, to photograph Native American delegations that came to the capital to confer with officials about tribal needs and concerns. Although Gill described Chief Joseph as having “an air of gentleness and quiet reserve,” the delegate skeptically appraises the photographer, which is not surprising given that the United States broke five treaties with Chief Joseph and his father between 1855 and 1885.\n",
+      "\n",
+      "More than a glance, second looks may reveal new knowledge into complex histories.\n",
+      "\n",
+      "Anne Wilkes Tucker is the photography curator emeritus of the Museum of Fine Arts, Houston and curator of the “Not an Ostrich” exhibition.\n",
+      "\n",
+      "28\n",
+      "\n",
+      "28 LIBRARY OF CONGRESS MAGAZINE\n",
+      "\n",
+      "LIBRARY OF CONGRESS MAGAZINE\n",
+      "THEYRE WILLING TO HAVE MEENTERTAIN THEM DURING THE DAY,BUT AS SOON AS IT STARTSGETTING DARK, THEY ALLGO OFF, AND LEAVE ME!   \n",
+      "ROSA PARKS: IN HER OWN WORDS\n",
+      "\n",
+      "COMIC ART: 120 YEARS OF PANELS AND PAGES\n",
+      "\n",
+      "SHALL NOT BE DENIED: WOMEN FIGHT FOR THE VOTE\n",
+      "\n",
+      "More information loc.gov/exhibits\n",
+      "Nuestra Sefiora de las Iguanas\n",
+      "\n",
+      "Graciela Iturbide’s 1979 portrait of Zobeida Díaz in the town of Juchitán in southeastern Mexico conveys the strength of women and reflects their important contributions to the economy. Díaz, a merchant, was selling iguanas to cook and eat, carrying them on her head, as is customary.\n",
+      "\n",
+      "GRACIELA ITURBIDE. “NUESTRA SEÑORA DE LAS IGUANAS.” 1979. GELATIN SILVER PRINT. © GRACIELA ITURBIDE, USED BY PERMISSION. PRINTS AND PHOTOGRAPHS DIVISION.\n",
+      "\n",
+      "Iturbide requested permission to take a photograph, but this proved challenging because the iguanas were constantly moving, causing Díaz to laugh. The result, however, was a brilliant portrait that the inhabitants of Juchitán claimed with pride. They have reproduced it on posters and erected a statue honoring Díaz and her iguanas. The photo now appears throughout the world, inspiring supporters of feminism, women’s rights and gender equality.\n",
+      "\n",
+      "—Adam Silvia is a curator in the Prints and Photographs Division.\n",
+      "\n",
+      "6\n",
+      "\n",
+      "6 LIBRARY OF CONGRESS MAGAZINE\n",
+      "\n",
+      "LIBRARY OF CONGRESS MAGAZINE\n",
+      "\n",
+      "‘Migrant Mother’ is Florence Owens Thompson\n",
+      "\n",
+      "The iconic portrait that became the face of the Great Depression is also the most famous photograph in the collections of the Library of Congress.\n",
+      "\n",
+      "The Library holds the original source of the photo — a nitrate negative measuring 4 by 5 inches. Do you see a faint thumb in the bottom right? The photographer, Dorothea Lange, found the thumb distracting and after a few years had the negative altered to make the thumb almost invisible. Lange’s boss at the Farm Security Administration, Roy Stryker, criticized her action because altering a negative undermines the credibility of a documentary photo.\n",
+      "Shrimp Picker\n",
+      "\n",
+      "The photos and evocative captions of Lewis Hine served as source material for National Child Labor Committee reports and exhibits exposing abusive child labor practices in the United States in the first decades of the 20th century.\n",
+      "\n",
+      "LEWIS WICKES HINE. “MANUEL, THE YOUNG SHRIMP-PICKER, FIVE YEARS OLD, AND A MOUNTAIN OF CHILD-LABOR OYSTER SHELLS BEHIND HIM. HE WORKED LAST YEAR. UNDERSTANDS NOT A WORD OF ENGLISH. DUNBAR, LOPEZ, DUKATE COMPANY. LOCATION: BILOXI, MISSISSIPPI.” FEBRUARY 1911. NATIONAL CHILD LABOR COMMITTEE COLLECTION. PRINTS AND PHOTOGRAPHS DIVISION.\n",
+      "\n",
+      "For 15 years, Hine\n",
+      "\n",
+      "crisscrossed the country, documenting the practices of the worst offenders. His effective use of photography made him one of the committee's greatest publicists in the campaign for legislation to ban child labor.\n",
+      "\n",
+      "Hine was a master at taking photos that catch attention and convey a message and, in this photo, he framed Manuel in a setting that drove home the boy’s small size and unsafe environment.\n",
+      "\n",
+      "Captions on photos of other shrimp pickers emphasized their long working hours as well as one hazard of the job: The acid from the shrimp made pickers’ hands sore and “eats the shoes off your feet.”\n",
+      "\n",
+      "Such images alerted viewers to all that workers, their families and the nation sacrificed when children were part of the labor force. The Library holds paper records of the National Child Labor Committee as well as over 5,000 photographs.\n",
+      "\n",
+      "—Barbara Natanson is head of the Reference Section in the Prints and Photographs Division.\n",
+      "\n",
+      "8\n",
+      "\n",
+      "LIBRARY OF CONGRESS MAGAZINE\n",
+      "\n",
+      "LIBRARY OF CONGRESS MAGAZINE\n",
+      "\n",
+      "Intergenerational Portrait\n",
+      "\n",
+      "Raised on the Apsáalooke (Crow) reservation in Montana, photographer Wendy Red Star created her “Apsáalooke Feminist” self-portrait series with her daughter Beatrice. With a dash of wry humor, mother and daughter are their own first-person narrators.\n",
+      "\n",
+      "Red Star explains the significance of their appearance: “The dress has power: You feel strong and regal wearing it. In my art, the elk tooth dress specifically symbolizes Crow womanhood and the matrilineal line connecting me to my ancestors. As a mother, I spend hours searching for the perfect elk tooth dress materials to make a prized dress for my daughter.”\n",
+      "\n",
+      "In a world that struggles with cultural identities, this photograph shows us the power and beauty of blending traditional and contemporary styles.\n",
+      "‘American Gothic’ Product #216040262 Price: $24\n",
+      "\n",
+      "U.S. Capitol at Night Product #216040052 Price: $24\n",
+      "\n",
+      "Good Reading Ahead Product #21606142 Price: $24\n",
+      "\n",
+      "Gordon Parks created an iconic image with this 1942 photograph of cleaning woman Ella Watson.\n",
+      "\n",
+      "Snow blankets the U.S. Capitol in this classic image by Ernest L. Crandall.\n",
+      "\n",
+      "Start your new year out right with a poster promising good reading for months to come.\n",
+      "\n",
+      "▪ Order online: loc.gov/shop ▪ Order by phone: 888.682.3557\n",
+      "\n",
+      "26\n",
+      "\n",
+      "LIBRARY OF CONGRESS MAGAZINE\n",
+      "\n",
+      "LIBRARY OF CONGRESS MAGAZINE\n",
+      "\n",
+      "SUPPORT\n",
+      "\n",
+      "A PICTURE OF PHILANTHROPY Annenberg Foundation Gives $1 Million and a Photographic Collection to the Library.\n",
+      "\n",
+      "A major gift by Wallis Annenberg and the Annenberg Foundation in Los Angeles will support the effort to reimagine the visitor experience at the Library of Congress. The foundation also is donating 1,000 photographic prints from its Annenberg Space for Photography exhibitions to the Library.\n",
+      "\n",
+      "The Library is pursuing a multiyear plan to transform the experience of its nearly 2 million annual visitors, share more of its treasures with the public and show how Library collections connect with visitors’ own creativity and research. The project is part of a strategic plan established by Librarian of Congress Carla Hayden to make the Library more user-centered for Congress, creators and learners of all ages.\n",
+      "\n",
+      "A 2018 exhibition at the Annenberg Space for Photography in Los Angeles featured over 400 photographs from the Library. The Library is planning a future photography exhibition, based on the Annenberg-curated show, along with a documentary film on the Library and its history, produced by the Annenberg Space for Photography.\n",
+      "\n",
+      "“The nation’s library is honored to have the strong support of Wallis Annenberg and the Annenberg Foundation as we enhance the experience for our visitors,” Hayden said. “We know that visitors will find new connections to the Library through the incredible photography collections and countless other treasures held here to document our nation’s history and creativity.”\n",
+      "\n",
+      "To enhance the Library’s holdings, the foundation is giving the Library photographic prints for long-term preservation from 10 other exhibitions hosted at the Annenberg Space for Photography. The Library holds one of the world’s largest photography collections, with about 14 million photos and over 1 million images digitized and available online.\n",
+      "18  LIBRARY OF CONGRESS MAGAZINE\n"
+     ]
     }
    ],
    "source": [
@@ -452,6 +559,14 @@
     "        print(doc.page_content)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "15e9b54d",
+   "metadata": {},
+   "source": [
+    "Now let's use the `multi_modal_rag_chain` to process the same query and display the response."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 11,
@@ -462,10 +577,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1. Detailed description of the visual elements in the image: The image features a woman with children, likely a mother and her family, standing together outside. They appear to be poor or struggling financially, as indicated by their attire and surroundings.\n",
-      "2. Historical and cultural context of the image: The photo was taken in 1936 during the Great Depression, when many families struggled to make ends meet. Dorothea Lange, a renowned American photographer, took this iconic photograph that became an emblem of poverty and hardship experienced by many Americans at that time.\n",
-      "3. Interpretation of the image's symbolism and meaning: The image conveys a sense of unity and resilience despite adversity. The woman and her children are standing together, displaying their strength as a family unit in the face of economic challenges. The photograph also serves as a reminder of the importance of empathy and support for those who are struggling.\n",
-      "4. Connections between the image and the related text: The text provided offers additional context about the woman in the photo, her background, and her feelings towards the photograph. It highlights the historical backdrop of the Great Depression and emphasizes the significance of this particular image as a representation of that time period.\n"
+      " The image is a black and white photograph by Dorothea Lange titled \"Destitute Pea Pickers in California. Mother of Seven Children. Age Thirty-Two. Nipomo, California.\" It was taken in March 1936 as part of the Farm Security Administration-Office of War Information Collection.\n",
+      "\n",
+      "The photograph features a woman with seven children, who appear to be in a state of poverty and hardship. The woman is seated, looking directly at the camera, while three of her children are standing behind her. They all seem to be dressed in ragged clothing, indicative of their impoverished condition.\n",
+      "\n",
+      "The historical context of this image is related to the Great Depression, which was a period of economic hardship in the United States that lasted from 1929 to 1939. During this time, many people struggled to make ends meet, and poverty was widespread. This photograph captures the plight of one such family during this difficult period.\n",
+      "\n",
+      "The symbolism of the image is multifaceted. The woman's direct gaze at the camera can be seen as a plea for help or an expression of desperation. The ragged clothing of the children serves as a stark reminder of the poverty and hardship experienced by many during this time.\n",
+      "\n",
+      "In terms of connections to the related text, it is mentioned that Florence Owens Thompson, the woman in the photograph, initially regretted having her picture taken. However, she later came to appreciate the importance of the image as a representation of the struggles faced by many during the Great Depression. The mention of Helena Zinkham suggests that she may have played a role in the creation or distribution of this photograph.\n",
+      "\n",
+      "Overall, this image is a powerful depiction of poverty and hardship during the Great Depression, capturing the resilience and struggles of one family amidst difficult times. \n"
      ]
     }
    ],
@@ -494,17 +616,15 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8ba652da",
+   "cell_type": "markdown",
+   "id": "fe4a98ee",
    "metadata": {},
-   "outputs": [],
    "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".langchain-venv",
+   "display_name": ".test-venv",
    "language": "python",
    "name": "python3"
   },
@@ -518,7 +638,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.10"
   }
  },
  "nbformat": 4,

cookbook/nomic_embedding_rag.ipynb

@@ -71,9 +71,9 @@
     "# Optional: LangSmith API keys\n",
     "import os\n",
     "\n",
-    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
-    "os.environ[\"LANGCHAIN_API_KEY\"] = \"api_key\""
+    "os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+    "os.environ[\"LANGSMITH_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
+    "os.environ[\"LANGSMITH_API_KEY\"] = \"api_key\""
    ]
   },
   {
@@ -215,8 +215,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.chat_models import ChatOllama\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_ollama import ChatOllama\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
     "# Prompt\n",

cookbook/optimization.ipynb

@@ -29,7 +29,7 @@
    "source": [
     "import os\n",
     "\n",
-    "os.environ[\"LANGCHAIN_PROJECT\"] = \"movie-qa\""
+    "os.environ[\"LANGSMITH_PROJECT\"] = \"movie-qa\""
    ]
   },
   {

cookbook/oracleai_demo.ipynb

@@ -25,7 +25,7 @@
     " * [Oracle Blockchain](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_blockchain_table.html#GUID-B469E277-978E-4378-A8C1-26D3FF96C9A6)\n",
     " * [JSON](https://docs.oracle.com/en/database/oracle/oracle-database/23/adjsn/json-in-oracle-database.html)\n",
     "\n",
-    "This guide demonstrates how Oracle AI Vector Search can be used with Langchain to serve an end-to-end RAG pipeline. This guide goes through examples of:\n",
+    "This guide demonstrates how Oracle AI Vector Search can be used with LangChain to serve an end-to-end RAG pipeline. This guide goes through examples of:\n",
     "\n",
     " * Loading the documents from various sources using OracleDocLoader\n",
     " * Summarizing them within/outside the database using OracleSummary\n",
@@ -47,7 +47,19 @@
    "source": [
     "### Prerequisites\n",
     "\n",
-    "Please install Oracle Python Client driver to use Langchain with Oracle AI Vector Search. "
+    "Please install the Oracle Database [python-oracledb driver](https://pypi.org/project/oracledb/) to use LangChain with Oracle AI Vector Search:\n",
+    "\n",
+    "```\n",
+    "$ python -m pip install --upgrade oracledb\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create Demo User\n",
+    "First, connect as a privileged user to create a demo user with all the required privileges. Change the credentials for your environment. Also set the DEMO_PY_DIR path to a directory on the database host where your model file is located:"
    ]
   },
   {
@@ -56,65 +68,30 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# pip install oracledb"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Demo User\n",
-    "First, create a demo user with all the required privileges. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "User setup done!\n"
-     ]
-    }
-   ],
-   "source": [
-    "import sys\n",
-    "\n",
     "import oracledb\n",
     "\n",
-    "# Update with your username, password, hostname, and service_name\n",
-    "username = \"\"\n",
+    "# Please update with your SYSTEM (or privileged user) username, password, and database connection string\n",
+    "username = \"SYSTEM\"\n",
     "password = \"\"\n",
     "dsn = \"\"\n",
     "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
+    "with oracledb.connect(user=username, password=password, dsn=dsn) as connection:\n",
     "    print(\"Connection successful!\")\n",
     "\n",
-    "    cursor = conn.cursor()\n",
-    "    try:\n",
+    "    with connection.cursor() as cursor:\n",
     "        cursor.execute(\n",
     "            \"\"\"\n",
     "            begin\n",
     "                -- Drop user\n",
-    "                begin\n",
-    "                    execute immediate 'drop user testuser cascade';\n",
-    "                exception\n",
-    "                    when others then\n",
-    "                        dbms_output.put_line('Error dropping user: ' || SQLERRM);\n",
-    "                end;\n",
-    "                \n",
+    "                execute immediate 'drop user if exists testuser cascade';\n",
+    "\n",
     "                -- Create user and grant privileges\n",
     "                execute immediate 'create user testuser identified by testuser';\n",
     "                execute immediate 'grant connect, unlimited tablespace, create credential, create procedure, create any index to testuser';\n",
-    "                execute immediate 'create or replace directory DEMO_PY_DIR as ''/scratch/hroy/view_storage/hroy_devstorage/demo/orachain''';\n",
+    "                execute immediate 'create or replace directory DEMO_PY_DIR as ''/home/yourname/demo/orachain''';\n",
     "                execute immediate 'grant read, write on directory DEMO_PY_DIR to public';\n",
     "                execute immediate 'grant create mining model to testuser';\n",
-    "                \n",
+    "\n",
     "                -- Network access\n",
     "                begin\n",
     "                    DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
@@ -127,15 +104,7 @@
     "            end;\n",
     "            \"\"\"\n",
     "        )\n",
-    "        print(\"User setup done!\")\n",
-    "    except Exception as e:\n",
-    "        print(f\"User setup failed with error: {e}\")\n",
-    "    finally:\n",
-    "        cursor.close()\n",
-    "    conn.close()\n",
-    "except Exception as e:\n",
-    "    print(f\"Connection failed with error: {e}\")\n",
-    "    sys.exit(1)"
+    "        print(\"User setup done!\")"
    ]
   },
   {
@@ -143,13 +112,13 @@
    "metadata": {},
    "source": [
     "## Process Documents using Oracle AI\n",
-    "Consider the following scenario: users possess documents stored either in an Oracle Database or a file system and intend to utilize this data with Oracle AI Vector Search powered by Langchain.\n",
+    "Consider the following scenario: users possess documents stored either in an Oracle Database or a file system and intend to utilize this data with Oracle AI Vector Search powered by LangChain.\n",
     "\n",
     "To prepare the documents for analysis, a comprehensive preprocessing workflow is necessary. Initially, the documents must be retrieved, summarized (if required), and chunked as needed. Subsequent steps involve generating embeddings for these chunks and integrating them into the Oracle AI Vector Store. Users can then conduct semantic searches on this data.\n",
     "\n",
-    "The Oracle AI Vector Search Langchain library encompasses a suite of document processing tools that facilitate document loading, chunking, summary generation, and embedding creation.\n",
+    "The Oracle AI Vector Search LangChain library encompasses a suite of document processing tools that facilitate document loading, chunking, summary generation, and embedding creation.\n",
     "\n",
-    "In the sections that follow, we will detail the utilization of Oracle AI Langchain APIs to effectively implement each of these processes."
+    "In the sections that follow, we will detail the utilization of Oracle AI LangChain APIs to effectively implement each of these processes."
    ]
   },
   {
@@ -157,38 +126,24 @@
    "metadata": {},
    "source": [
     "### Connect to Demo User\n",
-    "The following sample code will show how to connect to Oracle Database. By default, python-oracledb runs in a ‘Thin’ mode which connects directly to Oracle Database. This mode does not need Oracle Client libraries. However, some additional functionality is available when python-oracledb uses them. Python-oracledb is said to be in ‘Thick’ mode when Oracle Client libraries are used. Both modes have comprehensive functionality supporting the Python Database API v2.0 Specification. See the following [guide](https://python-oracledb.readthedocs.io/en/latest/user_guide/appendix_a.html#featuresummary) that talks about features supported in each mode. You might want to switch to thick-mode if you are unable to use thin-mode."
+    "The following sample code shows how to connect to Oracle Database using the python-oracledb driver. By default, python-oracledb runs in a ‘Thin’ mode which connects directly to Oracle Database. This mode does not need Oracle Client libraries. However, some additional functionality is available when python-oracledb uses them. Python-oracledb is said to be in ‘Thick’ mode when Oracle Client libraries are used. Both modes have comprehensive functionality supporting the Python Database API v2.0 Specification. See the following [guide](https://python-oracledb.readthedocs.io/en/latest/user_guide/appendix_a.html#featuresummary) that talks about features supported in each mode. You can switch to Thick mode if you are unable to use Thin mode."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "import sys\n",
-    "\n",
     "import oracledb\n",
     "\n",
-    "# please update with your username, password, hostname and service_name\n",
-    "username = \"\"\n",
+    "# please update with your username, password, and database connection string\n",
+    "username = \"testuser\"\n",
     "password = \"\"\n",
     "dsn = \"\"\n",
     "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)"
+    "connection = oracledb.connect(user=username, password=password, dsn=dsn)\n",
+    "print(\"Connection successful!\")"
    ]
   },
   {
@@ -201,22 +156,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Table created and populated.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
-    "\n",
-    "    drop_table_sql = \"\"\"drop table demo_tab\"\"\"\n",
+    "with connection.cursor() as cursor:\n",
+    "    drop_table_sql = \"\"\"drop table if exists demo_tab\"\"\"\n",
     "    cursor.execute(drop_table_sql)\n",
     "\n",
     "    create_table_sql = \"\"\"create table demo_tab (id number, data clob)\"\"\"\n",
@@ -239,15 +184,9 @@
     "    ]\n",
     "    cursor.executemany(insert_row_sql, rows_to_insert)\n",
     "\n",
-    "    conn.commit()\n",
+    "connection.commit()\n",
     "\n",
-    "    print(\"Table created and populated.\")\n",
-    "    cursor.close()\n",
-    "except Exception as e:\n",
-    "    print(\"Table creation failed.\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
-    "    sys.exit(1)"
+    "print(\"Table created and populated.\")"
    ]
   },
   {
@@ -261,30 +200,22 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Load ONNX Model\n",
+    "### Load the ONNX Model\n",
     "\n",
-    "Oracle accommodates a variety of embedding providers, enabling users to choose between proprietary database solutions and third-party services such as OCIGENAI and HuggingFace. This selection dictates the methodology for generating and managing embeddings.\n",
+    "Oracle accommodates a variety of embedding providers, enabling you to choose between proprietary database solutions and third-party services such as Oracle Generative AI Service and HuggingFace. This selection dictates the methodology for generating and managing embeddings.\n",
     "\n",
-    "***Important*** : Should users opt for the database option, they must upload an ONNX model into the Oracle Database. Conversely, if a third-party provider is selected for embedding generation, uploading an ONNX model to Oracle Database is not required.\n",
+    "***Important*** : Should you opt for the database option, you must upload an ONNX model into the Oracle Database. Conversely, if a third-party provider is selected for embedding generation, uploading an ONNX model to Oracle Database is not required.\n",
     "\n",
-    "A significant advantage of utilizing an ONNX model directly within Oracle is the enhanced security and performance it offers by eliminating the need to transmit data to external parties. Additionally, this method avoids the latency typically associated with network or REST API calls.\n",
+    "A significant advantage of utilizing an ONNX model directly within Oracle Database is the enhanced security and performance it offers by eliminating the need to transmit data to external parties. Additionally, this method avoids the latency typically associated with network or REST API calls.\n",
     "\n",
     "Below is the example code to upload an ONNX model into Oracle Database:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ONNX model loaded.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
     "\n",
@@ -294,12 +225,8 @@
     "onnx_file = \"tinybert.onnx\"\n",
     "model_name = \"demo_model\"\n",
     "\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
-    "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)"
+    "OracleEmbeddings.load_onnx_model(connection, onnx_dir, onnx_file, model_name)\n",
+    "print(\"ONNX model loaded.\")"
    ]
   },
   {
@@ -321,8 +248,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
+    "with connection.cursor() as cursor:\n",
     "    cursor.execute(\n",
     "        \"\"\"\n",
     "       declare\n",
@@ -349,12 +275,7 @@
     "               params            => json(jo.to_string));\n",
     "       end;\n",
     "       \"\"\"\n",
-    "    )\n",
-    "    cursor.close()\n",
-    "    print(\"Credentials created.\")\n",
-    "except Exception as ex:\n",
-    "    cursor.close()\n",
-    "    raise"
+    "    )"
    ]
   },
   {
@@ -362,33 +283,24 @@
    "metadata": {},
    "source": [
     "### Load Documents\n",
-    "Users have the flexibility to load documents from either the Oracle Database, a file system, or both, by appropriately configuring the loader parameters. For comprehensive details on these parameters, please consult the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-73397E89-92FB-48ED-94BB-1AD960C4EA1F).\n",
+    "You have the flexibility to load documents from either the Oracle Database, a file system, or both, by appropriately configuring the loader parameters. For comprehensive details on these parameters, please consult the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-73397E89-92FB-48ED-94BB-1AD960C4EA1F).\n",
     "\n",
     "A significant advantage of utilizing OracleDocLoader is its capability to process over 150 distinct file formats, eliminating the need for multiple loaders for different document types. For a complete list of the supported formats, please refer to the [Oracle Text Supported Document Formats](https://docs.oracle.com/en/database/oracle/oracle-database/23/ccref/oracle-text-supported-document-formats.html).\n",
     "\n",
-    "Below is a sample code snippet that demonstrates how to use OracleDocLoader"
+    "Below is a sample code snippet that demonstrates how to use OracleDocLoader:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of docs loaded: 3\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.document_loaders.oracleai import OracleDocLoader\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "# loading from Oracle Database table\n",
     "# make sure you have the table with this specification\n",
-    "loader_params = {}\n",
     "loader_params = {\n",
     "    \"owner\": \"testuser\",\n",
     "    \"tablename\": \"demo_tab\",\n",
@@ -396,7 +308,7 @@
     "}\n",
     "\n",
     "\"\"\" load the docs \"\"\"\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
+    "loader = OracleDocLoader(conn=connection, params=loader_params)\n",
     "docs = loader.load()\n",
     "\n",
     "\"\"\" verify \"\"\"\n",
@@ -409,23 +321,23 @@
    "metadata": {},
    "source": [
     "### Generate Summary\n",
-    "Now that the user loaded the documents, they may want to generate a summary for each document. The Oracle AI Vector Search Langchain library offers a suite of APIs designed for document summarization. It supports multiple summarization providers such as Database, OCIGENAI, HuggingFace, among others, allowing users to select the provider that best meets their needs. To utilize these capabilities, users must configure the summary parameters as specified. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-EC9DDB58-6A15-4B36-BA66-ECBA20D2CE57)."
+    "Now that you have loaded the documents, you may want to generate a summary for each document. The Oracle AI Vector Search LangChain library offers a suite of APIs designed for document summarization. It supports multiple summarization providers such as Database, Oracle Generative AI Service, HuggingFace, among others, allowing you to select the provider that best meets their needs. To utilize these capabilities, you must configure the summary parameters as specified. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-EC9DDB58-6A15-4B36-BA66-ECBA20D2CE57)."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "***Note:*** The users may need to set proxy if they want to use some 3rd party summary generation providers other than Oracle's in-house and default provider: 'database'. If you don't have proxy, please remove the proxy parameter when you instantiate the OracleSummary."
+    "***Note:*** You may need to set proxy if you want to use some 3rd party summary generation providers other than Oracle's in-house and default provider: 'database'. If you don't have proxy, please remove the proxy parameter when you instantiate the OracleSummary."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# proxy to be used when we instantiate summary and embedder object\n",
+    "# proxy to be used when we instantiate summary and embedder objects\n",
     "proxy = \"\""
    ]
   },
@@ -433,22 +345,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The following sample code will show how to generate summary:"
+    "The following sample code shows how to generate a summary:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Summaries: 3\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.utilities.oracleai import OracleSummary\n",
     "from langchain_core.documents import Document\n",
@@ -463,7 +367,7 @@
     "\n",
     "# get the summary instance\n",
     "# Remove proxy if not required\n",
-    "summ = OracleSummary(conn=conn, params=summary_params, proxy=proxy)\n",
+    "summ = OracleSummary(conn=connection, params=summary_params, proxy=proxy)\n",
     "\n",
     "list_summary = []\n",
     "for doc in docs:\n",
@@ -487,17 +391,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Chunks: 3\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.document_loaders.oracleai import OracleTextSplitter\n",
     "from langchain_core.documents import Document\n",
@@ -506,7 +402,7 @@
     "splitter_params = {\"normalize\": \"all\"}\n",
     "\n",
     "\"\"\" get the splitter instance \"\"\"\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
+    "splitter = OracleTextSplitter(conn=connection, params=splitter_params)\n",
     "\n",
     "list_chunks = []\n",
     "for doc in docs:\n",
@@ -523,19 +419,19 @@
    "metadata": {},
    "source": [
     "### Generate Embeddings\n",
-    "Now that the documents are chunked as per requirements, the users may want to generate embeddings for these chunks. Oracle AI Vector Search provides multiple methods for generating embeddings, utilizing either locally hosted ONNX models or third-party APIs. For comprehensive instructions on configuring these alternatives, please refer to the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-C6439E94-4E86-4ECD-954E-4B73D53579DE)."
+    "Now that the documents are chunked as per requirements, you may want to generate embeddings for these chunks. Oracle AI Vector Search provides multiple methods for generating embeddings, utilizing either locally hosted ONNX models or third-party APIs. For comprehensive instructions on configuring these alternatives, please refer to the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-C6439E94-4E86-4ECD-954E-4B73D53579DE)."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "***Note:*** Users may need to configure a proxy to utilize third-party embedding generation providers, excluding the 'database' provider that utilizes an ONNX model."
+    "***Note:*** You may need to configure a proxy to utilize third-party embedding generation providers, excluding the 'database' provider that utilizes an ONNX model."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -547,22 +443,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The following sample code will show how to generate embeddings:"
+    "The following sample code shows how to generate embeddings:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of embeddings: 3\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
     "from langchain_core.documents import Document\n",
@@ -572,7 +460,7 @@
     "\n",
     "# get the embedding instance\n",
     "# Remove proxy if not required\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params, proxy=proxy)\n",
+    "embedder = OracleEmbeddings(conn=connection, params=embedder_params, proxy=proxy)\n",
     "\n",
     "embeddings = []\n",
     "for doc in docs:\n",
@@ -591,19 +479,19 @@
    "metadata": {},
    "source": [
     "## Create Oracle AI Vector Store\n",
-    "Now that you know how to use Oracle AI Langchain library APIs individually to process the documents, let us show how to integrate with Oracle AI Vector Store to facilitate the semantic searches."
+    "Now that you know how to use Oracle AI LangChain library APIs individually to process the documents, let us show how to integrate with Oracle AI Vector Store to facilitate the semantic searches."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "First, let's import all the dependencies."
+    "First, let's import all the dependencies:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 52,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -626,100 +514,80 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Next, let's combine all document processing stages together. Here is the sample code below:"
+    "Next, let's combine all document processing stages together. Here is the sample code:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 53,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "ONNX model loaded.\n",
-      "Number of total chunks with metadata: 3\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "\"\"\"\n",
-    "In this sample example, we will use 'database' provider for both summary and embeddings.\n",
-    "So, we don't need to do the followings:\n",
+    "In this sample example, we will use 'database' provider for both summary and embeddings\n",
+    "so, we don't need to do the following:\n",
     "    - set proxy for 3rd party providers\n",
     "    - create credential for 3rd party providers\n",
     "\n",
-    "If you choose to use 3rd party provider, \n",
-    "please follow the necessary steps for proxy and credential.\n",
+    "If you choose to use 3rd party provider, please follow the necessary steps for proxy and credential.\n",
     "\"\"\"\n",
     "\n",
-    "# oracle connection\n",
-    "# please update with your username, password, hostname, and service_name\n",
+    "# please update with your username, password, and database connection string\n",
     "username = \"\"\n",
     "password = \"\"\n",
     "dsn = \"\"\n",
     "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
+    "with oracledb.connect(user=username, password=password, dsn=dsn) as connection:\n",
     "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)\n",
     "\n",
-    "\n",
-    "# load onnx model\n",
-    "# please update with your related information\n",
-    "onnx_dir = \"DEMO_PY_DIR\"\n",
-    "onnx_file = \"tinybert.onnx\"\n",
-    "model_name = \"demo_model\"\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
+    "    # load onnx model\n",
+    "    # please update with your related information\n",
+    "    onnx_dir = \"DEMO_PY_DIR\"\n",
+    "    onnx_file = \"tinybert.onnx\"\n",
+    "    model_name = \"demo_model\"\n",
+    "    OracleEmbeddings.load_onnx_model(connection, onnx_dir, onnx_file, model_name)\n",
     "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)\n",
     "\n",
+    "    # params\n",
+    "    # please update necessary fields with related information\n",
+    "    loader_params = {\n",
+    "        \"owner\": \"testuser\",\n",
+    "        \"tablename\": \"demo_tab\",\n",
+    "        \"colname\": \"data\",\n",
+    "    }\n",
+    "    summary_params = {\n",
+    "        \"provider\": \"database\",\n",
+    "        \"glevel\": \"S\",\n",
+    "        \"numParagraphs\": 1,\n",
+    "        \"language\": \"english\",\n",
+    "    }\n",
+    "    splitter_params = {\"normalize\": \"all\"}\n",
+    "    embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
     "\n",
-    "# params\n",
-    "# please update necessary fields with related information\n",
-    "loader_params = {\n",
-    "    \"owner\": \"testuser\",\n",
-    "    \"tablename\": \"demo_tab\",\n",
-    "    \"colname\": \"data\",\n",
-    "}\n",
-    "summary_params = {\n",
-    "    \"provider\": \"database\",\n",
-    "    \"glevel\": \"S\",\n",
-    "    \"numParagraphs\": 1,\n",
-    "    \"language\": \"english\",\n",
-    "}\n",
-    "splitter_params = {\"normalize\": \"all\"}\n",
-    "embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
+    "    # instantiate loader, summary, splitter, and embedder\n",
+    "    loader = OracleDocLoader(conn=connection, params=loader_params)\n",
+    "    summary = OracleSummary(conn=connection, params=summary_params)\n",
+    "    splitter = OracleTextSplitter(conn=connection, params=splitter_params)\n",
+    "    embedder = OracleEmbeddings(conn=connection, params=embedder_params)\n",
     "\n",
-    "# instantiate loader, summary, splitter, and embedder\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
-    "summary = OracleSummary(conn=conn, params=summary_params)\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params)\n",
+    "    # process the documents\n",
+    "    chunks_with_mdata = []\n",
+    "    for id, doc in enumerate(docs, start=1):\n",
+    "        summ = summary.get_summary(doc.page_content)\n",
+    "        chunks = splitter.split_text(doc.page_content)\n",
+    "        for ic, chunk in enumerate(chunks, start=1):\n",
+    "            chunk_metadata = doc.metadata.copy()\n",
+    "            chunk_metadata[\"id\"] = (\n",
+    "                chunk_metadata[\"_oid\"] + \"$\" + str(id) + \"$\" + str(ic)\n",
+    "            )\n",
+    "            chunk_metadata[\"document_id\"] = str(id)\n",
+    "            chunk_metadata[\"document_summary\"] = str(summ[0])\n",
+    "            chunks_with_mdata.append(\n",
+    "                Document(page_content=str(chunk), metadata=chunk_metadata)\n",
+    "            )\n",
     "\n",
-    "# process the documents\n",
-    "chunks_with_mdata = []\n",
-    "for id, doc in enumerate(docs, start=1):\n",
-    "    summ = summary.get_summary(doc.page_content)\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    for ic, chunk in enumerate(chunks, start=1):\n",
-    "        chunk_metadata = doc.metadata.copy()\n",
-    "        chunk_metadata[\"id\"] = chunk_metadata[\"_oid\"] + \"$\" + str(id) + \"$\" + str(ic)\n",
-    "        chunk_metadata[\"document_id\"] = str(id)\n",
-    "        chunk_metadata[\"document_summary\"] = str(summ[0])\n",
-    "        chunks_with_mdata.append(\n",
-    "            Document(page_content=str(chunk), metadata=chunk_metadata)\n",
-    "        )\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of total chunks with metadata: {len(chunks_with_mdata)}\")"
+    "    \"\"\" verify \"\"\"\n",
+    "    print(f\"Number of total chunks with metadata: {len(chunks_with_mdata)}\")"
    ]
   },
   {
@@ -733,23 +601,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Vector Store Table: oravs\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "# create Oracle AI Vector Store\n",
     "vectorstore = OracleVS.from_documents(\n",
     "    chunks_with_mdata,\n",
     "    embedder,\n",
-    "    client=conn,\n",
+    "    client=connection,\n",
     "    table_name=\"oravs\",\n",
     "    distance_strategy=DistanceStrategy.DOT_PRODUCT,\n",
     ")\n",
@@ -778,12 +638,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 56,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "oraclevs.create_index(\n",
-    "    conn, vectorstore, params={\"idx_name\": \"hnsw_oravs\", \"idx_type\": \"HNSW\"}\n",
+    "    connection, vectorstore, params={\"idx_name\": \"hnsw_oravs\", \"idx_type\": \"HNSW\"}\n",
     ")\n",
     "\n",
     "print(\"Index created.\")"
@@ -793,7 +653,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This example demonstrates the creation of a default HNSW index on embeddings within the 'oravs' table. Users may adjust various parameters according to their specific needs. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/vecse/manage-different-categories-vector-indexes.html).\n",
+    "This example demonstrates the creation of a default HNSW index on embeddings within the 'oravs' table. You may adjust various parameters according to your specific needs. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/vecse/manage-different-categories-vector-indexes.html).\n",
     "\n",
     "Additionally, various types of vector indices can be created to meet diverse requirements. More details can be found in our [comprehensive guide](https://python.langchain.com/v0.1/docs/integrations/vectorstores/oracle/).\n"
    ]
@@ -805,29 +665,16 @@
     "## Perform Semantic Search\n",
     "All set!\n",
     "\n",
-    "We have successfully processed the documents and stored them in the vector store, followed by the creation of an index to enhance query performance. We are now prepared to proceed with semantic searches.\n",
+    "You have successfully processed the documents and stored them in the vector store, followed by the creation of an index to enhance query performance. You are now prepared to proceed with semantic searches.\n",
     "\n",
     "Below is the sample code for this process:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'})]\n",
-      "[]\n",
-      "[(Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'}), 0.055675752460956573)]\n",
-      "[]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "query = \"What is Oracle AI Vector Store?\"\n",
     "filter = {\"document_id\": [\"1\"]}\n",
@@ -872,7 +719,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.13.3"
   }
  },
  "nbformat": 4,

cookbook/rag-locally-on-intel-cpu.ipynb

@@ -647,7 +647,7 @@
    "metadata": {},
    "source": [
     "**Now we see the results are correct as it is mentioned in earnings release.** <br>\n",
-    "**To further automate, we will create a chain that will take input as question and retriever so that we don't need to retrieve documents seperately**"
+    "**To further automate, we will create a chain that will take input as question and retriever so that we don't need to retrieve documents separately**"
    ]
   },
   {
@@ -734,9 +734,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "rag-on-intel",
+   "display_name": "Python 3.11.1 64-bit",
    "language": "python",
-   "name": "rag-on-intel"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -748,7 +748,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "1a1af0ee75eeea9e2e1ee996c87e7a2b11a0bebd85af04bb136d915cefc0abce"
+   }
   }
  },
  "nbformat": 4,

cookbook/rag_upstage_document_parse_groundedness_check.ipynb

@@ -0,0 +1,82 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# RAG using Upstage Document Parse and Groundedness Check\n",
+    "This example illustrates RAG using [Upstage](https://python.langchain.com/docs/integrations/providers/upstage/) Document Parse and Groundedness Check."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import List\n",
+    "\n",
+    "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_core.runnables.base import RunnableSerializable\n",
+    "from langchain_upstage import (\n",
+    "    ChatUpstage,\n",
+    "    UpstageDocumentParseLoader,\n",
+    "    UpstageEmbeddings,\n",
+    "    UpstageGroundednessCheck,\n",
+    ")\n",
+    "\n",
+    "model = ChatUpstage()\n",
+    "\n",
+    "files = [\"/PATH/TO/YOUR/FILE.pdf\", \"/PATH/TO/YOUR/FILE2.pdf\"]\n",
+    "\n",
+    "loader = UpstageDocumentParseLoader(file_path=files, split=\"element\")\n",
+    "\n",
+    "docs = loader.load()\n",
+    "\n",
+    "vectorstore = DocArrayInMemorySearch.from_documents(\n",
+    "    docs, embedding=UpstageEmbeddings(model=\"solar-embedding-1-large\")\n",
+    ")\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "\n",
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "output_parser = StrOutputParser()\n",
+    "\n",
+    "retrieved_docs = retriever.get_relevant_documents(\"How many parameters in SOLAR model?\")\n",
+    "\n",
+    "groundedness_check = UpstageGroundednessCheck()\n",
+    "groundedness = \"\"\n",
+    "while groundedness != \"grounded\":\n",
+    "    chain: RunnableSerializable = RunnablePassthrough() | prompt | model | output_parser\n",
+    "\n",
+    "    result = chain.invoke(\n",
+    "        {\n",
+    "            \"context\": retrieved_docs,\n",
+    "            \"question\": \"How many parameters in SOLAR model?\",\n",
+    "        }\n",
+    "    )\n",
+    "\n",
+    "    groundedness = groundedness_check.invoke(\n",
+    "        {\n",
+    "            \"context\": retrieved_docs,\n",
+    "            \"answer\": result,\n",
+    "        }\n",
+    "    )"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/rag_upstage_layout_analysis_groundedness_check.ipynb

@@ -1,82 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# RAG using Upstage Layout Analysis and Groundedness Check\n",
-    "This example illustrates RAG using [Upstage](https://python.langchain.com/docs/integrations/providers/upstage/) Layout Analysis and Groundedness Check."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from typing import List\n",
-    "\n",
-    "from langchain_community.vectorstores import DocArrayInMemorySearch\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_core.runnables.base import RunnableSerializable\n",
-    "from langchain_upstage import (\n",
-    "    ChatUpstage,\n",
-    "    UpstageEmbeddings,\n",
-    "    UpstageGroundednessCheck,\n",
-    "    UpstageLayoutAnalysisLoader,\n",
-    ")\n",
-    "\n",
-    "model = ChatUpstage()\n",
-    "\n",
-    "files = [\"/PATH/TO/YOUR/FILE.pdf\", \"/PATH/TO/YOUR/FILE2.pdf\"]\n",
-    "\n",
-    "loader = UpstageLayoutAnalysisLoader(file_path=files, split=\"element\")\n",
-    "\n",
-    "docs = loader.load()\n",
-    "\n",
-    "vectorstore = DocArrayInMemorySearch.from_documents(\n",
-    "    docs, embedding=UpstageEmbeddings(model=\"solar-embedding-1-large\")\n",
-    ")\n",
-    "retriever = vectorstore.as_retriever()\n",
-    "\n",
-    "template = \"\"\"Answer the question based only on the following context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "output_parser = StrOutputParser()\n",
-    "\n",
-    "retrieved_docs = retriever.get_relevant_documents(\"How many parameters in SOLAR model?\")\n",
-    "\n",
-    "groundedness_check = UpstageGroundednessCheck()\n",
-    "groundedness = \"\"\n",
-    "while groundedness != \"grounded\":\n",
-    "    chain: RunnableSerializable = RunnablePassthrough() | prompt | model | output_parser\n",
-    "\n",
-    "    result = chain.invoke(\n",
-    "        {\n",
-    "            \"context\": retrieved_docs,\n",
-    "            \"question\": \"How many parameters in SOLAR model?\",\n",
-    "        }\n",
-    "    )\n",
-    "\n",
-    "    groundedness = groundedness_check.invoke(\n",
-    "        {\n",
-    "            \"context\": retrieved_docs,\n",
-    "            \"answer\": result,\n",
-    "        }\n",
-    "    )"
-   ]
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}

cookbook/rag_with_quantized_embeddings.ipynb

@@ -53,7 +53,7 @@
    "id": "f5ccda4e-7af5-4355-b9c4-25547edf33f9",
    "metadata": {},
    "source": [
-    "Lets first load up this paper, and split into text chunks of size 1000."
+    "Let's first load up this paper, and split into text chunks of size 1000."
    ]
   },
   {
@@ -241,7 +241,7 @@
    "id": "360b2837-8024-47e0-a4ba-592505a9a5c8",
    "metadata": {},
    "source": [
-    "With our embedder in place, lets define our retriever:"
+    "With our embedder in place, let's define our retriever:"
    ]
   },
   {
@@ -312,7 +312,7 @@
    "id": "d84ea8f4-a5de-4d76-b44d-85e56583f489",
    "metadata": {},
    "source": [
-    "Lets write our documents into our new store. This will use our embedder on each document."
+    "Let's write our documents into our new store. This will use our embedder on each document."
    ]
   },
   {
@@ -339,7 +339,7 @@
    "id": "580bc212-8ecd-4d28-8656-b96fcd0d7eb6",
    "metadata": {},
    "source": [
-    "Great! Our retriever is good to go. Lets load up an LLM, that will reason over the retrieved documents:"
+    "Great! Our retriever is good to go. Let's load up an LLM, that will reason over the retrieved documents:"
    ]
   },
   {
@@ -430,7 +430,7 @@
    "id": "3bc53602-86d6-420f-91b1-fc2effa7e986",
    "metadata": {},
    "source": [
-    "Excellent! lets ask it a question.\n",
+    "Excellent! Let's ask it a question.\n",
     "We will also use a verbose and debug, to check which documents were used by the model to produce the answer."
    ]
   },

cookbook/sql_db_qa.mdx

@@ -233,7 +233,7 @@ Question: {input}"""
 
 _DEFAULT_TEMPLATE = """Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer. Unless the user specifies in his question a specific number of examples he wishes to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.
 
-Never query for all the columns from a specific table, only ask for a the few relevant columns given the question.
+Never query for all the columns from a specific table, only ask for a few relevant columns given the question.
 
 Pay attention to use only the column names that you can see in the schema description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
 

cookbook/visual_RAG_vdms.ipynb

@@ -26,7 +26,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "2e44b44201c8778b462342ac97f5ccf05a4e02aa8a04505ecde97bf20dcc4cbb\n"
+      "76e78b89cee4d6d31154823f93592315df79c28410dfbfc87c9f70cbfdfa648b\n"
      ]
     }
    ],
@@ -49,7 +49,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install --quiet -U vdms langchain-experimental sentence-transformers opencv-python open_clip_torch torch accelerate"
+    "! pip install --quiet -U langchain-vdms langchain-experimental sentence-transformers opencv-python open_clip_torch torch accelerate"
    ]
   },
   {
@@ -63,7 +63,16 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/data1/cwlacewe/apps/cwlacewe_langchain/.langchain-venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
+      "  from .autonotebook import tqdm as notebook_tqdm\n"
+     ]
+    }
+   ],
    "source": [
     "import json\n",
     "import os\n",
@@ -80,10 +89,10 @@
     "from langchain_community.embeddings.sentence_transformer import (\n",
     "    SentenceTransformerEmbeddings,\n",
     ")\n",
-    "from langchain_community.vectorstores.vdms import VDMS, VDMS_Client\n",
     "from langchain_core.callbacks.manager import CallbackManagerForLLMRun\n",
     "from langchain_core.runnables import ConfigurableField\n",
     "from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
+    "from langchain_vdms.vectorstores import VDMS, VDMS_Client\n",
     "from transformers import (\n",
     "    AutoModelForCausalLM,\n",
     "    AutoTokenizer,\n",
@@ -363,7 +372,7 @@
       "\t\tThere are 2 shoppers in this video. Shopper 1 is wearing a plaid shirt and a spectacle. Shopper 2 who is not completely captured in the frame seems to wear a black shirt and is moving away with his back turned towards the camera. There is a shelf towards the right of the camera frame. Shopper 2 is hanging an item back to a hanger and then quickly walks away in a similar fashion as shopper 2. Contents of the nearer side of the shelf with respect to camera seems to be camping lanterns and cleansing agents, arranged at the top. In the middle part of the shelf, various tools including grommets, a pocket saw, candles, and other helpful camping items can be observed. Midway through the shelf contains items which appear to be steel containers and items made up of plastic with red, green, orange, and yellow colors, while those at the bottom are packed in cardboard boxes. Contents at the farther part of the shelf are well stocked and organized but are not glaringly visible.\n",
       "\n",
       "\tMetadata:\n",
-      "\t\t{'fps': 24.0, 'id': 'c6e5f894-b905-46f5-ac9e-4487a9235561', 'total_frames': 120.0, 'video': 'clip16.mp4'}\n",
+      "\t\t{'fps': 24.0, 'total_frames': 120.0, 'video': 'clip16.mp4'}\n",
       "Retrieved Top matching video!\n",
       "\n",
       "\n"
@@ -392,18 +401,12 @@
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3edf8783e114487ca490d8dec5c46884",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Loading checkpoint shards: 100%|██████████| 2/2 [00:18<00:00,  9.01s/it]\n",
+      "WARNING:accelerate.big_modeling:Some parameters are on the meta device because they were offloaded to the cpu.\n"
+     ]
     }
    ],
    "source": [
@@ -555,7 +558,7 @@
       "\t\tA single shopper is seen in this video standing facing the shelf and in the bottom part of the frame. He's wearing a light-colored shirt and a spectacle. The shopper is carrying a red colored basket in his left hand. The entire basket is not clearly visible, but it does seem to contain something in a blue colored package which the shopper has just placed in the basket given his right hand was seen inside the basket. Then the shopper leans towards the shelf and checks out an item in orange package. He picks this single item with his right hand and proceeds to place the item in the basket. The entire shelf looks well stocked except for the top part of the shelf which is empty. The shopper has not picked any item from this part of the shelf. The rest of the shelf looks well stocked and does not need any restocking. The contents on the farther part of the shelf consists of items, majority of which are packed in black, yellow, and green packages. No other details are visible of these items.\n",
       "\n",
       "\tMetadata:\n",
-      "\t\t{'fps': 24.0, 'id': '37ddc212-994e-4db0-877f-5ed09965ab90', 'total_frames': 162.0, 'video': 'clip10.mp4'}\n",
+      "\t\t{'fps': 24.0, 'total_frames': 162.0, 'video': 'clip10.mp4'}\n",
       "Retrieved Top matching video!\n",
       "\n",
       "\n"
@@ -585,7 +588,7 @@
       "User :  Find a man holding a red shopping basket\n",
       "Assistant :  Most relevant retrieved video is **clip9.mp4** \n",
       "\n",
-      "I see a person standing in front of a well-stocked shelf, they are wearing a light-colored shirt and glasses, and they have a red shopping basket in their left hand. They are leaning forward and picking up an item from the shelf with their right hand. The item is packaged in a blue-green box. Based on the scene description, I can confirm that the person is indeed holding a red shopping basket.</s>\n"
+      "I see a person standing in front of a well-stocked shelf, they are wearing a light-colored shirt and glasses, and they have a red shopping basket in their left hand. They are leaning forward and picking up an item from the shelf with their right hand. The item is packaged in a blue-green box. Based on the available information, I cannot confirm whether the basket is empty or contains items. However, the rest of the\n"
      ]
     }
    ],
@@ -655,7 +658,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": ".langchain-venv",
    "language": "python",
    "name": "python3"
   },
@@ -669,7 +672,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.11.10"
   }
  },
  "nbformat": 4,

cookbook/wikibase_agent.ipynb

@@ -144,8 +144,8 @@
    "outputs": [],
    "source": [
     "# import os\n",
-    "# os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\"\n",
-    "# os.environ[\"LANGCHAIN_SESSION\"] = \"default\" # Make sure this session actually exists."
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
+    "# os.environ[\"LANGSMITH_PROJECT\"] = \"default\" # Make sure this session actually exists."
    ]
   },
   {

docker/Dockerfile.base

@@ -1,3 +0,0 @@
-FROM python:3.11
-
-RUN pip install langchain

docker/Makefile

@@ -1,12 +0,0 @@
-# Makefile
-
-build_graphdb:
-	docker build --tag graphdb ./graphdb
-
-start_graphdb:
-	docker-compose up -d graphdb
-
-down:
-	docker-compose down -v --remove-orphans
-
-.PHONY: build_graphdb start_graphdb down

docker/docker-compose.yml

@@ -1,84 +0,0 @@
-# docker-compose to make it easier to spin up integration tests.
-# Services should use NON standard ports to avoid collision with
-# any existing services that might be used for development.
-# ATTENTION: When adding a service below use a non-standard port
-# increment by one from the preceding port.
-# For credentials always use `langchain` and `langchain` for the
-# username and password.
-version: "3"
-name: langchain-tests
-
-services:
-  redis:
-    image: redis/redis-stack-server:latest
-    # We use non standard ports since
-    # these instances are used for testing
-    # and users may already have existing
-    # redis instances set up locally
-    # for other projects
-    ports:
-      - "6020:6379"
-    volumes:
-      - ./redis-volume:/data
-  graphdb:
-    image: graphdb
-    ports:
-      - "6021:7200"
-  mongo:
-    image: mongo:latest
-    container_name: mongo_container
-    ports:
-      - "6022:27017"
-    environment:
-      MONGO_INITDB_ROOT_USERNAME: langchain
-      MONGO_INITDB_ROOT_PASSWORD: langchain
-  postgres:
-    image: postgres:16
-    environment:
-      POSTGRES_DB: langchain
-      POSTGRES_USER: langchain
-      POSTGRES_PASSWORD: langchain
-    ports:
-      - "6023:5432"
-    command: |
-      postgres -c log_statement=all
-    healthcheck:
-      test:
-        [
-          "CMD-SHELL",
-          "psql postgresql://langchain:langchain@localhost/langchain --command 'SELECT 1;' || exit 1",
-        ]
-      interval: 5s
-      retries: 60
-    volumes:
-      - postgres_data:/var/lib/postgresql/data
-  pgvector:
-    # postgres with the pgvector extension
-    image: ankane/pgvector
-    environment:
-      POSTGRES_DB: langchain
-      POSTGRES_USER: langchain
-      POSTGRES_PASSWORD: langchain
-    ports:
-      - "6024:5432"
-    command: |
-      postgres -c log_statement=all
-    healthcheck:
-      test:
-        [
-          "CMD-SHELL",
-          "psql postgresql://langchain:langchain@localhost/langchain --command 'SELECT 1;' || exit 1",
-        ]
-      interval: 5s
-      retries: 60
-    volumes:
-      - postgres_data_pgvector:/var/lib/postgresql/data
-  vdms:
-    image: intellabs/vdms:latest
-    container_name: vdms_container
-    ports:
-      - "6025:55555"
-
-volumes:
-  postgres_data:
-  postgres_data_pgvector:

docker/graphdb/Dockerfile

@@ -1,5 +0,0 @@
-FROM ontotext/graphdb:10.5.1
-RUN mkdir -p /opt/graphdb/dist/data/repositories/langchain
-COPY config.ttl /opt/graphdb/dist/data/repositories/langchain/
-COPY graphdb_create.sh /run.sh
-ENTRYPOINT bash /run.sh

docker/graphdb/config.ttl

@@ -1,46 +0,0 @@
-@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>.
-@prefix rep: <http://www.openrdf.org/config/repository#>.
-@prefix sr: <http://www.openrdf.org/config/repository/sail#>.
-@prefix sail: <http://www.openrdf.org/config/sail#>.
-@prefix graphdb: <http://www.ontotext.com/config/graphdb#>.
-
-[] a rep:Repository ;
-    rep:repositoryID "langchain" ;
-    rdfs:label "" ;
-    rep:repositoryImpl [
-        rep:repositoryType "graphdb:SailRepository" ;
-        sr:sailImpl [
-            sail:sailType "graphdb:Sail" ;
-
-            graphdb:read-only "false" ;
-
-            # Inference and Validation
-            graphdb:ruleset "empty" ;
-            graphdb:disable-sameAs "true" ;
-            graphdb:check-for-inconsistencies "false" ;
-
-            # Indexing
-            graphdb:entity-id-size "32" ;
-            graphdb:enable-context-index "false" ;
-            graphdb:enablePredicateList "true" ;
-            graphdb:enable-fts-index "false" ;
-            graphdb:fts-indexes ("default" "iri") ;
-            graphdb:fts-string-literals-index "default" ;
-            graphdb:fts-iris-index "none" ;
-
-            # Queries and Updates
-            graphdb:query-timeout "0" ;
-            graphdb:throw-QueryEvaluationException-on-timeout "false" ;
-            graphdb:query-limit-results "0" ;
-
-            # Settable in the file but otherwise hidden in the UI and in the RDF4J console
-            graphdb:base-URL "http://example.org/owlim#" ;
-            graphdb:defaultNS "" ;
-            graphdb:imports "" ;
-            graphdb:repository-type "file-repository" ;
-            graphdb:storage-folder "storage" ;
-            graphdb:entity-index-size "10000000" ;
-            graphdb:in-memory-literal-properties "true" ;
-            graphdb:enable-literal-index "true" ;
-        ]
-    ].

docker/graphdb/graphdb_create.sh

@@ -1,28 +0,0 @@
-#! /bin/bash
-REPOSITORY_ID="langchain"
-GRAPHDB_URI="http://localhost:7200/"
-
-echo -e "\nUsing GraphDB: ${GRAPHDB_URI}"
-
-function startGraphDB {
- echo -e "\nStarting GraphDB..."
- exec /opt/graphdb/dist/bin/graphdb
-}
-
-function waitGraphDBStart {
-  echo -e "\nWaiting GraphDB to start..."
-  for _ in $(seq 1 5); do
-    CHECK_RES=$(curl --silent --write-out '%{http_code}' --output /dev/null ${GRAPHDB_URI}/rest/repositories)
-    if [ "${CHECK_RES}" = '200' ]; then
-        echo -e "\nUp and running"
-        break
-    fi
-    sleep 30s
-    echo "CHECK_RES: ${CHECK_RES}"
-  done
-}
-
-
-startGraphDB &
-waitGraphDBStart
-wait

docs/Makefile

@@ -13,38 +13,34 @@ 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' ' ')
-
 PORT ?= 3001
 
 clean:
 	rm -rf build
 
 install-vercel-deps:
-	yum -y update
-	yum install gcc bzip2-devel libffi-devel zlib-devel wget tar gzip rsync -y
+	yum -y -q update
+	yum -y -q install gcc bzip2-devel libffi-devel zlib-devel wget tar gzip rsync -y
 
 install-py-deps:
 	python3 -m venv .venv
-	$(PYTHON) -m pip install --upgrade pip
-	$(PYTHON) -m pip install --upgrade uv
-	$(PYTHON) -m uv pip install -r vercel_requirements.txt
-	$(PYTHON) -m uv pip install --editable $(PARTNER_DEPS_LIST)
+	$(PYTHON) -m pip install -q --upgrade pip
+	$(PYTHON) -m pip install -q --upgrade uv
+	$(PYTHON) -m uv pip install -q --pre -r vercel_requirements.txt
+	$(PYTHON) -m uv pip install -q --pre $$($(PYTHON) scripts/partner_deps_list.py) --overrides vercel_overrides.txt
 
 generate-files:
 	mkdir -p $(INTERMEDIATE_DIR)
-	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
-	mkdir -p $(INTERMEDIATE_DIR)/templates
-
-	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
+	cp -rp $(SOURCE_DIR)/* $(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/copy_templates.py $(INTERMEDIATE_DIR)
+	$(PYTHON) scripts/partner_pkg_table.py $(INTERMEDIATE_DIR)
 
-	wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
+	curl https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md | sed 's/<=/\&lt;=/g' > $(INTERMEDIATE_DIR)/langserve.md
+	cp ../SECURITY.md $(INTERMEDIATE_DIR)/security.md
 	$(PYTHON) scripts/resolve_local_links.py $(INTERMEDIATE_DIR)/langserve.md https://github.com/langchain-ai/langserve/tree/main/
 
 copy-infra:
@@ -57,28 +53,35 @@ copy-infra:
 	cp package.json $(OUTPUT_NEW_DIR)
 	cp sidebars.js $(OUTPUT_NEW_DIR)
 	cp -r static $(OUTPUT_NEW_DIR)
+	cp -r ../libs/cli/langchain_cli/integration_template $(OUTPUT_NEW_DIR)/src/theme
 	cp yarn.lock $(OUTPUT_NEW_DIR)
 
 render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
 
 md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+	rsync -avmq --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
+
+append-related:
+	$(PYTHON) scripts/append_related_links.py $(OUTPUT_NEW_DOCS_DIR)
 
 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)
 
-build: install-py-deps generate-files copy-infra render md-sync
+update-md: generate-files md-sync
+
+build: install-py-deps generate-files copy-infra render md-sync append-related
 
 vercel-build: install-vercel-deps build generate-references
 	rm -rf docs
 	mv $(OUTPUT_NEW_DOCS_DIR) docs
+	cp -r ../libs/cli/langchain_cli/integration_template src/theme
 	rm -rf build
-	yarn run docusaurus build
-	mv build v0.2
-	mkdir build
-	mv v0.2 build
-	mv build/v0.2/404.html build
+	mkdir static/api_reference
+	git clone --depth=1 https://github.com/langchain-ai/langchain-api-docs-html.git
+	mv langchain-api-docs-html/api_reference_build/html/* static/api_reference/
+	rm -rf langchain-api-docs-html
+	NODE_OPTIONS="--max-old-space-size=5000" yarn run docusaurus build
 
 start:
 	cd $(OUTPUT_NEW_DIR) && yarn && yarn start --port=$(PORT)

docs/README.md

@@ -1,3 +1,3 @@
 # LangChain Documentation
 
-For more information on contributing to our documentation, see the [Documentation Contributing Guide](https://python.langchain.com/docs/contributing/documentation)
+For more information on contributing to our documentation, see the [Documentation Contributing Guide](https://python.langchain.com/docs/contributing/how_to/documentation)

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 +1,396 @@
-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;
+
+    --pst-icon-versionmodified-deprecated: var(--pst-icon-exclamation-triangle);
 }
 
-#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]), 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;
+  --pst-color-deprecated: #f47d2e;
+  --pst-color-deprecated-bg: #fff3e8;
 }
 
-table.longtable code {
-  white-space: normal;
+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;
+  --pst-color-deprecated: #b46f3e;
+  --pst-color-deprecated-bg: #341906;
+  /* 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;
 }
 
-table.longtable td {
-  max-width: 600px;
+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;
+}
+
+/* NOTE: @each {...} is like a for-loop
+ * https://sass-lang.com/documentation/at-rules/control/each
+ */
+html[data-theme=light] {
+  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;
+}
+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: max-content;  /* 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;
+
+  background-color: var(--pst-color-deprecated-bg);
+  border-color: var(--pst-color-deprecated);
+}
+
+span.versionmodified.deprecated:before {
+  color: var(--pst-color-deprecated);
+}
+
+.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

@@ -11,10 +11,13 @@
 import json
 import os
 import sys
+from datetime import datetime
 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,
@@ -24,7 +27,6 @@ from sphinx.util.docutils import SphinxDirective
 _DIR = Path(__file__).parent.absolute()
 sys.path.insert(0, os.path.abspath("."))
 sys.path.insert(0, os.path.abspath("../../libs/langchain"))
-sys.path.insert(0, os.path.abspath("../../libs/experimental"))
 
 with (_DIR.parents[1] / "libs" / "langchain" / "pyproject.toml").open("r") as f:
     data = toml.load(f)
@@ -60,26 +62,53 @@ 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)
+    app.connect("autodoc-skip-member", skip_private_members)
+
+
+def skip_private_members(app, what, name, obj, skip, options):
+    if skip:
+        return True
+    if hasattr(obj, "__doc__") and obj.__doc__ and ":private:" in obj.__doc__:
+        return True
+    if name == "__init__" and obj.__objclass__ is object:
+        # dont document default init
+        return True
+    return None
 
 
 # -- Project information -----------------------------------------------------
 
 project = "🦜🔗 LangChain"
-copyright = "2023, LangChain, Inc."
-author = "LangChain, Inc."
+copyright = f"{datetime.now().year}, 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 +124,14 @@ 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",
+    "sphinxcontrib.googleanalytics",
 ]
-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 +163,82 @@ 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": [],
 }
-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 +246,6 @@ 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 +255,7 @@ 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"]
@@ -182,6 +269,14 @@ html_show_sourcelink = False
 # Set canonical URL from the Read the Docs Domain
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "")
 
+googleanalytics_id = "G-9B66JQQH2F"
+
 # Tell Jinja2 templates the build is running on Read the Docs
 if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = True
+
+master_doc = "index"
+
+# If a signature’s length in characters exceeds 60,
+# each parameter within the signature will be displayed on an individual logical line
+maximum_signature_line_length = 60

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):
@@ -68,14 +72,21 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
     Returns:
         list: A list of loaded module objects.
     """
+
     classes_: List[ClassInfo] = []
     functions: List[FunctionInfo] = []
     module = importlib.import_module(module_path)
+
+    if ":private:" in (module.__doc__ or ""):
+        return ModuleMembers(classes_=[], functions=[])
+
     for name, type_ in inspect.getmembers(module):
         if not hasattr(type_, "__module__"):
             continue
         if type_.__module__ != module_path:
             continue
+        if ":private:" in (type_.__doc__ or ""):
+            continue
 
         if inspect.isclass(type_):
             # The type of the class is used to select a template
@@ -121,6 +132,7 @@ 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 +141,7 @@ 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 +246,7 @@ 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 +258,62 @@ 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}
+
+.. _{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 +321,26 @@ def _construct_doc(
     :no-members:
     :no-inherited-members:
 
+"""
+
+        index_autosummary += f"""
+:ref:`{package_namespace}_{module}`
+{'^' * (len(package_namespace) + len(module) + 8)}
 """
 
         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 +357,22 @@ 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 +382,80 @@ 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:
@@ -329,21 +467,30 @@ 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:
-    return (
-        package_name
-        if package_name == "langchain"
-        else f"langchain_{package_name.replace('-', '_')}"
-    )
+    """Returns the package name used.
+
+    Args:
+        package_name: Can be either "langchain" or "core" or "experimental".
+
+    Returns:
+        modified package_name: Can be either "langchain" or "langchain_{package_name}"
+    """
+    if package_name == "langchain":
+        return "langchain"
+    if package_name == "standard-tests":
+        return "langchain_tests"
+    return f"langchain_{package_name.replace('-', '_')}"
 
 
 def _package_dir(package_name: str = "langchain") -> Path:
@@ -355,6 +502,7 @@ def _package_dir(package_name: str = "langchain") -> Path:
         "core",
         "cli",
         "text-splitters",
+        "standard-tests",
     ):
         return ROOT_DIR / "libs" / package_name / _package_namespace(package_name)
     else:
@@ -380,17 +528,131 @@ def _get_package_version(package_dir: Path) -> str:
             "Aborting the build."
         )
         exit(1)
-    return pyproject["tool"]["poetry"]["version"]
+    try:
+        # uses uv
+        return pyproject["project"]["version"]
+    except KeyError:
+        # uses poetry
+        return pyproject["tool"]["poetry"]["version"]
 
 
 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 = {
+        "aws": "AWS",
+        "ai21": "AI21",
+        "ibm": "IBM",
+    }
+    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_)
+    doc = """# 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/).
+"""
+
+    if main_:
+        main_headers = [
+            " ".join(custom_names.get(x, x.title()) for x in dir_.split("-"))
+            for dir_ in main_
+        ]
+        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_)
+        )
+        doc += f"""## Base packages
+
+```{{gallery-grid}}
+:grid-columns: "1 2 2 3"
+
+{main_grid}
+```
+
+```{{toctree}}
+:maxdepth: 2
+:hidden:
+:caption: Base packages
+
+{main_tree}
+```
+"""
+    if integrations:
+        integration_headers = [
+            " ".join(
+                custom_names.get(x, x.title().replace("ai", "AI").replace("db", "DB"))
+                for x in dir_.split("-")
+            )
+            for dir_ in integrations
+        ]
+        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"""## 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:
@@ -400,7 +662,8 @@ def main(dirs: Optional[list] = None) -> None:
         dirs = [
             dir_
             for dir_ in os.listdir(ROOT_DIR / "libs")
-            if dir_ not in ("cli", "partners", "standard-tests")
+            if dir_ not in ("cli", "partners", "packages.yml")
+            and "pyproject.toml" in os.listdir(ROOT_DIR / "libs" / dir_)
         ]
         dirs += [
             dir_
@@ -418,6 +681,8 @@ 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 +1,12 @@
--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>=2,<3
+sphinx>=8,<9
+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
+sphinxcontrib-googleanalytics

docs/api_reference/scripts/custom_formatter.py

@@ -0,0 +1,44 @@
+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:
+        try:
+            element = element.a.code.span
+        except Exception:
+            continue
+        # 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 }}
@@ -15,7 +15,7 @@
     :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, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace
+    :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, to_json_not_implemented, lc_secrets, lc_attributes, lc_id, get_lc_namespace, model_construct, model_copy, model_dump, model_dump_json, model_parametrized_name, model_post_init, model_rebuild, model_validate, model_validate_json, model_validate_strings, model_extra, model_fields_set, model_json_schema
 
 
     {% block attributes %}

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_config <langchain_core.runnables.base.Runnable.with_config>`, :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, InputType, OutputType, config_specs, output_schema, get_input_schema, get_graph, get_name, input_schema, name, assign, as_tool, get_config_jsonschema, get_input_jsonschema, get_output_jsonschema, model_construct, model_copy, model_dump, model_dump_json, model_parametrized_name, model_post_init, model_rebuild, model_validate, model_validate_json, model_validate_strings, to_json, model_extra, model_fields_set, model_json_schema, predict, apredict, predict_messages, apredict_messages, generate, generate_prompt, agenerate, agenerate_prompt, call_as_llm
+
+    .. 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_config <langchain_core.runnables.base.Runnable.with_config>`, :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 }}