test ci

.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/devcontainer.json

@@ -12,7 +12,7 @@
 
 	// The optional 'workspaceFolder' property is the path VS Code should open by default when
 	// connected. This is typically a file mount in .devcontainer/docker-compose.yml
-	"workspaceFolder": "/workspaces/langchain",
+	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
 
 	// Prevent the container from shutting down
 	"overrideCommand": true

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

.github/CODEOWNERS

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

.github/DISCUSSION_TEMPLATE/q-a.yml

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

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -16,7 +16,7 @@ body:
         if there's another way to solve your problem:
         
         [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-        [API Reference](https://python.langchain.com/api_reference/),
+        [API Reference](https://api.python.langchain.com/en/stable/),
         [GitHub search](https://github.com/langchain-ai/langchain),
         [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
         [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
@@ -29,14 +29,14 @@ body:
       options:
         - label: I added a very descriptive title to this issue.
           required: true
+        - label: I searched the LangChain documentation with the integrated search.
+          required: true
         - label: I used the GitHub search to find a similar question and didn't find it.
           required: true
         - label: I am sure that this is a bug in LangChain rather than my code.
           required: true
         - label: The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
           required: true
-        - label: I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.
-          required: true
   - type: textarea
     id: reproduction
     validations:
@@ -96,21 +96,25 @@ body:
     attributes:
       label: System Info
       description: |
-        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.
+        Please share your system info with us. 
         
-        Run the following command in your terminal and paste the output here:
+        "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:
         
         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

@@ -4,6 +4,9 @@ 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/ISSUE_TEMPLATE/documentation.yml

@@ -21,18 +21,11 @@ body:
       place to ask your question:
       
       [LangChain documentation with the integrated search](https://python.langchain.com/docs/get_started/introduction),
-      [API Reference](https://python.langchain.com/api_reference/),
+      [API Reference](https://api.python.langchain.com/en/stable/),
       [GitHub search](https://github.com/langchain-ai/langchain),
       [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
       [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
       [LangChain ChatBot](https://chat.langchain.com/)
-- type: input
-  id: url
-  attributes:
-    label: URL
-    description: URL to documentation
-  validations:
-    required: false
 - type: checkboxes
   id: checks
   attributes:
@@ -55,4 +48,4 @@ body:
     label: "Idea or request for content:"
     description: >
       Please describe as clearly as possible what topics you think are missing
-      from the current documentation.
+      from the current documentation.

.github/PULL_REQUEST_TEMPLATE.md

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

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

@@ -350,7 +350,11 @@ 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
 
@@ -480,16 +484,10 @@ 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(
@@ -526,13 +524,9 @@ 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 = {
@@ -543,9 +537,7 @@ if __name__ == "__main__":
         "nfcampos",
         "efriis",
         "eyurtsev",
-        "rlancemartin",
-        "ccurme",
-        "vbarda",
+        "rlancemartin"
     }
     hidden_logins = {
         "dev2049",
@@ -553,7 +545,6 @@ if __name__ == "__main__":
         "obi1kenobi",
         "langchain-infra",
         "jacoblee93",
-        "isahers1",
         "dqbd",
         "bracesproul",
         "akira",
@@ -565,7 +556,7 @@ 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,
@@ -621,7 +612,9 @@ 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")
@@ -634,7 +627,9 @@ 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)
@@ -643,4 +638,4 @@ 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/actions/uv_setup/action.yml

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

.github/scripts/check_diff.py

@@ -1,224 +1,15 @@
-import glob
 import json
-import os
 import sys
-from collections import defaultdict
-from typing import Dict, List, Set
-from pathlib import Path
-import tomllib
-
-from packaging.requirements import Requirement
-
-from get_min_versions import get_min_version_from_toml
-
+import os
+from typing import Dict
 
 LANGCHAIN_DIRS = [
     "libs/core",
-    "libs/text-splitters",
     "libs/langchain",
+    "libs/experimental",
+    "libs/community",
 ]
 
-# when set to True, we are ignoring core dependents
-# in order to be able to get CI to pass for each individual
-# package that depends on core
-# e.g. if you touch core, we don't then add textsplitters/etc to CI
-IGNORE_CORE_DEPENDENTS = False
-
-# ignored partners are removed from dependents
-# but still run if directly edited
-IGNORED_PARTNERS = [
-    # remove huggingface from dependents because of CI instability
-    # specifically in huggingface jobs
-    # https://github.com/langchain-ai/langchain/issues/25558
-    "huggingface",
-    # prompty exhibiting issues with numpy for Python 3.13
-    # https://github.com/langchain-ai/langchain/actions/runs/12651104685/job/35251034969?pr=29065
-    "prompty",
-]
-
-PY_312_MAX_PACKAGES = [
-    "libs/partners/voyageai",
-    "libs/partners/chroma", # https://github.com/chroma-core/chroma/issues/4382
-]
-
-
-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)
-
-        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
-        for dep in [
-            *pyproject["project"]["dependencies"],
-            *pyproject["dependency-groups"]["test"],
-        ]:
-            requirement = Requirement(dep)
-            package_name = requirement.name
-            if "langchain" in dep:
-                dependents[package_name].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 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_ == "libs/langchain" and job == "extended-tests":
-        py_versions = ["3.9", "3.13"]
-
-    elif dir_ == ".":
-        # unable to install with 3.13 because tokenizers doesn't support 3.13 yet
-        py_versions = ["3.9", "3.12"]
-    else:
-        py_versions = ["3.9", "3.13"]
-
-    return [{"working-directory": dir_, "python-version": py_v} for py_v in py_versions]
-
-
-def _get_pydantic_test_configs(
-    dir_: str, *, python_version: str = "3.11"
-) -> List[Dict[str, str]]:
-    with open("./libs/core/uv.lock", "rb") as f:
-        core_uv_lock_data = tomllib.load(f)
-    for package in core_uv_lock_data["package"]:
-        if package["name"] == "pydantic":
-            core_max_pydantic_minor = package["version"].split(".")[1]
-            break
-
-    with open(f"./{dir_}/uv.lock", "rb") as f:
-        dir_uv_lock_data = tomllib.load(f)
-
-    for package in dir_uv_lock_data["package"]:
-        if package["name"] == "pydantic":
-            dir_max_pydantic_minor = package["version"].split(".")[1]
-            break
-
-    core_min_pydantic_version = get_min_version_from_toml(
-        "./libs/core/pyproject.toml", "release", python_version, include=["pydantic"]
-    )["pydantic"]
-    core_min_pydantic_minor = (
-        core_min_pydantic_version.split(".")[1]
-        if "." in core_min_pydantic_version
-        else "0"
-    )
-    dir_min_pydantic_version = get_min_version_from_toml(
-        f"./{dir_}/pyproject.toml", "release", python_version, include=["pydantic"]
-    ).get("pydantic", "0.0.0")
-    dir_min_pydantic_minor = (
-        dir_min_pydantic_version.split(".")[1]
-        if "." in dir_min_pydantic_version
-        else "0"
-    )
-
-    max_pydantic_minor = min(
-        int(dir_max_pydantic_minor),
-        int(core_max_pydantic_minor),
-    )
-    min_pydantic_minor = max(
-        int(dir_min_pydantic_minor),
-        int(core_min_pydantic_minor),
-    )
-
-    configs = [
-        {
-            "working-directory": dir_,
-            "pydantic-version": f"2.{v}.0",
-            "python-version": python_version,
-        }
-        for v in range(min_pydantic_minor, max_pydantic_minor + 1)
-    ]
-    return configs
-
-
-def _get_configs_for_multi_dirs(
-    job: str, dirs_to_run: 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:]
 
@@ -227,13 +18,10 @@ if __name__ == "__main__":
         "test": set(),
         "extended-test": set(),
     }
-    docs_edited = False
 
-    if len(files) >= 300:
+    if len(files) == 300:
         # max diff length is 300 files - there are likely files missing
-        dirs_to_run["lint"] = all_package_dirs()
-        dirs_to_run["test"] = all_package_dirs()
-        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
+        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
 
     for file in files:
         if any(
@@ -252,72 +40,32 @@ 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:
                     dirs_to_run["extended-test"].add(dir_)
-        elif file.startswith("libs/standard-tests"):
-            # TODO: update to include all packages that rely on standard-tests (all partner packages)
-            # note: won't run on external repo partners
-            dirs_to_run["lint"].add("libs/standard-tests")
-            dirs_to_run["test"].add("libs/standard-tests")
-            dirs_to_run["lint"].add("libs/cli")
-            dirs_to_run["test"].add("libs/cli")
-            dirs_to_run["test"].add("libs/partners/mistralai")
-            dirs_to_run["test"].add("libs/partners/openai")
-            dirs_to_run["test"].add("libs/partners/anthropic")
-            dirs_to_run["test"].add("libs/partners/fireworks")
-            dirs_to_run["test"].add("libs/partners/groq")
-
-        elif file.startswith("libs/cli"):
-            dirs_to_run["lint"].add("libs/cli")
-            dirs_to_run["test"].add("libs/cli")
-            
         elif file.startswith("libs/partners"):
             partner_dir = file.split("/")[2]
-            if os.path.isdir(f"libs/partners/{partner_dir}") and [
-                filename
-                for filename in os.listdir(f"libs/partners/{partner_dir}")
-                if not filename.startswith(".")
-            ] != ["README.md"]:
+            if os.path.isdir(f"libs/partners/{partner_dir}"):
                 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
+            # Skip if the directory was deleted
         elif file.startswith("libs/"):
             raise ValueError(
                 f"Unknown lib: {file}. check_diff.py likely needs "
                 "an update for this new library!"
             )
-        elif file.startswith("docs/") or file in ["pyproject.toml", "uv.lock"]: # docs or root uv files
-            docs_edited = True
+        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
             dirs_to_run["lint"].add(".")
 
-    dependents = dependents_graph()
-
-    # we now have dirs_by_job
-    # todo: clean this up
-    map_job_to_configs = {
-        job: _get_configs_for_multi_dirs(job, dirs_to_run, dependents)
-        for job in [
-            "lint",
-            "test",
-            "extended-tests",
-            "compile-integration-tests",
-            "dependencies",
-            "test-pydantic",
-        ]
+    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"]),
     }
-    map_job_to_configs["test-doc-imports"] = (
-        [{"python-version": "3.12"}] if docs_edited else []
-    )
-
-    for key, value in map_job_to_configs.items():
+    for key, value in outputs.items():
         json_output = json.dumps(value)
-        print(f"{key}={json_output}")
+        print(f"{key}={json_output}")  # noqa: T201

.github/scripts/check_prerelease_dependencies.py

@@ -1,34 +0,0 @@
-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["project"]["version"]
-    releasing_rc = "rc" in version or "dev" in version
-
-    # if not, iterate through dependencies and make sure none allow prereleases
-    if not releasing_rc:
-        dependencies = toml_data["project"]["dependencies"]
-        for dep_version in dependencies:
-            dep_version_string = (
-                dep_version["version"] if isinstance(dep_version, dict) else dep_version
-            )
-
-            if "rc" in dep_version_string:
-                raise ValueError(
-                    f"Dependency {dep_version} has a prerelease version. Please remove this."
-                )
-
-            if isinstance(dep_version, dict) and dep_version.get(
-                "allow-prereleases", False
-            ):
-                raise ValueError(
-                    f"Dependency {dep_version} has allow-prereleases set to true. Please remove this."
-                )

.github/scripts/get_min_versions.py

@@ -1,153 +1,54 @@
-from collections import defaultdict
 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.requirements import Requirement
-from packaging.specifiers import SpecifierSet
-from packaging.version import Version
-
-
-import requests
-from packaging.version import parse
-from typing import List
 
+import tomllib
+from packaging.version import parse as parse_version
 import re
 
-
-MIN_VERSION_LIBS = [
-    "langchain-core",
-    "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",
-]
+MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain"]
 
 
-def get_pypi_versions(package_name: str) -> List[str]:
-    """
-    Fetch all available versions for a package from PyPI.
+def get_min_version(version: str) -> str:
+    # case ^x.x.x
+    _match = re.match(r"^\^(\d+(?:\.\d+){0,2})$", version)
+    if _match:
+        return _match.group(1)
 
-    Args:
-        package_name (str): Name of the package
+    # case >=x.x.x,<y.y.y
+    _match = re.match(r"^>=(\d+(?:\.\d+){0,2}),<(\d+(?:\.\d+){0,2})$", version)
+    if _match:
+        _min = _match.group(1)
+        _max = _match.group(2)
+        assert parse_version(_min) < parse_version(_max)
+        return _min
 
-    Returns:
-        List[str]: List of all available versions
+    # case x.x.x
+    _match = re.match(r"^(\d+(?:\.\d+){0,2})$", version)
+    if _match:
+        return _match.group(1)
 
-    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())
+    raise ValueError(f"Unrecognized version format: {version}")
 
 
-def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
-    """
-    Find the minimum published version that satisfies the given constraints.
-
-    Args:
-        package_name (str): Name of the package
-        spec_string (str): Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
-
-    Returns:
-        Optional[str]: Minimum compatible version or None if no compatible version found
-    """
-    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
-    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        spec_string = re.sub(rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}", spec_string)
-    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        spec_string = re.sub(
-            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x+1}", spec_string
-        )
-
-    spec_set = SpecifierSet(spec_string)
-    all_versions = get_pypi_versions(package_name)
-
-    valid_versions = []
-    for version_str in all_versions:
-        try:
-            version = parse(version_str)
-            if spec_set.contains(version):
-                valid_versions.append(version)
-        except ValueError:
-            continue
-
-    return str(min(valid_versions)) if valid_versions else None
-
-
-def _check_python_version_from_requirement(
-    requirement: Requirement, python_version: str
-) -> bool:
-    if not requirement.marker:
-        return True
-    else:
-        marker_str = str(requirement.marker)
-        if "python_version" or "python_full_version" in marker_str:
-            python_version_str = "".join(
-                char
-                for char in marker_str
-                if char.isdigit() or char in (".", "<", ">", "=", ",")
-            )
-            return check_python_version(python_version, python_version_str)
-        return True
-
-
-def get_min_version_from_toml(
-    toml_path: str,
-    versions_for: str,
-    python_version: str,
-    *,
-    include: Optional[list] = None,
-):
+def get_min_version_from_toml(toml_path: str):
     # Parse the TOML file
     with open(toml_path, "rb") as file:
         toml_data = tomllib.load(file)
 
-    dependencies = defaultdict(list)
-    for dep in toml_data["project"]["dependencies"]:
-        requirement = Requirement(dep)
-        dependencies[requirement.name].append(requirement)
+    # Get the dependencies from tool.poetry.dependencies
+    dependencies = toml_data["tool"]["poetry"]["dependencies"]
 
     # Initialize a dictionary to store the minimum versions
     min_versions = {}
 
     # Iterate over the libs 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
+    for lib in MIN_VERSION_LIBS:
         # Check if the lib is present in the dependencies
         if lib in dependencies:
-            if include and lib not in include:
-                continue
-            requirements = dependencies[lib]
-            for requirement in requirements:
-                if _check_python_version_from_requirement(requirement, python_version):
-                    version_string = str(requirement.specifier)
-                    break
+            # Get the version string
+            version_string = dependencies[lib]
 
             # Use parse_version to get the minimum supported version from version_string
-            min_version = get_minimum_version(lib, version_string)
+            min_version = get_min_version(version_string)
 
             # Store the minimum version in the min_versions dictionary
             min_versions[lib] = min_version
@@ -155,45 +56,12 @@ def get_min_version_from_toml(
     return min_versions
 
 
-def check_python_version(version_string, constraint_string):
-    """
-    Check if the given Python version matches the given constraints.
+# Get the TOML file path from the command line argument
+toml_file = sys.argv[1]
 
-    :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.
-    """
+# Call the function to get the minimum versions
+min_versions = get_min_version_from_toml(toml_file)
 
-    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
-    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
-    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
-    for y in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}.0", constraint_string
-        )
-    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
-    for x in range(1, 10):
-        constraint_string = re.sub(
-            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x+1}.0.0", constraint_string
-        )
-
-    try:
-        version = Version(version_string)
-        constraints = SpecifierSet(constraint_string)
-        return version in constraints
-    except Exception as e:
-        print(f"Error: {e}")
-        return False
-
-
-if __name__ == "__main__":
-    # Get the TOML file path from the command line argument
-    toml_file = sys.argv[1]
-    versions_for = sys.argv[2]
-    python_version = sys.argv[3]
-    assert versions_for in ["release", "pull_request"]
-
-    # Call the function to get the minimum versions
-    min_versions = get_min_version_from_toml(toml_file, versions_for, 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()])
+)  # noqa: T201

.github/scripts/prep_api_docs_build.py

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

.github/workflows/.codespell-exclude

@@ -1,6 +0,0 @@
-"NotIn": "not in",
-- `/checkin`: Check-in
-docs/docs/integrations/providers/trulens.mdx
-self.assertIn(
-from trulens_eval import Tru
-tru = Tru()

.github/workflows/_compile_integration_test.yml

@@ -7,13 +7,9 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
-  UV_FROZEN: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
@@ -21,23 +17,32 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "uv run pytest -m compile tests/integration_tests #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: compile-integration
 
       - name: Install integration dependencies
         shell: bash
-        run: uv sync --group test --group test_integration
+        run: poetry install --with=test_integration,test
 
       - name: Check integration tests compile
         shell: bash
-        run: uv run pytest -m compile tests/integration_tests
+        run: poetry run pytest -m compile tests/integration_tests
 
       - name: Ensure the tests did not create any additional files
         shell: bash

.github/workflows/_dependencies.yml

@@ -0,0 +1,117 @@
+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

@@ -6,72 +6,74 @@ on:
       working-directory:
         required: true
         type: string
-        description: "From which folder this pipeline executes"
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
 
 env:
-  UV_FROZEN: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
+    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    name: Python ${{ inputs.python-version }}
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: core
 
       - name: Install dependencies
         shell: bash
-        run: uv sync --group test --group test_integration
+        run: poetry install --with test,test_integration
+
+      - name: Install deps outside pyproject
+        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
+        shell: bash
+        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
+
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: google-github-actions/auth@v2
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
       - 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 }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
           WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
+          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
+          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
         run: |
           make integration_tests
 

.github/workflows/_lint.yml

@@ -7,31 +7,56 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
+      langchain-location:
+        required: false
         type: string
-        description: "Python version to use"
+        description: "Relative path to the langchain library folder"
 
 env:
+  POETRY_VERSION: "1.7.1"
   WORKDIR: ${{ inputs.working-directory == '' && '.' || inputs.working-directory }}
 
   # This env var allows us to get inline annotations when ruff has complaints.
   RUFF_OUTPUT_FORMAT: github
 
-  UV_FROZEN: "true"
-
 jobs:
   build:
-    name: "make lint #${{ inputs.python-version }}"
+    name: "make lint #${{ matrix.python-version }}"
     runs-on: ubuntu-latest
-    timeout-minutes: 20
+    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 ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: lint-with-extras
+
+      - name: Check Poetry File
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          poetry check
+
+      - name: Check lock file
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          poetry lock --check
 
       - name: Install dependencies
         # Also installs dev/lint/test/typing dependencies, to ensure we have
@@ -44,7 +69,25 @@ jobs:
         # It doesn't matter how you change it, any change will cause a cache-bust.
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --group lint --group typing
+          poetry install --with lint,typing
+
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
+
+      - name: Get .mypy_cache to speed up mypy
+        uses: actions/cache@v4
+        env:
+          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
+        with:
+          path: |
+            ${{ env.WORKDIR }}/.mypy_cache
+          key: mypy-lint-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.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 }}
@@ -63,12 +106,21 @@ jobs:
         if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --inexact --group test
+          poetry install --with test
       - name: Install unit+integration test dependencies
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         working-directory: ${{ inputs.working-directory }}
         run: |
-          uv sync --inexact --group test --group test_integration
+          poetry install --with test,test_integration
+
+      - name: Get .mypy_cache_test to speed up mypy
+        uses: actions/cache@v4
+        env:
+          SEGMENT_DOWNLOAD_TIMEOUT_MIN: "2"
+        with:
+          path: |
+            ${{ env.WORKDIR }}/.mypy_cache_test
+          key: mypy-test-${{ runner.os }}-${{ runner.arch }}-py${{ matrix.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

@@ -12,22 +12,15 @@ on:
       working-directory:
         required: true
         type: string
-        description: "From which folder this pipeline executes"
         default: 'libs/langchain'
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
 
 env:
   PYTHON_VERSION: "3.11"
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     environment: Scheduled testing
     runs-on: ubuntu-latest
 
@@ -38,10 +31,13 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
@@ -55,142 +51,37 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: uv build
+        run: poetry build
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
 
       - name: Check Version
         id: check-version
-        shell: python
+        shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          import os
-          import tomllib
-          with open("pyproject.toml", "rb") as f:
-              data = tomllib.load(f)
-          pkg_name = data["project"]["name"]
-          version = data["project"]["version"]
-          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
-              f.write(f"pkg-name={pkg_name}\n")
-              f.write(f"version={version}\n")
-  release-notes:
-    needs:
-      - build
-    runs-on: ubuntu-latest
-    outputs:
-      release-body: ${{ steps.generate-release-body.outputs.release-body }}
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain
-          path: langchain
-          sparse-checkout: | # this only grabs files for relevant dir
-            ${{ inputs.working-directory }}
-          ref: ${{ github.ref }} # this scopes to just ref'd branch
-          fetch-depth: 0 # this fetches entire commit history
-      - name: Check Tags
-        id: check-tags
-        shell: bash
-        working-directory: langchain/${{ inputs.working-directory }}
-        env:
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          VERSION: ${{ needs.build.outputs.version }}
-        run: |
-          # Handle regular versions and pre-release versions differently
-          if [[ "$VERSION" == *"-"* ]]; then
-            # This is a pre-release version (contains a hyphen)
-            # Extract the base version without the pre-release suffix
-            BASE_VERSION=${VERSION%%-*}
-            # Look for the latest release of the same base version
-            REGEX="^$PKG_NAME==$BASE_VERSION\$"
-            PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
-            
-            # If no exact base version match, look for the latest release of any kind
-            if [ -z "$PREV_TAG" ]; then
-              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-              PREV_TAG=$(git tag --sort=-creatordate | (grep -P "$REGEX" || true) | head -1)
-            fi
-          else
-            # Regular version handling
-            PREV_TAG="$PKG_NAME==${VERSION%.*}.$(( ${VERSION##*.} - 1 ))"; [[ "${VERSION##*.}" -eq 0 ]] && PREV_TAG=""
-
-            # backup case if releasing e.g. 0.3.0, looks up last release
-            # note if last release (chronologically) was e.g. 0.1.47 it will get 
-            # that instead of the last 0.2 release
-            if [ -z "$PREV_TAG" ]; then
-              REGEX="^$PKG_NAME==\\d+\\.\\d+\\.\\d+\$"
-              echo $REGEX
-              PREV_TAG=$(git tag --sort=-creatordate | (grep -P $REGEX || true) | head -1)
-            fi
-          fi
-
-          # if PREV_TAG is empty, let it be empty
-          if [ -z "$PREV_TAG" ]; then
-            echo "No previous tag found - first release"
-          else
-            # confirm prev-tag actually exists in git repo with git tag
-            GIT_TAG_RESULT=$(git tag -l "$PREV_TAG")
-            if [ -z "$GIT_TAG_RESULT" ]; then
-              echo "Previous tag $PREV_TAG not found in git repo"
-              exit 1
-            fi
-          fi
-
-
-          TAG="${PKG_NAME}==${VERSION}"
-          if [ "$TAG" == "$PREV_TAG" ]; then
-            echo "No new version to release"
-            exit 1
-          fi
-          echo tag="$TAG" >> $GITHUB_OUTPUT
-          echo prev-tag="$PREV_TAG" >> $GITHUB_OUTPUT
-      - name: Generate release body
-        id: generate-release-body
-        working-directory: langchain
-        env:
-          WORKING_DIR: ${{ inputs.working-directory }}
-          PKG_NAME: ${{ needs.build.outputs.pkg-name }}
-          TAG: ${{ steps.check-tags.outputs.tag }}
-          PREV_TAG: ${{ steps.check-tags.outputs.prev-tag }}
-        run: |
-          PREAMBLE="Changes since $PREV_TAG"
-          # if PREV_TAG is empty, then we are releasing the first version
-          if [ -z "$PREV_TAG" ]; then
-            PREAMBLE="Initial release"
-            PREV_TAG=$(git rev-list --max-parents=0 HEAD)
-          fi
-          {
-            echo 'release-body<<EOF'
-            echo $PREAMBLE
-            echo
-            git log --format="%s" "$PREV_TAG"..HEAD -- $WORKING_DIR
-            echo EOF
-          } >> "$GITHUB_OUTPUT"
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
 
   test-pypi-publish:
     needs:
       - build
-      - release-notes
     uses:
       ./.github/workflows/_test_release.yml
-    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
-      dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
     secrets: inherit
 
   pre-release-checks:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     steps:
       - uses: actions/checkout@v4
 
@@ -207,25 +98,21 @@ jobs:
       # - The package is published, and it breaks on the missing dependency when
       #   used in the real world.
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
-        id: setup-python
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
 
-      - uses: actions/download-artifact@v4
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Import dist package
+      - name: Import published package
         shell: bash
         working-directory: ${{ inputs.working-directory }}
         env:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         # Here we use:
-        # - The default regular PyPI index as the *primary* index, meaning
+        # - The default regular PyPI index as the *primary* index, meaning 
         #   that it takes priority (https://pypi.org/simple)
         # - The test PyPI index as an extra index, so that any dependencies that
         #   are not found on test PyPI can be resolved and installed anyway.
@@ -234,21 +121,27 @@ jobs:
         # - attempt install again after 5 seconds if it fails because there is
         #   sometimes a delay in availability on test pypi
         run: |
-          uv venv
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
+          poetry run pip install \
+            --extra-index-url https://test.pypi.org/simple/ \
+            "$PKG_NAME==$VERSION" || \
+          ( \
+            sleep 5 && \
+            poetry run pip install \
+              --extra-index-url https://test.pypi.org/simple/ \
+              "$PKG_NAME==$VERSION" \
+          )
 
           # Replace all dashes in the package name with underscores,
           # since that's how Python imports packages with dashes in the name.
-          # also remove _official suffix
-          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g | sed s/_official//g)"
+          IMPORT_NAME="$(echo "$PKG_NAME" | sed s/-/_/g)"
 
-          uv run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
+          poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: uv sync --group test
+        run: poetry install --with test,test_integration
         working-directory: ${{ inputs.working-directory }}
 
-      # Overwrite the local version of the package with the built version
+      # Overwrite the local version of the package with the test PyPI version.
       - name: Import published package (again)
         working-directory: ${{ inputs.working-directory }}
         shell: bash
@@ -256,39 +149,19 @@ jobs:
           PKG_NAME: ${{ needs.build.outputs.pkg-name }}
           VERSION: ${{ needs.build.outputs.version }}
         run: |
-          VIRTUAL_ENV=.venv uv pip install dist/*.whl
+          poetry run pip install \
+            --extra-index-url https://test.pypi.org/simple/ \
+            "$PKG_NAME==$VERSION"
 
       - name: Run unit tests
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Check for prerelease versions
-        working-directory: ${{ inputs.working-directory }}
-        run: |
-          uv run python $GITHUB_WORKSPACE/.github/scripts/check_prerelease_dependencies.py pyproject.toml
-
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          VIRTUAL_ENV=.venv uv pip install packaging requests
-          python_version="$(uv run python --version | awk '{print $2}')"
-          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release $python_version)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          VIRTUAL_ENV=.venv uv pip install --force-reinstall $MIN_VERSIONS --editable .
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
-      - name: Import integration test dependencies
-        run: uv sync --group test --group test_integration
-        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: Run integration tests
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
@@ -303,120 +176,51 @@ jobs:
           AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
           AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-          AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
           GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
           WATSONX_PROJECT_ID: ${{ secrets.WATSONX_PROJECT_ID }}
+          PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
+          PINECONE_ENVIRONMENT: ${{ secrets.PINECONE_ENVIRONMENT }}
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
           ES_URL: ${{ secrets.ES_URL }}
           ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
-          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
-          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
-          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
-  # Test select published packages against new core
-  test-prior-published-packages-against-new-core:
-    needs:
-      - build
-      - release-notes
-      - test-pypi-publish
-      - pre-release-checks
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        partner: [openai, anthropic]
-      fail-fast: false  # Continue testing other partners if one fails
-    env:
-      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-      OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
-      AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
-      AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
-      AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LEGACY_CHAT_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
-      AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
-    steps:
-      - uses: actions/checkout@v4
-
-      # We implement this conditional as Github Actions does not have good support
-      # for conditionally needing steps. https://github.com/actions/runner/issues/491
-      - name: Check if libs/core
+      - name: Get minimum versions
+        working-directory: ${{ inputs.working-directory }}
+        id: min-version
         run: |
-          if [ "${{ startsWith(inputs.working-directory, 'libs/core') }}" != "true" ]; then
-            echo "Not in libs/core. Exiting successfully."
-            exit 0
-          fi
+          poetry run pip install packaging
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
+          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
+          echo "min-versions=$min_versions"
 
-      - name: Set up Python + uv
-        if: startsWith(inputs.working-directory, 'libs/core')
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - uses: actions/download-artifact@v4
-        if: startsWith(inputs.working-directory, 'libs/core')
-        with:
-          name: dist
-          path: ${{ inputs.working-directory }}/dist/
-
-      - name: Test against ${{ matrix.partner }}
-        if: startsWith(inputs.working-directory, 'libs/core')
+      - name: Run unit tests with minimum dependency versions
+        if: ${{ steps.min-version.outputs.min-versions != '' }}
+        env:
+          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
         run: |
-          # Identify latest tag
-          LATEST_PACKAGE_TAG="$(
-            git ls-remote --tags origin "langchain-${{ matrix.partner }}*" \
-            | awk '{print $2}' \
-            | sed 's|refs/tags/||' \
-            | sort -Vr \
-            | head -n 1
-          )"
-          echo "Latest package tag: $LATEST_PACKAGE_TAG"
-
-          # Shallow-fetch just that single tag
-          git fetch --depth=1 origin tag "$LATEST_PACKAGE_TAG"
-
-          # Checkout the latest package files
-          rm -rf $GITHUB_WORKSPACE/libs/partners/${{ matrix.partner }}/*
-          rm -rf $GITHUB_WORKSPACE/libs/standard-tests/*
-          cd $GITHUB_WORKSPACE/libs/
-          git checkout "$LATEST_PACKAGE_TAG" -- standard-tests/
-          git checkout "$LATEST_PACKAGE_TAG" -- partners/${{ matrix.partner }}/
-          cd partners/${{ matrix.partner }}
-
-          # Print as a sanity check
-          echo "Version number from pyproject.toml: "
-          cat pyproject.toml | grep "version = "
-
-          # Run tests
-          uv sync --group test --group test_integration
-          uv pip install ../../core/dist/*.whl
-          make integration_tests
+          poetry run pip install $MIN_VERSIONS
+          make tests
+        working-directory: ${{ inputs.working-directory }}
 
   publish:
     needs:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
-      - test-prior-published-packages-against-new-core
     runs-on: ubuntu-latest
     permissions:
       # This permission is used for trusted publishing:
@@ -433,12 +237,15 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -449,13 +256,10 @@ 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:
       - build
-      - release-notes
       - test-pypi-publish
       - pre-release-checks
       - publish
@@ -472,23 +276,26 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
-          
-      - name: Create Tag
+
+      - name: Create Release
         uses: ncipollo/release-action@v1
+        if: ${{ inputs.working-directory == 'libs/langchain' }}
         with:
           artifacts: "dist/*"
           token: ${{ secrets.GITHUB_TOKEN }}
-          generateReleaseNotes: false
-          tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
-          body: ${{ needs.release-notes.outputs.release-body }}
-          commit: ${{ github.sha }}
-          makeLatest: ${{ needs.build.outputs.pkg-name == 'langchain-core'}}
+          draft: false
+          generateReleaseNotes: true
+          tag: v${{ needs.build.outputs.version }}
+          commit: master

.github/workflows/_release_docker.yml

@@ -0,0 +1,62 @@
+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

@@ -7,14 +7,13 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      python-version:
-        required: true
+      langchain-location:
+        required: false
         type: string
-        description: "Python version to use"
+        description: "Relative path to the langchain library folder"
 
 env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
@@ -22,45 +21,42 @@ jobs:
       run:
         working-directory: ${{ inputs.working-directory }}
     runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "make test #${{ inputs.python-version }}"
+    strategy:
+      matrix:
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: "make test #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
-        id: setup-python
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ inputs.python-version }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: core
+
       - name: Install dependencies
         shell: bash
-        run: uv sync --group test --dev
+        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: ${{ inputs.working-directory }}
-        id: min-version
-        shell: bash
-        run: |
-          VIRTUAL_ENV=.venv uv pip install packaging tomli requests
-          python_version="$(uv run python --version | awk '{print $2}')"
-          min_versions="$(uv run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          VIRTUAL_ENV=.venv uv pip install $MIN_VERSIONS
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
       - name: Ensure the tests did not create any additional files
         shell: bash
         run: |
@@ -72,4 +68,3 @@ jobs:
           # grep will exit non-zero if the target message isn't found,
           # and `set -e` above will cause the step to fail.
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
-          

.github/workflows/_test_doc_imports.yml

@@ -1,50 +0,0 @@
-name: test_doc_imports
-
-on:
-  workflow_call:
-    inputs:
-      python-version:
-        required: true
-        type: string
-        description: "Python version to use"
-
-env:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "check doc imports #${{ inputs.python-version }}"
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-
-      - name: Install dependencies
-        shell: bash
-        run: uv sync --group test
-
-      - name: Install langchain editable
-        run: |
-          VIRTUAL_ENV=.venv uv pip install langchain-experimental langchain-community -e libs/core libs/langchain
-
-      - name: Check doc imports
-        shell: bash
-        run: |
-          uv run python docs/scripts/check_imports.py
-
-      - name: Ensure the test did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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_pydantic.yml

@@ -1,63 +0,0 @@
-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:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
-
-jobs:
-  build:
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    runs-on: ubuntu-latest
-    timeout-minutes: 20
-    name: "make test # pydantic: ~=${{ inputs.pydantic-version }}, python: ${{ inputs.python-version }}, "
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python ${{ inputs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ inputs.python-version }}
-
-      - name: Install dependencies
-        shell: bash
-        run: uv sync --group test
-
-      - name: Overwrite pydantic version
-        shell: bash
-        run: VIRTUAL_ENV=.venv uv pip install pydantic~=${{ inputs.pydantic-version }}
-
-      - name: Run core tests
-        shell: bash
-        run: |
-          make test
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(git status)"
-          echo "$STATUS"
-
-          # grep will exit non-zero if the target message isn't found,
-          # and `set -e` above will cause the step to fail.
-          echo "$STATUS" | grep 'nothing to commit, working tree clean'

.github/workflows/_test_release.yml

@@ -7,19 +7,14 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
-      dangerous-nonmaster-release:
-        required: false
-        type: boolean
-        default: false
-        description: "Release from a non-master branch (danger!)"
 
 env:
-  PYTHON_VERSION: "3.11"
-  UV_FROZEN: "true"
+  POETRY_VERSION: "1.7.1"
+  PYTHON_VERSION: "3.10"
 
 jobs:
   build:
-    if: github.ref == 'refs/heads/master' || inputs.dangerous-nonmaster-release
+    if: github.ref == 'refs/heads/master'
     runs-on: ubuntu-latest
 
     outputs:
@@ -29,10 +24,13 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ env.PYTHON_VERSION }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ inputs.working-directory }}
+          cache-key: release
 
       # We want to keep this build stage *separate* from the release stage,
       # so that there's no sharing of permissions between them.
@@ -46,29 +44,22 @@ jobs:
       # > from the publish job.
       # https://github.com/pypa/gh-action-pypi-publish#non-goals
       - name: Build project for distribution
-        run: uv build
+        run: poetry build
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@v3
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
 
       - name: Check Version
         id: check-version
-        shell: python
+        shell: bash
         working-directory: ${{ inputs.working-directory }}
         run: |
-          import os
-          import tomllib
-          with open("pyproject.toml", "rb") as f:
-              data = tomllib.load(f)
-          pkg_name = data["project"]["name"]
-          version = data["project"]["version"]
-          with open(os.environ["GITHUB_OUTPUT"], "a") as f:
-              f.write(f"pkg-name={pkg_name}\n")
-              f.write(f"version={version}\n")
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
 
   publish:
     needs:
@@ -85,7 +76,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - uses: actions/download-artifact@v4
+      - uses: actions/download-artifact@v3
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
@@ -102,5 +93,3 @@ 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

@@ -5,84 +5,26 @@ on:
   schedule:
     - cron:  '0 13 * * *'
 env:
-  PYTHON_VERSION: "3.11"
+  POETRY_VERSION: "1.7.1"
+  PYTHON_VERSION: "3.10"
 
 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:
+          ref: bagatur/api_docs_build
           path: langchain
       - uses: actions/checkout@v4
         with:
-          repository: langchain-ai/langchain-api-docs-html
-          path: langchain-api-docs-html
-          token: ${{ secrets.TOKEN_GITHUB_API_DOCS_HTML }}
-
-      - name: Get repos with yq
-        id: get-unsorted-repos
-        uses: mikefarah/yq@master
-        with:
-          cmd: |
-            yq '
-              .packages[]
-              | select(
-                  (
-                    (.repo | test("^langchain-ai/"))
-                    and
-                    (.repo != "langchain-ai/langchain")
-                  )
-                  or
-                  (.include_in_api_ref // false)
-                )
-              | .repo
-            ' langchain/libs/packages.yml
-
-      - name: Parse YAML and checkout repos
-        env:
-          REPOS_UNSORTED: ${{ steps.get-unsorted-repos.outputs.result }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          repository: langchain-ai/langchain-google
+          path: langchain-google
+      - name: Move google libs
         run: |
-          # Get unique repositories
-          REPOS=$(echo "$REPOS_UNSORTED" | sort -u)
-          
-          # Checkout each unique repository that is in langchain-ai org
-          for repo in $REPOS; do
-            REPO_NAME=$(echo $repo | cut -d'/' -f2)
-            echo "Checking out $repo to $REPO_NAME"
-            git clone --depth 1 https://github.com/$repo.git $REPO_NAME
-          done
-
-      - name: Setup python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@v5
-        id: setup-python
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-
-      - name: Install initial py deps
-        working-directory: langchain
-        run: |
-          python -m pip install -U uv
-          python -m uv pip install --upgrade --no-cache-dir pip setuptools pyyaml
-
-      - name: Move libs 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/{}") --overrides ./docs/vercel_overrides.txt
-          python -m uv pip install libs/core libs/langchain libs/text-splitters libs/community libs/experimental libs/standard-tests
-          python -m uv pip install -r docs/api_reference/requirements.txt
+          rm -rf langchain/libs/partners/google-genai 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
 
       - name: Set Git config
         working-directory: langchain
@@ -90,18 +32,38 @@ jobs:
           git config --local user.email "actions@github.com"
           git config --local user.name "Github Actions"
 
+      - name: Merge master
+        working-directory: langchain
+        run: | 
+          git fetch origin master
+          git merge origin/master -m "Merge master" --allow-unrelated-histories -X theirs
+
+      - 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 dependencies
+        working-directory: langchain
+        run: |
+          poetry run python -m pip install --upgrade --no-cache-dir pip setuptools
+          poetry run python -m pip install --upgrade --no-cache-dir sphinx readthedocs-sphinx-ext
+          # skip airbyte and ibm due to pandas dependency issue
+          poetry run python -m pip install $(ls ./libs/partners | grep -vE "airbyte|ibm" | xargs -I {} echo "./libs/partners/{}")
+          poetry run python -m pip install --exists-action=w --no-cache-dir -r docs/api_reference/requirements.txt
+
       - 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/
+          poetry run python -m pip install --upgrade --no-cache-dir pip setuptools
+          poetry run python docs/api_reference/create_api_rst.py
+          poetry run python -m sphinx -T -E -b html -d _build/doctrees -c docs/api_reference docs/api_reference api_reference_build/html -j auto
 
       # https://github.com/marketplace/actions/add-commit
       - uses: EndBug/add-and-commit@v9
         with:
-          cwd: langchain-api-docs-html
+          cwd: langchain
           message: 'Update API docs build'

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

@@ -1,25 +0,0 @@
-name: Check Broken Links
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'
-
-jobs:
-  check-links:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-      - name: Use Node.js 18.x
-        uses: actions/setup-node@v3
-        with:
-          node-version: 18.x
-          cache: "yarn"
-          cache-dependency-path: ./docs/yarn.lock
-      - name: Install dependencies
-        run: yarn install --immutable --mode=skip-build
-        working-directory: ./docs
-      - name: Check broken links
-        run: yarn check-broken-links
-        working-directory: ./docs

.github/workflows/check_core_versions.yml

@@ -1,29 +0,0 @@
-name: Check `langchain-core` version equality
-
-on:
-  pull_request:
-    paths:
-      - 'libs/core/pyproject.toml'
-      - 'libs/core/langchain_core/version.py'
-
-jobs:
-  check_version_equality:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Check version equality
-        run: |
-          PYPROJECT_VERSION=$(grep -Po '(?<=^version = ")[^"]*' libs/core/pyproject.toml)
-          VERSION_PY_VERSION=$(grep -Po '(?<=^VERSION = ")[^"]*' libs/core/langchain_core/version.py)
-
-          # Compare the two versions
-          if [ "$PYPROJECT_VERSION" != "$VERSION_PY_VERSION" ]; then
-            echo "langchain-core versions in pyproject.toml and version.py do not match!"
-            echo "pyproject.toml version: $PYPROJECT_VERSION"
-            echo "version.py version: $VERSION_PY_VERSION"
-            exit 1
-          else
-            echo "Versions match: $PYPROJECT_VERSION"
-          fi

.github/workflows/check_diffs.yml

@@ -1,10 +1,10 @@
+---
 name: CI
 
 on:
   push:
     branches: [master]
   pull_request:
-  merge_group:
 
 # If another push to the same PR or branch happens while this workflow is still running,
 # cancel the earlier run in favor of the next run.
@@ -17,8 +17,7 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  UV_FROZEN: "true"
-  UV_NO_SYNC: "true"
+  POETRY_VERSION: "1.7.1"
 
 jobs:
   build:
@@ -27,119 +26,100 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.11'
+          python-version: '3.10'
       - 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:
-      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 }}
+      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 }}
   lint:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.lint != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.lint) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
     uses: ./.github/workflows/_lint.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
   test:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.test != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      working-directory: ${{ matrix.working-directory }}
     secrets: inherit
 
-  test-pydantic:
-    name: cd ${{ matrix.job-configs.working-directory }}
-    needs: [ build ]
-    if: ${{ needs.build.outputs.test-pydantic != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-pydantic) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_pydantic.yml
-    with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      pydantic-version: ${{ matrix.job-configs.pydantic-version }}
-    secrets: inherit
-
-  test-doc-imports:
-    needs: [ build ]
-    if: ${{ needs.build.outputs.test-doc-imports != '[]' }}
-    strategy:
-      matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.test-doc-imports) }}
-      fail-fast: false
-    uses: ./.github/workflows/_test_doc_imports.yml
-    secrets: inherit
-    with:
-      python-version: ${{ matrix.job-configs.python-version }}
-
   compile-integration-tests:
-    name: cd ${{ matrix.job-configs.working-directory }}
+    name: cd ${{ matrix.working-directory }}
     needs: [ build ]
-    if: ${{ needs.build.outputs.compile-integration-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
     strategy:
       matrix:
-        job-configs: ${{ fromJson(needs.build.outputs.compile-integration-tests) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
     uses: ./.github/workflows/_compile_integration_test.yml
     with:
-      working-directory: ${{ matrix.job-configs.working-directory }}
-      python-version: ${{ matrix.job-configs.python-version }}
+      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 }}
     secrets: inherit
 
   extended-tests:
-    name: "cd ${{ matrix.job-configs.working-directory }} / make extended_tests #${{ matrix.job-configs.python-version }}"
+    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
     needs: [ build ]
-    if: ${{ needs.build.outputs.extended-tests != '[]' }}
+    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
     strategy:
       matrix:
         # note different variable for extended test dirs
-        job-configs: ${{ fromJson(needs.build.outputs.extended-tests) }}
-      fail-fast: false
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
     runs-on: ubuntu-latest
-    timeout-minutes: 20
     defaults:
       run:
-        working-directory: ${{ matrix.job-configs.working-directory }}
+        working-directory: ${{ matrix.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
-      - name: Set up Python ${{ matrix.job-configs.python-version }} + uv
-        uses: "./.github/actions/uv_setup"
+      - name: Set up Python ${{ matrix.python-version }} + Poetry ${{ env.POETRY_VERSION }}
+        uses: "./.github/actions/poetry_setup"
         with:
-          python-version: ${{ matrix.job-configs.python-version }}
+          python-version: ${{ matrix.python-version }}
+          poetry-version: ${{ env.POETRY_VERSION }}
+          working-directory: ${{ matrix.working-directory }}
+          cache-key: extended
 
-      - name: Install dependencies and run extended tests
+      - name: Install dependencies
         shell: bash
         run: |
-          echo "Running extended tests, installing dependencies with uv..."
-          uv venv
-          uv sync --group test
-          VIRTUAL_ENV=.venv uv pip install -r extended_testing_deps.txt
-          VIRTUAL_ENV=.venv make extended_tests
+          echo "Running extended tests, installing dependencies with poetry..."
+          poetry install -E extended_testing --with test
+
+      - name: Run extended tests
+        run: make extended_tests
 
       - name: Ensure the tests did not create any additional files
         shell: bash
@@ -154,7 +134,7 @@ jobs:
           echo "$STATUS" | grep 'nothing to commit, working tree clean'
   ci_success:
     name: "CI Success"
-    needs: [build, lint, test, compile-integration-tests, extended-tests, test-doc-imports, test-pydantic]
+    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests]
     if: |
       always()
     runs-on: ubuntu-latest

.github/workflows/check_new_docs.yml

@@ -1,35 +0,0 @@
-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

@@ -1,9 +1,11 @@
+---
 name: CI / cd . / make spell_check
 
 on:
   push:
-    branches: [master, v0.1, v0.2]
+    branches: [master]
   pull_request:
+    branches: [master]
 
 permissions:
   contents: read
@@ -27,9 +29,9 @@ jobs:
           python .github/workflows/extract_ignored_words_list.py
         id: extract_ignore_words
 
-#      - name: Codespell
-#        uses: codespell-project/actions-codespell@v2
-#        with:
-#          skip: guide_imports.json,*.ambr,./cookbook/data/imdb_top_1000.csv,*.lock
-#          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
-#          exclude_file: ./.github/workflows/codespell-exclude
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          skip: guide_imports.json,*.ambr,./cookbook/data/imdb_top_1000.csv
+          ignore_words_list: ${{ steps.extract_ignore_words.outputs.ignore_words_list }}
+          exclude_file: libs/community/langchain_community/llms/yuan2.py

.github/workflows/codspeed.yml

@@ -1,44 +0,0 @@
-name: CodSpeed
-
-on:
-  push:
-    branches:
-        - master
-  pull_request:
-    paths:
-      - 'libs/core/**'
-  # `workflow_dispatch` allows CodSpeed to trigger backtest
-  # performance analysis in order to generate initial data.
-  workflow_dispatch:
-
-jobs:
-  codspeed:
-    name: Run benchmarks
-    if: (github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, 'run-codspeed-benchmarks')) || github.event_name == 'workflow_dispatch' || github.event_name == 'push'
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      # We have to use 3.12, 3.13 is not yet supported
-      - name: Install uv
-        uses: astral-sh/setup-uv@v5
-        with:
-          python-version: "3.12"
-
-      # Using this action is still necessary for CodSpeed to work
-      - uses: actions/setup-python@v3
-        with:
-          python-version: "3.12"
-
-      - name: install deps
-        run: uv sync --group test
-        working-directory: ./libs/core
-
-      - name: Run benchmarks
-        uses: CodSpeedHQ/action@v3
-        with:
-          token: ${{ secrets.CODSPEED_TOKEN }}
-          run: |
-            cd libs/core
-            uv run --no-sync pytest ./tests/benchmarks --codspeed
-          mode: walltime

.github/workflows/extract_ignored_words_list.py

@@ -7,4 +7,4 @@ ignore_words_list = (
     pyproject_toml.get("tool", {}).get("codespell", {}).get("ignore-words-list")
 )
 
-print(f"::set-output name=ignore_words_list::{ignore_words_list}")
+print(f"::set-output name=ignore_words_list::{ignore_words_list}")  # noqa: T201

.github/workflows/langchain_release_docker.yml

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

.github/workflows/people.yml

@@ -6,12 +6,16 @@ on:
   push:
     branches: [jacob/people]
   workflow_dispatch:
+    inputs:
+      debug_enabled:
+        description: 'Run the build with tmate debugging enabled (https://github.com/marketplace/actions/debugging-with-tmate)'
+        required: false
+        default: 'false'
 
 jobs:
   langchain-people:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
+    if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
-    permissions: write-all
     steps:
       - name: Dump GitHub context
         env:
@@ -21,6 +25,12 @@ jobs:
       # Ref: https://github.com/actions/runner/issues/2033
       - name: Fix git safe.directory in container
         run: mkdir -p /home/runner/work/_temp/_github_home && printf "[safe]\n\tdirectory = /github/workspace" > /home/runner/work/_temp/_github_home/.gitconfig
+      # Allow debugging with tmate
+      - name: Setup tmate session
+        uses: mxschmitt/action-tmate@v3
+        if: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.debug_enabled == 'true' }}
+        with:
+          limit-access-to-actor: true
       - uses: ./.github/actions/people
         with:
           token: ${{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}

.github/workflows/run_notebooks.yml

@@ -1,72 +0,0 @@
-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:
-  UV_FROZEN: "true"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    if: github.repository == 'langchain-ai/langchain' || github.event_name != 'schedule'
-    name: "Test docs"
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python + uv
-        uses: "./.github/actions/uv_setup"
-        with:
-          python-version: ${{ github.event.inputs.python_version || '3.11' }}
-
-      - name: 'Authenticate to Google Cloud'
-        id: 'auth'
-        uses: google-github-actions/auth@v2
-        with:
-          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
-
-      - name: Configure AWS Credentials
-        uses: aws-actions/configure-aws-credentials@v4
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
-
-      - name: Install dependencies
-        run: |
-          uv sync --group dev --group test
-
-      - name: Pre-download files
-        run: |
-          uv run python docs/scripts/cache_data.py
-          curl -s https://raw.githubusercontent.com/lerocha/chinook-database/master/ChinookDatabase/DataSources/Chinook_Sqlite.sql | sqlite3 docs/docs/how_to/Chinook.db
-          cp docs/docs/how_to/Chinook.db docs/docs/tutorials/Chinook.db
-
-      - name: Prepare notebooks
-        run: |
-          uv run python docs/scripts/prepare_notebooks_for_ci.py --comment-install-cells --working-directory ${{ github.event.inputs.working-directory || 'all' }}
-
-      - name: Run notebooks
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
-          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-          TAVILY_API_KEY: ${{ secrets.TAVILY_API_KEY }}
-          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
-          WORKING_DIRECTORY: ${{ github.event.inputs.working-directory || 'all' }}
-        run: |
-          ./docs/scripts/execute_notebooks.sh $WORKING_DIRECTORY

.github/workflows/scheduled_test.yml

@@ -2,100 +2,38 @@ name: Scheduled tests
 
 on:
   workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
-    inputs:
-      working-directory-force:
-        type: string
-        description: "From which folder this pipeline executes - defaults to all in matrix - example value: libs/partners/anthropic"
-      python-version-force:
-        type: string
-        description: "Python version to use - defaults to 3.9 and 3.11 in matrix - example value: 3.9"
   schedule:
     - cron:  '0 13 * * *'
 
 env:
-  POETRY_VERSION: "1.8.4"
-  UV_FROZEN: "true"
-  DEFAULT_LIBS: '["libs/partners/openai", "libs/partners/anthropic", "libs/partners/fireworks", "libs/partners/groq", "libs/partners/mistralai", "libs/partners/xai", "libs/partners/google-vertexai", "libs/partners/google-genai", "libs/partners/aws"]'
-  POETRY_LIBS: ("libs/partners/google-vertexai" "libs/partners/google-genai" "libs/partners/aws")
+  POETRY_VERSION: "1.7.1"
 
 jobs:
-  compute-matrix:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    runs-on: ubuntu-latest
-    name: Compute matrix
-    outputs:
-      matrix: ${{ steps.set-matrix.outputs.matrix }}
-    steps:
-      - name: Set matrix
-        id: set-matrix
-        env:
-          DEFAULT_LIBS: ${{ env.DEFAULT_LIBS }}
-          WORKING_DIRECTORY_FORCE: ${{ github.event.inputs.working-directory-force || '' }}
-          PYTHON_VERSION_FORCE: ${{ github.event.inputs.python-version-force || '' }}
-        run: |
-          # echo "matrix=..." where matrix is a json formatted str with keys python-version and working-directory
-          # python-version should default to 3.9 and 3.11, but is overridden to [PYTHON_VERSION_FORCE] if set
-          # working-directory should default to DEFAULT_LIBS, but is overridden to [WORKING_DIRECTORY_FORCE] if set
-          python_version='["3.9", "3.11"]'
-          working_directory="$DEFAULT_LIBS"
-          if [ -n "$PYTHON_VERSION_FORCE" ]; then
-            python_version="[\"$PYTHON_VERSION_FORCE\"]"
-          fi
-          if [ -n "$WORKING_DIRECTORY_FORCE" ]; then
-            working_directory="[\"$WORKING_DIRECTORY_FORCE\"]"
-          fi
-          matrix="{\"python-version\": $python_version, \"working-directory\": $working_directory}"
-          echo $matrix
-          echo "matrix=$matrix" >> $GITHUB_OUTPUT
   build:
-    if: github.repository_owner == 'langchain-ai' || github.event_name != 'schedule'
-    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
+    defaults:
+      run:
+        working-directory: libs/langchain
     runs-on: ubuntu-latest
-    needs: [compute-matrix]
-    timeout-minutes: 20
+    environment: Scheduled testing
     strategy:
-      fail-fast: false
       matrix:
-        python-version: ${{ fromJSON(needs.compute-matrix.outputs.matrix).python-version }}
-        working-directory: ${{ fromJSON(needs.compute-matrix.outputs.matrix).working-directory }}
-
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    name: Python ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4
-        with:
-          path: langchain
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-google
-          path: langchain-google
-      - uses: actions/checkout@v4
-        with:
-          repository: langchain-ai/langchain-aws
-          path: langchain-aws
 
-      - name: Move libs
-        run: |
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            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-aws/libs/aws langchain/libs/partners/aws
-
-      - name: Set up Python ${{ matrix.python-version }} with poetry
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
-        uses: "./langchain/.github/actions/poetry_setup"
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: "./.github/actions/poetry_setup"
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: langchain/${{ matrix.working-directory }}
+          working-directory: libs/langchain
           cache-key: scheduled
 
-      - name: Set up Python ${{ matrix.python-version }} + uv
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        uses: "./langchain/.github/actions/uv_setup"
-        with:
-          python-version: ${{ matrix.python-version }}
-
       - name: 'Authenticate to Google Cloud'
         id: 'auth'
         uses: google-github-actions/auth@v2
@@ -107,23 +45,22 @@ jobs:
         with:
           aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
           aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ secrets.AWS_REGION }}
+          aws-region: ${{ vars.AWS_REGION }}
 
-      - name: Install dependencies (poetry)
-        if: contains(env.POETRY_LIBS, matrix.working-directory)
+      - name: Install dependencies
+        working-directory: libs/langchain
+        shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
-          cd langchain/${{ matrix.working-directory }}
           poetry install --with=test_integration,test
 
-      - name: Install dependencies (uv)
-        if: "!contains(env.POETRY_LIBS, matrix.working-directory)"
-        run: |
-          echo "Running scheduled tests, installing dependencies with uv..."
-          cd langchain/${{ matrix.working-directory }}
-          uv sync --group test --group test_integration
+      - name: Install deps outside pyproject
+        if: ${{ startsWith(inputs.working-directory, 'libs/community/') }}
+        shell: bash
+        run: poetry run pip install "boto3<2" "google-cloud-aiplatform<2"
 
-      - name: Run integration tests
+      - name: Run tests
+        shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
@@ -131,34 +68,14 @@ 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 }}
-          DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
-          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
-          HUGGINGFACEHUB_API_TOKEN: ${{ secrets.HUGGINGFACEHUB_API_TOKEN }}
-          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
-          XAI_API_KEY: ${{ secrets.XAI_API_KEY }}
-          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
-          NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
-          GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
-          GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
-          GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
-          PPLX_API_KEY: ${{ secrets.PPLX_API_KEY }}
         run: |
-          cd langchain/${{ matrix.working-directory }}
-          make integration_tests
-
-      - name: Remove external libraries
-        run: | 
-          rm -rf \
-            langchain/libs/partners/google-genai \
-            langchain/libs/partners/google-vertexai \
-            langchain/libs/partners/aws
+          make scheduled_tests
 
       - name: Ensure the tests did not create any additional files
-        working-directory: langchain
+        shell: bash
         run: |
           set -eu
 

.gitignore

@@ -59,7 +59,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-.codspeed/
 
 # Translations
 *.mo
@@ -117,7 +116,6 @@ celerybeat.pid
 .env
 .envrc
 .venv*
-venv*
 env/
 ENV/
 env.bak/
@@ -134,7 +132,6 @@ env.bak/
 
 # mypy
 .mypy_cache/
-.mypy_cache_test/
 .dmypy.json
 dmypy.json
 
@@ -168,14 +165,11 @@ 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
@@ -183,4 +177,3 @@ _dist
 docs/docs/templates
 
 prof
-virtualenv/

.pre-commit-config.yaml

@@ -1,117 +0,0 @@
-repos:
-- repo: local
-  hooks:
-    - id: core
-      name: format core
-      language: system
-      entry: make -C libs/core format
-      files: ^libs/core/
-      pass_filenames: false
-    - id: langchain
-      name: format langchain
-      language: system
-      entry: make -C libs/langchain format
-      files: ^libs/langchain/
-      pass_filenames: false
-    - id: standard-tests
-      name: format standard-tests
-      language: system
-      entry: make -C libs/standard-tests format
-      files: ^libs/standard-tests/
-      pass_filenames: false
-    - id: text-splitters
-      name: format text-splitters
-      language: system
-      entry: make -C libs/text-splitters format
-      files: ^libs/text-splitters/
-      pass_filenames: false
-    - id: anthropic
-      name: format partners/anthropic
-      language: system
-      entry: make -C libs/partners/anthropic format
-      files: ^libs/partners/anthropic/
-      pass_filenames: false
-    - id: chroma
-      name: format partners/chroma
-      language: system
-      entry: make -C libs/partners/chroma format
-      files: ^libs/partners/chroma/
-      pass_filenames: false
-    - id: couchbase
-      name: format partners/couchbase
-      language: system
-      entry: make -C libs/partners/couchbase format
-      files: ^libs/partners/couchbase/
-      pass_filenames: false
-    - id: exa
-      name: format partners/exa
-      language: system
-      entry: make -C libs/partners/exa format
-      files: ^libs/partners/exa/
-      pass_filenames: false
-    - id: fireworks
-      name: format partners/fireworks
-      language: system
-      entry: make -C libs/partners/fireworks format
-      files: ^libs/partners/fireworks/
-      pass_filenames: false
-    - id: groq
-      name: format partners/groq
-      language: system
-      entry: make -C libs/partners/groq format
-      files: ^libs/partners/groq/
-      pass_filenames: false
-    - id: huggingface
-      name: format partners/huggingface
-      language: system
-      entry: make -C libs/partners/huggingface format
-      files: ^libs/partners/huggingface/
-      pass_filenames: false
-    - id: mistralai
-      name: format partners/mistralai
-      language: system
-      entry: make -C libs/partners/mistralai format
-      files: ^libs/partners/mistralai/
-      pass_filenames: false
-    - id: nomic
-      name: format partners/nomic
-      language: system
-      entry: make -C libs/partners/nomic format
-      files: ^libs/partners/nomic/
-      pass_filenames: false
-    - id: ollama
-      name: format partners/ollama
-      language: system
-      entry: make -C libs/partners/ollama format
-      files: ^libs/partners/ollama/
-      pass_filenames: false
-    - id: openai
-      name: format partners/openai
-      language: system
-      entry: make -C libs/partners/openai format
-      files: ^libs/partners/openai/
-      pass_filenames: false
-    - id: prompty
-      name: format partners/prompty
-      language: system
-      entry: make -C libs/partners/prompty format
-      files: ^libs/partners/prompty/
-      pass_filenames: false
-    - id: qdrant
-      name: format partners/qdrant
-      language: system
-      entry: make -C libs/partners/qdrant format
-      files: ^libs/partners/qdrant/
-      pass_filenames: false
-    - id: voyageai
-      name: format partners/voyageai
-      language: system
-      entry: make -C libs/partners/voyageai format
-      files: ^libs/partners/voyageai/
-      pass_filenames: false
-    - id: root
-      name: format docs, cookbook
-      language: system
-      entry: make format
-      files: ^(docs|cookbook)/
-      pass_filenames: false

.readthedocs.yaml

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

MIGRATE.md

@@ -1,11 +1,70 @@
 # Migrating
 
-Please see the following guides for migrating LangChain code:
+## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
 
-* 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/)
+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).
 
-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.
+### 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`

Makefile

@@ -1,87 +1,76 @@
-.PHONY: all clean help docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck spell_check spell_fix lint lint_package lint_tests format format_diff
+.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
 
-.EXPORT_ALL_VARIABLES:
-UV_FROZEN = true
-
-## help: Show this help info.
-help: Makefile
-	@printf "\n\033[1mUsage: make <TARGETS> ...\033[0m\n\n\033[1mTargets:\033[0m\n\n"
-	@sed -n 's/^## //p' $< | awk -F':' '{printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}' | sort | sed -e 's/^/  /'
-
-## all: Default target, shows help.
+# Default target executed when no arguments are given to make.
 all: help
 
-## clean: Clean documentation and API documentation artifacts.
-clean: docs_clean api_docs_clean
 
 ######################
 # DOCUMENTATION
 ######################
 
-## docs_build: Build the documentation.
+clean: docs_clean api_docs_clean
+
+
 docs_build:
-	cd docs && make build
+	docs/.local_build.sh
 
-## docs_clean: Clean the documentation build artifacts.
 docs_clean:
-	cd docs && make clean
+	@if [ -d _dist ]; then \
+			rm -r _dist; \
+			echo "Directory _dist has been cleaned."; \
+	else \
+			echo "Nothing to clean."; \
+	fi
 
-## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
-	uv run --no-group test linkchecker _dist/docs/ --ignore-url node_modules
+	poetry run linkchecker _dist/docs/ --ignore-url node_modules
 
-## api_docs_build: Build the API Reference documentation.
 api_docs_build:
-	uv run --no-group test python docs/api_reference/create_api_rst.py
-	cd docs/api_reference && uv run --no-group test make html
-	uv run --no-group test python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
+	poetry run python docs/api_reference/create_api_rst.py
+	cd docs/api_reference && poetry run make html
 
-API_PKG ?= text-splitters
-
-api_docs_quick_preview:
-	uv run --no-group test python docs/api_reference/create_api_rst.py $(API_PKG)
-	cd docs/api_reference && uv run make html
-	uv run --no-group test python docs/api_reference/scripts/custom_formatter.py docs/api_reference/_build/html/
-	open docs/api_reference/_build/html/reference.html
-
-## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
-	find ./docs/api_reference -name '*_api_reference.rst' -delete
-	git clean -fdX ./docs/api_reference
-	rm docs/api_reference/index.md
-	
+	rm -f docs/api_reference/api_reference.rst
+	cd docs/api_reference && poetry run make clean
 
-## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
-	uv run --no-group test linkchecker docs/api_reference/_build/html/index.html
+	poetry run linkchecker docs/api_reference/_build/html/index.html
 
-## spell_check: Run codespell on the project.
 spell_check:
-	uv run --no-group test codespell --toml pyproject.toml
+	poetry run codespell --toml pyproject.toml
 
-## spell_fix: Run codespell on the project and fix the errors.
 spell_fix:
-	uv run --no-group test codespell --toml pyproject.toml -w
+	poetry run codespell --toml pyproject.toml -w
 
 ######################
 # LINTING AND FORMATTING
 ######################
 
-## lint: Run linting on the project.
 lint lint_package lint_tests:
-	uv run --group lint ruff check docs cookbook
-	uv run --group lint ruff format docs cookbook cookbook --diff
-	uv run --group lint ruff check --select I docs cookbook
-	git --no-pager grep 'from langchain import' docs cookbook | grep -vE 'from langchain import (hub)' && echo "Error: no importing langchain from root in docs, except for hub" && exit 1 || exit 0
-	
-	git --no-pager grep 'api.python.langchain.com' -- docs/docs ':!docs/docs/additional_resources/arxiv_references.mdx' ':!docs/docs/integrations/document_loaders/sitemap.ipynb' || exit 0 && \
-	echo "Error: you should link python.langchain.com/api_reference, not api.python.langchain.com in the docs" && \
-	exit 1
+	poetry run ruff docs templates cookbook
+	poetry run ruff format docs templates cookbook --diff
+	poetry run ruff --select I docs templates cookbook
+	git grep 'from langchain import' {docs/docs,templates,cookbook} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
 
-## format: Format the project files.
 format format_diff:
-	uv run --group lint ruff format docs cookbook
-	uv run --group lint ruff check --select I --fix docs cookbook
+	poetry run ruff format docs templates cookbook
+	poetry run ruff --select I --fix docs templates cookbook
 
-update-package-downloads:
-	uv run python docs/scripts/packages_yml_get_downloads.py
+
+######################
+# HELP
+######################
+
+help:
+	@echo '===================='
+	@echo '-- DOCUMENTATION --'
+	@echo 'clean                        - run docs_clean and api_docs_clean'
+	@echo 'docs_build                   - build the documentation'
+	@echo 'docs_clean                   - clean the documentation build artifacts'
+	@echo 'docs_linkcheck               - run linkchecker on the documentation'
+	@echo 'api_docs_build               - build the API Reference documentation'
+	@echo 'api_docs_clean               - clean the API Reference documentation build artifacts'
+	@echo 'api_docs_linkcheck           - run linkchecker on the API Reference documentation'
+	@echo 'spell_check               	- run codespell on the project'
+	@echo 'spell_fix               		- run codespell on the project and fix the errors'
+	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'

README.md

@@ -1,83 +1,113 @@
-<picture>
-  <source media="(prefers-color-scheme: light)" srcset="docs/static/img/logo-dark.svg">
-  <source media="(prefers-color-scheme: dark)" srcset="docs/static/img/logo-light.svg">
-  <img alt="LangChain Logo" src="docs/static/img/logo-dark.svg" width="80%">
-</picture>
+# 🦜️🔗 LangChain
 
-<div>
-<br>
-</div>
+⚡ Build context-aware reasoning applications ⚡
 
-[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/releases)
+[![Release Notes](https://img.shields.io/github/release/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/releases)
 [![CI](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml/badge.svg)](https://github.com/langchain-ai/langchain/actions/workflows/check_diffs.yml)
-[![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
-[![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-core?style=flat-square)](https://pypistats.org/packages/langchain-core)
-[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
-[![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)
-[<img src="https://github.com/codespaces/badge.svg" title="Open in Github Codespace" width="150" height="20">](https://codespaces.new/langchain-ai/langchain)
+[![Downloads](https://static.pepy.tech/badge/langchain/month)](https://pepy.tech/project/langchain)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
-[![CodSpeed Badge](https://img.shields.io/endpoint?url=https://codspeed.io/badge.json)](https://codspeed.io/langchain-ai/langchain)
+[![](https://dcbadge.vercel.app/api/server/6adMQxSpJS?compact=true&style=flat)](https://discord.gg/6adMQxSpJS)
+[![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](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)
+[![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=social)](https://star-history.com/#langchain-ai/langchain)
+[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain)](https://libraries.io/github/langchain-ai/langchain)
+[![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain)](https://github.com/langchain-ai/langchain/issues)
 
-> [!NOTE]
-> Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
+Looking for the JS/TS library? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-LangChain is a framework for building LLM-powered applications. It helps you chain
-together interoperable components and third-party integrations to simplify AI
-application development —  all while future-proofing decisions as the underlying
-technology evolves.
+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 -U langchain
+pip install langchain
 ```
 
-To learn more about LangChain, check out
-[the docs](https://python.langchain.com/docs/introduction/). If you’re looking for more
-advanced customization or agent orchestration, check out
-[LangGraph](https://langchain-ai.github.io/langgraph/), our framework for building
-controllable agent workflows.
+With conda:
+```bash
+conda install langchain -c conda-forge
+```
 
-## Why use LangChain?
+## 🤔 What is LangChain?
 
-LangChain helps developers build applications powered by LLMs through a standard
-interface for models, embeddings, vector stores, and more. 
+**LangChain** is a framework for developing applications powered by language models. It enables applications that:
+- **Are context-aware**: connect a language model to sources of context (prompt instructions, few shot examples, content to ground its response in, etc.)
+- **Reason**: rely on a language model to reason (about how to answer based on provided context, what actions to take, etc.)
 
-Use LangChain for:
-- **Real-time data augmentation**. Easily connect LLMs to diverse data sources and
-external / internal systems, drawing from LangChain’s vast library of integrations with
-model providers, tools, vector stores, retrievers, and more.
-- **Model interoperability**. Swap models in and out as your engineering team
-experiments to find the best choice for your application’s needs. As the industry
-frontier evolves, adapt quickly — LangChain’s abstractions keep you moving without
-losing momentum.
+This framework consists of several parts.
+- **LangChain Libraries**: The Python and JavaScript libraries. Contains interfaces and integrations for a myriad of components, a basic run time for combining these components into chains and agents, and off-the-shelf implementations of chains and agents.
+- **[LangChain Templates](templates)**: A collection of easily deployable reference architectures for a wide variety of tasks.
+- **[LangServe](https://github.com/langchain-ai/langserve)**: A library for deploying LangChain chains as a REST API.
+- **[LangSmith](https://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.
+- **[LangGraph](https://python.langchain.com/docs/langgraph)**: LangGraph is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain. It extends the LangChain Expression Language with the ability to coordinate multiple chains (or actors) across multiple steps of computation in a cyclic manner. 
 
-## LangChain’s ecosystem
-While the LangChain framework can be used standalone, it also integrates seamlessly
-with any LangChain product, giving developers a full suite of tools when building LLM
-applications. 
+The LangChain libraries themselves are made up of several different packages.
+- **[`langchain-core`](libs/core)**: Base abstractions and LangChain Expression Language.
+- **[`langchain-community`](libs/community)**: Third party integrations.
+- **[`langchain`](libs/langchain)**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
 
-To improve your LLM application development, pair LangChain with:
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/img/langchain_stack.png "LangChain Architecture Overview")
 
-- [LangSmith](http://www.langchain.com/langsmith) - Helpful for agent evals and
-observability. Debug poor-performing LLM app runs, evaluate agent trajectories, gain
-visibility in production, and improve performance over time.
-- [LangGraph](https://langchain-ai.github.io/langgraph/) - Build agents that can
-reliably handle complex tasks with LangGraph, our low-level agent orchestration
-framework. LangGraph offers customizable architecture, long-term memory, and
-human-in-the-loop workflows — and is trusted in production by companies like LinkedIn,
-Uber, Klarna, and GitLab.
-- [LangGraph Platform](https://langchain-ai.github.io/langgraph/concepts/#langgraph-platform) - Deploy
-and scale agents effortlessly with a purpose-built deployment platform for long
-running, stateful workflows. Discover, reuse, configure, and share agents across
-teams — and iterate quickly with visual prototyping in
-[LangGraph Studio](https://langchain-ai.github.io/langgraph/concepts/langgraph_studio/).
+## 🧱 What can you build with LangChain?
+**❓ Retrieval augmented generation**
 
-## Additional resources
-- [Tutorials](https://python.langchain.com/docs/tutorials/): Simple walkthroughs with
-guided examples on getting started with LangChain.
-- [How-to Guides](https://python.langchain.com/docs/how_to/): Quick, actionable code
-snippets for topics such as tool calling, RAG use cases, and more.
-- [Conceptual Guides](https://python.langchain.com/docs/concepts/): Explanations of key
-concepts behind the LangChain framework.
-- [API Reference](https://python.langchain.com/api_reference/): Detailed reference on
-navigating base packages and integrations for LangChain.
+- [Documentation](https://python.langchain.com/docs/use_cases/question_answering/)
+- End-to-end Example: [Chat LangChain](https://chat.langchain.com) and [repo](https://github.com/langchain-ai/chat-langchain)
+
+**💬 Analyzing structured data**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/qa_structured/sql)
+- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain/tree/master/templates/sql-llama2)
+
+**🤖 Chatbots**
+
+- [Documentation](https://python.langchain.com/docs/use_cases/chatbots)
+- 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 [Use cases](https://python.langchain.com/docs/use_cases/) section of the docs for more.
+
+## 🚀 How does LangChain help?
+The main value props of the LangChain libraries are:
+1. **Components**: composable 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. 
+
+Components fall into the following **modules**:
+
+**📃 Model I/O:**
+
+This includes prompt management, prompt optimization, a generic interface for all LLMs, and common utilities for working with LLMs.
+
+**📚 Retrieval:**
+
+Data Augmented Generation involves specific types of chains that first interact with an external data source to fetch data for use in the generation step. Examples include summarization of long pieces of text and question/answering over specific data sources.
+
+**🤖 Agents:**
+
+Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end-to-end agents.
+
+## 📖 Documentation
+
+Please see [here](https://python.langchain.com) for full documentation, which includes:
+
+- [Getting started](https://python.langchain.com/docs/get_started/introduction): installation, setting up the environment, simple examples
+- Overview of the [interfaces](https://python.langchain.com/docs/expression_language/), [modules](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
+- [Use case](https://python.langchain.com/docs/use_cases/qa_structured/sql) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/adapters/openai)
+- [LangSmith](https://python.langchain.com/docs/langsmith/), [LangServe](https://python.langchain.com/docs/langserve), and [LangChain Template](https://python.langchain.com/docs/templates/) overviews
+- [Reference](https://api.python.langchain.com): full API docs
+
+
+## 💁 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/docs/contributing/).
+
+## 🌟 Contributors
+
+[![langchain contributors](https://contrib.rocks/image?repo=langchain-ai/langchain&max=2000)](https://github.com/langchain-ai/langchain/graphs/contributors)

SECURITY.md

@@ -1,86 +1,6 @@
 # Security Policy
 
-LangChain has a large ecosystem of integrations with various external resources like local and remote file systems, APIs and databases. These integrations allow developers to create versatile applications that combine the power of LLMs with the ability to access, interact with and manipulate external resources.
+## Reporting a Vulnerability
 
-## Best practices
-
-When building such applications developers should remember to follow good security practices:
-
-* [**Limit Permissions**](https://en.wikipedia.org/wiki/Principle_of_least_privilege): Scope permissions specifically to the application's need. Granting broad or excessive permissions can introduce significant security vulnerabilities. To avoid such vulnerabilities, consider using read-only credentials, disallowing access to sensitive resources, using sandboxing techniques (such as running inside a container), specifying proxy configurations to control external requests, etc. as appropriate for your application.
-* **Anticipate Potential Misuse**: Just as humans can err, so can Large Language Models (LLMs). Always assume that any system access or credentials may be used in any way allowed by the permissions they are assigned. For example, if a pair of database credentials allows deleting data, it’s safest to assume that any LLM able to use those credentials may in fact delete data.
-* [**Defense in Depth**](https://en.wikipedia.org/wiki/Defense_in_depth_(computing)): No security technique is perfect. Fine-tuning and good chain design can reduce, but not eliminate, the odds that a Large Language Model (LLM) may make a mistake. It’s best to combine multiple layered security approaches rather than relying on any single layer of defense to ensure security. For example: use both read-only permissions and sandboxing to ensure that LLMs are only able to access data that is explicitly meant for them to use.
-
-Risks of not doing so include, but are not limited to:
-* Data corruption or loss.
-* Unauthorized access to confidential information.
-* Compromised performance or availability of critical resources.
-
-Example scenarios with mitigation strategies:
-
-* A user may ask an agent with access to the file system to delete files that should not be deleted or read the content of files that contain sensitive information. To mitigate, limit the agent to only use a specific directory and only allow it to read or write files that are safe to read or write. Consider further sandboxing the agent by running it in a container.
-* A user may ask an agent with write access to an external API to write malicious data to the API, or delete data from that API. To mitigate, give the agent read-only API keys, or limit it to only use endpoints that are already resistant to such misuse.
-* A user may ask an agent with access to a database to drop a table or mutate the schema. To mitigate, scope the credentials to only the tables that the agent needs to access and consider issuing READ-ONLY credentials.
-
-If you're building applications that access external resources like file systems, APIs
-or databases, consider speaking with your company's security team to determine how to best
-design and secure your applications.
-
-## Reporting OSS Vulnerabilities
-
-LangChain is partnered with [huntr by Protect AI](https://huntr.com/) to provide 
-a bounty program for our open source projects. 
-
-Please report security vulnerabilities associated with the LangChain 
-open source projects by visiting the following link:
-
-[https://huntr.com/bounties/disclose/](https://huntr.com/bounties/disclose/?target=https%3A%2F%2Fgithub.com%2Flangchain-ai%2Flangchain&validSearch=true)
-
-Before reporting a vulnerability, please review:
-
-1) In-Scope Targets and Out-of-Scope Targets below.
-2) The [langchain-ai/langchain](https://python.langchain.com/docs/contributing/repo_structure) monorepo structure.
-3) The [Best practicies](#best-practices) above to
-   understand what we consider to be a security vulnerability vs. developer
-   responsibility.
-
-### In-Scope Targets
-
-The following packages and repositories are eligible for bug bounties:
-
-- langchain-core
-- langchain (see exceptions)
-- langchain-community (see exceptions)
-- langgraph
-- langserve
-
-### Out of Scope Targets
-
-All out of scope targets defined by huntr as well as:
-
-- **langchain-experimental**: This repository is for experimental code and is not
-  eligible for bug bounties (see [package warning](https://pypi.org/project/langchain-experimental/)), bug reports to it will be marked as interesting or waste of
-  time and published with no bounty attached.
-- **tools**: Tools in either langchain or langchain-community are not eligible for bug
-  bounties. This includes the following directories
-  - libs/langchain/langchain/tools
-  - libs/community/langchain_community/tools
-  - Please review the [best practices](#best-practices)
-    for more details, but generally tools interact with the real world. Developers are
-    expected to understand the security implications of their code and are responsible
-    for the security of their tools.
-- Code documented with security notices. This will be decided done on a case by
-  case basis, but likely will not be eligible for a bounty as the code is already
-  documented with guidelines for developers that should be followed for making their
-  application secure.
-- Any LangSmith related repositories or APIs (see [Reporting LangSmith Vulnerabilities](#reporting-langsmith-vulnerabilities)).
-
-## Reporting LangSmith Vulnerabilities
-
-Please report security vulnerabilities associated with LangSmith by email to `security@langchain.dev`.
-
-- LangSmith site: https://smith.langchain.com
-- SDK client: https://github.com/langchain-ai/langsmith-sdk
-
-### Other Security Concerns
-
-For any other security concerns, please contact us at `security@langchain.dev`.
+Please report security vulnerabilities by email to `security@langchain.dev`.
+This email is an alias to a subset of our maintainers, and will ensure the issue is promptly triaged and acted upon as needed.

cookbook/Gemma_LangChain.ipynb

@@ -1,932 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "BYejgj8Zf-LG",
-    "tags": []
-   },
-   "source": [
-    "## Getting started with LangChain and Gemma, running locally or in the Cloud"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "2IxjMb9-jIJ8"
-   },
-   "source": [
-    "### Installing dependencies"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "executionInfo": {
-     "elapsed": 9436,
-     "status": "ok",
-     "timestamp": 1708975187360,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "XZaTsXfcheTF",
-    "outputId": "eb21d603-d824-46c5-f99f-087fb2f618b1",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "!pip install --upgrade langchain langchain-google-vertexai"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "IXmAujvC3Kwp"
-   },
-   "source": [
-    "### Running the model"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "CI8Elyc5gBQF"
-   },
-   "source": [
-    "Go to the VertexAI Model Garden on Google Cloud [console](https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/335), and deploy the desired version of Gemma to VertexAI. It will take a few minutes, and after the endpoint is ready, you need to copy its number."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "id": "gv1j8FrVftsC"
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "project: str = \"PUT_YOUR_PROJECT_ID_HERE\"  # @param {type:\"string\"}\n",
-    "endpoint_id: str = \"PUT_YOUR_ENDPOINT_ID_HERE\"  # @param {type:\"string\"}\n",
-    "location: str = \"PUT_YOUR_ENDPOINT_LOCAtION_HERE\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 3,
-     "status": "ok",
-     "timestamp": 1708975440503,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "bhIHsFGYjtFt",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 17:15:10.457149: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 17:15:10.508925: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 17:15:10.508957: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 17:15:10.510289: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 17:15:10.518898: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import (\n",
-    "    GemmaChatVertexAIModelGarden,\n",
-    "    GemmaVertexAIModelGarden,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 351,
-     "status": "ok",
-     "timestamp": 1708975440852,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "WJv-UVWwh0lk",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "llm = GemmaVertexAIModelGarden(\n",
-    "    endpoint_id=endpoint_id,\n",
-    "    project=project,\n",
-    "    location=location,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "executionInfo": {
-     "elapsed": 714,
-     "status": "ok",
-     "timestamp": 1708975441564,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "6kM7cEFdiN9h",
-    "outputId": "fb420c56-5614-4745-cda8-0ee450a3e539",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Prompt:\n",
-      "What is the meaning of life?\n",
-      "Output:\n",
-      " Who am I? Why do I exist? These are questions I have struggled with\n"
-     ]
-    }
-   ],
-   "source": [
-    "output = llm.invoke(\"What is the meaning of life?\")\n",
-    "print(output)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "zzep9nfmuUcO"
-   },
-   "source": [
-    "We can also use Gemma as a multi-turn chat model:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "colab": {
-     "base_uri": "https://localhost:8080/"
-    },
-    "executionInfo": {
-     "elapsed": 964,
-     "status": "ok",
-     "timestamp": 1708976298189,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "8tPHoM5XiZOl",
-    "outputId": "7b8fb652-9aed-47b0-c096-aa1abfc3a2a9",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='Prompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\n8-years old.<end_of_turn>\\n\\n<start_of'\n",
-      "content='Prompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nPrompt:\\n<start_of_turn>user\\nHow much is 2+2?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\n8-years old.<end_of_turn>\\n\\n<start_of<end_of_turn>\\n<start_of_turn>user\\nHow much is 3+3?<end_of_turn>\\n<start_of_turn>model\\nOutput:\\nOutput:\\n3-years old.<end_of_turn>\\n\\n<'\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "llm = GemmaChatVertexAIModelGarden(\n",
-    "    endpoint_id=endpoint_id,\n",
-    "    project=project,\n",
-    "    location=location,\n",
-    ")\n",
-    "\n",
-    "message1 = HumanMessage(content=\"How much is 2+2?\")\n",
-    "answer1 = llm.invoke([message1])\n",
-    "print(answer1)\n",
-    "\n",
-    "message2 = HumanMessage(content=\"How much is 3+3?\")\n",
-    "answer2 = llm.invoke([message1, answer1, message2])\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can post-process response to avoid repetitions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content='Output:\\n<<humming>>: 2+2 = 4.\\n<end'\n",
-      "content='Output:\\nOutput:\\n<<humming>>: 3+3 = 6.'\n"
-     ]
-    }
-   ],
-   "source": [
-    "answer1 = llm.invoke([message1], parse_response=True)\n",
-    "print(answer1)\n",
-    "\n",
-    "answer2 = llm.invoke([message1, answer1, message2], parse_response=True)\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "VEfjqo7fjARR"
-   },
-   "source": [
-    "## Running Gemma locally from Kaggle"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "gVW8QDzHu7TA"
-   },
-   "source": [
-    "In order to run Gemma locally, you can download it from Kaggle first. In order to do this, you'll need to login into the Kaggle platform, create a API key and download a `kaggle.json` Read more about Kaggle auth [here](https://www.kaggle.com/docs/api)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "S1EsXQ3XvZkQ"
-   },
-   "source": [
-    "### Installation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 335,
-     "status": "ok",
-     "timestamp": 1708976305471,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "p8SMwpKRvbef",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/lib/python3.10/pty.py:89: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n",
-      "  pid, fd = os.forkpty()\n"
-     ]
-    }
-   ],
-   "source": [
-    "!mkdir -p ~/.kaggle && cp kaggle.json ~/.kaggle/kaggle.json"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 7802,
-     "status": "ok",
-     "timestamp": 1708976363010,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "Yr679aePv9Fq",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/opt/conda/lib/python3.10/pty.py:89: RuntimeWarning: os.fork() was called. os.fork() is incompatible with multithreaded code, and JAX is multithreaded, so this will likely lead to a deadlock.\n",
-      "  pid, fd = os.forkpty()\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
-      "tensorstore 0.1.54 requires ml-dtypes>=0.3.1, but you have ml-dtypes 0.2.0 which is incompatible.\u001b[0m\u001b[31m\n",
-      "\u001b[0m"
-     ]
-    }
-   ],
-   "source": [
-    "!pip install keras>=3 keras_nlp"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "E9zn8nYpv3QZ"
-   },
-   "source": [
-    "### Usage"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 8536,
-     "status": "ok",
-     "timestamp": 1708976601206,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "0LFRmY8TjCkI",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:38:40.797559: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 16:38:40.848444: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 16:38:40.848478: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 16:38:40.849728: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 16:38:40.857936: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import GemmaLocalKaggle"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "v-o7oXVavdMQ"
-   },
-   "source": [
-    "You can specify the keras backend (by default it's `tensorflow`, but you can change it be `jax` or `torch`)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 9,
-     "status": "ok",
-     "timestamp": 1708976601206,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "vvTUH8DNj5SF",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "keras_backend: str = \"jax\"  # @param {type:\"string\"}\n",
-    "model_name: str = \"gemma_2b_en\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 40836,
-     "status": "ok",
-     "timestamp": 1708976761257,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "YOmrqxo5kHXK",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:23:14.661164: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 20549 MB memory:  -> device: 0, name: NVIDIA L4, pci bus id: 0000:00:03.0, compute capability: 8.9\n",
-      "normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.\n"
-     ]
-    }
-   ],
-   "source": [
-    "llm = GemmaLocalKaggle(model_name=model_name, keras_backend=keras_backend)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "id": "Zu6yPDUgkQtQ",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "W0000 00:00:1709051129.518076  774855 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "What is the meaning of life?\n",
-      "\n",
-      "The question is one of the most important questions in the world.\n",
-      "\n",
-      "It’s the question that has\n"
-     ]
-    }
-   ],
-   "source": [
-    "output = llm.invoke(\"What is the meaning of life?\", max_tokens=30)\n",
-    "print(output)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### ChatModel"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "MSctpRE4u43N"
-   },
-   "source": [
-    "Same as above, using Gemma locally as a multi-turn chat model. You might need to re-start the notebook and clean your GPU memory in order to avoid OOM errors:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:58:22.331067: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 16:58:22.382948: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 16:58:22.382978: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 16:58:22.384312: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 16:58:22.392767: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import GemmaChatLocalKaggle"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "keras_backend: str = \"jax\"  # @param {type:\"string\"}\n",
-    "model_name: str = \"gemma_2b_en\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:58:29.001922: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1929] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 20549 MB memory:  -> device: 0, name: NVIDIA L4, pci bus id: 0000:00:03.0, compute capability: 8.9\n",
-      "normalizer.cc(51) LOG(INFO) precompiled_charsmap is empty. use identity normalization.\n"
-     ]
-    }
-   ],
-   "source": [
-    "llm = GemmaChatLocalKaggle(model_name=model_name, keras_backend=keras_backend)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "executionInfo": {
-     "elapsed": 3,
-     "status": "aborted",
-     "timestamp": 1708976382957,
-     "user": {
-      "displayName": "",
-      "userId": ""
-     },
-     "user_tz": -60
-    },
-    "id": "JrJmvZqwwLqj"
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 16:58:49.848412: I external/local_xla/xla/service/service.cc:168] XLA service 0x55adc0cf2c10 initialized for platform CUDA (this does not guarantee that XLA will be used). Devices:\n",
-      "2024-02-27 16:58:49.848458: I external/local_xla/xla/service/service.cc:176]   StreamExecutor device (0): NVIDIA L4, Compute Capability 8.9\n",
-      "2024-02-27 16:58:50.116614: I tensorflow/compiler/mlir/tensorflow/utils/dump_mlir_util.cc:269] disabling MLIR crash reproducer, set env var `MLIR_CRASH_REPRODUCER_DIRECTORY` to enable.\n",
-      "2024-02-27 16:58:54.389324: I external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:454] Loaded cuDNN version 8900\n",
-      "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
-      "I0000 00:00:1709053145.225207  784891 device_compiler.h:186] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.\n",
-      "W0000 00:00:1709053145.284227  784891 graph_launch.cc:671] Fallback to op-by-op mode because memset node breaks graph update\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n Tampoco\\nI'm a model.\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "message1 = HumanMessage(content=\"Hi! Who are you?\")\n",
-    "answer1 = llm.invoke([message1], max_tokens=30)\n",
-    "print(answer1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\n<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n Tampoco\\nI'm a model.<end_of_turn>\\n<start_of_turn>user\\nWhat can you help me with?<end_of_turn>\\n<start_of_turn>model\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "message2 = HumanMessage(content=\"What can you help me with?\")\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=60)\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can post-process the response if you want to avoid multi-turn statements:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"I'm a model.\\n Tampoco\\nI'm a model.\"\n",
-      "content='I can help you with your modeling.\\n Tampoco\\nI can'\n"
-     ]
-    }
-   ],
-   "source": [
-    "answer1 = llm.invoke([message1], max_tokens=30, parse_response=True)\n",
-    "print(answer1)\n",
-    "\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=60, parse_response=True)\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "EiZnztso7hyF"
-   },
-   "source": [
-    "## Running Gemma locally from HuggingFace"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "id": "qqAqsz5R7nKf",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2024-02-27 17:02:21.832409: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
-      "2024-02-27 17:02:21.883625: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
-      "2024-02-27 17:02:21.883656: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
-      "2024-02-27 17:02:21.884987: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
-      "2024-02-27 17:02:21.893340: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
-      "To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_google_vertexai import GemmaChatLocalHF, GemmaLocalHF"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "id": "tsyntzI08cOr",
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "# @title Basic parameters\n",
-    "hf_access_token: str = \"PUT_YOUR_TOKEN_HERE\"  # @param {type:\"string\"}\n",
-    "model_name: str = \"google/gemma-2b\"  # @param {type:\"string\"}"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "id": "JWrqEkOo8sm9",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a0d6de5542254ed1b6d3ba65465e050e",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "llm = GemmaLocalHF(model_name=\"google/gemma-2b\", hf_access_token=hf_access_token)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "id": "VX96Jf4Y84k-",
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "What is the meaning of life?\n",
-      "\n",
-      "The question is one of the most important questions in the world.\n",
-      "\n",
-      "It’s the question that has been asked by philosophers, theologians, and scientists for centuries.\n",
-      "\n",
-      "And it’s the question that\n"
-     ]
-    }
-   ],
-   "source": [
-    "output = llm.invoke(\"What is the meaning of life?\", max_tokens=50)\n",
-    "print(output)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Same as above, using Gemma locally as a multi-turn chat model. You might need to re-start the notebook and clean your GPU memory in order to avoid OOM errors:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "id": "9x-jmEBg9Mk1"
-   },
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c9a0b8e161d74a6faca83b1be96dee27",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Loading checkpoint shards:   0%|          | 0/2 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "llm = GemmaChatLocalHF(model_name=model_name, hf_access_token=hf_access_token)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "id": "qv_OSaMm9PVy"
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n<end_of_turn>\\n<start_of_turn>user\\nWhat do you mean\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "\n",
-    "message1 = HumanMessage(content=\"Hi! Who are you?\")\n",
-    "answer1 = llm.invoke([message1], max_tokens=60)\n",
-    "print(answer1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\n<start_of_turn>user\\nHi! Who are you?<end_of_turn>\\n<start_of_turn>model\\nI'm a model.\\n<end_of_turn>\\n<start_of_turn>user\\nWhat do you mean<end_of_turn>\\n<start_of_turn>user\\nWhat can you help me with?<end_of_turn>\\n<start_of_turn>model\\nI can help you with anything.\\n<\"\n"
-     ]
-    }
-   ],
-   "source": [
-    "message2 = HumanMessage(content=\"What can you help me with?\")\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=140)\n",
-    "\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And the same with posprocessing:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "content=\"I'm a model.\\n<end_of_turn>\\n\"\n",
-      "content='I can help you with anything.\\n<end_of_turn>\\n<end_of_turn>\\n'\n"
-     ]
-    }
-   ],
-   "source": [
-    "answer1 = llm.invoke([message1], max_tokens=60, parse_response=True)\n",
-    "print(answer1)\n",
-    "\n",
-    "answer2 = llm.invoke([message1, answer1, message2], max_tokens=120, parse_response=True)\n",
-    "print(answer2)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "colab": {
-   "provenance": []
-  },
-  "environment": {
-   "kernel": "python3",
-   "name": ".m116",
-   "type": "gcloud",
-   "uri": "gcr.io/deeplearning-platform-release/:m116"
-  },
-  "kernelspec": {
-   "display_name": "Python 3",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/LLaMA2_sql_chat.ipynb

@@ -38,9 +38,9 @@
     "\n",
     "To run locally, we use Ollama.ai. \n",
     "\n",
-    "See [here](/docs/integrations/chat/ollama) for details on installation and setup.\n",
+    "See [here](https://python.langchain.com/docs/integrations/chat/ollama) for details on installation and setup.\n",
     "\n",
-    "Also, see [here](/docs/guides/development/local_llms) for our full guide on local LLMs.\n",
+    "Also, see [here](https://python.langchain.com/docs/guides/local_llms) for our full guide on local LLMs.\n",
     " \n",
     "To use an external API, which is not private, we can use Replicate."
    ]

cookbook/Multi_modal_RAG.ipynb

@@ -64,7 +64,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -116,7 +116,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "\n",
@@ -355,7 +355,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
@@ -464,8 +464,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -604,7 +604,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"Give me company names that are interesting investments based on EV / NTM and NTM rev growth. Consider EV / NTM multiples vs historical?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"
@@ -630,7 +630,7 @@
    "source": [
     "# Check retrieval\n",
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=6)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=6)\n",
     "\n",
     "# We get 4 docs\n",
     "len(docs)"

cookbook/Multi_modal_RAG_google.ipynb

@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -U --quiet langchain langchain-chroma langchain-community openai langchain-experimental\n",
+    "%pip install -U --quiet langchain langchain_community openai chromadb langchain-experimental\n",
     "%pip install --quiet \"unstructured[all-docs]\" pypdf pillow pydantic lxml pillow matplotlib chromadb tiktoken"
    ]
   },
@@ -185,7 +185,7 @@
     "    )\n",
     "    # Text summary chain\n",
     "    model = VertexAI(\n",
-    "        temperature=0, model_name=\"gemini-pro\", max_tokens=1024\n",
+    "        temperature=0, model_name=\"gemini-pro\", max_output_tokens=1024\n",
     "    ).with_fallbacks([empty_response])\n",
     "    summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
     "\n",
@@ -254,9 +254,9 @@
     "\n",
     "def image_summarize(img_base64, prompt):\n",
     "    \"\"\"Make image summary\"\"\"\n",
-    "    model = ChatVertexAI(model=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(model_name=\"gemini-pro-vision\", max_output_tokens=1024)\n",
     "\n",
-    "    msg = model.invoke(\n",
+    "    msg = model(\n",
     "        [\n",
     "            HumanMessage(\n",
     "                content=[\n",
@@ -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",
-    "    \"\"\"Display base64 encoded string as image\"\"\"\n",
+    "    \"\"\"Disply 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",
@@ -462,8 +462,8 @@
     "    Check if the base64 data is an image by looking at the start of the data\n",
     "    \"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",
@@ -553,7 +553,9 @@
     "    \"\"\"\n",
     "\n",
     "    # Multi-modal LLM\n",
-    "    model = ChatVertexAI(temperature=0, model_name=\"gemini-pro-vision\", max_tokens=1024)\n",
+    "    model = ChatVertexAI(\n",
+    "        temperature=0, model_name=\"gemini-pro-vision\", max_output_tokens=1024\n",
+    "    )\n",
     "\n",
     "    # RAG pipeline\n",
     "    chain = (\n",
@@ -602,7 +604,7 @@
    ],
    "source": [
     "query = \"What are the EV / NTM and NTM rev growth for MongoDB, Cloudflare, and Datadog?\"\n",
-    "docs = retriever_multi_vector_img.invoke(query, limit=1)\n",
+    "docs = retriever_multi_vector_img.get_relevant_documents(query, limit=1)\n",
     "\n",
     "# We get 2 docs\n",
     "len(docs)"

cookbook/README.md

@@ -4,13 +4,10 @@ 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.
 [Semi_structured_multi_modal_RA...](https://github.com/langchain-ai/langchain/tree/master/cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb) | Perform retrieval-augmented generation (rag) on documents with semi-structured data and images, using various tools and methods such as unstructured for parsing, multi-vector retriever for storing, lcel for implementing chains, and open source language models like llama2, llava, and gpt4all.
-[amazon_personalize_how_to.ipynb](https://github.com/langchain-ai/langchain/blob/master/cookbook/amazon_personalize_how_to.ipynb) | Retrieving personalized recommendations from Amazon Personalize and use custom agents to build generative AI apps
 [analyze_document.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/analyze_document.ipynb) | Analyze a single long document.
 [autogpt/autogpt.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/autogpt.ipynb) | Implement autogpt, a language model, with langchain primitives such as llms, prompttemplates, vectorstores, embeddings, and tools.
 [autogpt/marathon_times.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/autogpt/marathon_times.ipynb) | Implement autogpt for finding winning marathon times.
@@ -21,6 +18,7 @@ Notebook | Description
 [code-analysis-deeplake.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/code-analysis-deeplake.ipynb) | Analyze its own code base with the help of gpt and activeloop's deep lake.
 [custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval.ipynb) | Build a custom agent that can interact with ai plugins by retrieving tools and creating natural language wrappers around openapi endpoints.
 [custom_agent_with_plugin_retri...](https://github.com/langchain-ai/langchain/tree/master/cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb) | Build a custom agent with plugin retrieval functionality, utilizing ai plugins from the `plugnplai` directory.
+[databricks_sql_db.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/databricks_sql_db.ipynb) | Connect to databricks runtimes and databricks sql.
 [deeplake_semantic_search_over_...](https://github.com/langchain-ai/langchain/tree/master/cookbook/deeplake_semantic_search_over_chat.ipynb) | Perform semantic search and question-answering over a group chat using activeloop's deep lake with gpt4.
 [elasticsearch_db_qa.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/elasticsearch_db_qa.ipynb) | Interact with elasticsearch analytics databases in natural language and build search queries via the elasticsearch dsl API.
 [extraction_openai_tools.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/extraction_openai_tools.ipynb) | Structured Data Extraction with OpenAI Tools
@@ -37,7 +35,6 @@ 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.
@@ -49,7 +46,6 @@ Notebook | Description
 [press_releases.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/press_releases.ipynb) | Retrieve and query company press release data powered by [Kay.ai](https://kay.ai).
 [program_aided_language_model.i...](https://github.com/langchain-ai/langchain/tree/master/cookbook/program_aided_language_model.ipynb) | Implement program-aided language models as described in the provided research paper.
 [qa_citations.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/qa_citations.ipynb) | Different ways to get a model to cite its sources.
-[rag_upstage_document_parse_groundedness_check.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/rag_upstage_document_parse_groundedness_check.ipynb) | End-to-end RAG example using Upstage Document Parse and Groundedness Check.
 [retrieval_in_sql.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/retrieval_in_sql.ipynb) | Perform retrieval-augmented-generation (rag) on a PostgreSQL database using pgvector.
 [sales_agent_with_context.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/sales_agent_with_context.ipynb) | Implement a context-aware ai sales agent, salesgpt, that can have natural sales conversations, interact with other systems, and use a product knowledge base to discuss a company's offerings.
 [self_query_hotel_search.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/self_query_hotel_search.ipynb) | Build a hotel room search feature with self-querying retrieval, using a specific hotel recommendation dataset.
@@ -59,8 +55,3 @@ 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.
-[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.
-[rag-agents-locally-on-intel-cpu.ipynb](https://github.com/langchain-ai/langchain/tree/master/cookbook/local_rag_agents_intel_cpu.ipynb) | Build a RAG agent locally with open source models that routes questions through one of two paths to find answers. The agent generates answers based on documents retrieved from either the vector database or retrieved from web search. If the vector database lacks relevant information, the agent opts for web search. Open-source models for LLM and embeddings are used locally on an Intel Xeon CPU to execute this pipeline.

cookbook/Semi_Structured_RAG.ipynb

@@ -39,7 +39,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml langchainhub"
+    "! pip install langchain unstructured[all-docs] pydantic lxml langchainhub"
    ]
   },
   {
@@ -75,7 +75,7 @@
     "\n",
     "Apply to the [`LLaMA2`](https://arxiv.org/pdf/2307.09288.pdf) paper. \n",
     "\n",
-    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/core/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
+    "We use the Unstructured [`partition_pdf`](https://unstructured-io.github.io/unstructured/bricks/partition.html#partition-pdf), which segments a PDF document by using a layout model. \n",
     "\n",
     "This layout model makes it possible to extract elements, such as tables, from pdfs. \n",
     "\n",
@@ -320,7 +320,7 @@
     "\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryStore\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores 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 langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
+    "! pip install langchain 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_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
@@ -562,7 +562,9 @@
    ],
    "source": [
     "# We can retrieve this table\n",
-    "retriever.invoke(\"What are results for LLaMA across across domains / subjects?\")[1]"
+    "retriever.get_relevant_documents(\n",
+    "    \"What are results for LLaMA across across domains / subjects?\"\n",
+    ")[1]"
    ]
   },
   {
@@ -612,7 +614,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[1]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    1\n",
+    "]"
    ]
   },
   {

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -59,7 +59,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install langchain langchain-chroma \"unstructured[all-docs]\" pydantic lxml"
+    "! pip install langchain unstructured[all-docs] pydantic lxml"
    ]
   },
   {
@@ -191,15 +191,15 @@
    "source": [
     "## Multi-vector retriever\n",
     "\n",
-    "Use [multi-vector-retriever](/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
+    "Use [multi-vector-retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
     "\n",
     "Summaries are used to retrieve raw tables and / or raw chunks of text.\n",
     "\n",
     "### Text and Table summaries\n",
     "\n",
-    "Here, we use Ollama to run LLaMA2 locally. \n",
+    "Here, we use ollama.ai to run LLaMA2 locally. \n",
     "\n",
-    "See details on installation [here](/docs/guides/development/local_llms)."
+    "See details on installation [here](https://python.langchain.com/docs/guides/local_llms)."
    ]
   },
   {
@@ -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",
@@ -501,7 +501,9 @@
     }
    ],
    "source": [
-    "retriever.invoke(\"Images / figures with playful and creative examples\")[0]"
+    "retriever.get_relevant_documents(\"Images / figures with playful and creative examples\")[\n",
+    "    0\n",
+    "]"
    ]
   },
   {

cookbook/advanced_rag_eval.ipynb

@@ -19,7 +19,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain_chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -30,7 +30,7 @@
    "outputs": [],
    "source": [
     "# lock to 0.10.19 due to a persistent bug in more recent versions\n",
-    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml matplotlib tiktoken open_clip_torch torch"
+    "! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken open_clip_torch torch"
    ]
   },
   {
@@ -68,7 +68,7 @@
     "pdf_pages = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
     "all_splits_pypdf = text_splitter.split_documents(pdf_pages)\n",
@@ -132,7 +132,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "baseline = Chroma.from_texts(\n",
@@ -342,7 +342,7 @@
     "# Testing on retrieval\n",
     "query = \"What percentage of CPI is dedicated to Housing, and how does it compare to the combined percentage of Medical Care, Apparel, and Other Goods and Services?\"\n",
     "suffix_for_images = \" Include any pie charts, graphs, or tables.\"\n",
-    "docs = retriever_multi_vector_img.invoke(query + suffix_for_images)"
+    "docs = retriever_multi_vector_img.get_relevant_documents(query + suffix_for_images)"
    ]
   },
   {
@@ -409,7 +409,7 @@
     "    table_summaries,\n",
     "    tables,\n",
     "    image_summaries,\n",
-    "    img_base64_list,\n",
+    "    image_summaries,\n",
     ")"
    ]
   },
@@ -532,8 +532,8 @@
     "def is_image_data(b64data):\n",
     "    \"\"\"Check if the base64 data is an image by looking at the start of the data.\"\"\"\n",
     "    image_signatures = {\n",
-    "        b\"\\xff\\xd8\\xff\": \"jpg\",\n",
-    "        b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
+    "        b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
+    "        b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
     "        b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
     "        b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
     "    }\n",

cookbook/agent_vectorstore.ipynb

@@ -28,9 +28,9 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
-    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "llm = OpenAI(temperature=0)"
    ]

cookbook/airbyte_github.ipynb

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

cookbook/apache_kafka_message_handling.ipynb

@@ -14,9 +14,9 @@
     "\n",
     "This notebook shows you how to use LangChain's standard chat features while passing the chat messages back and forth via Apache Kafka.\n",
     "\n",
-    "This goal is to simulate an architecture where the chat front end and the LLM are running as separate services that need to communicate with one another over an internal network.\n",
+    "This goal is to simulate an architecture where the chat front end and the LLM are running as separate services that need to communicate with one another over an internal nework.\n",
     "\n",
-    "It's an alternative to typical pattern of requesting a response from the model via a REST API (there's more info on why you would want to do this at the end of the notebook)."
+    "It's an alternative to typical pattern of requesting a reponse from the model via a REST API (there's more info on why you would want to do this at the end of the notebook)."
    ]
   },
   {
@@ -261,7 +261,7 @@
     "\n",
     "Load Llama 2 and set the conversation buffer to 300 tokens using `ConversationTokenBufferMemory`. This value was used for running Llama in a CPU only container, so you can raise it if running in Google Colab. It prevents the container that is hosting the model from running out of memory.\n",
     "\n",
-    "Here, we're overriding the default system persona so that the chatbot has the personality of Marvin The Paranoid Android from the Hitchhiker's Guide to the Galaxy."
+    "Here, we're overiding the default system persona so that the chatbot has the personality of Marvin The Paranoid Android from the Hitchhiker's Guide to the Galaxy."
    ]
   },
   {
@@ -272,7 +272,7 @@
    },
    "outputs": [],
    "source": [
-    "# Load the model with the appropriate parameters:\n",
+    "# Load the model with the apporiate parameters:\n",
     "llm = LlamaCpp(\n",
     "    model_path=model_path,\n",
     "    max_tokens=250,\n",
@@ -551,7 +551,7 @@
     "\n",
     "  * **Scalability**: Apache Kafka is designed with parallel processing in mind, so many teams prefer to use it to more effectively distribute work to available workers (in this case the \"worker\" is a container running an LLM).\n",
     "\n",
-    "  * **Durability**: Kafka is designed to allow services to pick up where another service left off in the case where that service experienced a memory issue or went offline. This prevents data loss in highly complex, distributed architectures where multiple systems are communicating with one another (LLMs being just one of many interdependent systems that also include vector databases and traditional databases).\n",
+    "  * **Durability**: Kafka is designed to allow services to pick up where another service left off in the case where that service experienced a memory issue or went offline. This prevents data loss in highly complex, distribuited architectures where multiple systems are communicating with one another (LLMs being just one of many interdependent systems that also include vector databases and traditional databases).\n",
     "\n",
     "For more background on why event streaming is a good fit for Gen AI application architecture, see Kai Waehner's article [\"Apache Kafka + Vector Database + LLM = Real-Time GenAI\"](https://www.kai-waehner.de/blog/2023/11/08/apache-kafka-flink-vector-database-llm-real-time-genai/)."
    ]

cookbook/autogpt/marathon_times.ipynb

@@ -40,13 +40,11 @@
     "import nest_asyncio\n",
     "import pandas as pd\n",
     "from langchain.docstore.document import Document\n",
-    "from langchain_experimental.agents.agent_toolkits.pandas.base import (\n",
-    "    create_pandas_dataframe_agent,\n",
-    ")\n",
+    "from langchain_community.agent_toolkits.pandas.base import create_pandas_dataframe_agent\n",
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "# Needed since jupyter runs an async eventloop\n",
+    "# Needed synce jupyter runs an async eventloop\n",
     "nest_asyncio.apply()"
    ]
   },
@@ -59,7 +57,7 @@
    },
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4\", temperature=1.0)"
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
    ]
   },
   {
@@ -229,8 +227,8 @@
     "    BaseCombineDocumentsChain,\n",
     "    load_qa_with_sources_chain,\n",
     ")\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain.tools import BaseTool, DuckDuckGoSearchRun\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "from pydantic import Field\n",
     "\n",
     "\n",

cookbook/camel_role_playing.ipynb

@@ -90,7 +90,7 @@
     "    ) -> AIMessage:\n",
     "        messages = self.update_messages(input_message)\n",
     "\n",
-    "        output_message = self.model.invoke(messages)\n",
+    "        output_message = self.model(messages)\n",
     "        self.update_messages(output_message)\n",
     "\n",
     "        return output_message"

cookbook/code-analysis-deeplake.ipynb

@@ -24,7 +24,7 @@
    "source": [
     "1. Prepare data:\n",
     "   1. Upload all python project files using the `langchain_community.document_loaders.TextLoader`. We will call these files the **documents**.\n",
-    "   2. Split all documents to chunks using the `langchain_text_splitters.CharacterTextSplitter`.\n",
+    "   2. Split all documents to chunks using the `langchain.text_splitter.CharacterTextSplitter`.\n",
     "   3. Embed chunks and upload them into the DeepLake using `langchain.embeddings.openai.OpenAIEmbeddings` and `langchain_community.vectorstores.DeepLake`\n",
     "2. Question-Answering:\n",
     "   1. Build a chain from `langchain.chat_models.ChatOpenAI` and `langchain.chains.ConversationalRetrievalChain`\n",
@@ -66,7 +66,7 @@
    },
    "outputs": [],
    "source": [
-    "#!python3 -m pip install --upgrade langchain langchain-deeplake openai"
+    "#!python3 -m pip install --upgrade langchain deeplake openai"
    ]
   },
   {
@@ -90,8 +90,7 @@
     "import os\n",
     "from getpass import getpass\n",
     "\n",
-    "if \"OPENAI_API_KEY\" not in os.environ:\n",
-    "    os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()\n",
     "# Please manually enter OpenAI Key"
    ]
   },
@@ -622,7 +621,7 @@
     }
    ],
    "source": [
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "texts = text_splitter.split_documents(docs)\n",
@@ -666,26 +665,89 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Your Deep Lake dataset has been successfully created!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      " \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset(path='hub://adilkhan/langchain-code', tensors=['embedding', 'id', 'metadata', 'text'])\n",
+      "\n",
+      "  tensor      htype       shape       dtype  compression\n",
+      "  -------    -------     -------     -------  ------- \n",
+      " embedding  embedding  (8244, 1536)  float32   None   \n",
+      "    id        text      (8244, 1)      str     None   \n",
+      " metadata     json      (8244, 1)      str     None   \n",
+      "   text       text      (8244, 1)      str     None   \n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": []
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<langchain_community.vectorstores.deeplake.DeepLake at 0x7fe1b67d7a30>"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "from langchain_deeplake.vectorstores import DeeplakeVectorStore\n",
+    "from langchain_community.vectorstores import DeepLake\n",
     "\n",
     "username = \"<USERNAME_OR_ORG>\"\n",
     "\n",
     "\n",
-    "db = DeeplakeVectorStore.from_documents(\n",
-    "    documents=texts,\n",
-    "    embedding=embeddings,\n",
-    "    dataset_path=f\"hub://{username}/langchain-code\",\n",
-    "    overwrite=True,\n",
+    "db = DeepLake.from_documents(\n",
+    "    texts, embeddings, dataset_path=f\"hub://{username}/langchain-code\", overwrite=True\n",
     ")\n",
     "db"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`Optional`: You can also use Deep Lake's Managed Tensor Database as a hosting service and run queries there. In order to do so, it is necessary to specify the runtime parameter as {'tensor_db': True} during the creation of the vector store. This configuration enables the execution of queries on the Managed Tensor Database, rather than on the client side. It should be noted that this functionality is not applicable to datasets stored locally or in-memory. In the event that a vector store has already been created outside of the Managed Tensor Database, it is possible to transfer it to the Managed Tensor Database by following the prescribed steps."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# from langchain_community.vectorstores import DeepLake\n",
+    "\n",
+    "# db = DeepLake.from_documents(\n",
+    "#     texts, embeddings, dataset_path=f\"hub://{<org_id>}/langchain-code\", runtime={\"tensor_db\": True}\n",
+    "# )\n",
+    "# db"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -697,16 +759,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 17,
    "metadata": {
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Deep Lake Dataset in hub://adilkhan/langchain-code already exists, loading from the storage\n"
+     ]
+    }
+   ],
    "source": [
-    "db = DeeplakeVectorStore(\n",
+    "db = DeepLake(\n",
     "    dataset_path=f\"hub://{username}/langchain-code\",\n",
     "    read_only=True,\n",
-    "    embedding_function=embeddings,\n",
+    "    embedding=embeddings,\n",
     ")"
    ]
   },
@@ -725,6 +795,36 @@
     "retriever.search_kwargs[\"k\"] = 20"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can also specify user defined functions using [Deep Lake filters](https://docs.deeplake.ai/en/latest/deeplake.core.dataset.html#deeplake.core.dataset.Dataset.filter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def filter(x):\n",
+    "    # filter based on source code\n",
+    "    if \"something\" in x[\"text\"].data()[\"value\"]:\n",
+    "        return False\n",
+    "\n",
+    "    # filter based on path e.g. extension\n",
+    "    metadata = x[\"metadata\"].data()[\"value\"]\n",
+    "    return \"only_this\" in metadata[\"source\"] or \"also_that\" in metadata[\"source\"]\n",
+    "\n",
+    "\n",
+    "### turn on below for custom filtering\n",
+    "# retriever.search_kwargs['filter'] = filter"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 20,
@@ -736,8 +836,10 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0613\")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
-    "qa = RetrievalQA.from_llm(model, retriever=retriever)"
+    "model = ChatOpenAI(\n",
+    "    model_name=\"gpt-3.5-turbo-0613\"\n",
+    ")  # 'ada' 'gpt-3.5-turbo-0613' 'gpt-4',\n",
+    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },
   {
@@ -831,7 +933,7 @@
       "**Answer**: The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",
@@ -891,7 +993,7 @@
     {
      "data": {
       "text/plain": [
-       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureAISearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
+       "{'question': 'LangChain possesses a variety of retrievers including:\\n\\n1. ArxivRetriever\\n2. AzureCognitiveSearchRetriever\\n3. BM25Retriever\\n4. ChaindeskRetriever\\n5. ChatGPTPluginRetriever\\n6. ContextualCompressionRetriever\\n7. DocArrayRetriever\\n8. ElasticSearchBM25Retriever\\n9. EnsembleRetriever\\n10. GoogleVertexAISearchRetriever\\n11. AmazonKendraRetriever\\n12. KNNRetriever\\n13. LlamaIndexGraphRetriever\\n14. LlamaIndexRetriever\\n15. MergerRetriever\\n16. MetalRetriever\\n17. MilvusRetriever\\n18. MultiQueryRetriever\\n19. ParentDocumentRetriever\\n20. PineconeHybridSearchRetriever\\n21. PubMedRetriever\\n22. RePhraseQueryRetriever\\n23. RemoteLangChainRetriever\\n24. SelfQueryRetriever\\n25. SVMRetriever\\n26. TFIDFRetriever\\n27. TimeWeightedVectorStoreRetriever\\n28. VespaRetriever\\n29. WeaviateHybridSearchRetriever\\n30. WebResearchRetriever\\n31. WikipediaRetriever\\n32. ZepRetriever\\n33. ZillizRetriever\\n\\nIt also includes self query translators like:\\n\\n1. ChromaTranslator\\n2. DeepLakeTranslator\\n3. MyScaleTranslator\\n4. PineconeTranslator\\n5. QdrantTranslator\\n6. WeaviateTranslator\\n\\nAnd remote retrievers like:\\n\\n1. RemoteLangChainRetriever'}"
       ]
      },
      "execution_count": 31,
@@ -1015,7 +1117,7 @@
       "The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureAISearchRetriever\n",
+      "- AzureCognitiveSearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",

cookbook/cql_agent.ipynb

@@ -1,557 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Environment"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Python Modules"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Install the following Python modules:\n",
-    "\n",
-    "```bash\n",
-    "pip install ipykernel python-dotenv cassio pandas langchain_openai langchain langchain-community langchainhub langchain_experimental openai-multi-tool-use-parallel-patch\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load the `.env` File"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Connection is via `cassio` using `auto=True` parameter, and the notebook uses OpenAI. You should create a `.env` file accordingly.\n",
-    "\n",
-    "For Cassandra, set:\n",
-    "```bash\n",
-    "CASSANDRA_CONTACT_POINTS\n",
-    "CASSANDRA_USERNAME\n",
-    "CASSANDRA_PASSWORD\n",
-    "CASSANDRA_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For Astra, set:\n",
-    "```bash\n",
-    "ASTRA_DB_APPLICATION_TOKEN\n",
-    "ASTRA_DB_DATABASE_ID\n",
-    "ASTRA_DB_KEYSPACE\n",
-    "```\n",
-    "\n",
-    "For example:\n",
-    "\n",
-    "```bash\n",
-    "# Connection to Astra:\n",
-    "ASTRA_DB_DATABASE_ID=a1b2c3d4-...\n",
-    "ASTRA_DB_APPLICATION_TOKEN=AstraCS:...\n",
-    "ASTRA_DB_KEYSPACE=notebooks\n",
-    "\n",
-    "# Also set \n",
-    "OPENAI_API_KEY=sk-....\n",
-    "```\n",
-    "\n",
-    "(You may also modify the below code to directly connect with `cassio`.)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from dotenv import load_dotenv\n",
-    "\n",
-    "load_dotenv(override=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Cassandra"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "import cassio\n",
-    "\n",
-    "cassio.init(auto=True)\n",
-    "session = cassio.config.resolve_session()\n",
-    "if not session:\n",
-    "    raise Exception(\n",
-    "        \"Check environment configuration or manually configure cassio connection parameters\"\n",
-    "    )\n",
-    "\n",
-    "keyspace = os.environ.get(\n",
-    "    \"ASTRA_DB_KEYSPACE\", os.environ.get(\"CASSANDRA_KEYSPACE\", None)\n",
-    ")\n",
-    "if not keyspace:\n",
-    "    raise ValueError(\"a KEYSPACE environment variable must be set\")\n",
-    "\n",
-    "session.set_keyspace(keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Setup Database"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This needs to be done one time only!"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Download Data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The dataset used is from Kaggle, the [Environmental Sensor Telemetry Data](https://www.kaggle.com/datasets/garystafford/environmental-sensor-data-132k?select=iot_telemetry_data.csv). The next cell will download and unzip the data into a Pandas dataframe. The following cell is instructions to download manually. \n",
-    "\n",
-    "The net result of this section is you should have a Pandas dataframe variable `df`."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Automatically"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from io import BytesIO\n",
-    "from zipfile import ZipFile\n",
-    "\n",
-    "import pandas as pd\n",
-    "import requests\n",
-    "\n",
-    "datasetURL = \"https://storage.googleapis.com/kaggle-data-sets/788816/1355729/bundle/archive.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=gcp-kaggle-com%40kaggle-161607.iam.gserviceaccount.com%2F20240404%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20240404T115828Z&X-Goog-Expires=259200&X-Goog-SignedHeaders=host&X-Goog-Signature=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\"\n",
-    "\n",
-    "response = requests.get(datasetURL)\n",
-    "if response.status_code == 200:\n",
-    "    zip_file = ZipFile(BytesIO(response.content))\n",
-    "    csv_file_name = zip_file.namelist()[0]\n",
-    "else:\n",
-    "    print(\"Failed to download the file\")\n",
-    "\n",
-    "with zip_file.open(csv_file_name) as csv_file:\n",
-    "    df = pd.read_csv(csv_file)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "#### Download Manually"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "You can download the `.zip` file and unpack the `.csv` contained within. Comment in the next line, and adjust the path to this `.csv` file appropriately."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# df = pd.read_csv(\"/path/to/iot_telemetry_data.csv\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Data into Cassandra"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This section assumes the existence of a dataframe `df`, the following cell validates its structure. The Download section above creates this object."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "assert df is not None, \"Dataframe 'df' must be set\"\n",
-    "expected_columns = [\n",
-    "    \"ts\",\n",
-    "    \"device\",\n",
-    "    \"co\",\n",
-    "    \"humidity\",\n",
-    "    \"light\",\n",
-    "    \"lpg\",\n",
-    "    \"motion\",\n",
-    "    \"smoke\",\n",
-    "    \"temp\",\n",
-    "]\n",
-    "assert all(\n",
-    "    [column in df.columns for column in expected_columns]\n",
-    "), \"DataFrame does not have the expected columns\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Create and load tables:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from datetime import UTC, datetime\n",
-    "\n",
-    "from cassandra.query import BatchStatement\n",
-    "\n",
-    "# Create sensors table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_sensors (\n",
-    "    device text,\n",
-    "    conditions text,\n",
-    "    room text,\n",
-    "    PRIMARY KEY (device)\n",
-    ")\n",
-    "WITH COMMENT = 'Environmental IoT room sensor metadata.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_sensors (device, conditions, room)\n",
-    "VALUES (?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "devices = [\n",
-    "    (\"00:0f:00:70:91:0a\", \"stable conditions, cooler and more humid\", \"room 1\"),\n",
-    "    (\"1c:bf:ce:15:ec:4d\", \"highly variable temperature and humidity\", \"room 2\"),\n",
-    "    (\"b8:27:eb:bf:9d:51\", \"stable conditions, warmer and dryer\", \"room 3\"),\n",
-    "]\n",
-    "\n",
-    "for device, conditions, room in devices:\n",
-    "    session.execute(pstmt, (device, conditions, room))\n",
-    "\n",
-    "print(\"Sensors inserted successfully.\")\n",
-    "\n",
-    "# Create data table\n",
-    "table_query = \"\"\"\n",
-    "CREATE TABLE IF NOT EXISTS iot_data (\n",
-    "    day text,\n",
-    "    device text,\n",
-    "    ts timestamp,\n",
-    "    co double,\n",
-    "    humidity double,\n",
-    "    light boolean,\n",
-    "    lpg double,\n",
-    "    motion boolean,\n",
-    "    smoke double,\n",
-    "    temp double,\n",
-    "    PRIMARY KEY ((day, device), ts)\n",
-    ")\n",
-    "WITH COMMENT = 'Data from environmental IoT room sensors. Columns include device identifier, timestamp (ts) of the data collection, carbon monoxide level (co), relative humidity, light presence, LPG concentration, motion detection, smoke concentration, and temperature (temp). Data is partitioned by day and device.';\n",
-    "\"\"\"\n",
-    "session.execute(table_query)\n",
-    "\n",
-    "pstmt = session.prepare(\n",
-    "    \"\"\"\n",
-    "INSERT INTO iot_data (day, device, ts, co, humidity, light, lpg, motion, smoke, temp)\n",
-    "VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?)\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "\n",
-    "def insert_data_batch(name, group):\n",
-    "    batch = BatchStatement()\n",
-    "    day, device = name\n",
-    "    print(f\"Inserting batch for day: {day}, device: {device}\")\n",
-    "\n",
-    "    for _, row in group.iterrows():\n",
-    "        timestamp = datetime.fromtimestamp(row[\"ts\"], UTC)\n",
-    "        batch.add(\n",
-    "            pstmt,\n",
-    "            (\n",
-    "                day,\n",
-    "                row[\"device\"],\n",
-    "                timestamp,\n",
-    "                row[\"co\"],\n",
-    "                row[\"humidity\"],\n",
-    "                row[\"light\"],\n",
-    "                row[\"lpg\"],\n",
-    "                row[\"motion\"],\n",
-    "                row[\"smoke\"],\n",
-    "                row[\"temp\"],\n",
-    "            ),\n",
-    "        )\n",
-    "\n",
-    "    session.execute(batch)\n",
-    "\n",
-    "\n",
-    "# Convert columns to appropriate types\n",
-    "df[\"light\"] = df[\"light\"] == \"true\"\n",
-    "df[\"motion\"] = df[\"motion\"] == \"true\"\n",
-    "df[\"ts\"] = df[\"ts\"].astype(float)\n",
-    "df[\"day\"] = df[\"ts\"].apply(\n",
-    "    lambda x: datetime.fromtimestamp(x, UTC).strftime(\"%Y-%m-%d\")\n",
-    ")\n",
-    "\n",
-    "grouped_df = df.groupby([\"day\", \"device\"])\n",
-    "\n",
-    "for name, group in grouped_df:\n",
-    "    insert_data_batch(name, group)\n",
-    "\n",
-    "print(\"Data load complete\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "print(session.keyspace)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Load the Tools"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Python `import` statements for the demo:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import AgentExecutor, create_openai_tools_agent\n",
-    "from langchain_community.agent_toolkits.cassandra_database.toolkit import (\n",
-    "    CassandraDatabaseToolkit,\n",
-    ")\n",
-    "from langchain_community.tools.cassandra_database.prompt import QUERY_PATH_PROMPT\n",
-    "from langchain_community.tools.cassandra_database.tool import (\n",
-    "    GetSchemaCassandraDatabaseTool,\n",
-    "    GetTableDataCassandraDatabaseTool,\n",
-    "    QueryCassandraDatabaseTool,\n",
-    ")\n",
-    "from langchain_community.utilities.cassandra_database import CassandraDatabase\n",
-    "from langchain_openai import ChatOpenAI"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The `CassandraDatabase` object is loaded from `cassio`, though it does accept a `Session`-type parameter as an alternative."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a CassandraDatabase instance\n",
-    "db = CassandraDatabase(include_tables=[\"iot_sensors\", \"iot_data\"])\n",
-    "\n",
-    "# Create the Cassandra Database tools\n",
-    "query_tool = QueryCassandraDatabaseTool(db=db)\n",
-    "schema_tool = GetSchemaCassandraDatabaseTool(db=db)\n",
-    "select_data_tool = GetTableDataCassandraDatabaseTool(db=db)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The tools can be invoked directly:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Test the tools\n",
-    "print(\"Executing a CQL query:\")\n",
-    "query = \"SELECT * FROM iot_sensors LIMIT 5;\"\n",
-    "result = query_tool.run({\"query\": query})\n",
-    "print(result)\n",
-    "\n",
-    "print(\"\\nGetting the schema for a keyspace:\")\n",
-    "schema = schema_tool.run({\"keyspace\": keyspace})\n",
-    "print(schema)\n",
-    "\n",
-    "print(\"\\nGetting data from a table:\")\n",
-    "table = \"iot_data\"\n",
-    "predicate = \"day = '2020-07-14' and device = 'b8:27:eb:bf:9d:51'\"\n",
-    "data = select_data_tool.run(\n",
-    "    {\"keyspace\": keyspace, \"table\": table, \"predicate\": predicate, \"limit\": 5}\n",
-    ")\n",
-    "print(data)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Agent Configuration"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import Tool\n",
-    "from langchain_experimental.utilities import PythonREPL\n",
-    "\n",
-    "python_repl = PythonREPL()\n",
-    "\n",
-    "repl_tool = Tool(\n",
-    "    name=\"python_repl\",\n",
-    "    description=\"A Python shell. Use this to execute python commands. Input should be a valid python command. If you want to see the output of a value, you should print it out with `print(...)`.\",\n",
-    "    func=python_repl.run,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "llm = ChatOpenAI(temperature=0, model=\"gpt-4-1106-preview\")\n",
-    "toolkit = CassandraDatabaseToolkit(db=db)\n",
-    "\n",
-    "# context = toolkit.get_context()\n",
-    "# tools = toolkit.get_tools()\n",
-    "tools = [schema_tool, select_data_tool, repl_tool]\n",
-    "\n",
-    "input = (\n",
-    "    QUERY_PATH_PROMPT\n",
-    "    + f\"\"\"\n",
-    "\n",
-    "Here is your task: In the {keyspace} keyspace, find the total number of times the temperature of each device has exceeded 23 degrees on July 14, 2020.\n",
-    " Create a summary report including the name of the room. Use Pandas if helpful.\n",
-    "\"\"\"\n",
-    ")\n",
-    "\n",
-    "prompt = hub.pull(\"hwchase17/openai-tools-agent\")\n",
-    "\n",
-    "# messages = [\n",
-    "#     HumanMessagePromptTemplate.from_template(input),\n",
-    "#     AIMessage(content=QUERY_PATH_PROMPT),\n",
-    "#     MessagesPlaceholder(variable_name=\"agent_scratchpad\"),\n",
-    "# ]\n",
-    "\n",
-    "# prompt = ChatPromptTemplate.from_messages(messages)\n",
-    "# print(prompt)\n",
-    "\n",
-    "# Choose the LLM that will drive the agent\n",
-    "# Only certain models support this\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-1106\", temperature=0)\n",
-    "\n",
-    "# Construct the OpenAI Tools agent\n",
-    "agent = create_openai_tools_agent(llm, tools, prompt)\n",
-    "\n",
-    "print(\"Available tools:\")\n",
-    "for tool in tools:\n",
-    "    print(\"\\t\" + tool.name + \" - \" + tool.description + \" - \" + str(tool))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\n",
-    "\n",
-    "response = agent_executor.invoke({\"input\": input})\n",
-    "\n",
-    "print(response[\"output\"])"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

cookbook/custom_agent_with_plugin_retrieval.ipynb

@@ -169,7 +169,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -193,7 +193,7 @@
     "\n",
     "def get_tools(query):\n",
     "    # Get documents, which contain the Plugins to use\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    # Get the toolkits, one for each plugin\n",
     "    tool_kits = [toolkits_dict[d.metadata[\"plugin_name\"]] for d in docs]\n",
     "    # Get the tools: a separate NLAChain for each endpoint\n",

cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -142,7 +142,7 @@
     "\n",
     "\n",
     "def get_tools(query):\n",
-    "    docs = retriever.invoke(query)\n",
+    "    docs = retriever.get_relevant_documents(query)\n",
     "    return [ALL_TOOLS[d.metadata[\"index\"]] for d in docs]"
    ]
   },

cookbook/databricks_sql_db.ipynb

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

cookbook/deeplake_semantic_search_over_chat.ipynb

@@ -52,12 +52,12 @@
     "import os\n",
     "\n",
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_community.vectorstores import DeepLake\n",
-    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
-    "from langchain_text_splitters import (\n",
+    "from langchain.text_splitter import (\n",
     "    CharacterTextSplitter,\n",
     "    RecursiveCharacterTextSplitter,\n",
     ")\n",
+    "from langchain_community.vectorstores import DeepLake\n",
+    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
     "\n",
     "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
     "activeloop_token = getpass.getpass(\"Activeloop Token:\")\n",

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

cookbook/elasticsearch_db_qa.ipynb

@@ -84,7 +84,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
+    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
     "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
    ]
   },
@@ -115,7 +115,7 @@
     "\n",
     "PROMPT_TEMPLATE = \"\"\"Given an input question, create a syntactically correct Elasticsearch query to run. Unless the user specifies in their question a specific number of examples they wish to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.\n",
     "\n",
-    "Unless told to do not query for all the columns from a specific index, only ask for a few relevant columns given the question.\n",
+    "Unless told to do not query for all the columns from a specific index, only ask for a the few relevant columns given the question.\n",
     "\n",
     "Pay attention to use only the column names that you can see in the mapping description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which index. Return the query as valid json.\n",
     "\n",

cookbook/fake_llm.ipynb

@@ -100,7 +100,7 @@
     }
    ],
    "source": [
-    "agent.invoke(\"whats 2 + 2\")"
+    "agent.run(\"whats 2 + 2\")"
    ]
   },
   {

cookbook/fireworks_rag.ipynb

@@ -84,7 +84,7 @@
     }
    ],
    "source": [
-    "%pip install --quiet pypdf langchain-chroma tiktoken openai \n",
+    "%pip install --quiet pypdf chromadb tiktoken openai \n",
     "%pip uninstall -y langchain-fireworks\n",
     "%pip install --editable /mnt/disks/data/langchain/libs/partners/fireworks"
    ]
@@ -132,13 +132,13 @@
     "data = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=0)\n",
     "all_splits = text_splitter.split_documents(data)\n",
     "\n",
     "# Add to vectorDB\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_fireworks.embeddings import FireworksEmbeddings\n",
     "\n",
     "vectorstore = Chroma.from_documents(\n",

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -362,7 +362,7 @@
    ],
    "source": [
     "llm = OpenAI()\n",
-    "llm.invoke(query)"
+    "llm(query)"
    ]
   },
   {

cookbook/gymnasium_agent_simulation.ipynb

@@ -108,7 +108,7 @@
     "        return obs_message\n",
     "\n",
     "    def _act(self):\n",
-    "        act_message = self.model.invoke(self.message_history)\n",
+    "        act_message = self.model(self.message_history)\n",
     "        self.message_history.append(act_message)\n",
     "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
     "        return action\n",

cookbook/hypothetical_document_embeddings.ipynb

@@ -170,8 +170,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_chroma import Chroma\n",
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "\n",
     "with open(\"../../state_of_the_union.txt\") as f:\n",
     "    state_of_the_union = f.read()\n",

cookbook/llm_bash.ipynb

@@ -52,7 +52,7 @@
     "\n",
     "bash_chain = LLMBashChain.from_llm(llm, verbose=True)\n",
     "\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   },
   {
@@ -135,7 +135,7 @@
     "\n",
     "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
     "\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   },
   {
@@ -190,7 +190,7 @@
     "\n",
     "text = \"List the current directory then move up a level.\"\n",
     "\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   },
   {
@@ -231,7 +231,7 @@
    ],
    "source": [
     "# Run the same command again and see that the state is maintained between calls\n",
-    "bash_chain.invoke(text)"
+    "bash_chain.run(text)"
    ]
   }
  ],

cookbook/llm_checker.ipynb

@@ -50,7 +50,7 @@
     "\n",
     "checker_chain = LLMCheckerChain.from_llm(llm, verbose=True)\n",
     "\n",
-    "checker_chain.invoke(text)"
+    "checker_chain.run(text)"
    ]
   },
   {

cookbook/llm_math.ipynb

@@ -51,7 +51,7 @@
     "llm = OpenAI(temperature=0)\n",
     "llm_math = LLMMathChain.from_llm(llm, verbose=True)\n",
     "\n",
-    "llm_math.invoke(\"What is 13 raised to the .3432 power?\")"
+    "llm_math.run(\"What is 13 raised to the .3432 power?\")"
    ]
   },
   {

cookbook/llm_symbolic_math.ipynb

@@ -45,7 +45,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
+    "llm_symbolic_math.run(\"What is the derivative of sin(x)*exp(x) with respect to x?\")"
    ]
   },
   {
@@ -65,7 +65,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\n",
+    "llm_symbolic_math.run(\n",
     "    \"What is the integral of exp(x)*sin(x) + exp(x)*cos(x) with respect to x?\"\n",
     ")"
    ]
@@ -94,7 +94,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke('Solve the differential equation y\" - y = e^t')"
+    "llm_symbolic_math.run('Solve the differential equation y\" - y = e^t')"
    ]
   },
   {
@@ -114,7 +114,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\"What are the solutions to this equation y^3 + 1/3y?\")"
+    "llm_symbolic_math.run(\"What are the solutions to this equation y^3 + 1/3y?\")"
    ]
   },
   {
@@ -134,7 +134,7 @@
     }
    ],
    "source": [
-    "llm_symbolic_math.invoke(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
+    "llm_symbolic_math.run(\"x = y + 5, y = z - 3, z = x * y. Solve for x, y, z\")"
    ]
   }
  ],

cookbook/mongodb-langchain-cache-memory.ipynb

@@ -1,818 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "70b333e6",
-   "metadata": {},
-   "source": [
-    "[![View Article](https://img.shields.io/badge/View%20Article-blue)](https://www.mongodb.com/developer/products/atlas/advanced-rag-langchain-mongodb/)\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d84a72ea",
-   "metadata": {},
-   "source": [
-    "# Adding Semantic Caching and Memory to your RAG Application using MongoDB and LangChain\n",
-    "\n",
-    "In this notebook, we will see how to use the new MongoDBCache and MongoDBChatMessageHistory in your RAG application.\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "65527202",
-   "metadata": {},
-   "source": [
-    "## Step 1: Install required libraries\n",
-    "\n",
-    "- **datasets**: Python library to get access to datasets available on Hugging Face Hub\n",
-    "\n",
-    "- **langchain**: Python toolkit for LangChain\n",
-    "\n",
-    "- **langchain-mongodb**: Python package to use MongoDB as a vector store, semantic cache, chat history store etc. in LangChain\n",
-    "\n",
-    "- **langchain-openai**: Python package to use OpenAI models with LangChain\n",
-    "\n",
-    "- **pymongo**: Python toolkit for MongoDB\n",
-    "\n",
-    "- **pandas**: Python library for data analysis, exploration, and manipulation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "cbc22fa4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! pip install -qU datasets langchain langchain-mongodb langchain-openai pymongo pandas"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "39c41e87",
-   "metadata": {},
-   "source": [
-    "## Step 2: Setup pre-requisites\n",
-    "\n",
-    "* Set the MongoDB connection string. Follow the steps [here](https://www.mongodb.com/docs/manual/reference/connection-string/) to get the connection string from the Atlas UI.\n",
-    "\n",
-    "* Set the OpenAI API key. Steps to obtain an API key as [here](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "b56412ae",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "16a20d7a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter your MongoDB connection string:········\n"
-     ]
-    }
-   ],
-   "source": [
-    "MONGODB_URI = getpass.getpass(\"Enter your MongoDB connection string:\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "978682d4",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Enter your OpenAI API key:········\n"
-     ]
-    }
-   ],
-   "source": [
-    "OPENAI_API_KEY = getpass.getpass(\"Enter your OpenAI API key:\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "606081c5",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "········\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Optional-- If you want to enable Langsmith -- good for debugging\n",
-    "import os\n",
-    "\n",
-    "os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
-    "os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f6b8302c",
-   "metadata": {},
-   "source": [
-    "## Step 3: Download the dataset\n",
-    "\n",
-    "We will be using MongoDB's [embedded_movies](https://huggingface.co/datasets/MongoDB/embedded_movies) dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "1a3433a6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "from datasets import load_dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "aee5311b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Ensure you have an HF_TOKEN in your development environment:\n",
-    "# access tokens can be created or copied from the Hugging Face platform (https://huggingface.co/docs/hub/en/security-tokens)\n",
-    "\n",
-    "# Load MongoDB's embedded_movies dataset from Hugging Face\n",
-    "# https://huggingface.co/datasets/MongoDB/airbnb_embeddings\n",
-    "\n",
-    "data = load_dataset(\"MongoDB/embedded_movies\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "1d630a26",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df = pd.DataFrame(data[\"train\"])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a1f94f43",
-   "metadata": {},
-   "source": [
-    "## Step 4: Data analysis\n",
-    "\n",
-    "Make sure length of the dataset is what we expect, drop Nones etc."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "b276df71",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>fullplot</th>\n",
-       "      <th>type</th>\n",
-       "      <th>plot_embedding</th>\n",
-       "      <th>num_mflix_comments</th>\n",
-       "      <th>runtime</th>\n",
-       "      <th>writers</th>\n",
-       "      <th>imdb</th>\n",
-       "      <th>countries</th>\n",
-       "      <th>rated</th>\n",
-       "      <th>plot</th>\n",
-       "      <th>title</th>\n",
-       "      <th>languages</th>\n",
-       "      <th>metacritic</th>\n",
-       "      <th>directors</th>\n",
-       "      <th>awards</th>\n",
-       "      <th>genres</th>\n",
-       "      <th>poster</th>\n",
-       "      <th>cast</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
-       "      <td>movie</td>\n",
-       "      <td>[0.00072939653, -0.026834568, 0.013515796, -0....</td>\n",
-       "      <td>0</td>\n",
-       "      <td>199.0</td>\n",
-       "      <td>[Charles W. Goddard (screenplay), Basil Dickey...</td>\n",
-       "      <td>{'id': 4465, 'rating': 7.6, 'votes': 744}</td>\n",
-       "      <td>[USA]</td>\n",
-       "      <td>None</td>\n",
-       "      <td>Young Pauline is left a lot of money when her ...</td>\n",
-       "      <td>The Perils of Pauline</td>\n",
-       "      <td>[English]</td>\n",
-       "      <td>NaN</td>\n",
-       "      <td>[Louis J. Gasnier, Donald MacKenzie]</td>\n",
-       "      <td>{'nominations': 0, 'text': '1 win.', 'wins': 1}</td>\n",
-       "      <td>[Action]</td>\n",
-       "      <td>https://m.media-amazon.com/images/M/MV5BMzgxOD...</td>\n",
-       "      <td>[Pearl White, Crane Wilbur, Paul Panzer, Edwar...</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                            fullplot   type  \\\n",
-       "0  Young Pauline is left a lot of money when her ...  movie   \n",
-       "\n",
-       "                                      plot_embedding  num_mflix_comments  \\\n",
-       "0  [0.00072939653, -0.026834568, 0.013515796, -0....                   0   \n",
-       "\n",
-       "   runtime                                            writers  \\\n",
-       "0    199.0  [Charles W. Goddard (screenplay), Basil Dickey...   \n",
-       "\n",
-       "                                        imdb countries rated  \\\n",
-       "0  {'id': 4465, 'rating': 7.6, 'votes': 744}     [USA]  None   \n",
-       "\n",
-       "                                                plot                  title  \\\n",
-       "0  Young Pauline is left a lot of money when her ...  The Perils of Pauline   \n",
-       "\n",
-       "   languages  metacritic                             directors  \\\n",
-       "0  [English]         NaN  [Louis J. Gasnier, Donald MacKenzie]   \n",
-       "\n",
-       "                                            awards    genres  \\\n",
-       "0  {'nominations': 0, 'text': '1 win.', 'wins': 1}  [Action]   \n",
-       "\n",
-       "                                              poster  \\\n",
-       "0  https://m.media-amazon.com/images/M/MV5BMzgxOD...   \n",
-       "\n",
-       "                                                cast  \n",
-       "0  [Pearl White, Crane Wilbur, Paul Panzer, Edwar...  "
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Previewing the contents of the data\n",
-    "df.head(1)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "22ab375d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Only keep records where the fullplot field is not null\n",
-    "df = df[df[\"fullplot\"].notna()]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "fceed99a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Renaming the embedding field to \"embedding\" -- required by LangChain\n",
-    "df.rename(columns={\"plot_embedding\": \"embedding\"}, inplace=True)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aedec13a",
-   "metadata": {},
-   "source": [
-    "## Step 5: Create a simple RAG chain using MongoDB as the vector store"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "11d292f3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_mongodb import MongoDBAtlasVectorSearch\n",
-    "from pymongo import MongoClient\n",
-    "\n",
-    "# Initialize MongoDB python client\n",
-    "client = MongoClient(MONGODB_URI, appname=\"devrel.content.python\")\n",
-    "\n",
-    "DB_NAME = \"langchain_chatbot\"\n",
-    "COLLECTION_NAME = \"data\"\n",
-    "ATLAS_VECTOR_SEARCH_INDEX_NAME = \"vector_index\"\n",
-    "collection = client[DB_NAME][COLLECTION_NAME]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "d8292d53",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "DeleteResult({'n': 1000, 'electionId': ObjectId('7fffffff00000000000000f6'), 'opTime': {'ts': Timestamp(1710523288, 1033), 't': 246}, 'ok': 1.0, '$clusterTime': {'clusterTime': Timestamp(1710523288, 1042), 'signature': {'hash': b\"i\\xa8\\xe9'\\x1ed\\xf2u\\xf3L\\xff\\xb1\\xf5\\xbfA\\x90\\xabJ\\x12\\x83\", 'keyId': 7299545392000008318}}, 'operationTime': Timestamp(1710523288, 1033)}, acknowledged=True)"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Delete any existing records in the collection\n",
-    "collection.delete_many({})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "36c68914",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Data ingestion into MongoDB completed\n"
-     ]
-    }
-   ],
-   "source": [
-    "# Data Ingestion\n",
-    "records = df.to_dict(\"records\")\n",
-    "collection.insert_many(records)\n",
-    "\n",
-    "print(\"Data ingestion into MongoDB completed\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "cbfca0b8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "\n",
-    "# Using the text-embedding-ada-002 since that's what was used to create embeddings in the movies dataset\n",
-    "embeddings = OpenAIEmbeddings(\n",
-    "    openai_api_key=OPENAI_API_KEY, model=\"text-embedding-ada-002\"\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "798e176c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Vector Store Creation\n",
-    "vector_store = MongoDBAtlasVectorSearch.from_connection_string(\n",
-    "    connection_string=MONGODB_URI,\n",
-    "    namespace=DB_NAME + \".\" + COLLECTION_NAME,\n",
-    "    embedding=embeddings,\n",
-    "    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
-    "    text_key=\"fullplot\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "id": "c71cd087",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Using the MongoDB vector store as a retriever in a RAG chain\n",
-    "retriever = vector_store.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 5})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "b6588cd3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "# Generate context using the retriever, and pass the user question through\n",
-    "retrieve = {\n",
-    "    \"context\": retriever | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs])),\n",
-    "    \"question\": RunnablePassthrough(),\n",
-    "}\n",
-    "template = \"\"\"Answer the question based only on the following context: \\\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "# Defining the chat prompt\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "# Defining the model to be used for chat completion\n",
-    "model = ChatOpenAI(temperature=0, openai_api_key=OPENAI_API_KEY)\n",
-    "# Parse output as a string\n",
-    "parse_output = StrOutputParser()\n",
-    "\n",
-    "# Naive RAG chain\n",
-    "naive_rag_chain = retrieve | prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
-   "id": "aaae21f5",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 26,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "75f929ef",
-   "metadata": {},
-   "source": [
-    "## Step 6: Create a RAG chain with chat history"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 27,
-   "id": "94e7bd4a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import MessagesPlaceholder\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "from langchain_mongodb.chat_message_histories import MongoDBChatMessageHistory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 29,
-   "id": "5bb30860",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def get_session_history(session_id: str) -> MongoDBChatMessageHistory:\n",
-    "    return MongoDBChatMessageHistory(\n",
-    "        MONGODB_URI, session_id, database_name=DB_NAME, collection_name=\"history\"\n",
-    "    )"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "id": "f51d0f35",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Given a follow-up question and history, create a standalone question\n",
-    "standalone_system_prompt = \"\"\"\n",
-    "Given a chat history and a follow-up question, rephrase the follow-up question to be a standalone question. \\\n",
-    "Do NOT answer the question, just reformulate it if needed, otherwise return it as is. \\\n",
-    "Only return the final standalone question. \\\n",
-    "\"\"\"\n",
-    "standalone_question_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", standalone_system_prompt),\n",
-    "        MessagesPlaceholder(variable_name=\"history\"),\n",
-    "        (\"human\", \"{question}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "question_chain = standalone_question_prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
-   "id": "f3ef3354",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Generate context by passing output of the question_chain i.e. the standalone question to the retriever\n",
-    "retriever_chain = RunnablePassthrough.assign(\n",
-    "    context=question_chain\n",
-    "    | retriever\n",
-    "    | (lambda docs: \"\\n\\n\".join([d.page_content for d in docs]))\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "id": "5afb7345",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Create a prompt that includes the context, history and the follow-up question\n",
-    "rag_system_prompt = \"\"\"Answer the question based only on the following context: \\\n",
-    "{context}\n",
-    "\"\"\"\n",
-    "rag_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", rag_system_prompt),\n",
-    "        MessagesPlaceholder(variable_name=\"history\"),\n",
-    "        (\"human\", \"{question}\"),\n",
-    "    ]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "id": "f95f47d0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# RAG chain\n",
-    "rag_chain = retriever_chain | rag_prompt | model | parse_output"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 57,
-   "id": "9618d395",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'The best movie to watch when feeling down could be \"Last Action Hero.\" It\\'s a fun and action-packed film that blends reality and fantasy, offering an escape from the real world and providing an entertaining distraction.'"
-      ]
-     },
-     "execution_count": 57,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# RAG chain with history\n",
-    "with_message_history = RunnableWithMessageHistory(\n",
-    "    rag_chain,\n",
-    "    get_session_history,\n",
-    "    input_messages_key=\"question\",\n",
-    "    history_messages_key=\"history\",\n",
-    ")\n",
-    "with_message_history.invoke(\n",
-    "    {\"question\": \"What is the best movie to watch when sad?\"},\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "id": "6e3080d1",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'I apologize for the confusion. Another movie that might lift your spirits when you\\'re feeling sad is \"Smilla\\'s Sense of Snow.\" It\\'s a mystery thriller that could engage your mind and distract you from your sadness with its intriguing plot and suspenseful storyline.'"
-      ]
-     },
-     "execution_count": 58,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "with_message_history.invoke(\n",
-    "    {\n",
-    "        \"question\": \"Hmmm..I don't want to watch that one. Can you suggest something else?\"\n",
-    "    },\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 59,
-   "id": "daea2953",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'For a lighter movie option, you might enjoy \"Cousins.\" It\\'s a comedy film set in Barcelona with action and humor, offering a fun and entertaining escape from reality. The storyline is engaging and filled with comedic moments that could help lift your spirits.'"
-      ]
-     },
-     "execution_count": 59,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "with_message_history.invoke(\n",
-    "    {\"question\": \"How about something more light?\"},\n",
-    "    {\"configurable\": {\"session_id\": \"1\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0de23a88",
-   "metadata": {},
-   "source": [
-    "## Step 7: Get faster responses using Semantic Cache\n",
-    "\n",
-    "**NOTE:** Semantic cache only caches the input to the LLM. When using it in retrieval chains, remember that documents retrieved can change between runs resulting in cache misses for semantically similar queries."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 61,
-   "id": "5d6b6741",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.globals import set_llm_cache\n",
-    "from langchain_mongodb.cache import MongoDBAtlasSemanticCache\n",
-    "\n",
-    "set_llm_cache(\n",
-    "    MongoDBAtlasSemanticCache(\n",
-    "        connection_string=MONGODB_URI,\n",
-    "        embedding=embeddings,\n",
-    "        collection_name=\"semantic_cache\",\n",
-    "        database_name=DB_NAME,\n",
-    "        index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,\n",
-    "        wait_until_ready=True,  # Optional, waits until the cache is ready to be used\n",
-    "    )\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 62,
-   "id": "9825bc7b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 87.8 ms, sys: 670 µs, total: 88.5 ms\n",
-      "Wall time: 1.24 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 62,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 63,
-   "id": "a5e518cf",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 43.5 ms, sys: 4.16 ms, total: 47.7 ms\n",
-      "Wall time: 255 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Once a Thief'"
-      ]
-     },
-     "execution_count": 63,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"What is the best movie to watch when sad?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 64,
-   "id": "3d3d3ad3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "CPU times: user 115 ms, sys: 171 µs, total: 115 ms\n",
-      "Wall time: 1.38 s\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'I would recommend watching \"Last Action Hero\" when sad, as it is a fun and action-packed film that can help lift your spirits.'"
-      ]
-     },
-     "execution_count": 64,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "%%time\n",
-    "naive_rag_chain.invoke(\"Which movie do I watch when sad?\")"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "conda_pytorch_p310",
-   "language": "python",
-   "name": "conda_pytorch_p310"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.13"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

cookbook/multi_modal_RAG_chroma.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain openai langchain-chroma langchain-experimental # (newest versions required for multi-modal)"
+    "! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
    ]
   },
   {
@@ -187,7 +187,7 @@
     "\n",
     "import chromadb\n",
     "import numpy as np\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
     "from PIL import Image as _PILImage\n",
     "\n",
@@ -435,7 +435,7 @@
     "    display(HTML(image_html))\n",
     "\n",
     "\n",
-    "docs = retriever.invoke(\"Woman with children\", k=10)\n",
+    "docs = retriever.get_relevant_documents(\"Woman with children\", k=10)\n",
     "for doc in docs:\n",
     "    if is_base64(doc.page_content):\n",
     "        plt_img_base64(doc.page_content)\n",

cookbook/multi_player_dnd.ipynb

@@ -74,7 +74,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",

cookbook/multiagent_authoritarian.ipynb

@@ -79,7 +79,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -234,7 +234,7 @@
     "            termination_clause=self.termination_clause if self.stop else \"\",\n",
     "        )\n",
     "\n",
-    "        self.response = self.model.invoke(\n",
+    "        self.response = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=response_prompt),\n",
@@ -263,7 +263,7 @@
     "            speaker_names=speaker_names,\n",
     "        )\n",
     "\n",
-    "        choice_string = self.model.invoke(\n",
+    "        choice_string = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=choice_prompt),\n",
@@ -299,7 +299,7 @@
     "                ),\n",
     "                next_speaker=self.next_speaker,\n",
     "            )\n",
-    "            message = self.model.invoke(\n",
+    "            message = self.model(\n",
     "                [\n",
     "                    self.system_message,\n",
     "                    HumanMessage(content=next_prompt),\n",

cookbook/multiagent_bidding.ipynb

@@ -71,7 +71,7 @@
     "        Applies the chatmodel to the message history\n",
     "        and returns the message string\n",
     "        \"\"\"\n",
-    "        message = self.model.invoke(\n",
+    "        message = self.model(\n",
     "            [\n",
     "                self.system_message,\n",
     "                HumanMessage(content=\"\\n\".join(self.message_history + [self.prefix])),\n",
@@ -164,7 +164,7 @@
     "            message_history=\"\\n\".join(self.message_history),\n",
     "            recent_message=self.message_history[-1],\n",
     "        )\n",
-    "        bid_string = self.model.invoke([SystemMessage(content=prompt)]).content\n",
+    "        bid_string = self.model([SystemMessage(content=prompt)]).content\n",
     "        return bid_string"
    ]
   },

cookbook/nomic_embedding_rag.ipynb

@@ -58,7 +58,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! pip install -U langchain-nomic langchain-chroma langchain-community tiktoken langchain-openai langchain"
+    "! pip install -U langchain-nomic langchain_community tiktoken langchain-openai chromadb langchain"
    ]
   },
   {
@@ -71,9 +71,9 @@
     "# Optional: LangSmith API keys\n",
     "import os\n",
     "\n",
-    "os.environ[\"LANGSMITH_TRACING\"] = \"true\"\n",
-    "os.environ[\"LANGSMITH_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
-    "os.environ[\"LANGSMITH_API_KEY\"] = \"api_key\""
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "os.environ[\"LANGCHAIN_ENDPOINT\"] = \"https://api.smith.langchain.com\"\n",
+    "os.environ[\"LANGCHAIN_API_KEY\"] = \"api_key\""
    ]
   },
   {
@@ -124,7 +124,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_text_splitters import CharacterTextSplitter\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter.from_tiktoken_encoder(\n",
     "    chunk_size=7500, chunk_overlap=100\n",
@@ -167,7 +167,7 @@
    "source": [
     "import os\n",
     "\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores 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

@@ -1,497 +0,0 @@
-{
- "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

@@ -20,10 +20,10 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "from langchain_text_splitters import CharacterTextSplitter"
+    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_openai import OpenAIEmbeddings"
    ]
   },
   {

cookbook/optimization.ipynb

@@ -29,7 +29,7 @@
    "source": [
     "import os\n",
     "\n",
-    "os.environ[\"LANGSMITH_PROJECT\"] = \"movie-qa\""
+    "os.environ[\"LANGCHAIN_PROJECT\"] = \"movie-qa\""
    ]
   },
   {
@@ -80,7 +80,7 @@
    "outputs": [],
    "source": [
     "from langchain.schema import Document\n",
-    "from langchain_chroma import Chroma\n",
+    "from langchain_community.vectorstores import Chroma\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"

cookbook/oracleai_demo.ipynb

@@ -1,880 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Oracle AI Vector Search with Document Processing\n",
-    "Oracle AI Vector Search is designed for Artificial Intelligence (AI) workloads that allows you to query data based on semantics, rather than keywords.\n",
-    "One of the biggest benefits of Oracle AI Vector Search is that semantic search on unstructured data can be combined with relational search on business data in one single system.\n",
-    "This is not only powerful but also significantly more effective because you don't need to add a specialized vector database, eliminating the pain of data fragmentation between multiple systems.\n",
-    "\n",
-    "In addition, your vectors can benefit from all of Oracle Database’s most powerful features, like the following:\n",
-    "\n",
-    " * [Partitioning Support](https://www.oracle.com/database/technologies/partitioning.html)\n",
-    " * [Real Application Clusters scalability](https://www.oracle.com/database/real-application-clusters/)\n",
-    " * [Exadata smart scans](https://www.oracle.com/database/technologies/exadata/software/smartscan/)\n",
-    " * [Shard processing across geographically distributed databases](https://www.oracle.com/database/distributed-database/)\n",
-    " * [Transactions](https://docs.oracle.com/en/database/oracle/oracle-database/23/cncpt/transactions.html)\n",
-    " * [Parallel SQL](https://docs.oracle.com/en/database/oracle/oracle-database/21/vldbg/parallel-exec-intro.html#GUID-D28717E4-0F77-44F5-BB4E-234C31D4E4BA)\n",
-    " * [Disaster recovery](https://www.oracle.com/database/data-guard/)\n",
-    " * [Security](https://www.oracle.com/security/database-security/)\n",
-    " * [Oracle Machine Learning](https://www.oracle.com/artificial-intelligence/database-machine-learning/)\n",
-    " * [Oracle Graph Database](https://www.oracle.com/database/integrated-graph-database/)\n",
-    " * [Oracle Spatial and Graph](https://www.oracle.com/database/spatial/)\n",
-    " * [Oracle Blockchain](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_blockchain_table.html#GUID-B469E277-978E-4378-A8C1-26D3FF96C9A6)\n",
-    " * [JSON](https://docs.oracle.com/en/database/oracle/oracle-database/23/adjsn/json-in-oracle-database.html)\n",
-    "\n",
-    "This guide demonstrates how Oracle AI Vector Search can be used with Langchain to serve an end-to-end RAG pipeline. This guide goes through examples of:\n",
-    "\n",
-    " * Loading the documents from various sources using OracleDocLoader\n",
-    " * Summarizing them within/outside the database using OracleSummary\n",
-    " * Generating embeddings for them within/outside the database using OracleEmbeddings\n",
-    " * Chunking them according to different requirements using Advanced Oracle Capabilities from OracleTextSplitter\n",
-    " * Storing and Indexing them in a Vector Store and querying them for queries in OracleVS"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "If you are just starting with Oracle Database, consider exploring the [free Oracle 23 AI](https://www.oracle.com/database/free/#resources) which provides a great introduction to setting up your database environment. While working with the database, it is often advisable to avoid using the system user by default; instead, you can create your own user for enhanced security and customization. For detailed steps on user creation, refer to our [end-to-end guide](https://github.com/langchain-ai/langchain/blob/master/cookbook/oracleai_demo.ipynb) which also shows how to set up a user in Oracle. Additionally, understanding user privileges is crucial for managing database security effectively. You can learn more about this topic in the official [Oracle guide](https://docs.oracle.com/en/database/oracle/oracle-database/19/admqs/administering-user-accounts-and-security.html#GUID-36B21D72-1BBB-46C9-A0C9-F0D2A8591B8D) on administering user accounts and security."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Prerequisites\n",
-    "\n",
-    "Please install Oracle Python Client driver to use Langchain with Oracle AI Vector Search. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# pip install oracledb"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Demo User\n",
-    "First, create a demo user with all the required privileges. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "User setup done!\n"
-     ]
-    }
-   ],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "\n",
-    "# Update with your username, password, hostname, and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "\n",
-    "    cursor = conn.cursor()\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(f\"Connection failed with error: {e}\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Process Documents using Oracle AI\n",
-    "Consider the following scenario: users possess documents stored either in an Oracle Database or a file system and intend to utilize this data with Oracle AI Vector Search powered by Langchain.\n",
-    "\n",
-    "To prepare the documents for analysis, a comprehensive preprocessing workflow is necessary. Initially, the documents must be retrieved, summarized (if required), and chunked as needed. Subsequent steps involve generating embeddings for these chunks and integrating them into the Oracle AI Vector Store. Users can then conduct semantic searches on this data.\n",
-    "\n",
-    "The Oracle AI Vector Search Langchain library encompasses a suite of document processing tools that facilitate document loading, chunking, summary generation, and embedding creation.\n",
-    "\n",
-    "In the sections that follow, we will detail the utilization of Oracle AI Langchain APIs to effectively implement each of these processes."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Connect to Demo User\n",
-    "The following sample code will show how to connect to Oracle Database. By default, python-oracledb runs in a ‘Thin’ mode which connects directly to Oracle Database. This mode does not need Oracle Client libraries. However, some additional functionality is available when python-oracledb uses them. Python-oracledb is said to be in ‘Thick’ mode when Oracle Client libraries are used. Both modes have comprehensive functionality supporting the Python Database API v2.0 Specification. See the following [guide](https://python-oracledb.readthedocs.io/en/latest/user_guide/appendix_a.html#featuresummary) that talks about features supported in each mode. You might want to switch to thick-mode if you are unable to use thin-mode."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 45,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n"
-     ]
-    }
-   ],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "\n",
-    "# please update with your username, password, hostname and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Populate a Demo Table\n",
-    "Create a demo table and insert some sample documents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 46,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Table created and populated.\n"
-     ]
-    }
-   ],
-   "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
-    "\n",
-    "    drop_table_sql = \"\"\"drop table demo_tab\"\"\"\n",
-    "    cursor.execute(drop_table_sql)\n",
-    "\n",
-    "    create_table_sql = \"\"\"create table demo_tab (id number, data clob)\"\"\"\n",
-    "    cursor.execute(create_table_sql)\n",
-    "\n",
-    "    insert_row_sql = \"\"\"insert into demo_tab values (:1, :2)\"\"\"\n",
-    "    rows_to_insert = [\n",
-    "        (\n",
-    "            1,\n",
-    "            \"If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\",\n",
-    "        ),\n",
-    "        (\n",
-    "            2,\n",
-    "            \"A tablespace can be online (accessible) or offline (not accessible) whenever the database is open.\\nA tablespace is usually online so that its data is available to users. The SYSTEM tablespace and temporary tablespaces cannot be taken offline.\",\n",
-    "        ),\n",
-    "        (\n",
-    "            3,\n",
-    "            \"The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table.\\nSometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\",\n",
-    "        ),\n",
-    "    ]\n",
-    "    cursor.executemany(insert_row_sql, rows_to_insert)\n",
-    "\n",
-    "    conn.commit()\n",
-    "\n",
-    "    print(\"Table created and populated.\")\n",
-    "    cursor.close()\n",
-    "except Exception as e:\n",
-    "    print(\"Table creation failed.\")\n",
-    "    cursor.close()\n",
-    "    conn.close()\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "With the inclusion of a demo user and a populated sample table, the remaining configuration involves setting up embedding and summary functionalities. Users are presented with multiple provider options, including local database solutions and third-party services such as Ocigenai, Hugging Face, and OpenAI. Should users opt for a third-party provider, they are required to establish credentials containing the necessary authentication details. Conversely, if selecting a database as the provider for embeddings, it is necessary to upload an ONNX model to the Oracle Database. No additional setup is required for summary functionalities when using the database option."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load ONNX Model\n",
-    "\n",
-    "Oracle accommodates a variety of embedding providers, enabling users to choose between proprietary database solutions and third-party services such as OCIGENAI and HuggingFace. This selection dictates the methodology for generating and managing embeddings.\n",
-    "\n",
-    "***Important*** : Should users opt for the database option, they must upload an ONNX model into the Oracle Database. Conversely, if a third-party provider is selected for embedding generation, uploading an ONNX model to Oracle Database is not required.\n",
-    "\n",
-    "A significant advantage of utilizing an ONNX model directly within Oracle is the enhanced security and performance it offers by eliminating the need to transmit data to external parties. Additionally, this method avoids the latency typically associated with network or REST API calls.\n",
-    "\n",
-    "Below is the example code to upload an ONNX model into Oracle Database:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 47,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "ONNX model loaded.\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "\n",
-    "# please update with your related information\n",
-    "# make sure that you have onnx file in the system\n",
-    "onnx_dir = \"DEMO_PY_DIR\"\n",
-    "onnx_file = \"tinybert.onnx\"\n",
-    "model_name = \"demo_model\"\n",
-    "\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
-    "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Create Credential\n",
-    "\n",
-    "When selecting third-party providers for generating embeddings, users are required to establish credentials to securely access the provider's endpoints.\n",
-    "\n",
-    "***Important:*** No credentials are necessary when opting for the 'database' provider to generate embeddings. However, should users decide to utilize a third-party provider, they must create credentials specific to the chosen provider.\n",
-    "\n",
-    "Below is an illustrative example:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "try:\n",
-    "    cursor = conn.cursor()\n",
-    "    cursor.execute(\n",
-    "        \"\"\"\n",
-    "       declare\n",
-    "           jo json_object_t;\n",
-    "       begin\n",
-    "           -- HuggingFace\n",
-    "           dbms_vector_chain.drop_credential(credential_name  => 'HF_CRED');\n",
-    "           jo := json_object_t();\n",
-    "           jo.put('access_token', '<access_token>');\n",
-    "           dbms_vector_chain.create_credential(\n",
-    "               credential_name   =>  'HF_CRED',\n",
-    "               params            => json(jo.to_string));\n",
-    "\n",
-    "           -- OCIGENAI\n",
-    "           dbms_vector_chain.drop_credential(credential_name  => 'OCI_CRED');\n",
-    "           jo := json_object_t();\n",
-    "           jo.put('user_ocid','<user_ocid>');\n",
-    "           jo.put('tenancy_ocid','<tenancy_ocid>');\n",
-    "           jo.put('compartment_ocid','<compartment_ocid>');\n",
-    "           jo.put('private_key','<private_key>');\n",
-    "           jo.put('fingerprint','<fingerprint>');\n",
-    "           dbms_vector_chain.create_credential(\n",
-    "               credential_name   => 'OCI_CRED',\n",
-    "               params            => json(jo.to_string));\n",
-    "       end;\n",
-    "       \"\"\"\n",
-    "    )\n",
-    "    cursor.close()\n",
-    "    print(\"Credentials created.\")\n",
-    "except Exception as ex:\n",
-    "    cursor.close()\n",
-    "    raise"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Load Documents\n",
-    "Users have the flexibility to load documents from either the Oracle Database, a file system, or both, by appropriately configuring the loader parameters. For comprehensive details on these parameters, please consult the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-73397E89-92FB-48ED-94BB-1AD960C4EA1F).\n",
-    "\n",
-    "A significant advantage of utilizing OracleDocLoader is its capability to process over 150 distinct file formats, eliminating the need for multiple loaders for different document types. For a complete list of the supported formats, please refer to the [Oracle Text Supported Document Formats](https://docs.oracle.com/en/database/oracle/oracle-database/23/ccref/oracle-text-supported-document-formats.html).\n",
-    "\n",
-    "Below is a sample code snippet that demonstrates how to use OracleDocLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 48,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of docs loaded: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders.oracleai import OracleDocLoader\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# loading from Oracle Database table\n",
-    "# make sure you have the table with this specification\n",
-    "loader_params = {}\n",
-    "loader_params = {\n",
-    "    \"owner\": \"testuser\",\n",
-    "    \"tablename\": \"demo_tab\",\n",
-    "    \"colname\": \"data\",\n",
-    "}\n",
-    "\n",
-    "\"\"\" load the docs \"\"\"\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
-    "docs = loader.load()\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of docs loaded: {len(docs)}\")\n",
-    "# print(f\"Document-0: {docs[0].page_content}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Generate Summary\n",
-    "Now that the user loaded the documents, they may want to generate a summary for each document. The Oracle AI Vector Search Langchain library offers a suite of APIs designed for document summarization. It supports multiple summarization providers such as Database, OCIGENAI, HuggingFace, among others, allowing users to select the provider that best meets their needs. To utilize these capabilities, users must configure the summary parameters as specified. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-EC9DDB58-6A15-4B36-BA66-ECBA20D2CE57)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "***Note:*** The users may need to set proxy if they want to use some 3rd party summary generation providers other than Oracle's in-house and default provider: 'database'. If you don't have proxy, please remove the proxy parameter when you instantiate the OracleSummary."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proxy to be used when we instantiate summary and embedder object\n",
-    "proxy = \"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following sample code will show how to generate summary:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 49,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Summaries: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.utilities.oracleai import OracleSummary\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# using 'database' provider\n",
-    "summary_params = {\n",
-    "    \"provider\": \"database\",\n",
-    "    \"glevel\": \"S\",\n",
-    "    \"numParagraphs\": 1,\n",
-    "    \"language\": \"english\",\n",
-    "}\n",
-    "\n",
-    "# get the summary instance\n",
-    "# Remove proxy if not required\n",
-    "summ = OracleSummary(conn=conn, params=summary_params, proxy=proxy)\n",
-    "\n",
-    "list_summary = []\n",
-    "for doc in docs:\n",
-    "    summary = summ.get_summary(doc.page_content)\n",
-    "    list_summary.append(summary)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of Summaries: {len(list_summary)}\")\n",
-    "# print(f\"Summary-0: {list_summary[0]}\") #content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Split Documents\n",
-    "The documents may vary in size, ranging from small to very large. Users often prefer to chunk their documents into smaller sections to facilitate the generation of embeddings. A wide array of customization options is available for this splitting process. For comprehensive details regarding these parameters, please consult the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-4E145629-7098-4C7C-804F-FC85D1F24240).\n",
-    "\n",
-    "Below is a sample code illustrating how to implement this:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 50,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of Chunks: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.document_loaders.oracleai import OracleTextSplitter\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# split by default parameters\n",
-    "splitter_params = {\"normalize\": \"all\"}\n",
-    "\n",
-    "\"\"\" get the splitter instance \"\"\"\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
-    "\n",
-    "list_chunks = []\n",
-    "for doc in docs:\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    list_chunks.extend(chunks)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of Chunks: {len(list_chunks)}\")\n",
-    "# print(f\"Chunk-0: {list_chunks[0]}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Generate Embeddings\n",
-    "Now that the documents are chunked as per requirements, the users may want to generate embeddings for these chunks. Oracle AI Vector Search provides multiple methods for generating embeddings, utilizing either locally hosted ONNX models or third-party APIs. For comprehensive instructions on configuring these alternatives, please refer to the [Oracle AI Vector Search Guide](https://docs.oracle.com/en/database/oracle/oracle-database/23/arpls/dbms_vector_chain1.html#GUID-C6439E94-4E86-4ECD-954E-4B73D53579DE)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "***Note:*** Users may need to configure a proxy to utilize third-party embedding generation providers, excluding the 'database' provider that utilizes an ONNX model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# proxy to be used when we instantiate summary and embedder object\n",
-    "proxy = \"\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The following sample code will show how to generate embeddings:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 51,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Number of embeddings: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "from langchain_core.documents import Document\n",
-    "\n",
-    "# using ONNX model loaded to Oracle Database\n",
-    "embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
-    "\n",
-    "# get the embedding instance\n",
-    "# Remove proxy if not required\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params, proxy=proxy)\n",
-    "\n",
-    "embeddings = []\n",
-    "for doc in docs:\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    for chunk in chunks:\n",
-    "        embed = embedder.embed_query(chunk)\n",
-    "        embeddings.append(embed)\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of embeddings: {len(embeddings)}\")\n",
-    "# print(f\"Embedding-0: {embeddings[0]}\") # content"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create Oracle AI Vector Store\n",
-    "Now that you know how to use Oracle AI Langchain library APIs individually to process the documents, let us show how to integrate with Oracle AI Vector Store to facilitate the semantic searches."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "First, let's import all the dependencies."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 52,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import sys\n",
-    "\n",
-    "import oracledb\n",
-    "from langchain_community.document_loaders.oracleai import (\n",
-    "    OracleDocLoader,\n",
-    "    OracleTextSplitter,\n",
-    ")\n",
-    "from langchain_community.embeddings.oracleai import OracleEmbeddings\n",
-    "from langchain_community.utilities.oracleai import OracleSummary\n",
-    "from langchain_community.vectorstores import oraclevs\n",
-    "from langchain_community.vectorstores.oraclevs import OracleVS\n",
-    "from langchain_community.vectorstores.utils import DistanceStrategy\n",
-    "from langchain_core.documents import Document"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next, let's combine all document processing stages together. Here is the sample code below:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 53,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Connection successful!\n",
-      "ONNX model loaded.\n",
-      "Number of total chunks with metadata: 3\n"
-     ]
-    }
-   ],
-   "source": [
-    "\"\"\"\n",
-    "In this sample example, we will use 'database' provider for both summary and embeddings.\n",
-    "So, we don't need to do the followings:\n",
-    "    - set proxy for 3rd party providers\n",
-    "    - create credential for 3rd party providers\n",
-    "\n",
-    "If you choose to use 3rd party provider, \n",
-    "please follow the necessary steps for proxy and credential.\n",
-    "\"\"\"\n",
-    "\n",
-    "# oracle connection\n",
-    "# please update with your username, password, hostname, and service_name\n",
-    "username = \"\"\n",
-    "password = \"\"\n",
-    "dsn = \"\"\n",
-    "\n",
-    "try:\n",
-    "    conn = oracledb.connect(user=username, password=password, dsn=dsn)\n",
-    "    print(\"Connection successful!\")\n",
-    "except Exception as e:\n",
-    "    print(\"Connection failed!\")\n",
-    "    sys.exit(1)\n",
-    "\n",
-    "\n",
-    "# load onnx model\n",
-    "# please update with your related information\n",
-    "onnx_dir = \"DEMO_PY_DIR\"\n",
-    "onnx_file = \"tinybert.onnx\"\n",
-    "model_name = \"demo_model\"\n",
-    "try:\n",
-    "    OracleEmbeddings.load_onnx_model(conn, onnx_dir, onnx_file, model_name)\n",
-    "    print(\"ONNX model loaded.\")\n",
-    "except Exception as e:\n",
-    "    print(\"ONNX model loading failed!\")\n",
-    "    sys.exit(1)\n",
-    "\n",
-    "\n",
-    "# params\n",
-    "# please update necessary fields with related information\n",
-    "loader_params = {\n",
-    "    \"owner\": \"testuser\",\n",
-    "    \"tablename\": \"demo_tab\",\n",
-    "    \"colname\": \"data\",\n",
-    "}\n",
-    "summary_params = {\n",
-    "    \"provider\": \"database\",\n",
-    "    \"glevel\": \"S\",\n",
-    "    \"numParagraphs\": 1,\n",
-    "    \"language\": \"english\",\n",
-    "}\n",
-    "splitter_params = {\"normalize\": \"all\"}\n",
-    "embedder_params = {\"provider\": \"database\", \"model\": \"demo_model\"}\n",
-    "\n",
-    "# instantiate loader, summary, splitter, and embedder\n",
-    "loader = OracleDocLoader(conn=conn, params=loader_params)\n",
-    "summary = OracleSummary(conn=conn, params=summary_params)\n",
-    "splitter = OracleTextSplitter(conn=conn, params=splitter_params)\n",
-    "embedder = OracleEmbeddings(conn=conn, params=embedder_params)\n",
-    "\n",
-    "# process the documents\n",
-    "chunks_with_mdata = []\n",
-    "for id, doc in enumerate(docs, start=1):\n",
-    "    summ = summary.get_summary(doc.page_content)\n",
-    "    chunks = splitter.split_text(doc.page_content)\n",
-    "    for ic, chunk in enumerate(chunks, start=1):\n",
-    "        chunk_metadata = doc.metadata.copy()\n",
-    "        chunk_metadata[\"id\"] = chunk_metadata[\"_oid\"] + \"$\" + str(id) + \"$\" + str(ic)\n",
-    "        chunk_metadata[\"document_id\"] = str(id)\n",
-    "        chunk_metadata[\"document_summary\"] = str(summ[0])\n",
-    "        chunks_with_mdata.append(\n",
-    "            Document(page_content=str(chunk), metadata=chunk_metadata)\n",
-    "        )\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Number of total chunks with metadata: {len(chunks_with_mdata)}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "At this point, we have processed the documents and generated chunks with metadata. Next, we will create Oracle AI Vector Store with those chunks.\n",
-    "\n",
-    "Here is the sample code how to do that:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 55,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Vector Store Table: oravs\n"
-     ]
-    }
-   ],
-   "source": [
-    "# create Oracle AI Vector Store\n",
-    "vectorstore = OracleVS.from_documents(\n",
-    "    chunks_with_mdata,\n",
-    "    embedder,\n",
-    "    client=conn,\n",
-    "    table_name=\"oravs\",\n",
-    "    distance_strategy=DistanceStrategy.DOT_PRODUCT,\n",
-    ")\n",
-    "\n",
-    "\"\"\" verify \"\"\"\n",
-    "print(f\"Vector Store Table: {vectorstore.table_name}\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The example provided illustrates the creation of a vector store using the DOT_PRODUCT distance strategy. Users have the flexibility to employ various distance strategies with the Oracle AI Vector Store, as detailed in our [comprehensive guide](https://python.langchain.com/v0.1/docs/integrations/vectorstores/oracle/)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "With embeddings now stored in vector stores, it is advisable to establish an index to enhance semantic search performance during query execution.\n",
-    "\n",
-    "***Note*** Should you encounter an \"insufficient memory\" error, it is recommended to increase the  ***vector_memory_size*** in your database configuration\n",
-    "\n",
-    "Below is a sample code snippet for creating an index:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 56,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "oraclevs.create_index(\n",
-    "    conn, vectorstore, params={\"idx_name\": \"hnsw_oravs\", \"idx_type\": \"HNSW\"}\n",
-    ")\n",
-    "\n",
-    "print(\"Index created.\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "This example demonstrates the creation of a default HNSW index on embeddings within the 'oravs' table. Users may adjust various parameters according to their specific needs. For detailed information on these parameters, please consult the [Oracle AI Vector Search Guide book](https://docs.oracle.com/en/database/oracle/oracle-database/23/vecse/manage-different-categories-vector-indexes.html).\n",
-    "\n",
-    "Additionally, various types of vector indices can be created to meet diverse requirements. More details can be found in our [comprehensive guide](https://python.langchain.com/v0.1/docs/integrations/vectorstores/oracle/).\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Perform Semantic Search\n",
-    "All set!\n",
-    "\n",
-    "We have successfully processed the documents and stored them in the vector store, followed by the creation of an index to enhance query performance. We are now prepared to proceed with semantic searches.\n",
-    "\n",
-    "Below is the sample code for this process:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 58,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'})]\n",
-      "[]\n",
-      "[(Document(page_content='The database stores LOBs differently from other data types. Creating a LOB column implicitly creates a LOB segment and a LOB index. The tablespace containing the LOB segment and LOB index, which are always stored together, may be different from the tablespace containing the table. Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.', metadata={'_oid': '662f2f257677f3c2311a8ff999fd34e5', '_rowid': 'AAAR/xAAEAAAAAnAAC', 'id': '662f2f257677f3c2311a8ff999fd34e5$3$1', 'document_id': '3', 'document_summary': 'Sometimes the database can store small amounts of LOB data in the table itself rather than in a separate LOB segment.\\n\\n'}), 0.055675752460956573)]\n",
-      "[]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n",
-      "[Document(page_content='If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.', metadata={'_oid': '662f2f253acf96b33b430b88699490a2', '_rowid': 'AAAR/xAAEAAAAAnAAA', 'id': '662f2f253acf96b33b430b88699490a2$1$1', 'document_id': '1', 'document_summary': 'If the answer to any preceding questions is yes, then the database stops the search and allocates space from the specified tablespace; otherwise, space is allocated from the database default shared temporary tablespace.\\n\\n'})]\n"
-     ]
-    }
-   ],
-   "source": [
-    "query = \"What is Oracle AI Vector Store?\"\n",
-    "filter = {\"document_id\": [\"1\"]}\n",
-    "\n",
-    "# Similarity search without a filter\n",
-    "print(vectorstore.similarity_search(query, 1))\n",
-    "\n",
-    "# Similarity search with a filter\n",
-    "print(vectorstore.similarity_search(query, 1, filter=filter))\n",
-    "\n",
-    "# Similarity search with relevance score\n",
-    "print(vectorstore.similarity_search_with_score(query, 1))\n",
-    "\n",
-    "# Similarity search with relevance score with filter\n",
-    "print(vectorstore.similarity_search_with_score(query, 1, filter=filter))\n",
-    "\n",
-    "# Max marginal relevance search\n",
-    "print(vectorstore.max_marginal_relevance_search(query, 1, fetch_k=20, lambda_mult=0.5))\n",
-    "\n",
-    "# Max marginal relevance search with filter\n",
-    "print(\n",
-    "    vectorstore.max_marginal_relevance_search(\n",
-    "        query, 1, fetch_k=20, lambda_mult=0.5, filter=filter\n",
-    "    )\n",
-    ")"
-   ]
-  }
- ],
- "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": 4
-}

cookbook/petting_zoo.ipynb

@@ -129,7 +129,7 @@
     "        return obs_message\n",
     "\n",
     "    def _act(self):\n",
-    "        act_message = self.model.invoke(self.message_history)\n",
+    "        act_message = self.model(self.message_history)\n",
     "        self.message_history.append(act_message)\n",
     "        action = int(self.action_parser.parse(act_message.content)[\"action\"])\n",
     "        return action\n",

cookbook/press_releases.ipynb

@@ -84,7 +84,7 @@
     "from langchain.retrievers import KayAiRetriever\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
+    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
     "retriever = KayAiRetriever.create(\n",
     "    dataset_id=\"company\", data_types=[\"PressRelease\"], num_contexts=6\n",
     ")\n",