langchain[patch]: release 0.3.8 (#28315)

pydantic compat 2.10 for langchain

.devcontainer/README.md

@@ -10,7 +10,7 @@ You can use the dev container configuration in this folder to build and run the
 You may use the button above, or follow these steps to open this repo in a Codespace:
 1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
-1. Click **Create codespace on master** .
+1. Click **Create codespace on master**.
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
   

.devcontainer/docker-compose.yaml

@@ -5,10 +5,10 @@ services:
       dockerfile: libs/langchain/dev.Dockerfile
       context: ..
     volumes:
-   # Update this to wherever you want VS Code to mount the folder of your project
+      # Update this to wherever you want VS Code to mount the folder of your project
       - ..:/workspaces/langchain:cached
     networks:
-      - langchain-network 
+      - langchain-network
   #   environment:
   #     MONGO_ROOT_USERNAME: root
   #     MONGO_ROOT_PASSWORD: example123
@@ -28,5 +28,3 @@ services:
 networks:
   langchain-network:
     driver: bridge
-    
-    

.github/CODEOWNERS

@@ -0,0 +1,2 @@
+/.github/   @efriis @baskaryan @ccurme
+/libs/packages.yml   @efriis

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -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

@@ -4,9 +4,6 @@ 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: Discord
-    url: https://discord.gg/6adMQxSpJS
-    about: General community discussions
   - name: Feature Request
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
     about: Suggest a feature or an idea

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,7 +1,7 @@
 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.
+  - Where "package" is whichever of langchain, community, core, etc. is being modified. Use "docs: ..." for purely docs changes, "infra: ..." for CI changes.
   - Example: "community: add foobar LLM"
 
 

.github/actions/people/app/main.py

@@ -350,11 +350,7 @@ def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
         print("Querying PRs...")
     else:
         print(f"Querying PRs with cursor {after}...")
-    data = get_graphql_response(
-        settings=settings,
-        query=prs_query,
-        after=after
-    )
+    data = get_graphql_response(settings=settings, query=prs_query, after=after)
     graphql_response = PRsResponse.model_validate(data)
     return graphql_response.data.repository.pullRequests.edges
 
@@ -484,10 +480,16 @@ def get_contributors(settings: Settings):
             lines_changed = pr.additions + pr.deletions
             score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
             contributor_scores[pr.author.login] += score
-            three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
+            three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
             if pr.createdAt > three_months_ago:
                 recent_contributor_scores[pr.author.login] += score
-    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
+    return (
+        contributors,
+        contributor_scores,
+        recent_contributor_scores,
+        reviewers,
+        authors,
+    )
 
 
 def get_top_users(
@@ -524,9 +526,13 @@ if __name__ == "__main__":
     # question_commentors, question_last_month_commentors, question_authors = get_experts(
     #     settings=settings
     # )
-    contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
-        settings=settings
-    )
+    (
+        contributors,
+        contributor_scores,
+        recent_contributor_scores,
+        reviewers,
+        pr_authors,
+    ) = get_contributors(settings=settings)
     # authors = {**question_authors, **pr_authors}
     authors = {**pr_authors}
     maintainers_logins = {
@@ -547,6 +553,7 @@ if __name__ == "__main__":
         "obi1kenobi",
         "langchain-infra",
         "jacoblee93",
+        "isahers1",
         "dqbd",
         "bracesproul",
         "akira",
@@ -558,7 +565,7 @@ if __name__ == "__main__":
         maintainers.append(
             {
                 "login": login,
-                "count": contributors[login], #+ question_commentors[login],
+                "count": contributors[login],  # + question_commentors[login],
                 "avatarUrl": user.avatarUrl,
                 "twitterUsername": user.twitterUsername,
                 "url": user.url,
@@ -614,9 +621,7 @@ if __name__ == "__main__":
     new_people_content = yaml.dump(
         people, sort_keys=False, width=200, allow_unicode=True
     )
-    if (
-        people_old_content == new_people_content
-    ):
+    if people_old_content == new_people_content:
         logging.info("The LangChain People data hasn't changed, finishing.")
         sys.exit(0)
     people_path.write_text(new_people_content, encoding="utf-8")
@@ -629,9 +634,7 @@ if __name__ == "__main__":
     logging.info(f"Creating a new branch {branch_name}")
     subprocess.run(["git", "checkout", "-B", branch_name], check=True)
     logging.info("Adding updated file")
-    subprocess.run(
-        ["git", "add", str(people_path)], check=True
-    )
+    subprocess.run(["git", "add", str(people_path)], check=True)
     logging.info("Committing updated file")
     message = "👥 Update LangChain people data"
     result = subprocess.run(["git", "commit", "-m", message], check=True)
@@ -640,4 +643,4 @@ if __name__ == "__main__":
     logging.info("Creating PR")
     pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
     logging.info(f"Created PR: {pr.number}")
-    logging.info("Finished")
+    logging.info("Finished")

.github/scripts/check_diff.py

@@ -1,16 +1,239 @@
+import glob
 import json
-import sys
 import os
-from typing import Dict
+import sys
+from collections import defaultdict
+from typing import Dict, List, Set
+from pathlib import Path
+import tomllib
+
+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",
+]
+
+# Cap python version at 3.12 for some packages with dependencies that are not yet
+# compatible with python 3.13 (mostly hf tokenizers).
+PY_312_MAX_PACKAGES = [
+    f"libs/partners/{integration}"
+    for integration in [
+        "chroma",
+        "couchbase",
+        "huggingface",
+        "mistralai",
+        "nomic",
+        "qdrant",
+    ]
+]
+
+
+def all_package_dirs() -> Set[str]:
+    return {
+        "/".join(path.split("/")[:-1]).lstrip("./")
+        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
+        if "libs/cli" not in path and "libs/standard-tests" not in path
+    }
+
+
+def dependents_graph() -> dict:
+    """
+    Construct a mapping of package -> dependents, such that we can
+    run tests on all dependents of a package when a change is made.
+    """
+    dependents = defaultdict(set)
+
+    for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
+        if "template" in path:
+            continue
+
+        # load regular and test deps from pyproject.toml
+        with open(path, "rb") as f:
+            pyproject = tomllib.load(f)["tool"]["poetry"]
+
+        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
+        for dep in [
+            *pyproject["dependencies"].keys(),
+            *pyproject["group"]["test"]["dependencies"].keys(),
+        ]:
+            if "langchain" in dep:
+                dependents[dep].add(pkg_dir)
+                continue
+
+        # load extended deps from extended_testing_deps.txt
+        package_path = Path(path).parent
+        extended_requirement_path = package_path / "extended_testing_deps.txt"
+        if extended_requirement_path.exists():
+            with open(extended_requirement_path, "r") as f:
+                extended_deps = f.read().splitlines()
+                for depline in extended_deps:
+                    if depline.startswith("-e "):
+                        # editable dependency
+                        assert depline.startswith(
+                            "-e ../partners/"
+                        ), "Extended test deps should only editable install partner packages"
+                        partner = depline.split("partners/")[1]
+                        dep = f"langchain-{partner}"
+                    else:
+                        dep = depline.split("==")[0]
+
+                    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
+
+
+def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
+    updated = set()
+    for dir_ in dirs_to_eval:
+        # handle core manually because it has so many dependents
+        if "core" in dir_:
+            updated.add(dir_)
+            continue
+        pkg = "langchain-" + dir_.split("/")[-1]
+        updated.update(dependents[pkg])
+        updated.add(dir_)
+    return list(updated)
+
+
+def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
+    if job == "test-pydantic":
+        return _get_pydantic_test_configs(dir_)
+
+    if dir_ == "libs/core":
+        py_versions = ["3.9", "3.10", "3.11", "3.12", "3.13"]
+    # custom logic for specific directories
+    elif dir_ == "libs/partners/milvus":
+        # milvus poetry doesn't allow 3.12 because they
+        # declare deps in funny way
+        py_versions = ["3.9", "3.11"]
+
+    elif dir_ in PY_312_MAX_PACKAGES:
+        py_versions = ["3.9", "3.12"]
+
+    elif dir_ in ["libs/community", "libs/langchain"] and job == "extended-tests":
+        # community extended test resolution in 3.12 is slow
+        # even in uv
+        py_versions = ["3.9", "3.11"]
+
+    elif dir_ == "libs/community" and job == "compile-integration-tests":
+        # community integration deps are slow in 3.12
+        py_versions = ["3.9", "3.11"]
+    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/poetry.lock", "rb") as f:
+        core_poetry_lock_data = tomllib.load(f)
+    for package in core_poetry_lock_data["package"]:
+        if package["name"] == "pydantic":
+            core_max_pydantic_minor = package["version"].split(".")[1]
+            break
+
+    with open(f"./{dir_}/poetry.lock", "rb") as f:
+        dir_poetry_lock_data = tomllib.load(f)
+
+    for package in dir_poetry_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"
+    )
+
+    custom_mins = {
+        # depends on pydantic-settings 2.4 which requires pydantic 2.7
+        "libs/community": 7,
+    }
+
+    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),
+        custom_mins.get(dir_, 0),
+    )
+
+    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: 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", "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"])
+    else:
+        raise ValueError(f"Unknown job: {job}")
+
+    return [
+        config for dir_ in dirs for config in _get_configs_for_single_dir(job, dir_)
+    ]
+
+
 if __name__ == "__main__":
     files = sys.argv[1:]
 
@@ -21,9 +244,11 @@ if __name__ == "__main__":
     }
     docs_edited = False
 
-    if len(files) == 300:
+    if len(files) >= 300:
         # max diff length is 300 files - there are likely files missing
-        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
+        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(
@@ -42,8 +267,12 @@ if __name__ == "__main__":
         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:
@@ -55,7 +284,6 @@ if __name__ == "__main__":
             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")
 
@@ -71,24 +299,37 @@ if __name__ == "__main__":
             ] != ["README.md"]:
                 dirs_to_run["test"].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/"]):
+        elif any(file.startswith(p) for p in ["docs/", "cookbook/"]):
             if file.startswith("docs/"):
                 docs_edited = True
             dirs_to_run["lint"].add(".")
 
-    outputs = {
-        "dirs-to-lint": list(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"]
-        ),
-        "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
-        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
-        "docs-edited": "true" if docs_edited else "",
+    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 [
+            "lint",
+            "test",
+            "extended-tests",
+            "compile-integration-tests",
+            "dependencies",
+            "test-pydantic",
+        ]
     }
-    for key, value in outputs.items():
+    map_job_to_configs["test-doc-imports"] = (
+        [{"python-version": "3.12"}] if docs_edited else []
+    )
+
+    for key, value in map_job_to_configs.items():
         json_output = json.dumps(value)
         print(f"{key}={json_output}")

.github/scripts/check_prerelease_dependencies.py

@@ -0,0 +1,35 @@
+import sys
+import tomllib
+
+if __name__ == "__main__":
+    # Get the TOML file path from the command line argument
+    toml_file = sys.argv[1]
+
+    # read toml file
+    with open(toml_file, "rb") as file:
+        toml_data = tomllib.load(file)
+
+    # see if we're releasing an rc
+    version = toml_data["tool"]["poetry"]["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]
+            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."
+                )
+
+            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."
+                )

.github/scripts/get_min_versions.py

@@ -1,43 +1,106 @@
 import sys
+from typing import Optional
+
+if sys.version_info >= (3, 11):
+    import tomllib
+else:
+    # for python 3.10 and below, which doesnt have stdlib tomllib
+    import tomli as tomllib
+
+from packaging.specifiers import SpecifierSet
+from packaging.version import Version
+
+
+import requests
+from packaging.version import parse
+from typing import List
 
-import tomllib
-from packaging.version import parse as parse_version
 import re
 
+
 MIN_VERSION_LIBS = [
     "langchain-core",
     "langchain-community",
     "langchain",
     "langchain-text-splitters",
+    "numpy",
+    "SQLAlchemy",
+]
+
+# some libs only get checked on release because of simultaneous changes in
+# multiple libs
+SKIP_IF_PULL_REQUEST = [
+    "langchain-core",
+    "langchain-text-splitters",
+    "langchain",
+    "langchain-community",
 ]
 
 
-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):
+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 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)
@@ -49,17 +112,29 @@ def get_min_version_from_toml(toml_path: str):
     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 in multiple libs
+            continue
         # Check if the lib is present in the dependencies
         if lib in dependencies:
+            if include and lib not in include:
+                continue
             # Get the version string
             version_string = dependencies[lib]
 
             if isinstance(version_string, dict):
                 version_string = version_string["version"]
+            if isinstance(version_string, list):
+                version_string = [
+                    vs
+                    for vs in version_string
+                    if check_python_version(python_version, vs["python"])
+                ][0]["version"]
 
             # 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
@@ -67,13 +142,45 @@ def get_min_version_from_toml(toml_path: 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)
+    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()])
-    )
+    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))

.github/scripts/prep_api_docs_build.py

@@ -0,0 +1,89 @@
+#!/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"
+    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()
+        packages = [
+            p
+            for p in package_yaml["packages"]
+            if not p.get("disabled", False)
+            and p["repo"].startswith("langchain-ai/")
+            and p["repo"] != "langchain-ai/langchain"
+        ]
+
+        # Clean target directories
+        clean_target_directories(packages)
+
+        # Move libraries to their new locations
+        move_libraries(packages)
+
+        print("Library sync completed successfully!")
+
+    except Exception as e:
+        print(f"Error during library sync: {e}")
+        raise
+
+
+if __name__ == "__main__":
+    main()

.github/workflows/_compile_integration_test.yml

@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -17,21 +21,14 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: compile-integration

.github/workflows/_dependencies.yml

@@ -1,117 +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"
-
-env:
-  POETRY_VERSION: "1.7.1"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: dependency checks ${{ matrix.python-version }}
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
-        uses: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ matrix.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

@@ -6,30 +6,28 @@ on:
       working-directory:
         required: true
         type: string
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
-    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.11"
-    name: Python ${{ matrix.python-version }}
+    name: Python ${{ inputs.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: core
@@ -43,18 +41,20 @@ jobs:
         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 }}'
-
       - name: Run integration tests
         shell: bash
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_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 }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -62,6 +62,7 @@ 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 }}
@@ -74,11 +75,11 @@ jobs:
           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 }}
         run: |
           make integration_tests
 

.github/workflows/_lint.yml

@@ -7,10 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      langchain-location:
-        required: false
+      python-version:
+        required: true
         type: string
-        description: "Relative path to the langchain library folder"
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,27 +21,15 @@ env:
 
 jobs:
   build:
-    name: "make lint #${{ matrix.python-version }}"
+    name: "make lint #${{ inputs.python-version }}"
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        # Only lint on the min and max supported Python versions.
-        # It's extremely unlikely that there's a lint issue on any version in between
-        # that doesn't show up on the min or max versions.
-        #
-        # GitHub rate-limits how many jobs can be running at any one time.
-        # Starting new jobs is also relatively slow,
-        # so linting on fewer versions makes CI faster.
-        python-version:
-          - "3.8"
-          - "3.11"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           working-directory: ${{ inputs.working-directory }}
           cache-key: lint-with-extras
@@ -71,14 +59,6 @@ jobs:
         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:
@@ -86,7 +66,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache
-          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
 
       - name: Analysing the code with our lint
@@ -120,7 +100,7 @@ jobs:
         with:
           path: |
             ${{ env.WORKDIR }}/.mypy_cache_test
-          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ inputs.python-version }}-${{ inputs.working-directory }}-${{ hashFiles(format('{0}/poetry.lock', inputs.working-directory)) }}
 
       - name: Analysing the code with our lint
         working-directory: ${{ inputs.working-directory }}

.github/workflows/_release.yml

@@ -85,7 +85,7 @@ 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
         id: check-tags
@@ -95,9 +95,30 @@ 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 $REGEX || true | head -1)
+          PREV_TAG="$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 $REGEX || true) | head -1)
+          fi
+
+          # if PREV_TAG is empty, let it be empty
+          if [ -z "$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"
@@ -122,7 +143,6 @@ jobs:
           fi
           {
             echo 'release-body<<EOF'
-            echo "# Release $TAG"
             echo $PREAMBLE
             echo
             git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
@@ -135,6 +155,7 @@ jobs:
       - release-notes
     uses:
       ./.github/workflows/_test_release.yml
+    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
       dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
@@ -164,6 +185,7 @@ jobs:
 
       - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
+        id: setup-python
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           poetry-version: ${{ env.POETRY_VERSION }}
@@ -189,7 +211,7 @@ jobs:
             --extra-index-url https://test.pypi.org/simple/ \
             "$PKG_NAME==$VERSION" || \
           ( \
-            sleep 5 && \
+            sleep 15 && \
             poetry run pip install \
               --extra-index-url https://test.pypi.org/simple/ \
               "$PKG_NAME==$VERSION" \
@@ -202,7 +224,7 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test,test_integration
+        run: poetry install --with test
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -221,12 +243,18 @@ jobs:
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
+      - name: Check for prerelease versions
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          poetry 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 $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
+          poetry run pip install packaging requests
+          python_version="$(poetry run python --version | awk '{print $2}')"
+          min_versions="$(poetry 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"
 
@@ -239,11 +267,9 @@ jobs:
           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
+        working-directory: ${{ inputs.working-directory }}
 
       - name: Run integration tests
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
@@ -258,12 +284,14 @@ 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 }}
@@ -276,11 +304,11 @@ jobs:
           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 }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
@@ -325,6 +353,8 @@ 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:

.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

@@ -7,10 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      langchain-location:
-        required: false
+      python-version:
+        required: true
         type: string
-        description: "Relative path to the langchain library folder"
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -21,42 +21,47 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    name: "make test #${{ matrix.python-version }}"
+    name: "make test #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
+        id: setup-python
         with:
-          python-version: ${{ matrix.python-version }}
+          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"
-
       - name: Run core tests
         shell: bash
         run: |
           make test
 
+      - name: Get minimum versions
+        working-directory: ${{ inputs.working-directory }}
+        id: min-version
+        shell: bash
+        run: |
+          poetry run pip install packaging tomli requests
+          python_version="$(poetry run python --version | awk '{print $2}')"
+          min_versions="$(poetry 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: |
+          poetry run pip install $MIN_VERSIONS
+          make tests
+        working-directory: ${{ inputs.working-directory }}
+
       - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
@@ -68,3 +73,4 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
+          

.github/workflows/_test_doc_imports.yml

@@ -2,6 +2,11 @@ name: test_doc_imports
 
 on:
   workflow_call:
+    inputs:
+      python-version:
+        required: true
+        type: string
+        description: "Python version to use"
 
 env:
   POETRY_VERSION: "1.7.1"
@@ -9,18 +14,14 @@ env:
 jobs:
   build:
     runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.11"
-    name: "check doc imports #${{ matrix.python-version }}"
+    name: "check doc imports #${{ inputs.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ inputs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ inputs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
           cache-key: core
 
@@ -30,7 +31,7 @@ jobs:
 
       - name: Install langchain editable
         run: |
-          poetry run pip install -e libs/core libs/langchain libs/community libs/experimental
+          poetry run pip install langchain-experimental -e libs/core libs/langchain libs/community
 
       - name: Check doc imports
         shell: bash

.github/workflows/_test_pydantic.yml

@@ -0,0 +1,64 @@
+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."
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    defaults:
+      run:
+        working-directory: ${{ inputs.working-directory }}
+    runs-on: ubuntu-latest
+    name: "make test # pydantic: ~=${{ inputs.pydantic-version }}, python: ${{ 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: ${{ inputs.working-directory }}
+          cache-key: core
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install --with test
+
+      - name: Overwrite pydantic version
+        shell: bash
+        run: poetry run pip install pydantic~=${{ 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

@@ -98,3 +98,5 @@ 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 +1,99 @@
+name: API docs build
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 13 * * *'
+env:
+  POETRY_VERSION: "1.8.1"
+  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[].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 $REPOS; do
+            if [[ "$repo" != "langchain-ai/langchain" && "$repo" == langchain-ai/* ]]; then
+              REPO_NAME=$(echo $repo | cut -d'/' -f2)
+              echo "Checking out $repo to $REPO_NAME"
+              git clone --depth 1 https://github.com/$repo.git $REPO_NAME
+            fi
+          done
+
+      - name: Set up Python ${{ env.PYTHON_VERSION }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./langchain/.github/actions/poetry_setup"
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          cache-key: api-docs
+          working-directory: langchain
+
+      - 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 with script
+        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/{}")
+          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

@@ -7,6 +7,7 @@ on:
 
 jobs:
   check-links:
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4

.github/workflows/check_diffs.yml

@@ -26,104 +26,120 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
       - id: files
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
         run: |
+          python -m pip install packaging requests
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
-      dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
-      dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
-      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
+      lint: ${{ steps.set-matrix.outputs.lint }}
+      test: ${{ steps.set-matrix.outputs.test }}
+      extended-tests: ${{ steps.set-matrix.outputs.extended-tests }}
+      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.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
+    if: ${{ needs.build.outputs.lint != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
+        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
+      fail-fast: false
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   test:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.test != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.test) }}
+      fail-fast: false
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
+      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.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
+    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:
+      python-version: ${{ matrix.job-configs.python-version }}
 
   compile-integration-tests:
-    name: cd ${{ matrix.working-directory }}
+    name: cd ${{ matrix.job-configs.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
+      fail-fast: false
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.working-directory }}
-    secrets: inherit
-
-  dependencies:
-    name: cd ${{ matrix.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
-    strategy:
-      matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
-    uses: ./.github/workflows/_dependencies.yml
-    with:
-      working-directory: ${{ matrix.working-directory }}
+      working-directory: ${{ matrix.job-configs.working-directory }}
+      python-version: ${{ matrix.job-configs.python-version }}
     secrets: inherit
 
   extended-tests:
-    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
+    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
     needs: [ build ]
-    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
+    if: ${{ needs.build.outputs.extended-tests != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
+        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
+      fail-fast: false
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: ${{ matrix.working-directory }}
+        working-directory: ${{ matrix.job-configs.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+      - name: Set up Python ${{ matrix.job-configs.python-version }} + Poetry ${{ env.POETRY_VERSION }}
         uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: ${{ matrix.job-configs.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: ${{ matrix.working-directory }}
+          working-directory: ${{ matrix.job-configs.working-directory }}
           cache-key: extended
 
       - name: Install dependencies
         shell: bash
         run: |
           echo "Running extended tests, installing dependencies with poetry..."
-          poetry install -E extended_testing --with test
+          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
@@ -141,7 +157,7 @@ jobs:
           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

@@ -0,0 +1,36 @@
+---
+name: Integration docs lint
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+
+# 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.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+      - id: files
+        uses: Ana06/get-changed-files@v2.2.0
+        with:
+          filter: |
+            *.ipynb
+            *.md
+            *.mdx
+      - name: Check new docs
+        run: |
+          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/codespell.yml

@@ -3,9 +3,8 @@ 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/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

@@ -14,8 +14,9 @@ on:
 
 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
     steps:
       - name: Dump GitHub context
         env:

.github/workflows/run_notebooks.yml

@@ -0,0 +1,74 @@
+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 * * *'
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+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 + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
+        with:
+          python-version: ${{ github.event.inputs.python_version || '3.11' }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: run-notebooks
+
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ 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: |
+          poetry install --with dev,test
+
+      - name: Pre-download files
+        run: |
+          poetry 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: |
+          poetry 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 }}
+          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

@@ -10,27 +10,24 @@ env:
 
 jobs:
   build:
+    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
     name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
         python-version:
-          - "3.8"
+          - "3.9"
           - "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/cohere"
           - "libs/partners/google-vertexai"
           - "libs/partners/google-genai"
           - "libs/partners/aws"
-          - "libs/partners/nvidia-ai-endpoints"
 
     steps:
       - uses: actions/checkout@v4
@@ -40,14 +37,6 @@ jobs:
         with:
           repository: langchain-ai/langchain-google
           path: langchain-google
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-nvidia
-          path: langchain-nvidia
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-cohere
-          path: langchain-cohere
       - uses: actions/checkout@v4
         with:
           repository: langchain-ai/langchain-aws
@@ -57,13 +46,9 @@ jobs:
         run: |
           rm -rf \
             langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
-            langchain/libs/partners/cohere
+            langchain/libs/partners/google-vertexai
           mv langchain-google/libs/genai langchain/libs/partners/google-genai
           mv langchain-google/libs/vertexai langchain/libs/partners/google-vertexai
-          mv langchain-nvidia/libs/ai-endpoints langchain/libs/partners/nvidia-ai-endpoints
-          mv langchain-cohere/libs/cohere langchain/libs/partners/cohere
           mv langchain-aws/libs/aws langchain/libs/partners/aws
 
       - name: Set up Python ${{ matrix.python-version }}
@@ -101,13 +86,13 @@ 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 }}
-          AI21_API_KEY: ${{ secrets.AI21_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 }}
           COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
@@ -122,8 +107,6 @@ jobs:
           rm -rf \
             langchain/libs/partners/google-genai \
             langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/nvidia-ai-endpoints \
-            langchain/libs/partners/cohere \
             langchain/libs/partners/aws
 
       - name: Ensure the tests did not create any additional files

.gitignore

@@ -133,6 +133,7 @@ env.bak/
 
 # mypy
 .mypy_cache/
+.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -166,11 +167,14 @@ 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

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

@@ -31,19 +31,21 @@ docs_linkcheck:
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
+	poetry run python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
 
 API_PKG ?= text-splitters
 
 api_docs_quick_preview:
-	poetry run pip install "pydantic<2"
 	poetry run python docs/api_reference/create_api_rst.py $(API_PKG)
 	cd docs/api_reference && poetry run make html
-	open docs/api_reference/_build/html/$(shell echo $(API_PKG) | sed 's/-/_/g')_api_reference.html
+	poetry run python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
+	open docs/api_reference/_build/html/reference.html
 
 ## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
 	find ./docs/api_reference -name '*_api_reference.rst' -delete
 	git clean -fdX ./docs/api_reference
+	rm docs/api_reference/index.md
 	
 
 ## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
@@ -64,12 +66,12 @@ 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
+	poetry run ruff check docs cookbook
+	poetry run ruff format docs cookbook cookbook --diff
+	poetry run ruff check --select I docs cookbook
+	git grep 'from langchain import' docs/docs cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
 
 ## 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
+	poetry run ruff format docs cookbook
+	poetry run ruff check --select I --fix docs cookbook

README.md

@@ -7,27 +7,27 @@
 [![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)
-[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
 
 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. 
+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.
 
 ## Quick Install
 
 With pip:
+
 ```bash
 pip install langchain
 ```
 
 With conda:
+
 ```bash
 conda install langchain -c conda-forge
 ```
@@ -38,59 +38,66 @@ conda install langchain -c conda-forge
 
 For these applications, LangChain simplifies the entire application lifecycle:
 
-- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/v0.2/docs/concepts/#langchain-expression-language-lcel) and [components](https://python.langchain.com/v0.2/docs/concepts/#components). Integrate with hundreds of [third-party providers](https://python.langchain.com/v0.2/docs/integrations/platforms/).
+- **Open-source libraries**: Build your applications using LangChain's open-source [building blocks](https://python.langchain.com/docs/concepts/#langchain-expression-language-lcel), [components](https://python.langchain.com/docs/concepts/), and [third-party integrations](https://python.langchain.com/docs/integrations/providers/).
+  Use [LangGraph](https://langchain-ai.github.io/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 any chain into a REST API with [LangServe](https://python.langchain.com/v0.2/docs/langserve/).
+- **Deployment**: Turn your LangGraph applications into production-ready APIs and Assistants with [LangGraph Cloud](https://langchain-ai.github.io/langgraph/cloud/).
 
 ### 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.
+- **[`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 learn more about LangGraph, check out our first LangChain Academy course, *Introduction to LangGraph*, available [here](https://academy.langchain.com/courses/intro-to-langgraph).
 
 ### 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.
 
 ### Deployment:
-- **[LangServe](https://python.langchain.com/v0.2/docs/langserve/)**: A library for deploying LangChain chains as REST APIs.
 
-![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
+- **[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_112024.svg#gh-light-mode-only "LangChain Architecture Overview")
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack_112024_dark.svg#gh-dark-mode-only "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
 
 **❓ Question answering with RAG**
 
-- [Documentation](https://python.langchain.com/v0.2/docs/tutorials/rag/)
+- [Documentation](https://python.langchain.com/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/)
+- [Documentation](https://python.langchain.com/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/)
+- [Documentation](https://python.langchain.com/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.
+And much more! Head to the [Tutorials](https://python.langchain.com/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. 
+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.
+LCEL is a key part of LangChain, allowing you to build and organize chains of processes in a straightforward, declarative manner. It was designed to support taking prototypes directly into production without needing to alter any code. This means you can use LCEL to set up everything from basic "prompt + LLM" setups to intricate, multi-step workflows.
 
-- **[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
+- **[Overview](https://python.langchain.com/docs/concepts/#langchain-expression-language-lcel)**: LCEL and its benefits
+- **[Interface](https://python.langchain.com/docs/concepts/#runnable-interface)**: The standard Runnable interface for LCEL objects
+- **[Primitives](https://python.langchain.com/docs/how_to/#langchain-expression-language-lcel)**: More on the primitives LCEL includes
+- **[Cheatsheet](https://python.langchain.com/docs/how_to/lcel_cheatsheet/)**: Quick overview of the most common usage patterns
 
 ## Components
 
@@ -98,39 +105,37 @@ 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).
+This includes [prompt management](https://python.langchain.com/docs/concepts/#prompt-templates), [prompt optimization](https://python.langchain.com/docs/concepts/#example-selectors), a generic interface for [chat models](https://python.langchain.com/docs/concepts/#chat-models) and [LLMs](https://python.langchain.com/docs/concepts/#llms), and common utilities for working with [model outputs](https://python.langchain.com/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.
+Retrieval Augmented Generation involves [loading data](https://python.langchain.com/docs/concepts/#document-loaders) from a variety of sources, [preparing it](https://python.langchain.com/docs/concepts/#text-splitters), then [searching over (a.k.a. retrieving from)](https://python.langchain.com/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 done. LangChain provides a [standard interface for agents](https://python.langchain.com/v0.2/docs/concepts/#agents) along with the [LangGraph](https://github.com/langchain-ai/langgraph) extension for building custom 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/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.
+- [Introduction](https://python.langchain.com/docs/introduction/): Overview of the framework and the structure of the docs.
+- [Tutorials](https://python.langchain.com/docs/tutorials/): 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/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/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/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
-- [🦜🕸️ LangGraph](https://langchain-ai.github.io/langgraph/): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
-- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
-  - [LangChain Templates](https://python.langchain.com/v0.2/docs/templates/): Example applications hosted with LangServe.
-
+- [🦜🛠️ 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.
+- [🦜🕸️ LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/#langgraph-platform): Deploy LLM applications built with LangGraph into production.
 
 ## 💁 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/).
+For detailed information on how to contribute, see [here](https://python.langchain.com/docs/contributing/).
 
 ## 🌟 Contributors
 

cookbook/Multi_modal_RAG.ipynb

@@ -64,7 +64,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -355,7 +355,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Multi_modal_RAG_google.ipynb

@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -U --quiet langchain langchain_community openai chromadb langchain-experimental\n",
+    "%pip install -U --quiet langchain langchain-chroma langchain-community openai langchain-experimental\n",
     "%pip install --quiet \"unstructured[all-docs]\" pypdf pillow pydantic lxml pillow matplotlib chromadb tiktoken"
    ]
   },
@@ -344,8 +344,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import VertexAIEmbeddings\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "\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",

cookbook/RAPTOR.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub chromadb langchain-anthropic"
+    "pip install -U langchain umap-learn scikit-learn langchain_community tiktoken langchain-openai langchainhub langchain-chroma langchain-anthropic"
    ]
   },
   {
@@ -645,7 +645,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "\n",
     "# Initialize all_texts with leaf_texts\n",
     "all_texts = leaf_texts.copy()\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.
@@ -36,6 +38,7 @@ 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.
@@ -57,4 +60,7 @@ Notebook | Description
 [two_agent_debate_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_agent_debate_tools.ipynb) | Simulate multi-agent dialogues where the agents can utilize various tools.
 [two_player_dnd.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/two_player_dnd.ipynb) | Simulate a two-player dungeons & dragons game, where a dialogue simulator class is used to coordinate the dialogue between the protagonist and the dungeon master.
 [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.
+[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.
+[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.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain unstructured[all-docs] pydantic lxml langchainhub"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml langchainhub"
    ]
   },
   {
@@ -320,7 +320,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Semi_structured_and_multi_modal_RAG.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
    ]
   },
   {
@@ -375,7 +375,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain unstructured[all-docs] pydantic lxml"
+    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
    ]
   },
   {
@@ -378,8 +378,8 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import GPT4AllEmbeddings\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "\n",
     "# The vectorstore to use to index the child chunks\n",

cookbook/advanced_rag_eval.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain_chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "baseline = Chroma.from_texts(\n",

cookbook/agent_vectorstore.ipynb

@@ -28,7 +28,7 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",

cookbook/airbyte_github.ipynb

@@ -14,7 +14,7 @@
     }
    ],
    "source": [
-    "%pip install -qU langchain-airbyte"
+    "%pip install -qU langchain-airbyte langchain_chroma"
    ]
   },
   {
@@ -123,7 +123,7 @@
    "outputs": [],
    "source": [
     "import tiktoken\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "enc = tiktoken.get_encoding(\"cl100k_base\")\n",

cookbook/autogpt/marathon_times.ipynb

@@ -46,7 +46,7 @@
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "# Needed synce jupyter runs an async eventloop\n",
+    "# Needed since jupyter runs an async eventloop\n",
     "nest_asyncio.apply()"
    ]
   },

cookbook/code-analysis-deeplake.ipynb

@@ -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"
    ]
   },

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

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

cookbook/docugami_xml_kg_rag.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain docugami==0.0.8 dgml-utils==0.3.0 pydantic langchainhub chromadb hnswlib --upgrade --quiet"
+    "! pip install langchain docugami==0.0.8 dgml-utils==0.3.0 pydantic langchainhub langchain-chroma hnswlib --upgrade --quiet"
    ]
   },
   {
@@ -547,7 +547,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_community.vectorstores.chroma import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",

cookbook/fireworks_rag.ipynb

@@ -84,7 +84,7 @@
     }
    ],
    "source": [
-    "%pip install --quiet pypdf chromadb tiktoken openai \n",
+    "%pip install --quiet pypdf langchain-chroma tiktoken openai \n",
     "%pip uninstall -y langchain-fireworks\n",
     "%pip install --editable /mnt/disks/data/langchain/libs/partners/fireworks"
    ]
@@ -138,7 +138,7 @@
     "all_splits = text_splitter.split_documents(data)\n",
     "\n",
     "# Add to vectorDB\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_fireworks.embeddings import FireworksEmbeddings\n",
     "\n",
     "vectorstore = Chroma.from_documents(\n",

cookbook/hypothetical_document_embeddings.ipynb

@@ -170,7 +170,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "with open(\"../../state_of_the_union.txt\") as f:\n",

cookbook/langgraph_agentic_rag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph"
    ]
   },
   {
@@ -30,8 +30,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",

cookbook/langgraph_crag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph tavily-python"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph tavily-python"
    ]
   },
   {
@@ -77,8 +77,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",
@@ -180,8 +180,8 @@
     "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
     "from langchain.prompts import PromptTemplate\n",
     "from langchain.schema import Document\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.tools.tavily_search import TavilySearchResults\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.messages import BaseMessage, FunctionMessage\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",

cookbook/langgraph_self_rag.ipynb

@@ -7,7 +7,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain_community tiktoken langchain-openai langchainhub chromadb langchain langgraph"
+    "! pip install langchain-chroma langchain_community tiktoken langchain-openai langchainhub langchain langgraph"
    ]
   },
   {
@@ -86,8 +86,8 @@
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "urls = [\n",
@@ -188,7 +188,7 @@
     "from langchain.output_parsers import PydanticOutputParser\n",
     "from langchain.output_parsers.openai_tools import PydanticToolsParser\n",
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.messages import BaseMessage, FunctionMessage\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",
@@ -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/multi_modal_RAG_chroma.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -187,7 +187,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
     "from PIL import Image as _PILImage\n",
     "\n",

cookbook/multi_modal_RAG_vdms.ipynb

@@ -18,26 +18,7 @@
     "* 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",
-    "## 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."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# (newest versions required for multi-modal)\n",
-    "! pip install --quiet -U vdms langchain-experimental\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"
+    "* Passing raw images and text chunks to a multimodal LLM for answer synthesis "
    ]
   },
   {
@@ -53,7 +34,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 1,
    "id": "5f483872",
    "metadata": {},
    "outputs": [
@@ -61,8 +42,7 @@
      "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"
+      "a1b9206b08ef626e15b356bf9e031171f7c7eb8f956a2733f196f0109246fe2b\n"
      ]
     }
    ],
@@ -75,9 +55,32 @@
     "vdms_client = VDMS_Client(port=55559)"
    ]
   },
+  {
+   "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."
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
+   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! pip install --quiet -U vdms langchain-experimental\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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "id": "78ac6543",
    "metadata": {},
    "outputs": [],
@@ -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."
    ]
   },
   {
@@ -116,8 +114,8 @@
     "\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",
+    "datapath = Path(\"./data/multimodal_files\").resolve()\n",
     "datapath.mkdir(parents=True, exist_ok=True)\n",
     "\n",
     "pdf_url = \"https://www.loc.gov/lcm/pdf/LCM_2020_1112.pdf\"\n",
@@ -174,14 +172,8 @@
    "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"
    ]
   },
   {
@@ -200,9 +192,7 @@
     "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 +223,7 @@
    "source": [
     "## RAG\n",
     "\n",
-    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings."
+    "Here we define helper functions for image results."
    ]
   },
   {
@@ -392,7 +382,8 @@
    "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."
    ]
   },
   {
@@ -452,6 +443,14 @@
     "        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 +461,10 @@
      "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 depicts a woman with several children. The woman appears to be of Cherokee heritage, as suggested by the text provided. The image is described as having been initially regretted by the subject, Florence Owens Thompson, due to her feeling that it did not accurately represent her leadership qualities.\n",
+      "The historical and cultural context of the image is tied to the Great Depression and the Dust Bowl, both of which affected the Cherokee people in Oklahoma. The photograph was taken during this period, and its subject, Florence Owens Thompson, was a leader within her community who worked tirelessly to help those affected by these crises.\n",
+      "The image's symbolism and meaning can be interpreted as a representation of resilience and strength in the face of adversity. The woman is depicted with multiple children, which could signify her role as a caregiver and protector during difficult times.\n",
+      "Connections between the image and the related text include Florence Owens Thompson's leadership qualities and her regretted feelings about the photograph. Additionally, the mention of Dorothea Lange, the photographer who took this photo, ties the image to its historical context and the broader narrative of the Great Depression and Dust Bowl in Oklahoma. \n"
      ]
     }
    ],
@@ -492,14 +491,6 @@
    "source": [
     "! docker kill vdms_rag_nb"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8ba652da",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -518,7 +509,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

cookbook/nomic_embedding_rag.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain"
+    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain"
    ]
   },
   {
@@ -167,7 +167,7 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_core.output_parsers import StrOutputParser\n",
     "from langchain_core.runnables import RunnableLambda, RunnablePassthrough\n",
     "from langchain_nomic import NomicEmbeddings\n",

cookbook/nomic_multimodal_rag.ipynb

@@ -0,0 +1,497 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "9fc3897d-176f-4729-8fd1-cfb4add53abd",
+   "metadata": {},
+   "source": [
+    "## Nomic multi-modal RAG\n",
+    "\n",
+    "Many documents contain a mixture of content types, including text and images. \n",
+    "\n",
+    "Yet, information captured in images is lost in most RAG applications.\n",
+    "\n",
+    "With the emergence of multimodal LLMs, like [GPT-4V](https://openai.com/research/gpt-4v-system-card), it is worth considering how to utilize images in RAG:\n",
+    "\n",
+    "In this demo we\n",
+    "\n",
+    "* Use multimodal embeddings from Nomic Embed [Vision](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) and [Text](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) to embed images and text\n",
+    "* Retrieve both using similarity search\n",
+    "* Pass raw images and text chunks to a multimodal LLM for answer synthesis \n",
+    "\n",
+    "## Signup\n",
+    "\n",
+    "Get your API token, then run:\n",
+    "```\n",
+    "! nomic login\n",
+    "```\n",
+    "\n",
+    "Then run with your generated API token \n",
+    "```\n",
+    "! nomic login < token > \n",
+    "```\n",
+    "\n",
+    "## 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."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "54926b9b-75c2-4cd4-8f14-b3882a0d370b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "! nomic login token"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "febbc459-ebba-4c1a-a52b-fed7731593f8",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain # (newest versions required for multi-modal)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "acbdc603-39e2-4a5f-836c-2bbaecd46b0b",
+   "metadata": {
+    "scrolled": true
+   },
+   "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"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1e94b3fb-8e3e-4736-be0a-ad881626c7bd",
+   "metadata": {},
+   "source": [
+    "## Data Loading\n",
+    "\n",
+    "### Partition PDF text and images\n",
+    "  \n",
+    "Let's look at an example pdfs containing interesting images.\n",
+    "\n",
+    "1/ Art from the J Paul Getty museum:\n",
+    "\n",
+    " * Here is a [zip file](https://drive.google.com/file/d/18kRKbq2dqAhhJ3DfZRnYcTBEUfYxe1YR/view?usp=sharing) with the PDF and the already extracted images. \n",
+    "* https://www.getty.edu/publications/resources/virtuallibrary/0892360224.pdf\n",
+    "\n",
+    "2/ 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.\n",
+    "\n",
+    "To supply this to extract the images:\n",
+    "```\n",
+    "extract_images_in_pdf=True\n",
+    "```\n",
+    "\n",
+    "\n",
+    "\n",
+    "If using this zip file, then you can simply process the text only with:\n",
+    "```\n",
+    "extract_images_in_pdf=False\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9646b524-71a7-4b2a-bdc8-0b81f77e968f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Folder with pdf and extracted images\n",
+    "from pathlib import Path\n",
+    "\n",
+    "# replace with actual path to images\n",
+    "path = Path(\"../art\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "77f096ab-a933-41d0-8f4e-1efc83998fc3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "path.resolve()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bc4839c0-8773-4a07-ba59-5364501269b2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Extract images, tables, and chunk text\n",
+    "from unstructured.partition.pdf import partition_pdf\n",
+    "\n",
+    "raw_pdf_elements = partition_pdf(\n",
+    "    filename=str(path.resolve()) + \"/getty.pdf\",\n",
+    "    extract_images_in_pdf=False,\n",
+    "    infer_table_structure=True,\n",
+    "    chunking_strategy=\"by_title\",\n",
+    "    max_characters=4000,\n",
+    "    new_after_n_chars=3800,\n",
+    "    combine_text_under_n_chars=2000,\n",
+    "    image_output_dir_path=path,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "969545ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Categorize text elements by type\n",
+    "tables = []\n",
+    "texts = []\n",
+    "for element in raw_pdf_elements:\n",
+    "    if \"unstructured.documents.elements.Table\" in str(type(element)):\n",
+    "        tables.append(str(element))\n",
+    "    elif \"unstructured.documents.elements.CompositeElement\" in str(type(element)):\n",
+    "        texts.append(str(element))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5d8e6349-1547-4cbf-9c6f-491d8610ec10",
+   "metadata": {},
+   "source": [
+    "## Multi-modal embeddings with our document\n",
+    "\n",
+    "We will use [nomic-embed-vision-v1.5](https://huggingface.co/nomic-ai/nomic-embed-vision-v1.5) embeddings. This model is aligned \n",
+    "to [nomic-embed-text-v1.5](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5) allowing for multimodal semantic search and Multimodal RAG!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4bc15842-cb95-4f84-9eb5-656b0282a800",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import uuid\n",
+    "\n",
+    "import chromadb\n",
+    "import numpy as np\n",
+    "from langchain_chroma import Chroma\n",
+    "from langchain_nomic import NomicEmbeddings\n",
+    "from PIL import Image as _PILImage\n",
+    "\n",
+    "# Create chroma\n",
+    "text_vectorstore = Chroma(\n",
+    "    collection_name=\"mm_rag_clip_photos_text\",\n",
+    "    embedding_function=NomicEmbeddings(\n",
+    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
+    "    ),\n",
+    ")\n",
+    "image_vectorstore = Chroma(\n",
+    "    collection_name=\"mm_rag_clip_photos_image\",\n",
+    "    embedding_function=NomicEmbeddings(\n",
+    "        vision_model=\"nomic-embed-vision-v1.5\", model=\"nomic-embed-text-v1.5\"\n",
+    "    ),\n",
+    ")\n",
+    "\n",
+    "# Get image URIs with .jpg extension only\n",
+    "image_uris = sorted(\n",
+    "    [\n",
+    "        os.path.join(path, image_name)\n",
+    "        for image_name in os.listdir(path)\n",
+    "        if image_name.endswith(\".jpg\")\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# Add images\n",
+    "image_vectorstore.add_images(uris=image_uris)\n",
+    "\n",
+    "# Add documents\n",
+    "text_vectorstore.add_texts(texts=texts)\n",
+    "\n",
+    "# Make retriever\n",
+    "image_retriever = image_vectorstore.as_retriever()\n",
+    "text_retriever = text_vectorstore.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "02a186d0-27e0-4820-8092-63b5349dd25d",
+   "metadata": {},
+   "source": [
+    "## RAG\n",
+    "\n",
+    "`vectorstore.add_images` will store / retrieve images as base64 encoded strings.\n",
+    "\n",
+    "These can be passed to [GPT-4V](https://platform.openai.com/docs/guides/vision)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "344f56a8-0dc3-433e-851c-3f7600c7a72b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import base64\n",
+    "import io\n",
+    "from io import BytesIO\n",
+    "\n",
+    "import numpy as np\n",
+    "from PIL import Image\n",
+    "\n",
+    "\n",
+    "def resize_base64_image(base64_string, size=(128, 128)):\n",
+    "    \"\"\"\n",
+    "    Resize an image encoded as a Base64 string.\n",
+    "\n",
+    "    Args:\n",
+    "    base64_string (str): Base64 string of the original image.\n",
+    "    size (tuple): Desired size of the image as (width, height).\n",
+    "\n",
+    "    Returns:\n",
+    "    str: Base64 string of the resized image.\n",
+    "    \"\"\"\n",
+    "    # Decode the Base64 string\n",
+    "    img_data = base64.b64decode(base64_string)\n",
+    "    img = Image.open(io.BytesIO(img_data))\n",
+    "\n",
+    "    # Resize the image\n",
+    "    resized_img = img.resize(size, Image.LANCZOS)\n",
+    "\n",
+    "    # Save the resized image to a bytes buffer\n",
+    "    buffered = io.BytesIO()\n",
+    "    resized_img.save(buffered, format=img.format)\n",
+    "\n",
+    "    # Encode the resized image to Base64\n",
+    "    return base64.b64encode(buffered.getvalue()).decode(\"utf-8\")\n",
+    "\n",
+    "\n",
+    "def is_base64(s):\n",
+    "    \"\"\"Check if a string is Base64 encoded\"\"\"\n",
+    "    try:\n",
+    "        return base64.b64encode(base64.b64decode(s)) == s.encode()\n",
+    "    except Exception:\n",
+    "        return False\n",
+    "\n",
+    "\n",
+    "def split_image_text_types(docs):\n",
+    "    \"\"\"Split numpy array images and texts\"\"\"\n",
+    "    images = []\n",
+    "    text = []\n",
+    "    for doc in docs:\n",
+    "        doc = doc.page_content  # Extract Document contents\n",
+    "        if is_base64(doc):\n",
+    "            # Resize image to avoid OAI server error\n",
+    "            images.append(\n",
+    "                resize_base64_image(doc, size=(250, 250))\n",
+    "            )  # base64 encoded str\n",
+    "        else:\n",
+    "            text.append(doc)\n",
+    "    return {\"images\": images, \"texts\": text}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "23a2c1d8-fea6-4152-b184-3172dd46c735",
+   "metadata": {},
+   "source": [
+    "Currently, we format the inputs using a `RunnableLambda` while we add image support to `ChatPromptTemplates`.\n",
+    "\n",
+    "Our runnable follows the classic RAG flow - \n",
+    "\n",
+    "* We first compute the context (both \"texts\" and \"images\" in this case) and the question (just a RunnablePassthrough here) \n",
+    "* Then we pass this into our prompt template, which is a custom function that formats the message for the gpt-4-vision-preview model. \n",
+    "* And finally we parse the output as a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5d8919dc-c238-4746-86ba-45d940a7d260",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4c93fab3-74c4-4f1d-958a-0bc4cdd0797e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from operator import itemgetter\n",
+    "\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_openai import ChatOpenAI\n",
+    "\n",
+    "\n",
+    "def prompt_func(data_dict):\n",
+    "    # Joining the context texts into a single string\n",
+    "    formatted_texts = \"\\n\".join(data_dict[\"text_context\"][\"texts\"])\n",
+    "    messages = []\n",
+    "\n",
+    "    # Adding image(s) to the messages if present\n",
+    "    if data_dict[\"image_context\"][\"images\"]:\n",
+    "        image_message = {\n",
+    "            \"type\": \"image_url\",\n",
+    "            \"image_url\": {\n",
+    "                \"url\": f\"data:image/jpeg;base64,{data_dict['image_context']['images'][0]}\"\n",
+    "            },\n",
+    "        }\n",
+    "        messages.append(image_message)\n",
+    "\n",
+    "    # Adding the text message for analysis\n",
+    "    text_message = {\n",
+    "        \"type\": \"text\",\n",
+    "        \"text\": (\n",
+    "            \"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 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",
+    "            \"- Connections between the image and the related text.\\n\\n\"\n",
+    "            f\"User-provided keywords: {data_dict['question']}\\n\\n\"\n",
+    "            \"Text and / or tables:\\n\"\n",
+    "            f\"{formatted_texts}\"\n",
+    "        ),\n",
+    "    }\n",
+    "    messages.append(text_message)\n",
+    "\n",
+    "    return [HumanMessage(content=messages)]\n",
+    "\n",
+    "\n",
+    "model = ChatOpenAI(temperature=0, model=\"gpt-4-vision-preview\", max_tokens=1024)\n",
+    "\n",
+    "# RAG pipeline\n",
+    "chain = (\n",
+    "    {\n",
+    "        \"text_context\": text_retriever | RunnableLambda(split_image_text_types),\n",
+    "        \"image_context\": image_retriever | RunnableLambda(split_image_text_types),\n",
+    "        \"question\": RunnablePassthrough(),\n",
+    "    }\n",
+    "    | RunnableLambda(prompt_func)\n",
+    "    | model\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1566096d-97c2-4ddc-ba4a-6ef88c525e4e",
+   "metadata": {},
+   "source": [
+    "## Test retrieval and run RAG"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "90121e56-674b-473b-871d-6e4753fd0c45",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython.display import HTML, display\n",
+    "\n",
+    "\n",
+    "def plt_img_base64(img_base64):\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",
+    "\n",
+    "    # Display the image by rendering the HTML\n",
+    "    display(HTML(image_html))\n",
+    "\n",
+    "\n",
+    "docs = text_retriever.invoke(\"Women with children\", k=5)\n",
+    "for doc in docs:\n",
+    "    if is_base64(doc.page_content):\n",
+    "        plt_img_base64(doc.page_content)\n",
+    "    else:\n",
+    "        print(doc.page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "44eaa532-f035-4c04-b578-02339d42554c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = image_retriever.invoke(\"Women with children\", k=5)\n",
+    "for doc in docs:\n",
+    "    if is_base64(doc.page_content):\n",
+    "        plt_img_base64(doc.page_content)\n",
+    "    else:\n",
+    "        print(doc.page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "69fb15fd-76fc-49b4-806d-c4db2990027d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"Women with children\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "227f08b8-e732-4089-b65c-6eb6f9e48f15",
+   "metadata": {},
+   "source": [
+    "We can see the images retrieved in the LangSmith trace:\n",
+    "\n",
+    "LangSmith [trace](https://smith.langchain.com/public/69c558a5-49dc-4c60-a49b-3adbb70f74c5/r/e872c2c8-528c-468f-aefd-8b5cd730a673)."
+   ]
+  }
+ ],
+ "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": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/openai_functions_retrieval_qa.ipynb

@@ -20,8 +20,8 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "from langchain_text_splitters import CharacterTextSplitter"
    ]

cookbook/optimization.ipynb

@@ -80,7 +80,7 @@
    "outputs": [],
    "source": [
     "from langchain.schema import Document\n",
-    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"

cookbook/oracleai_demo.ipynb

@@ -86,8 +86,7 @@
     "\n",
     "import oracledb\n",
     "\n",
-    "# please update with your username, password, hostname and service_name\n",
-    "# please make sure this user has sufficient privileges to perform all below\n",
+    "# Update with your username, password, hostname, and service_name\n",
     "username = \"\"\n",
     "password = \"\"\n",
     "dsn = \"\"\n",
@@ -97,40 +96,45 @@
     "    print(\"Connection successful!\")\n",
     "\n",
     "    cursor = conn.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 setting up user.');\n",
-    "        end;\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 'grant read, write on directory DEMO_PY_DIR to public';\n",
-    "        execute immediate 'grant create mining model to testuser';\n",
-    "\n",
-    "        -- network access\n",
-    "        begin\n",
-    "            DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
-    "                host => '*',\n",
-    "                ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
-    "                                principal_name => 'testuser',\n",
-    "                                principal_type => xs_acl.ptype_db));\n",
-    "        end;\n",
-    "    end;\n",
-    "    \"\"\"\n",
-    "    )\n",
-    "    print(\"User setup done!\")\n",
-    "    cursor.close()\n",
+    "    try:\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",
+    "                -- 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 'grant read, write on directory DEMO_PY_DIR to public';\n",
+    "                execute immediate 'grant create mining model to testuser';\n",
+    "                \n",
+    "                -- Network access\n",
+    "                begin\n",
+    "                    DBMS_NETWORK_ACL_ADMIN.APPEND_HOST_ACE(\n",
+    "                        host => '*',\n",
+    "                        ace => xs$ace_type(privilege_list => xs$name_list('connect'),\n",
+    "                                           principal_name => 'testuser',\n",
+    "                                           principal_type => xs_acl.ptype_db)\n",
+    "                    );\n",
+    "                end;\n",
+    "            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(\"User setup failed!\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
+    "    print(f\"Connection failed with error: {e}\")\n",
     "    sys.exit(1)"
    ]
   },

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

@@ -0,0 +1,761 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "10f50955-be55-422f-8c62-3a32f8cf02ed",
+   "metadata": {},
+   "source": [
+    "# RAG application running locally on Intel Xeon CPU using langchain and open-source models"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "48113be6-44bb-4aac-aed3-76a1365b9561",
+   "metadata": {},
+   "source": [
+    "Author - Pratool Bharti (pratool.bharti@intel.com)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8b10b54b-1572-4ea1-9c1e-1d29fcc3dcd9",
+   "metadata": {},
+   "source": [
+    "In this cookbook, we use langchain tools and open source models to execute locally on CPU. This notebook has been validated to run on Intel Xeon 8480+ CPU. Here we implement a RAG pipeline for Llama2 model to answer questions about Intel Q1 2024 earnings release."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "acadbcec-3468-4926-8ce5-03b678041c0a",
+   "metadata": {},
+   "source": [
+    "**Create a conda or virtualenv environment with python >=3.10 and install following libraries**\n",
+    "<br>\n",
+    "\n",
+    "`pip install --upgrade langchain langchain-community langchainhub langchain-chroma bs4 gpt4all pypdf pysqlite3-binary` <br>\n",
+    "`pip install llama-cpp-python   --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "84c392c8-700a-42ec-8e94-806597f22e43",
+   "metadata": {},
+   "source": [
+    "**Load pysqlite3 in sys modules since ChromaDB requires sqlite3.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "145cd491-b388-4ea7-bdc8-2f4995cac6fd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "__import__(\"pysqlite3\")\n",
+    "import sys\n",
+    "\n",
+    "sys.modules[\"sqlite3\"] = sys.modules.pop(\"pysqlite3\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "14dde7e2-b236-49b9-b3a0-08c06410418c",
+   "metadata": {},
+   "source": [
+    "**Import essential components from langchain to load and split data**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "887643ba-249e-48d6-9aa7-d25087e8dfbf",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_community.document_loaders import PyPDFLoader"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "922c0eba-8736-4de5-bd2f-3d0f00b16e43",
+   "metadata": {},
+   "source": [
+    "**Download Intel Q1 2024 earnings release**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2d6a2419-5338-4188-8615-a40a65ff8019",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--2024-07-15 15:04:43--  https://d1io3yog0oux5.cloudfront.net/_11d435a500963f99155ee058df09f574/intel/db/887/9014/earnings_release/Q1+24_EarningsRelease_FINAL.pdf\n",
+      "Resolving proxy-dmz.intel.com (proxy-dmz.intel.com)... 10.7.211.16\n",
+      "Connecting to proxy-dmz.intel.com (proxy-dmz.intel.com)|10.7.211.16|:912... connected.\n",
+      "Proxy request sent, awaiting response... 200 OK\n",
+      "Length: 133510 (130K) [application/pdf]\n",
+      "Saving to: ‘intel_q1_2024_earnings.pdf’\n",
+      "\n",
+      "intel_q1_2024_earni 100%[===================>] 130.38K  --.-KB/s    in 0.005s  \n",
+      "\n",
+      "2024-07-15 15:04:44 (24.6 MB/s) - ‘intel_q1_2024_earnings.pdf’ saved [133510/133510]\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "!wget  'https://d1io3yog0oux5.cloudfront.net/_11d435a500963f99155ee058df09f574/intel/db/887/9014/earnings_release/Q1+24_EarningsRelease_FINAL.pdf' -O intel_q1_2024_earnings.pdf"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3612627-e105-453d-8a50-bbd6e39dedb5",
+   "metadata": {},
+   "source": [
+    "**Loading earning release pdf document through PyPDFLoader**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "cac6278e-ebad-4224-a062-bf6daca24cb0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = PyPDFLoader(\"intel_q1_2024_earnings.pdf\")\n",
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a7dca43b-1c62-41df-90c7-6ed2904f823d",
+   "metadata": {},
+   "source": [
+    "**Splitting entire document in several chunks with each chunk size is 500 tokens**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "4486adbe-0d0e-4685-8c08-c1774ed6e993",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
+    "all_splits = text_splitter.split_documents(data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "af142346-e793-4a52-9a56-63e3be416b3d",
+   "metadata": {},
+   "source": [
+    "**Looking at the first split of the document**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "e4240fd1-898e-4bfc-a377-02c9bc25b56e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'source': 'intel_q1_2024_earnings.pdf', 'page': 0}, page_content='Intel Corporation\\n2200 Mission College Blvd.\\nSanta Clara, CA 95054-1549\\n                                                         \\nNews Release\\n Intel Reports First -Quarter 2024  Financial Results\\nNEWS SUMMARY\\n▪First-quarter revenue of $12.7 billion , up 9%  year over year (YoY).\\n▪First-quarter GAAP earnings (loss) per share (EPS) attributable to Intel was $(0.09) ; non-GAAP EPS \\nattributable to Intel was $0.18 .')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_splits[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b88d2632-7c1b-49ef-a691-c0eb67d23e6a",
+   "metadata": {},
+   "source": [
+    "**One of the major step in RAG is to convert each split of document into embeddings and store in a vector database such that searching relevant documents are efficient.** <br>\n",
+    "**For that, importing Chroma vector database from langchain. Also, importing open source GPT4All for embedding models**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "9ff99dd7-9d47-4239-ba0a-d775792334ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_chroma import Chroma\n",
+    "from langchain_community.embeddings import GPT4AllEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b5d1f4dd-dd8d-4a20-95d1-2dbdd204375a",
+   "metadata": {},
+   "source": [
+    "**In next step, we will download one of the most popular embedding model \"all-MiniLM-L6-v2\". Find more details of the model at this link https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "05db3494-5d8e-4a13-9941-26330a86f5e5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_name = \"all-MiniLM-L6-v2.gguf2.f16.gguf\"\n",
+    "gpt4all_kwargs = {\"allow_download\": \"True\"}\n",
+    "embeddings = GPT4AllEmbeddings(model_name=model_name, gpt4all_kwargs=gpt4all_kwargs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e53999e-1983-46ac-8039-2783e194c3ae",
+   "metadata": {},
+   "source": [
+    "**Store all the embeddings in the Chroma database**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "0922951a-9ddf-4761-973d-8e9a86f61284",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "29f94fa0-6c75-4a65-a1a3-debc75422479",
+   "metadata": {},
+   "source": [
+    "**Now, let's find relevant splits from the documents related to the question**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "88c8152d-ec7a-4f0b-9d86-877789407537",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n"
+     ]
+    }
+   ],
+   "source": [
+    "question = \"What is Intel CCG revenue in Q1 2024\"\n",
+    "docs = vectorstore.similarity_search(question)\n",
+    "print(len(docs))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53330c6b-cb0f-43f9-b379-2e57ac1e5335",
+   "metadata": {},
+   "source": [
+    "**Look at the first retrieved document from the vector database**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "43a6d94f-b5c4-47b0-a353-2db4c3d24d9c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(metadata={'page': 1, 'source': 'intel_q1_2024_earnings.pdf'}, page_content='Client Computing Group (CCG) $7.5 billion up31%\\nData Center and AI (DCAI) $3.0 billion up5%\\nNetwork and Edge (NEX) $1.4 billion down 8%\\nTotal Intel Products revenue $11.9 billion up17%\\nIntel Foundry $4.4 billion down 10%\\nAll other:\\nAltera $342 million down 58%\\nMobileye $239 million down 48%\\nOther $194 million up17%\\nTotal all other revenue $775 million down 46%\\nIntersegment eliminations $(4.4) billion\\nTotal net revenue $12.7 billion up9%\\nIntel Products Highlights')"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "64ba074f-4b36-442e-b7e2-b26d6e2815c3",
+   "metadata": {},
+   "source": [
+    "**Download Lllama-2 model from Huggingface and store locally** <br>\n",
+    "**You can download different quantization variant of Lllama-2 model from the link below. We are using Q8 version here (7.16GB).** <br>\n",
+    "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c8dd0811-6f43-4bc6-b854-2ab377639c9a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!huggingface-cli download TheBloke/Llama-2-7b-Chat-GGUF llama-2-7b-chat.Q8_0.gguf --local-dir . --local-dir-use-symlinks False"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3895b1f5-f51d-4539-abf0-af33d7ca48ea",
+   "metadata": {},
+   "source": [
+    "**Import langchain components required to load downloaded LLMs model**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "fb087088-aa62-44c0-8356-061e9b9f1186",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.callbacks.manager import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "from langchain_community.llms import LlamaCpp"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5a8a111e-2614-4b70-b034-85cd3e7304cb",
+   "metadata": {},
+   "source": [
+    "**Loading the local Lllama-2 model using Llama-cpp library**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "fb917da2-c0d7-4995-b56d-26254276e0da",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from llama-2-7b-chat.Q8_0.gguf (version GGUF V2)\n",
+      "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n",
+      "llama_model_loader: - kv   0:                       general.architecture str              = llama\n",
+      "llama_model_loader: - kv   1:                               general.name str              = LLaMA v2\n",
+      "llama_model_loader: - kv   2:                       llama.context_length u32              = 4096\n",
+      "llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096\n",
+      "llama_model_loader: - kv   4:                          llama.block_count u32              = 32\n",
+      "llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 11008\n",
+      "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128\n",
+      "llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32\n",
+      "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 32\n",
+      "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000001\n",
+      "llama_model_loader: - kv  10:                          general.file_type u32              = 7\n",
+      "llama_model_loader: - kv  11:                       tokenizer.ggml.model str              = llama\n",
+      "llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr[str,32000]   = [\"<unk>\", \"<s>\", \"</s>\", \"<0x00>\", \"<...\n",
+      "llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...\n",
+      "llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...\n",
+      "llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32              = 1\n",
+      "llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32              = 2\n",
+      "llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32              = 0\n",
+      "llama_model_loader: - kv  18:               general.quantization_version u32              = 2\n",
+      "llama_model_loader: - type  f32:   65 tensors\n",
+      "llama_model_loader: - type q8_0:  226 tensors\n",
+      "llm_load_vocab: special tokens cache size = 259\n",
+      "llm_load_vocab: token to piece cache size = 0.1684 MB\n",
+      "llm_load_print_meta: format           = GGUF V2\n",
+      "llm_load_print_meta: arch             = llama\n",
+      "llm_load_print_meta: vocab type       = SPM\n",
+      "llm_load_print_meta: n_vocab          = 32000\n",
+      "llm_load_print_meta: n_merges         = 0\n",
+      "llm_load_print_meta: vocab_only       = 0\n",
+      "llm_load_print_meta: n_ctx_train      = 4096\n",
+      "llm_load_print_meta: n_embd           = 4096\n",
+      "llm_load_print_meta: n_layer          = 32\n",
+      "llm_load_print_meta: n_head           = 32\n",
+      "llm_load_print_meta: n_head_kv        = 32\n",
+      "llm_load_print_meta: n_rot            = 128\n",
+      "llm_load_print_meta: n_swa            = 0\n",
+      "llm_load_print_meta: n_embd_head_k    = 128\n",
+      "llm_load_print_meta: n_embd_head_v    = 128\n",
+      "llm_load_print_meta: n_gqa            = 1\n",
+      "llm_load_print_meta: n_embd_k_gqa     = 4096\n",
+      "llm_load_print_meta: n_embd_v_gqa     = 4096\n",
+      "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
+      "llm_load_print_meta: f_norm_rms_eps   = 1.0e-06\n",
+      "llm_load_print_meta: f_clamp_kqv      = 0.0e+00\n",
+      "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
+      "llm_load_print_meta: f_logit_scale    = 0.0e+00\n",
+      "llm_load_print_meta: n_ff             = 11008\n",
+      "llm_load_print_meta: n_expert         = 0\n",
+      "llm_load_print_meta: n_expert_used    = 0\n",
+      "llm_load_print_meta: causal attn      = 1\n",
+      "llm_load_print_meta: pooling type     = 0\n",
+      "llm_load_print_meta: rope type        = 0\n",
+      "llm_load_print_meta: rope scaling     = linear\n",
+      "llm_load_print_meta: freq_base_train  = 10000.0\n",
+      "llm_load_print_meta: freq_scale_train = 1\n",
+      "llm_load_print_meta: n_ctx_orig_yarn  = 4096\n",
+      "llm_load_print_meta: rope_finetuned   = unknown\n",
+      "llm_load_print_meta: ssm_d_conv       = 0\n",
+      "llm_load_print_meta: ssm_d_inner      = 0\n",
+      "llm_load_print_meta: ssm_d_state      = 0\n",
+      "llm_load_print_meta: ssm_dt_rank      = 0\n",
+      "llm_load_print_meta: model type       = 7B\n",
+      "llm_load_print_meta: model ftype      = Q8_0\n",
+      "llm_load_print_meta: model params     = 6.74 B\n",
+      "llm_load_print_meta: model size       = 6.67 GiB (8.50 BPW) \n",
+      "llm_load_print_meta: general.name     = LLaMA v2\n",
+      "llm_load_print_meta: BOS token        = 1 '<s>'\n",
+      "llm_load_print_meta: EOS token        = 2 '</s>'\n",
+      "llm_load_print_meta: UNK token        = 0 '<unk>'\n",
+      "llm_load_print_meta: LF token         = 13 '<0x0A>'\n",
+      "llm_load_print_meta: max token length = 48\n",
+      "llm_load_tensors: ggml ctx size =    0.14 MiB\n",
+      "llm_load_tensors:        CPU buffer size =  6828.64 MiB\n",
+      "...................................................................................................\n",
+      "llama_new_context_with_model: n_ctx      = 2048\n",
+      "llama_new_context_with_model: n_batch    = 512\n",
+      "llama_new_context_with_model: n_ubatch   = 512\n",
+      "llama_new_context_with_model: flash_attn = 0\n",
+      "llama_new_context_with_model: freq_base  = 10000.0\n",
+      "llama_new_context_with_model: freq_scale = 1\n",
+      "llama_kv_cache_init:        CPU KV buffer size =  1024.00 MiB\n",
+      "llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB\n",
+      "llama_new_context_with_model:        CPU  output buffer size =     0.12 MiB\n",
+      "llama_new_context_with_model:        CPU compute buffer size =   164.01 MiB\n",
+      "llama_new_context_with_model: graph nodes  = 1030\n",
+      "llama_new_context_with_model: graph splits = 1\n",
+      "AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 0 | \n",
+      "Model metadata: {'tokenizer.ggml.unknown_token_id': '0', 'tokenizer.ggml.eos_token_id': '2', 'general.architecture': 'llama', 'llama.context_length': '4096', 'general.name': 'LLaMA v2', 'llama.embedding_length': '4096', 'llama.feed_forward_length': '11008', 'llama.attention.layer_norm_rms_epsilon': '0.000001', 'llama.rope.dimension_count': '128', 'llama.attention.head_count': '32', 'tokenizer.ggml.bos_token_id': '1', 'llama.block_count': '32', 'llama.attention.head_count_kv': '32', 'general.quantization_version': '2', 'tokenizer.ggml.model': 'llama', 'general.file_type': '7'}\n",
+      "Using fallback chat format: llama-2\n"
+     ]
+    }
+   ],
+   "source": [
+    "llm = LlamaCpp(\n",
+    "    model_path=\"llama-2-7b-chat.Q8_0.gguf\",\n",
+    "    n_gpu_layers=-1,\n",
+    "    n_batch=512,\n",
+    "    n_ctx=2048,\n",
+    "    f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls\n",
+    "    callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "43e06f56-ef97-451b-87d9-8465ea442aed",
+   "metadata": {},
+   "source": [
+    "**Now let's ask the same question to Llama model without showing them the earnings release.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "1033dd82-5532-437d-a548-27695e109589",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "?\n",
+      "(NASDAQ:INTC)\n",
+      "Intel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year."
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     131.20 ms\n",
+      "llama_print_timings:      sample time =      16.05 ms /    68 runs   (    0.24 ms per token,  4236.76 tokens per second)\n",
+      "llama_print_timings: prompt eval time =     131.14 ms /    16 tokens (    8.20 ms per token,   122.01 tokens per second)\n",
+      "llama_print_timings:        eval time =    3225.00 ms /    67 runs   (   48.13 ms per token,    20.78 tokens per second)\n",
+      "llama_print_timings:       total time =    3466.40 ms /    83 tokens\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"?\\n(NASDAQ:INTC)\\nIntel's CCG (Client Computing Group) revenue for Q1 2024 was $9.6 billion, a decrease of 35% from the previous quarter and a decrease of 42% from the same period last year.\""
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm.invoke(question)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "75f5cb10-746f-4e37-9386-b85a4d2b84ef",
+   "metadata": {},
+   "source": [
+    "**As you can see, model is giving wrong information. Correct asnwer is CCG revenue in Q1 2024 is $7.5B. Now let's apply RAG using the earning release document**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f4150ec-5692-4756-b11a-22feb7ab88ff",
+   "metadata": {},
+   "source": [
+    "**in RAG, we modify the input prompt by adding relevent documents with the question. Here, we use one of the popular RAG prompt**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "226c14b0-f43e-4a1f-a1e4-04731d467ec4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['context', 'question'], template=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: {question} \\nContext: {context} \\nAnswer:\"))]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "\n",
+    "rag_prompt = hub.pull(\"rlm/rag-prompt\")\n",
+    "rag_prompt.messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77deb6a0-0950-450a-916a-f2a029676c20",
+   "metadata": {},
+   "source": [
+    "**Appending all retreived documents in a single document**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "2dbc3327-6ef3-4c1f-8797-0c71964b0921",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2e2d9f18-49d0-43a3-bea8-78746ffa86b7",
+   "metadata": {},
+   "source": [
+    "**The last step is to create a chain using langchain tool that will create an e2e pipeline. It will take question and context as an input.**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "427379c2-51ff-4e0f-8278-a45221363299",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough, RunnablePick\n",
+    "\n",
+    "# Chain\n",
+    "chain = (\n",
+    "    RunnablePassthrough.assign(context=RunnablePick(\"context\") | format_docs)\n",
+    "    | rag_prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "095d6280-c949-4d00-8e32-8895a82d245f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Llama.generate: prefix-match hit\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Based on the provided context, Intel CCG revenue in Q1 2024 was $7.5 billion up 31%."
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     131.20 ms\n",
+      "llama_print_timings:      sample time =       7.74 ms /    31 runs   (    0.25 ms per token,  4004.13 tokens per second)\n",
+      "llama_print_timings: prompt eval time =    2529.41 ms /   674 tokens (    3.75 ms per token,   266.46 tokens per second)\n",
+      "llama_print_timings:        eval time =    1542.94 ms /    30 runs   (   51.43 ms per token,    19.44 tokens per second)\n",
+      "llama_print_timings:       total time =    4123.68 ms /   704 tokens\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Based on the provided context, Intel CCG revenue in Q1 2024 was $7.5 billion up 31%.'"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"context\": docs, \"question\": question})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "638364b2-6bd2-4471-9961-d3a1d1b9d4ee",
+   "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 separately**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "4654e5b7-635f-4767-8b31-4c430164cdd5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vectorstore.as_retriever()\n",
+    "qa_chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | rag_prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0979f393-fd0a-4e82-b844-68371c6ad68f",
+   "metadata": {},
+   "source": [
+    "**Now we only need to pass the question to the chain and it will fetch the contexts directly from the vector database to generate the answer**\n",
+    "<br>\n",
+    "**Let's try with another question**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "3ea07b82-e6ec-4084-85f4-191373530172",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Llama.generate: prefix-match hit\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " According to the provided context, Intel DCAI revenue in Q1 2024 was $3.0 billion up 5%."
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     131.20 ms\n",
+      "llama_print_timings:      sample time =       6.28 ms /    31 runs   (    0.20 ms per token,  4937.88 tokens per second)\n",
+      "llama_print_timings: prompt eval time =    2681.93 ms /   730 tokens (    3.67 ms per token,   272.19 tokens per second)\n",
+      "llama_print_timings:        eval time =    1471.07 ms /    30 runs   (   49.04 ms per token,    20.39 tokens per second)\n",
+      "llama_print_timings:       total time =    4206.77 ms /   760 tokens\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' According to the provided context, Intel DCAI revenue in Q1 2024 was $3.0 billion up 5%.'"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "qa_chain.invoke(\"what is Intel DCAI revenue in Q1 2024?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9407f2a0-4a35-4315-8e96-02fcb80f210c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.11.1 64-bit",
+   "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": "3.11.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "1a1af0ee75eeea9e2e1ee996c87e7a2b11a0bebd85af04bb136d915cefc0abce"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/rag_with_quantized_embeddings.ipynb

@@ -36,10 +36,10 @@
     "from bs4 import BeautifulSoup as Soup\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryByteStore, LocalFileStore\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.document_loaders.recursive_url_loader import (\n",
     "    RecursiveUrlLoader,\n",
     ")\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "# For our example, we'll load docs from the web\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
@@ -370,13 +370,14 @@
    ],
    "source": [
     "import torch\n",
-    "from langchain.llms.huggingface_pipeline import HuggingFacePipeline\n",
-    "from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n",
+    "from langchain_huggingface.llms import HuggingFacePipeline\n",
+    "from optimum.intel.ipex import IPEXModelForCausalLM\n",
+    "from transformers import AutoTokenizer, pipeline\n",
     "\n",
     "model_id = \"Intel/neural-chat-7b-v3-3\"\n",
     "tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
-    "model = AutoModelForCausalLM.from_pretrained(\n",
-    "    model_id, device_map=\"auto\", torch_dtype=torch.bfloat16\n",
+    "model = IPEXModelForCausalLM.from_pretrained(\n",
+    "    model_id, torch_dtype=torch.bfloat16, export=True\n",
     ")\n",
     "\n",
     "pipe = pipeline(\"text-generation\", model=model, tokenizer=tokenizer, max_new_tokens=100)\n",
@@ -581,7 +582,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.10.14"
   }
  },
  "nbformat": 4,

cookbook/sql_db_qa.mdx

@@ -740,7 +740,7 @@ Even this relatively large model will most likely fail to generate more complica
 
 
 ```bash
-poetry run pip install pyyaml chromadb
+poetry run pip install pyyaml langchain_chroma
 import yaml
 ```
 
@@ -994,7 +994,7 @@ from langchain.prompts import FewShotPromptTemplate, PromptTemplate
 from langchain.chains.sql_database.prompt import _sqlite_prompt, PROMPT_SUFFIX
 from langchain_huggingface import HuggingFaceEmbeddings
 from langchain.prompts.example_selector.semantic_similarity import SemanticSimilarityExampleSelector
-from langchain_community.vectorstores import Chroma
+from langchain_chroma import Chroma
 
 example_prompt = PromptTemplate(
     input_variables=["table_info", "input", "sql_cmd", "sql_result", "answer"],

cookbook/together_ai.ipynb

@@ -22,7 +22,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install --quiet pypdf chromadb tiktoken openai langchain-together"
+    "! pip install --quiet pypdf tiktoken openai langchain-chroma langchain-together"
    ]
   },
   {
@@ -45,8 +45,8 @@
     "all_splits = text_splitter.split_documents(data)\n",
     "\n",
     "# Add to vectorDB\n",
+    "from langchain_chroma import Chroma\n",
     "from langchain_community.embeddings import OpenAIEmbeddings\n",
-    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "\"\"\"\n",
     "from langchain_together.embeddings import TogetherEmbeddings\n",

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

@@ -13,7 +13,12 @@ OUTPUT_NEW_DOCS_DIR = $(OUTPUT_NEW_DIR)/docs
 
 PYTHON = .venv/bin/python
 
-PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec test -e "{}/pyproject.toml" \; -print | grep -vE "airbyte|ibm" | tr '\n' ' ')
+PARTNER_DEPS_LIST := $(shell find ../libs/partners -mindepth 1 -maxdepth 1 -type d -exec sh -c ' \
+for dir; do \
+    if find "$$dir" -maxdepth 1 -type f \( -name "pyproject.toml" -o -name "setup.py" \) | grep -q .; then \
+        echo "$$dir"; \
+    fi \
+done' sh {} + | grep -vE "airbyte|ibm|databricks" | tr '\n' ' ')
 
 PORT ?= 3001
 
@@ -28,19 +33,20 @@ 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 uv pip install --pre -r vercel_requirements.txt
+	$(PYTHON) -m uv pip install --pre --editable $(PARTNER_DEPS_LIST)
 
 generate-files:
 	mkdir -p $(INTERMEDIATE_DIR)
-	cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
-	mkdir -p $(INTERMEDIATE_DIR)/templates
+	cp -rp $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
 
-	$(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
+	$(PYTHON) scripts/tool_feat_table.py $(INTERMEDIATE_DIR)
 
-	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
+	$(PYTHON) scripts/kv_store_feat_table.py $(INTERMEDIATE_DIR)
 
-	wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
+	$(PYTHON) scripts/partner_pkg_table.py $(INTERMEDIATE_DIR)
+
+	curl https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md | sed 's/<=/\&lt;=/g' > $(INTERMEDIATE_DIR)/langserve.md
 	$(PYTHON) scripts/resolve_local_links.py $(INTERMEDIATE_DIR)/langserve.md https://github.com/langchain-ai/langserve/tree/main/
 
 copy-infra:
@@ -59,22 +65,27 @@ render:
 	$(PYTHON) scripts/notebook_convert.py $(INTERMEDIATE_DIR) $(OUTPUT_NEW_DOCS_DIR)
 
 md-sync:
-	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --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
 	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 +1,411 @@
-pre {
-  white-space: break-spaces;
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@400;700&display=swap');
+
+/*******************************************************************************
+* master color map. Only the colors that actually differ between light and dark
+* themes are specified separately.
+*
+* To see the full list of colors see https://www.figma.com/file/rUrrHGhUBBIAAjQ82x6pz9/PyData-Design-system---proposal-for-implementation-(2)?node-id=1234%3A765&t=ifcFT1JtnrSshGfi-1
+*/
+/**
+* Function to get items from nested maps
+*/
+/* Assign base colors for the PyData theme */
+:root {
+  --pst-teal-50: #f4fbfc;
+  --pst-teal-100: #e9f6f8;
+  --pst-teal-200: #d0ecf1;
+  --pst-teal-300: #abdde6;
+  --pst-teal-400: #3fb1c5;
+  --pst-teal-500: #0a7d91;
+  --pst-teal-600: #085d6c;
+  --pst-teal-700: #064752;
+  --pst-teal-800: #042c33;
+  --pst-teal-900: #021b1f;
+  --pst-violet-50: #f4eefb;
+  --pst-violet-100: #e0c7ff;
+  --pst-violet-200: #d5b4fd;
+  --pst-violet-300: #b780ff;
+  --pst-violet-400: #9c5ffd;
+  --pst-violet-500: #8045e5;
+  --pst-violet-600: #6432bd;
+  --pst-violet-700: #4b258f;
+  --pst-violet-800: #341a61;
+  --pst-violet-900: #1e0e39;
+  --pst-gray-50: #f9f9fa;
+  --pst-gray-100: #f3f4f5;
+  --pst-gray-200: #e5e7ea;
+  --pst-gray-300: #d1d5da;
+  --pst-gray-400: #9ca4af;
+  --pst-gray-500: #677384;
+  --pst-gray-600: #48566b;
+  --pst-gray-700: #29313d;
+  --pst-gray-800: #222832;
+  --pst-gray-900: #14181e;
+  --pst-pink-50: #fcf8fd;
+  --pst-pink-100: #fcf0fa;
+  --pst-pink-200: #f8dff5;
+  --pst-pink-300: #f3c7ee;
+  --pst-pink-400: #e47fd7;
+  --pst-pink-500: #c132af;
+  --pst-pink-600: #912583;
+  --pst-pink-700: #6e1c64;
+  --pst-pink-800: #46123f;
+  --pst-pink-900: #2b0b27;
+  --pst-foundation-white: #ffffff;
+  --pst-foundation-black: #14181e;
+  --pst-green-10: #f1fdfd;
+  --pst-green-50: #E0F7F6;
+  --pst-green-100: #B3E8E6;
+  --pst-green-200: #80D6D3;
+  --pst-green-300: #4DC4C0;
+  --pst-green-400: #4FB2AD;
+  --pst-green-500: #287977;
+  --pst-green-600: #246161;
+  --pst-green-700: #204F4F;
+  --pst-green-800: #1C3C3C;
+  --pst-green-900: #0D2427;
+  --pst-lilac-50: #f4eefb;
+  --pst-lilac-100: #DAD6FE;
+  --pst-lilac-200: #BCB2FD;
+  --pst-lilac-300: #9F8BFA;
+  --pst-lilac-400: #7F5CF6;
+  --pst-lilac-500: #6F3AED;
+  --pst-lilac-600: #6028D9;
+  --pst-lilac-700: #5021B6;
+  --pst-lilac-800: #431D95;
+  --pst-lilac-900: #1e0e39;
+  --pst-header-height: 2.5rem;
 }
 
-@media (min-width: 1200px) {
-  .container,
-  .container-lg,
-  .container-md,
-  .container-sm,
-  .container-xl {
-    max-width: 2560px !important;
-  }
+html {
+    --pst-font-family-base: 'Inter';
+    --pst-font-family-heading: 'Inter Tight', sans-serif;
 }
 
-#my-component-root *,
-#headlessui-portal-root * {
-  z-index: 10000;
+/*******************************************************************************
+* write the color rules for each theme (light/dark)
+*/
+/* NOTE:
+ * Mixins enable us to reuse the same definitions for the different modes
+ * https://sass-lang.com/documentation/at-rules/mixin
+ * something inserts a variable into a CSS selector or property name
+ * https://sass-lang.com/documentation/interpolation
+ */
+/* Defaults to light mode if data-theme is not set */
+html:not([data-theme]) {
+  --pst-color-primary: #287977;
+  --pst-color-primary-bg: #80D6D3;
+  --pst-color-secondary: #6F3AED;
+  --pst-color-secondary-bg: #DAD6FE;
+  --pst-color-accent: #c132af;
+  --pst-color-accent-bg: #f8dff5;
+  --pst-color-info: #276be9;
+  --pst-color-info-bg: #dce7fc;
+  --pst-color-warning: #f66a0a;
+  --pst-color-warning-bg: #f8e3d0;
+  --pst-color-success: #00843f;
+  --pst-color-success-bg: #d6ece1;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #d72d47;
+  --pst-color-danger-bg: #f9e1e4;
+  --pst-color-text-base: #222832;
+  --pst-color-text-muted: #48566b;
+  --pst-color-heading-color: #ffffff;
+  --pst-color-shadow: rgba(0, 0, 0, 0.1);
+  --pst-color-border: #d1d5da;
+  --pst-color-border-muted: rgba(23, 23, 26, 0.2);
+  --pst-color-inline-code: #912583;
+  --pst-color-inline-code-links: #246161;
+  --pst-color-target: #f3cf95;
+  --pst-color-background: #ffffff;
+  --pst-color-on-background: #F4F9F8;
+  --pst-color-surface: #F4F9F8;
+  --pst-color-on-surface: #222832;
+}
+html:not([data-theme]) {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html:not([data-theme]) .only-dark,
+html:not([data-theme]) .only-dark ~ figcaption {
+  display: none !important;
 }
 
-table.longtable code {
-  white-space: normal;
+/* NOTE: @each {...} is like a for-loop
+ * https://sass-lang.com/documentation/at-rules/control/each
+ */
+html[data-theme=light] {
+  --pst-color-primary: #287977;
+  --pst-color-primary-bg: #80D6D3;
+  --pst-color-secondary: #6F3AED;
+  --pst-color-secondary-bg: #DAD6FE;
+  --pst-color-accent: #c132af;
+  --pst-color-accent-bg: #f8dff5;
+  --pst-color-info: #276be9;
+  --pst-color-info-bg: #dce7fc;
+  --pst-color-warning: #f66a0a;
+  --pst-color-warning-bg: #f8e3d0;
+  --pst-color-success: #00843f;
+  --pst-color-success-bg: #d6ece1;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #d72d47;
+  --pst-color-danger-bg: #f9e1e4;
+  --pst-color-text-base: #222832;
+  --pst-color-text-muted: #48566b;
+  --pst-color-heading-color: #ffffff;
+  --pst-color-shadow: rgba(0, 0, 0, 0.1);
+  --pst-color-border: #d1d5da;
+  --pst-color-border-muted: rgba(23, 23, 26, 0.2);
+  --pst-color-inline-code: #912583;
+  --pst-color-inline-code-links: #246161;
+  --pst-color-target: #f3cf95;
+  --pst-color-background: #ffffff;
+  --pst-color-on-background: #F4F9F8;
+  --pst-color-surface: #F4F9F8;
+  --pst-color-on-surface: #222832;
+  color-scheme: light;
+}
+html[data-theme=light] {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html[data-theme=light] .only-dark,
+html[data-theme=light] .only-dark ~ figcaption {
+  display: none !important;
 }
 
-table.longtable td {
-  max-width: 600px;
+html[data-theme=dark] {
+  --pst-color-primary: #4FB2AD;
+  --pst-color-primary-bg: #1C3C3C;
+  --pst-color-secondary: #7F5CF6;
+  --pst-color-secondary-bg: #431D95;
+  --pst-color-accent: #e47fd7;
+  --pst-color-accent-bg: #46123f;
+  --pst-color-info: #79a3f2;
+  --pst-color-info-bg: #06245d;
+  --pst-color-warning: #ff9245;
+  --pst-color-warning-bg: #652a02;
+  --pst-color-success: #5fb488;
+  --pst-color-success-bg: #002f17;
+  --pst-color-attention: var(--pst-color-warning);
+  --pst-color-attention-bg: var(--pst-color-warning-bg);
+  --pst-color-danger: #e78894;
+  --pst-color-danger-bg: #4e111b;
+  --pst-color-text-base: #ced6dd;
+  --pst-color-text-muted: #9ca4af;
+  --pst-color-heading-color: #14181e;
+  --pst-color-shadow: rgba(0, 0, 0, 0.2);
+  --pst-color-border: #48566b;
+  --pst-color-border-muted: #29313d;
+  --pst-color-inline-code: #f3c7ee;
+  --pst-color-inline-code-links: #4FB2AD;
+  --pst-color-target: #675c04;
+  --pst-color-background: #14181e;
+  --pst-color-on-background: #222832;
+  --pst-color-surface: #29313d;
+  --pst-color-on-surface: #f3f4f5;
+  /* Adjust images in dark mode (unless they have class .only-dark or
+   * .dark-light, in which case assume they're already optimized for dark
+   * mode).
+   */
+  /* Give images a light background in dark mode in case they have
+  *  transparency and black text (unless they have class .only-dark or .dark-light, in
+  *  which case assume they're already optimized for dark mode).
+  */
+  color-scheme: dark;
 }
+html[data-theme=dark] {
+  --pst-color-link: var(--pst-color-primary);
+  --pst-color-link-hover: var(--pst-color-secondary);
+}
+html[data-theme=dark] .only-light,
+html[data-theme=dark] .only-light ~ figcaption {
+  display: none !important;
+}
+html[data-theme=dark] img:not(.only-dark):not(.dark-light) {
+  filter: brightness(0.8) contrast(1.2);
+}
+html[data-theme=dark] .bd-content img:not(.only-dark):not(.dark-light) {
+  background: rgb(255, 255, 255);
+  border-radius: 0.25rem;
+}
+html[data-theme=dark] .MathJax_SVG * {
+  fill: var(--pst-color-text-base);
+}
+
+.pst-color-primary {
+  color: var(--pst-color-primary);
+}
+
+.pst-color-secondary {
+  color: var(--pst-color-secondary);
+}
+
+.pst-color-accent {
+  color: var(--pst-color-accent);
+}
+
+.pst-color-info {
+  color: var(--pst-color-info);
+}
+
+.pst-color-warning {
+  color: var(--pst-color-warning);
+}
+
+.pst-color-success {
+  color: var(--pst-color-success);
+}
+
+.pst-color-attention {
+  color: var(--pst-color-attention);
+}
+
+.pst-color-danger {
+  color: var(--pst-color-danger);
+}
+
+.pst-color-text-base {
+  color: var(--pst-color-text-base);
+}
+
+.pst-color-text-muted {
+  color: var(--pst-color-text-muted);
+}
+
+.pst-color-heading-color {
+  color: var(--pst-color-heading-color);
+}
+
+.pst-color-shadow {
+  color: var(--pst-color-shadow);
+}
+
+.pst-color-border {
+  color: var(--pst-color-border);
+}
+
+.pst-color-border-muted {
+  color: var(--pst-color-border-muted);
+}
+
+.pst-color-inline-code {
+  color: var(--pst-color-inline-code);
+}
+
+.pst-color-inline-code-links {
+  color: var(--pst-color-inline-code-links);
+}
+
+.pst-color-target {
+  color: var(--pst-color-target);
+}
+
+.pst-color-background {
+  color: var(--pst-color-background);
+}
+
+.pst-color-on-background {
+  color: var(--pst-color-on-background);
+}
+
+.pst-color-surface {
+  color: var(--pst-color-surface);
+}
+
+.pst-color-on-surface {
+  color: var(--pst-color-on-surface);
+}
+
+
+
+/* Adjust the height of the navbar */
+.bd-header .bd-header__inner{
+    height: 52px; /* Adjust this value as needed */
+}
+
+.navbar-nav > li > a {
+    line-height: 52px; /* Vertically center the navbar links */
+}
+
+/* Make sure the navbar items align properly */
+.navbar-nav {
+    display: flex;
+}
+
+
+.bd-header .navbar-header-items__start{
+  margin-left: 0rem
+}
+
+.bd-header button.primary-toggle {
+  margin-right: 0rem;
+}
+
+.bd-header ul.navbar-nav .dropdown .dropdown-menu {
+  overflow-y: auto; /* Enable vertical scrolling */
+  max-height: 80vh
+}
+
+.bd-sidebar-primary {
+    width: 22%;  /* Adjust this value to your preference */
+    line-height: 1.4;
+}
+
+.bd-sidebar-secondary {
+    line-height: 1.4;
+}
+
+.toc-entry a.nav-link, .toc-entry a>code {  
+  background-color: transparent;
+  border-color: transparent;
+}
+
+.bd-sidebar-primary code{
+  background-color: transparent;
+  border-color: transparent;
+}
+
+
+.toctree-wrapper li[class^=toctree-l1]>a {
+  font-size: 1.3em
+}
+
+.toctree-wrapper li[class^=toctree-l1] {
+  margin-bottom: 2em;
+}
+
+.toctree-wrapper li[class^=toctree-l]>ul {
+  margin-top: 0.5em;
+  font-size: 0.9em;
+}
+
+*, :after, :before {
+  font-style: normal;
+}
+
+div.deprecated {
+  margin-top: 0.5em;
+  margin-bottom: 2em;
+}
+
+.admonition-beta.admonition, div.admonition-beta.admonition {
+  border-color: var(--pst-color-warning);
+  margin-top:0.5em;
+  margin-bottom: 2em;
+}
+
+.admonition-beta>.admonition-title, div.admonition-beta>.admonition-title {
+  background-color: var(--pst-color-warning-bg);
+}
+
+dl[class]:not(.option-list):not(.field-list):not(.footnote):not(.glossary):not(.simple) dd {
+  margin-left: 1rem;
+}
+
+p {
+  font-size: 0.9rem;
+  margin-bottom: 0.5rem;
+}

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

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

docs/api_reference/_static/wordmark-api.svg

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

docs/api_reference/conf.py

@@ -15,6 +15,8 @@ from pathlib import Path
 
 import toml
 from docutils import nodes
+from docutils.parsers.rst.directives.admonitions import BaseAdmonition
+from docutils.statemachine import StringList
 from sphinx.util.docutils import SphinxDirective
 
 # If extensions (or modules to document with autodoc) are in another directory,
@@ -24,7 +26,6 @@ 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 +61,41 @@ class ExampleLinksDirective(SphinxDirective):
             item_node.append(para_node)
             list_node.append(item_node)
         if list_node.children:
-            title_node = nodes.title()
+            title_node = nodes.rubric()
             title_node.append(nodes.Text(f"Examples using {class_or_func_name}"))
             return [title_node, list_node]
         return [list_node]
 
 
+class Beta(BaseAdmonition):
+    required_arguments = 0
+    node_class = nodes.admonition
+
+    def run(self):
+        self.content = self.content or StringList(
+            [
+                (
+                    "This feature is in beta. It is actively being worked on, so the "
+                    "API may change."
+                )
+            ]
+        )
+        self.arguments = self.arguments or ["Beta"]
+        return super().run()
+
+
 def setup(app):
     app.add_directive("example_links", ExampleLinksDirective)
+    app.add_directive("beta", Beta)
 
 
 # -- Project information -----------------------------------------------------
 
 project = "🦜🔗 LangChain"
-copyright = "2023, LangChain, Inc."
-author = "LangChain, Inc."
+copyright = "2023, LangChain Inc"
+author = "LangChain, Inc"
 
-version = data["tool"]["poetry"]["version"]
-release = version
-
-html_title = project + " " + version
+html_favicon = "_static/img/brand/favicon.png"
 html_last_updated_fmt = "%b %d, %Y"
 
 
@@ -95,11 +111,13 @@ extensions = [
     "sphinx.ext.napoleon",
     "sphinx.ext.viewcode",
     "sphinxcontrib.autodoc_pydantic",
-    "sphinx_copybutton",
-    "sphinx_panels",
     "IPython.sphinxext.ipython_console_highlighting",
+    "myst_parser",
+    "_extensions.gallery_directive",
+    "sphinx_design",
+    "sphinx_copybutton",
 ]
-source_suffix = [".rst"]
+source_suffix = [".rst", ".md"]
 
 # some autodoc pydantic options are repeated in the actual template.
 # potentially user error, but there may be bugs in the sphinx extension
@@ -131,23 +149,82 @@ 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 +232,6 @@ 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 +241,7 @@ 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"]
@@ -178,3 +251,12 @@ autosummary_generate = True
 
 html_copy_source = False
 html_show_sourcelink = False
+
+# Set canonical URL from the Read the Docs Domain
+html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "")
+
+# Tell Jinja2 templates the build is running on Read the Docs
+if os.environ.get("READTHEDOCS", "") == "True":
+    html_context["READTHEDOCS"] = True
+
+master_doc = "index"

docs/api_reference/create_api_rst.py

@@ -10,12 +10,21 @@ from pathlib import Path
 from typing import Dict, List, Literal, Optional, Sequence, TypedDict, Union
 
 import toml
+import typing_extensions
+from langchain_core.runnables import Runnable, RunnableSerializable
 from pydantic import BaseModel
 
 ROOT_DIR = Path(__file__).parents[2].absolute()
 HERE = Path(__file__).parent
 
-ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
+ClassKind = Literal[
+    "TypedDict",
+    "Regular",
+    "Pydantic",
+    "enum",
+    "RunnablePydantic",
+    "RunnableNonPydantic",
+]
 
 
 class ClassInfo(TypedDict):
@@ -29,6 +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):
@@ -40,6 +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):
@@ -69,8 +82,36 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
             continue
 
         if inspect.isclass(type_):
-            if type(type_) == typing._TypedDictMeta:  # type: ignore
+            # The type of the class is used to select a template
+            # for the object when rendering the documentation.
+            # See `templates` directory for defined templates.
+            # This is a hacky solution to distinguish between different
+            # kinds of thing that we want to render.
+            if type(type_) is typing_extensions._TypedDictMeta:  # type: ignore
                 kind: ClassKind = "TypedDict"
+            elif type(type_) is typing._TypedDictMeta:  # type: ignore
+                kind: ClassKind = "TypedDict"
+            elif (
+                issubclass(type_, Runnable)
+                and issubclass(type_, BaseModel)
+                and type_ is not Runnable
+            ):
+                # RunnableSerializable subclasses from Pydantic which
+                # for which we use autodoc_pydantic for rendering.
+                # We need to distinguish these from regular Pydantic
+                # classes so we can hide inherited Runnable methods
+                # and provide a link to the Runnable interface from
+                # the template.
+                kind = "RunnablePydantic"
+            elif (
+                issubclass(type_, Runnable)
+                and not issubclass(type_, BaseModel)
+                and type_ is not Runnable
+            ):
+                # These are not pydantic classes but are Runnable.
+                # We'll hide all the inherited methods from Runnable
+                # but use a regular class template to render.
+                kind = "RunnableNonPydantic"
             elif issubclass(type_, Enum):
                 kind = "enum"
             elif issubclass(type_, BaseModel):
@@ -84,6 +125,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     qualified_name=f"{namespace}.{name}",
                     kind=kind,
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         elif inspect.isfunction(type_):
@@ -92,6 +134,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                     name=name,
                     qualified_name=f"{namespace}.{name}",
                     is_public=not name.startswith("_"),
+                    is_deprecated=".. deprecated::" in (type_.__doc__ or ""),
                 )
             )
         else:
@@ -128,11 +171,11 @@ def _load_package_modules(
     of the modules/packages are part of the package vs. 3rd party or built-in.
 
     Parameters:
-        package_directory: Path to the package directory.
-        submodule: Optional name of submodule to load.
+        package_directory (Union[str, Path]): Path to the package directory.
+        submodule (Optional[str]): Optional name of submodule to load.
 
     Returns:
-        list: A list of loaded module objects.
+        Dict[str, ModuleMembers]: A dictionary where keys are module names and values are ModuleMembers objects.
     """
     package_path = (
         Path(package_directory)
@@ -196,7 +239,7 @@ def _construct_doc(
     package_namespace: str,
     members_by_namespace: Dict[str, ModuleMembers],
     package_version: str,
-) -> str:
+) -> List[typing.Tuple[str, str]]:
     """Construct the contents of the reference.rst file for the given package.
 
     Args:
@@ -208,23 +251,62 @@ def _construct_doc(
     Returns:
         The contents of the reference.rst file.
     """
-    full_doc = f"""\
-=======================
-``{package_namespace}`` {package_version}
-=======================
+    docs = []
+    index_doc = f"""\
+:html_theme.sidebar_secondary.remove:
 
+.. currentmodule:: {package_namespace}
+
+.. _{package_namespace}:
+
+======================================
+{package_namespace.replace('_', '-')}: {package_version}
+======================================
+
+.. automodule:: {package_namespace}
+    :no-members:
+    :no-inherited-members:
+
+.. toctree::
+    :hidden:
+    :maxdepth: 2
+    
+"""
+    index_autosummary = """
 """
     namespaces = sorted(members_by_namespace)
 
     for module in namespaces:
+        index_doc += f"    {module}\n"
+        module_doc = f"""\
+.. currentmodule:: {package_namespace}
+
+.. _{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}
 
@@ -232,16 +314,26 @@ 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"]):
@@ -251,22 +343,29 @@ Classes
                     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"
 
-                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::
@@ -276,7 +375,80 @@ 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:
@@ -288,21 +460,30 @@ 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:
@@ -314,6 +495,7 @@ 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:
@@ -344,12 +526,121 @@ def _get_package_version(package_dir: Path) -> str:
 
 def _out_file_path(package_name: str) -> Path:
     """Return the path to the file containing the documentation."""
-    return HERE / f"{package_name.replace('-', '_')}_api_reference.rst"
+    return HERE / f"{package_name.replace('-', '_')}"
 
 
-def _doc_first_line(package_name: str) -> str:
-    """Return the path to the file containing the documentation."""
-    return f".. {package_name.replace('-', '_')}_api_reference:\n\n"
+def _build_index(dirs: List[str]) -> None:
+    custom_names = {
+        "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:
@@ -359,7 +650,7 @@ 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")
         ]
         dirs += [
             dir_
@@ -377,6 +668,8 @@ def main(dirs: Optional[list] = None) -> None:
         else:
             print("Building package:", dir_)
             _build_rst_file(package_name=dir_)
+
+    _build_index(dirs)
     print("API reference files built.")
 
 

docs/api_reference/index.rst

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

docs/api_reference/requirements.txt

@@ -1,17 +1,11 @@
--e libs/experimental
--e libs/langchain
--e libs/core
--e libs/community
-pydantic<2
-autodoc_pydantic==1.8.0
-myst_parser
-nbsphinx==0.8.9
-sphinx>=5
-sphinx-autobuild==2021.3.14
-sphinx_rtd_theme==1.0.0
-sphinx-typlog-theme==0.8.0
-sphinx-panels
-toml
-myst_nb
-sphinx_copybutton
-pydata-sphinx-theme==0.13.1
+autodoc_pydantic>=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

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 %}
@@ -22,15 +22,15 @@
 
    .. autosummary::
    {% for item in methods %}
-      ~{{ name }}.{{ item }}
+      ~{{ item }}
    {%- endfor %}
 
    {% for item in methods %}
-   .. automethod:: {{ name }}.{{ item }}
+   .. automethod:: {{ item }}
    {%- endfor %}
 
    {% endif %}
    {% endblock %}
 
 
-.. example_links:: {{ objname }}
+.. example_links:: {{ objname }}

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 }}
@@ -15,6 +15,8 @@
     :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, 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 %}
     {% endblock %}

docs/api_reference/templates/runnable_non_pydantic.rst

@@ -0,0 +1,40 @@
+{{ objname }}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autoclass:: {{ objname }}
+
+.. NOTE:: {{objname}} implements the standard :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>`. 🏃
+
+    The :py:class:`Runnable Interface <langchain_core.runnables.base.Runnable>` has additional methods that are available on runnables, such as :py:meth:`with_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
+   {% block attributes %}
+   {% if attributes %}
+   .. rubric:: {{ _('Attributes') }}
+
+   .. autosummary::
+   {% for item in attributes %}
+      ~{{ item }}
+   {%- endfor %}
+   {% endif %}
+   {% endblock %}
+
+   {% block methods %}
+   {% if methods %}
+   .. rubric:: {{ _('Methods') }}
+
+   .. autosummary::
+   {% for item in methods %}
+      ~{{ item }}
+   {%- endfor %}
+
+   {% for item in methods %}
+   .. automethod:: {{ item }}
+   {%- endfor %}
+
+   {% endif %}
+   {% endblock %}
+
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/runnable_pydantic.rst

@@ -0,0 +1,24 @@
+{{ objname }}
+{{ underline }}==============
+
+.. currentmodule:: {{ module }}
+
+.. autopydantic_model:: {{ objname }}
+    :model-show-json: False
+    :model-show-config-summary: False
+    :model-show-validator-members: False
+    :model-show-field-summary: False
+    :field-signature-prefix: param
+    :members:
+    :undoc-members:
+    :inherited-members:
+    :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, 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_types <langchain_core.runnables.base.Runnable.with_types>`, :py:meth:`with_retry <langchain_core.runnables.base.Runnable.with_retry>`, :py:meth:`assign <langchain_core.runnables.base.Runnable.assign>`, :py:meth:`bind <langchain_core.runnables.base.Runnable.bind>`, :py:meth:`get_graph <langchain_core.runnables.base.Runnable.get_graph>`, and more.
+
+.. example_links:: {{ objname }}

docs/api_reference/templates/typeddict.rst

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

docs/api_reference/themes/COPYRIGHT.txt

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

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

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

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

@@ -1,135 +0,0 @@
-{# TEMPLATE VAR SETTINGS #}
-{%- set url_root = pathto('', 1) %}
-{%- if url_root == '#' %}{% set url_root = '' %}{% endif %}
-{%- if not embedded and docstitle %}
-  {%- set titlesuffix = " — "|safe + docstitle|e %}
-{%- else %}
-  {%- set titlesuffix = "" %}
-{%- endif %}
-{%- set lang_attr = 'en' %}
-
-<!DOCTYPE html>
-<!--[if IE 8]><html class="no-js lt-ie9" lang="{{ lang_attr }}" > <![endif]-->
-<!--[if gt IE 8]><!--> <html class="no-js" lang="{{ lang_attr }}" > <!--<![endif]-->
-<head>
-  <meta charset="utf-8">
-  {{ metatags }}
-  <meta name="viewport" content="width=device-width, initial-scale=1.0">
-
-  {% block htmltitle %}
-  <title>{{ title|striptags|e }}{{ titlesuffix }}</title>
-  {% endblock %}
-  <link rel="canonical" href="https://api.python.langchain.com/en/latest/{{pagename}}.html" />
-
-  {% if favicon_url %}
-  <link rel="shortcut icon" href="{{ favicon_url|e }}"/>
-  {% endif %}
-
-  <link rel="stylesheet" href="{{ pathto('_static/css/vendor/bootstrap.min.css', 1) }}" type="text/css" />
-  {%- for css in css_files %}
-    {%- if css|attr("rel") %}
-  <link rel="{{ css.rel }}" href="{{ pathto(css.filename, 1) }}" type="text/css"{% if css.title is not none %} title="{{ css.title }}"{% endif %} />
-    {%- else %}
-  <link rel="stylesheet" href="{{ pathto(css, 1) }}" type="text/css" />
-    {%- endif %}
-  {%- endfor %}
-  <link rel="stylesheet" href="{{ pathto('_static/' + style, 1) }}" type="text/css" />
-<script id="documentation_options" data-url_root="{{ pathto('', 1) }}" src="{{ pathto('_static/documentation_options.js', 1) }}"></script>
-<script src="{{ pathto('_static/jquery.js', 1) }}"></script>
-{%- block extrahead %} {% endblock %}
-</head>
-<body>
-{% include "nav.html" %}
-{%- block content %}
-<div class="d-flex" id="sk-doc-wrapper">
-    <input type="checkbox" name="sk-toggle-checkbox" id="sk-toggle-checkbox">
-    <label id="sk-sidemenu-toggle" class="sk-btn-toggle-toc btn sk-btn-primary" for="sk-toggle-checkbox">Toggle Menu</label>
-    <div id="sk-sidebar-wrapper" class="border-right">
-      <div class="sk-sidebar-toc-wrapper">
-        <div class="btn-group w-100 mb-2" role="group" aria-label="rellinks">
-          {%- if prev %}
-            <a href="{{ prev.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ prev.title|striptags }}">Prev</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Prev</a>
-          {%- endif %}
-          {%- if parents -%}
-            <a href="{{ parents[-1].link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ parents[-1].title|striptags }}">Up</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink disabled py-1">Up</a>
-          {%- endif %}
-          {%- if next %}
-            <a href="{{ next.link|e }}" role="button" class="btn sk-btn-rellink py-1" sk-rellink-tooltip="{{ next.title|striptags }}">Next</a>
-          {%- else %}
-            <a href="#" role="button" class="btn sk-btn-rellink py-1 disabled"">Next</a>
-          {%- endif %}
-        </div>
-            {%- if meta and meta['parenttoc']|tobool %}
-            <div class="sk-sidebar-toc">
-            {% set nav = get_nav_object(maxdepth=3, collapse=True, numbered=True) %}
-              <ul>
-              {% for main_nav_item in nav %}
-              {% if main_nav_item.active %}
-              <li>
-                <a href="{{ main_nav_item.url }}" class="sk-toc-active">{{ main_nav_item.title }}</a>
-              </li>
-              <ul>
-              {% for nav_item in main_nav_item.children %}
-                <li>
-                  <a href="{{ nav_item.url }}" class="{% if nav_item.active %}sk-toc-active{% endif %}">{{ nav_item.title }}</a>
-                  {% if nav_item.children %}
-                  <ul>
-                    {% for inner_child in nav_item.children %}
-                      <li class="sk-toctree-l3">
-                        <a href="{{ inner_child.url }}">{{ inner_child.title }}</a>
-                      </li>
-                    {% endfor %}
-                  </ul>
-                  {% endif %}
-                </li>
-              {% endfor %}
-              </ul>
-              {% endif %}
-              {% endfor %}
-              </ul>
-            </div>
-            {%- elif meta and meta['globalsidebartoc']|tobool %}
-            <div class="sk-sidebar-toc sk-sidebar-global-toc">
-              {{ toctree(maxdepth=2, titles_only=True) }}
-            </div>
-            {%- else %}
-            <div class="sk-sidebar-toc">
-              {{ toc }}
-            </div>
-            {%- endif %}
-      </div>
-    </div>
-    <div id="sk-page-content-wrapper">
-      <div class="sk-page-content container-fluid body px-md-3" role="main">
-        {% block body %}{% endblock %}
-      </div>
-    <div class="container">
-      <footer class="sk-content-footer">
-        {%- if pagename != 'index' %}
-        {%- if show_copyright %}
-          {%- if hasdoc('copyright') %}
-            {% trans path=pathto('copyright'), copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
-          {%- else %}
-            {% trans copyright=copyright|e %}&copy; {{ copyright }}.{% endtrans %}
-          {%- endif %}
-        {%- endif %}
-        {%- if last_updated %}
-          {% trans last_updated=last_updated|e %}Last updated on {{ last_updated }}.{% endtrans %}
-        {%- endif %}
-        {%- if show_source and has_source and sourcename %}
-          <a href="{{ pathto('_sources/' + sourcename, true)|e }}" rel="nofollow">{{ _('Show this page source') }}</a>
-        {%- endif %}
-        {%- endif %}
-      </footer>
-    </div>
-  </div>
-</div>
-{%- endblock %}
-<script src="{{ pathto('_static/js/vendor/bootstrap.min.js', 1) }}"></script>
-{% include "javascript.html" %}
-</body>
-</html>