x

---------

Co-authored-by: Erick Friis <erick@langchain.dev>

.github/DISCUSSION_TEMPLATE/q-a.yml

@@ -3,18 +3,18 @@ body:
   - type: markdown
     attributes:
       value: |
-        Thanks for your interest in 🦜️🔗 LangChain!
+        Thanks for your interest in LangChain 🦜️🔗!
 
         Please follow these instructions, fill every question, and do every step. 🙏
         
         We're asking for this because answering questions and solving problems in GitHub takes a lot of time --
-        this is time that we cannot spend on adding new features, fixing bugs, write documentation or reviewing pull requests.
+        this is time that we cannot spend on adding new features, fixing bugs, writing documentation or reviewing pull requests.
 
-        By asking questions in a structured way (following this) it will be much easier to help you.
+        By asking questions in a structured way (following this) it will be much easier for us to help you.
 
-        And there's a high chance that you will find the solution along the way and you won't even have to submit it and wait for an answer. 😎
+        There's a high chance that by following this process, you'll find the solution on your own, eliminating the need to submit a question and wait for an answer. 😎
 
-        As there are too many questions, we will **DISCARD** and close the incomplete ones. 
+        As there are many questions submitted every day, we will **DISCARD** and close the incomplete ones. 
         
         That will allow us (and others) to focus on helping people like you that follow the whole process. 🤓
         

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -35,6 +35,8 @@ body:
           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
   - type: textarea
     id: reproduction
     validations:

.github/ISSUE_TEMPLATE/privileged.yml

@@ -9,7 +9,7 @@ body:
         If you are not a LangChain maintainer or were not asked directly by a maintainer to create an issue, then please start the conversation in a [Question in GitHub Discussions](https://github.com/langchain-ai/langchain/discussions/categories/q-a) instead.
         
         You are a LangChain maintainer if you maintain any of the packages inside of the LangChain repository 
-        or are a regular contributor to LangChain with previous merged merged pull requests.
+        or are a regular contributor to LangChain with previous merged pull requests.
   - type: checkboxes
     id: privileged
     attributes:

.github/actions/people/Dockerfile

@@ -0,0 +1,7 @@
+FROM python:3.9
+
+RUN pip install httpx PyGithub "pydantic==2.0.2" pydantic-settings "pyyaml>=5.3.1,<6.0.0"
+
+COPY ./app /app
+
+CMD ["python", "/app/main.py"]

.github/actions/people/action.yml

@@ -0,0 +1,11 @@
+# Adapted from https://github.com/tiangolo/fastapi/blob/master/.github/actions/people/action.yml
+name: "Generate LangChain People"
+description: "Generate the data for the LangChain People page"
+author: "Jacob Lee <jacob@langchain.dev>"
+inputs:
+  token:
+    description: 'User token, to read the GitHub API. Can be passed in using {{ secrets.LANGCHAIN_PEOPLE_GITHUB_TOKEN }}'
+    required: true
+runs:
+  using: 'docker'
+  image: 'Dockerfile'

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

@@ -0,0 +1,641 @@
+# Adapted from https://github.com/tiangolo/fastapi/blob/master/.github/actions/people/app/main.py
+
+import logging
+import subprocess
+import sys
+from collections import Counter
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+from typing import Any, Container, Dict, List, Set, Union
+
+import httpx
+import yaml
+from github import Github
+from pydantic import BaseModel, SecretStr
+from pydantic_settings import BaseSettings
+
+github_graphql_url = "https://api.github.com/graphql"
+questions_category_id = "DIC_kwDOIPDwls4CS6Ve"
+
+# discussions_query = """
+# query Q($after: String, $category_id: ID) {
+#   repository(name: "langchain", owner: "langchain-ai") {
+#     discussions(first: 100, after: $after, categoryId: $category_id) {
+#       edges {
+#         cursor
+#         node {
+#           number
+#           author {
+#             login
+#             avatarUrl
+#             url
+#           }
+#           title
+#           createdAt
+#           comments(first: 100) {
+#             nodes {
+#               createdAt
+#               author {
+#                 login
+#                 avatarUrl
+#                 url
+#               }
+#               isAnswer
+#               replies(first: 10) {
+#                 nodes {
+#                   createdAt
+#                   author {
+#                     login
+#                     avatarUrl
+#                     url
+#                   }
+#                 }
+#               }
+#             }
+#           }
+#         }
+#       }
+#     }
+#   }
+# }
+# """
+
+# issues_query = """
+# query Q($after: String) {
+#   repository(name: "langchain", owner: "langchain-ai") {
+#     issues(first: 100, after: $after) {
+#       edges {
+#         cursor
+#         node {
+#           number
+#           author {
+#             login
+#             avatarUrl
+#             url
+#           }
+#           title
+#           createdAt
+#           state
+#           comments(first: 100) {
+#             nodes {
+#               createdAt
+#               author {
+#                 login
+#                 avatarUrl
+#                 url
+#               }
+#             }
+#           }
+#         }
+#       }
+#     }
+#   }
+# }
+# """
+
+prs_query = """
+query Q($after: String) {
+  repository(name: "langchain", owner: "langchain-ai") {
+    pullRequests(first: 100, after: $after, states: MERGED) {
+      edges {
+        cursor
+        node {
+          changedFiles
+          additions
+          deletions
+          number
+          labels(first: 100) {
+            nodes {
+              name
+            }
+          }
+          author {
+            login
+            avatarUrl
+            url
+            ... on User {
+              twitterUsername
+            }
+          }
+          title
+          createdAt
+          state
+          reviews(first:100) {
+            nodes {
+              author {
+                login
+                avatarUrl
+                url
+                ... on User {
+                  twitterUsername
+                }
+              }
+              state
+            }
+          }
+        }
+      }
+    }
+  }
+}
+"""
+
+
+class Author(BaseModel):
+    login: str
+    avatarUrl: str
+    url: str
+    twitterUsername: Union[str, None] = None
+
+
+# Issues and Discussions
+
+
+class CommentsNode(BaseModel):
+    createdAt: datetime
+    author: Union[Author, None] = None
+
+
+class Replies(BaseModel):
+    nodes: List[CommentsNode]
+
+
+class DiscussionsCommentsNode(CommentsNode):
+    replies: Replies
+
+
+class Comments(BaseModel):
+    nodes: List[CommentsNode]
+
+
+class DiscussionsComments(BaseModel):
+    nodes: List[DiscussionsCommentsNode]
+
+
+class IssuesNode(BaseModel):
+    number: int
+    author: Union[Author, None] = None
+    title: str
+    createdAt: datetime
+    state: str
+    comments: Comments
+
+
+class DiscussionsNode(BaseModel):
+    number: int
+    author: Union[Author, None] = None
+    title: str
+    createdAt: datetime
+    comments: DiscussionsComments
+
+
+class IssuesEdge(BaseModel):
+    cursor: str
+    node: IssuesNode
+
+
+class DiscussionsEdge(BaseModel):
+    cursor: str
+    node: DiscussionsNode
+
+
+class Issues(BaseModel):
+    edges: List[IssuesEdge]
+
+
+class Discussions(BaseModel):
+    edges: List[DiscussionsEdge]
+
+
+class IssuesRepository(BaseModel):
+    issues: Issues
+
+
+class DiscussionsRepository(BaseModel):
+    discussions: Discussions
+
+
+class IssuesResponseData(BaseModel):
+    repository: IssuesRepository
+
+
+class DiscussionsResponseData(BaseModel):
+    repository: DiscussionsRepository
+
+
+class IssuesResponse(BaseModel):
+    data: IssuesResponseData
+
+
+class DiscussionsResponse(BaseModel):
+    data: DiscussionsResponseData
+
+
+# PRs
+
+
+class LabelNode(BaseModel):
+    name: str
+
+
+class Labels(BaseModel):
+    nodes: List[LabelNode]
+
+
+class ReviewNode(BaseModel):
+    author: Union[Author, None] = None
+    state: str
+
+
+class Reviews(BaseModel):
+    nodes: List[ReviewNode]
+
+
+class PullRequestNode(BaseModel):
+    number: int
+    labels: Labels
+    author: Union[Author, None] = None
+    changedFiles: int
+    additions: int
+    deletions: int
+    title: str
+    createdAt: datetime
+    state: str
+    reviews: Reviews
+    # comments: Comments
+
+
+class PullRequestEdge(BaseModel):
+    cursor: str
+    node: PullRequestNode
+
+
+class PullRequests(BaseModel):
+    edges: List[PullRequestEdge]
+
+
+class PRsRepository(BaseModel):
+    pullRequests: PullRequests
+
+
+class PRsResponseData(BaseModel):
+    repository: PRsRepository
+
+
+class PRsResponse(BaseModel):
+    data: PRsResponseData
+
+
+class Settings(BaseSettings):
+    input_token: SecretStr
+    github_repository: str
+    httpx_timeout: int = 30
+
+
+def get_graphql_response(
+    *,
+    settings: Settings,
+    query: str,
+    after: Union[str, None] = None,
+    category_id: Union[str, None] = None,
+) -> Dict[str, Any]:
+    headers = {"Authorization": f"token {settings.input_token.get_secret_value()}"}
+    # category_id is only used by one query, but GraphQL allows unused variables, so
+    # keep it here for simplicity
+    variables = {"after": after, "category_id": category_id}
+    response = httpx.post(
+        github_graphql_url,
+        headers=headers,
+        timeout=settings.httpx_timeout,
+        json={"query": query, "variables": variables, "operationName": "Q"},
+    )
+    if response.status_code != 200:
+        logging.error(
+            f"Response was not 200, after: {after}, category_id: {category_id}"
+        )
+        logging.error(response.text)
+        raise RuntimeError(response.text)
+    data = response.json()
+    if "errors" in data:
+        logging.error(f"Errors in response, after: {after}, category_id: {category_id}")
+        logging.error(data["errors"])
+        logging.error(response.text)
+        raise RuntimeError(response.text)
+    return data
+
+
+# def get_graphql_issue_edges(*, settings: Settings, after: Union[str, None] = None):
+#     data = get_graphql_response(settings=settings, query=issues_query, after=after)
+#     graphql_response = IssuesResponse.model_validate(data)
+#     return graphql_response.data.repository.issues.edges
+
+
+# def get_graphql_question_discussion_edges(
+#     *,
+#     settings: Settings,
+#     after: Union[str, None] = None,
+# ):
+#     data = get_graphql_response(
+#         settings=settings,
+#         query=discussions_query,
+#         after=after,
+#         category_id=questions_category_id,
+#     )
+#     graphql_response = DiscussionsResponse.model_validate(data)
+#     return graphql_response.data.repository.discussions.edges
+
+
+def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
+    if after is None:
+        print("Querying PRs...")
+    else:
+        print(f"Querying PRs with cursor {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
+
+
+# def get_issues_experts(settings: Settings):
+#     issue_nodes: List[IssuesNode] = []
+#     issue_edges = get_graphql_issue_edges(settings=settings)
+
+#     while issue_edges:
+#         for edge in issue_edges:
+#             issue_nodes.append(edge.node)
+#         last_edge = issue_edges[-1]
+#         issue_edges = get_graphql_issue_edges(settings=settings, after=last_edge.cursor)
+
+#     commentors = Counter()
+#     last_month_commentors = Counter()
+#     authors: Dict[str, Author] = {}
+
+#     now = datetime.now(tz=timezone.utc)
+#     one_month_ago = now - timedelta(days=30)
+
+#     for issue in issue_nodes:
+#         issue_author_name = None
+#         if issue.author:
+#             authors[issue.author.login] = issue.author
+#             issue_author_name = issue.author.login
+#         issue_commentors = set()
+#         for comment in issue.comments.nodes:
+#             if comment.author:
+#                 authors[comment.author.login] = comment.author
+#                 if comment.author.login != issue_author_name:
+#                     issue_commentors.add(comment.author.login)
+#         for author_name in issue_commentors:
+#             commentors[author_name] += 1
+#             if issue.createdAt > one_month_ago:
+#                 last_month_commentors[author_name] += 1
+
+#     return commentors, last_month_commentors, authors
+
+
+# def get_discussions_experts(settings: Settings):
+#     discussion_nodes: List[DiscussionsNode] = []
+#     discussion_edges = get_graphql_question_discussion_edges(settings=settings)
+
+#     while discussion_edges:
+#         for discussion_edge in discussion_edges:
+#             discussion_nodes.append(discussion_edge.node)
+#         last_edge = discussion_edges[-1]
+#         discussion_edges = get_graphql_question_discussion_edges(
+#             settings=settings, after=last_edge.cursor
+#         )
+
+#     commentors = Counter()
+#     last_month_commentors = Counter()
+#     authors: Dict[str, Author] = {}
+
+#     now = datetime.now(tz=timezone.utc)
+#     one_month_ago = now - timedelta(days=30)
+
+#     for discussion in discussion_nodes:
+#         discussion_author_name = None
+#         if discussion.author:
+#             authors[discussion.author.login] = discussion.author
+#             discussion_author_name = discussion.author.login
+#         discussion_commentors = set()
+#         for comment in discussion.comments.nodes:
+#             if comment.author:
+#                 authors[comment.author.login] = comment.author
+#                 if comment.author.login != discussion_author_name:
+#                     discussion_commentors.add(comment.author.login)
+#             for reply in comment.replies.nodes:
+#                 if reply.author:
+#                     authors[reply.author.login] = reply.author
+#                     if reply.author.login != discussion_author_name:
+#                         discussion_commentors.add(reply.author.login)
+#         for author_name in discussion_commentors:
+#             commentors[author_name] += 1
+#             if discussion.createdAt > one_month_ago:
+#                 last_month_commentors[author_name] += 1
+#     return commentors, last_month_commentors, authors
+
+
+# def get_experts(settings: Settings):
+#     (
+#         discussions_commentors,
+#         discussions_last_month_commentors,
+#         discussions_authors,
+#     ) = get_discussions_experts(settings=settings)
+#     commentors = discussions_commentors
+#     last_month_commentors = discussions_last_month_commentors
+#     authors = {**discussions_authors}
+#     return commentors, last_month_commentors, authors
+
+
+def _logistic(x, k):
+    return x / (x + k)
+
+
+def get_contributors(settings: Settings):
+    pr_nodes: List[PullRequestNode] = []
+    pr_edges = get_graphql_pr_edges(settings=settings)
+
+    while pr_edges:
+        for edge in pr_edges:
+            pr_nodes.append(edge.node)
+        last_edge = pr_edges[-1]
+        pr_edges = get_graphql_pr_edges(settings=settings, after=last_edge.cursor)
+
+    contributors = Counter()
+    contributor_scores = Counter()
+    recent_contributor_scores = Counter()
+    reviewers = Counter()
+    authors: Dict[str, Author] = {}
+
+    for pr in pr_nodes:
+        pr_reviewers: Set[str] = set()
+        for review in pr.reviews.nodes:
+            if review.author:
+                authors[review.author.login] = review.author
+                pr_reviewers.add(review.author.login)
+        for reviewer in pr_reviewers:
+            reviewers[reviewer] += 1
+        if pr.author:
+            authors[pr.author.login] = pr.author
+            contributors[pr.author.login] += 1
+            files_changed = pr.changedFiles
+            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))
+            if pr.createdAt > three_months_ago:
+                recent_contributor_scores[pr.author.login] += score
+    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
+
+
+def get_top_users(
+    *,
+    counter: Counter,
+    min_count: int,
+    authors: Dict[str, Author],
+    skip_users: Container[str],
+):
+    users = []
+    for commentor, count in counter.most_common():
+        if commentor in skip_users:
+            continue
+        if count >= min_count:
+            author = authors[commentor]
+            users.append(
+                {
+                    "login": commentor,
+                    "count": count,
+                    "avatarUrl": author.avatarUrl,
+                    "twitterUsername": author.twitterUsername,
+                    "url": author.url,
+                }
+            )
+    return users
+
+
+if __name__ == "__main__":
+    logging.basicConfig(level=logging.INFO)
+    settings = Settings()
+    logging.info(f"Using config: {settings.model_dump_json()}")
+    g = Github(settings.input_token.get_secret_value())
+    repo = g.get_repo(settings.github_repository)
+    # 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
+    )
+    # authors = {**question_authors, **pr_authors}
+    authors = {**pr_authors}
+    maintainers_logins = {
+        "hwchase17",
+        "agola11",
+        "baskaryan",
+        "hinthornw",
+        "nfcampos",
+        "efriis",
+        "eyurtsev",
+        "rlancemartin"
+    }
+    hidden_logins = {
+        "dev2049",
+        "vowelparrot",
+        "obi1kenobi",
+        "langchain-infra",
+        "jacoblee93",
+        "dqbd",
+        "bracesproul",
+        "akira",
+    }
+    bot_names = {"dosubot", "github-actions", "CodiumAI-Agent"}
+    maintainers = []
+    for login in maintainers_logins:
+        user = authors[login]
+        maintainers.append(
+            {
+                "login": login,
+                "count": contributors[login], #+ question_commentors[login],
+                "avatarUrl": user.avatarUrl,
+                "twitterUsername": user.twitterUsername,
+                "url": user.url,
+            }
+        )
+
+    # min_count_expert = 10
+    # min_count_last_month = 3
+    min_score_contributor = 1
+    min_count_reviewer = 5
+    skip_users = maintainers_logins | bot_names | hidden_logins
+    # experts = get_top_users(
+    #     counter=question_commentors,
+    #     min_count=min_count_expert,
+    #     authors=authors,
+    #     skip_users=skip_users,
+    # )
+    # last_month_active = get_top_users(
+    #     counter=question_last_month_commentors,
+    #     min_count=min_count_last_month,
+    #     authors=authors,
+    #     skip_users=skip_users,
+    # )
+    top_recent_contributors = get_top_users(
+        counter=recent_contributor_scores,
+        min_count=min_score_contributor,
+        authors=authors,
+        skip_users=skip_users,
+    )
+    top_contributors = get_top_users(
+        counter=contributor_scores,
+        min_count=min_score_contributor,
+        authors=authors,
+        skip_users=skip_users,
+    )
+    top_reviewers = get_top_users(
+        counter=reviewers,
+        min_count=min_count_reviewer,
+        authors=authors,
+        skip_users=skip_users,
+    )
+
+    people = {
+        "maintainers": maintainers,
+        # "experts": experts,
+        # "last_month_active": last_month_active,
+        "top_recent_contributors": top_recent_contributors,
+        "top_contributors": top_contributors,
+        "top_reviewers": top_reviewers,
+    }
+    people_path = Path("./docs/data/people.yml")
+    people_old_content = people_path.read_text(encoding="utf-8")
+    new_people_content = yaml.dump(
+        people, sort_keys=False, width=200, allow_unicode=True
+    )
+    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")
+    logging.info("Setting up GitHub Actions git user")
+    subprocess.run(["git", "config", "user.name", "github-actions"], check=True)
+    subprocess.run(
+        ["git", "config", "user.email", "github-actions@github.com"], check=True
+    )
+    branch_name = "langchain/langchain-people"
+    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
+    )
+    logging.info("Committing updated file")
+    message = "👥 Update LangChain people data"
+    result = subprocess.run(["git", "commit", "-m", message], check=True)
+    logging.info("Pushing branch")
+    subprocess.run(["git", "push", "origin", branch_name, "-f"], check=True)
+    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")

.github/scripts/check_diff.py

@@ -1,17 +1,25 @@
 import json
 import sys
 import os
+from typing import Dict
 
-LANGCHAIN_DIRS = {
+LANGCHAIN_DIRS = [
     "libs/core",
+    "libs/text-splitters",
+    "libs/community",
     "libs/langchain",
     "libs/experimental",
-    "libs/community",
-}
+]
 
 if __name__ == "__main__":
     files = sys.argv[1:]
-    dirs_to_run = set()
+
+    dirs_to_run: Dict[str, set] = {
+        "lint": set(),
+        "test": set(),
+        "extended-test": set(),
+    }
+    docs_edited = False
 
     if len(files) == 300:
         # max diff length is 300 files - there are likely files missing
@@ -24,27 +32,63 @@ if __name__ == "__main__":
                 ".github/workflows",
                 ".github/tools",
                 ".github/actions",
-                "libs/core",
                 ".github/scripts/check_diff.py",
             )
         ):
-            dirs_to_run.update(LANGCHAIN_DIRS)
-        elif "libs/community" in file:
-            dirs_to_run.update(
-                ("libs/community", "libs/langchain", "libs/experimental")
-            )
-        elif "libs/partners" in file:
-            partner_dir = file.split("/")[2]
-            if os.path.isdir(f"libs/partners/{partner_dir}"):
-                dirs_to_run.add(f"libs/partners/{partner_dir}")
-            # Skip if the directory was deleted
-        elif "libs/langchain" in file:
-            dirs_to_run.update(("libs/langchain", "libs/experimental"))
-        elif "libs/experimental" in file:
-            dirs_to_run.add("libs/experimental")
-        elif file.startswith("libs/"):
-            dirs_to_run.update(LANGCHAIN_DIRS)
-        else:
+            # add all LANGCHAIN_DIRS for infra changes
+            dirs_to_run["extended-test"].update(LANGCHAIN_DIRS)
+            dirs_to_run["lint"].add(".")
+
+        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 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/partners/mistralai")
+            dirs_to_run["test"].add("libs/partners/openai")
+            dirs_to_run["test"].add("libs/partners/anthropic")
+            dirs_to_run["test"].add("libs/partners/ai21")
+            dirs_to_run["test"].add("libs/partners/fireworks")
+            dirs_to_run["test"].add("libs/partners/groq")
+
+        elif file.startswith("libs/cli"):
+            # todo: add cli makefile
             pass
-    json_output = json.dumps(list(dirs_to_run))
-    print(f"dirs-to-run={json_output}")  # noqa: T201
+        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"]:
+                dirs_to_run["test"].add(f"libs/partners/{partner_dir}")
+            # Skip if the directory was deleted or is just a tombstone readme
+        elif file.startswith("libs/"):
+            raise ValueError(
+                f"Unknown lib: {file}. check_diff.py likely needs "
+                "an update for this new library!"
+            )
+        elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
+            if file.startswith("docs/"):
+                docs_edited = True
+            dirs_to_run["lint"].add(".")
+
+    outputs = {
+        "dirs-to-lint": list(
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"]
+        ),
+        "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
+        "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
+        "docs-edited": "true" if docs_edited else "",
+    }
+    for key, value in outputs.items():
+        json_output = json.dumps(value)
+        print(f"{key}={json_output}")  # noqa: T201

.github/scripts/get_min_versions.py

@@ -4,17 +4,25 @@ import tomllib
 from packaging.version import parse as parse_version
 import re
 
-MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain"]
+MIN_VERSION_LIBS = [
+    "langchain-core",
+    "langchain-community",
+    "langchain",
+    "langchain-text-splitters",
+]
 
 
 def get_min_version(version: str) -> str:
+    # base regex for x.x.x with cases for rc/post/etc
+    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
+    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
     # case ^x.x.x
-    _match = re.match(r"^\^(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^\\^({vstring})$", version)
     if _match:
         return _match.group(1)
 
     # case >=x.x.x,<y.y.y
-    _match = re.match(r"^>=(\d+(?:\.\d+){0,2}),<(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
     if _match:
         _min = _match.group(1)
         _max = _match.group(2)
@@ -22,7 +30,7 @@ def get_min_version(version: str) -> str:
         return _min
 
     # case x.x.x
-    _match = re.match(r"^(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^({vstring})$", version)
     if _match:
         return _match.group(1)
 
@@ -47,6 +55,9 @@ def get_min_version_from_toml(toml_path: str):
             # Get the version string
             version_string = dependencies[lib]
 
+            if isinstance(version_string, dict):
+                version_string = version_string["version"]
+
             # Use parse_version to get the minimum supported version from version_string
             min_version = get_min_version(version_string)
 
@@ -56,12 +67,13 @@ def get_min_version_from_toml(toml_path: str):
     return min_versions
 
 
-# Get the TOML file path from the command line argument
-toml_file = sys.argv[1]
+if __name__ == "__main__":
+    # Get the TOML file path from the command line argument
+    toml_file = sys.argv[1]
 
-# Call the function to get the minimum versions
-min_versions = get_min_version_from_toml(toml_file)
+    # Call the function to get the minimum versions
+    min_versions = get_min_version_from_toml(toml_file)
 
-print(
-    " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-)  # noqa: T201
+    print(
+        " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
+    )  # noqa: T201

.github/workflows/_all_ci.yml

@@ -1,110 +0,0 @@
----
-name: langchain CI
-
-on:
-  workflow_call:
-    inputs:
-      working-directory:
-        required: true
-        type: string
-        description: "From which folder this pipeline executes"
-  workflow_dispatch:
-    inputs:
-      working-directory:
-        required: true
-        type: choice
-        default: 'libs/langchain'
-        options:
-        - libs/langchain
-        - libs/core
-        - libs/experimental
-        - libs/community
-
-
-# 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 }}-${{ inputs.working-directory }}
-  cancel-in-progress: true
-
-env:
-  POETRY_VERSION: "1.7.1"
-
-jobs:
-  lint:
-    name: "-"
-    uses: ./.github/workflows/_lint.yml
-    with:
-      working-directory: ${{ inputs.working-directory }}
-    secrets: inherit
-
-  test:
-    name: "-"
-    uses: ./.github/workflows/_test.yml
-    with:
-      working-directory: ${{ inputs.working-directory }}
-    secrets: inherit
-
-  compile-integration-tests:
-    name: "-"
-    uses: ./.github/workflows/_compile_integration_test.yml
-    with:
-      working-directory: ${{ inputs.working-directory }}
-    secrets: inherit
-
-  dependencies:
-    name: "-"
-    uses: ./.github/workflows/_dependencies.yml
-    with:
-      working-directory: ${{ inputs.working-directory }}
-    secrets: inherit
-
-  extended-tests:
-    name: "make extended_tests #${{ matrix.python-version }}"
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.8"
-          - "3.9"
-          - "3.10"
-          - "3.11"
-    defaults:
-      run:
-        working-directory: ${{ inputs.working-directory }}
-    if: ${{ ! startsWith(inputs.working-directory, 'libs/partners/') }}
-    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: ${{ inputs.working-directory }}
-          cache-key: extended
-
-      - name: Install dependencies
-        shell: bash
-        run: |
-          echo "Running extended tests, installing dependencies with poetry..."
-          poetry install -E extended_testing --with test
-
-      - name: Run extended tests
-        run: make extended_tests
-
-      - name: Ensure the tests did not create any additional files
-        shell: bash
-        run: |
-          set -eu
-
-          STATUS="$(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/_dependencies.yml

@@ -63,6 +63,8 @@ jobs:
       - 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)
@@ -97,6 +99,8 @@ jobs:
           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
 

.github/workflows/_integration_test.yml

@@ -58,6 +58,7 @@ jobs:
           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 }}
@@ -70,6 +71,14 @@ jobs:
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
+          ES_URL: ${{ secrets.ES_URL }}
+          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
+          ES_API_KEY: ${{ secrets.ES_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
+          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
+          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
         run: |
           make integration_tests
 

.github/workflows/_release.yml

@@ -55,7 +55,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -157,6 +157,24 @@ jobs:
         run: make tests
         working-directory: ${{ inputs.working-directory }}
 
+      - name: Get minimum versions
+        working-directory: ${{ inputs.working-directory }}
+        id: min-version
+        run: |
+          poetry run pip install packaging
+          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
+          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
+          echo "min-versions=$min_versions"
+
+      - name: Run unit tests with minimum dependency versions
+        if: ${{ steps.min-version.outputs.min-versions != '' }}
+        env:
+          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
+        run: |
+          poetry run pip install $MIN_VERSIONS
+          make tests
+        working-directory: ${{ inputs.working-directory }}
+
       - name: 'Authenticate to Google Cloud'
         id: 'auth'
         uses: google-github-actions/auth@v2
@@ -181,6 +199,7 @@ jobs:
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           EXA_API_KEY: ${{ secrets.EXA_API_KEY }}
           NOMIC_API_KEY: ${{ secrets.NOMIC_API_KEY }}
           WATSONX_APIKEY: ${{ secrets.WATSONX_APIKEY }}
@@ -190,27 +209,16 @@ jobs:
           ASTRA_DB_API_ENDPOINT: ${{ secrets.ASTRA_DB_API_ENDPOINT }}
           ASTRA_DB_APPLICATION_TOKEN: ${{ secrets.ASTRA_DB_APPLICATION_TOKEN }}
           ASTRA_DB_KEYSPACE: ${{ secrets.ASTRA_DB_KEYSPACE }}
+          ES_URL: ${{ secrets.ES_URL }}
+          ES_CLOUD_ID: ${{ secrets.ES_CLOUD_ID }}
+          ES_API_KEY: ${{ secrets.ES_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
+          MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
+          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
+          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
         run: make integration_tests
         working-directory: ${{ inputs.working-directory }}
 
-      - name: Get minimum versions
-        working-directory: ${{ inputs.working-directory }}
-        id: min-version
-        run: |
-          poetry run pip install packaging
-          min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml)"
-          echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"
-          echo "min-versions=$min_versions"
-
-      - name: Run unit tests with minimum dependency versions
-        if: ${{ steps.min-version.outputs.min-versions != '' }}
-        env:
-          MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
-        run: |
-          poetry run pip install $MIN_VERSIONS
-          make tests
-        working-directory: ${{ inputs.working-directory }}
-
   publish:
     needs:
       - build
@@ -240,7 +248,7 @@ jobs:
           working-directory: ${{ inputs.working-directory }}
           cache-key: release
 
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/
@@ -279,7 +287,7 @@ jobs:
           working-directory: ${{ inputs.working-directory }}
           cache-key: release
 
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: dist
           path: ${{ inputs.working-directory }}/dist/

.github/workflows/_release_note_experiments.yml

@@ -0,0 +1,59 @@
+name: release note experiments
+run-name: Release note for ${{ inputs.working-directory }} by @${{ github.actor }}
+on:
+  workflow_dispatch:
+    inputs:
+      working-directory:
+        required: true
+        type: string
+        default: 'libs/langchain'
+
+env:
+  PYTHON_VERSION: "3.11"
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    outputs:
+      pkg-name: ${{ steps.check-version.outputs.pkg-name }}
+      version: ${{ steps.check-version.outputs.version }}
+
+    steps:
+      - uses: actions/checkout@v4
+      - 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
+      - name: Check Version
+        id: check-version
+        shell: bash
+        working-directory: ${{ inputs.working-directory }}
+        run: |
+          echo pkg-name="$(poetry version | cut -d ' ' -f 1)" >> $GITHUB_OUTPUT
+          echo version="$(poetry version --short)" >> $GITHUB_OUTPUT
+  release-notes:
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - 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
+      - name: Generate Release Notes
+        env:
+          TAG_NAME: ${{ needs.build.outputs.pkg-name }}-v${{ needs.build.outputs.version }}
+          RELEASE_NAME: ${{ needs.build.outputs.pkg-name }}==${{ needs.build.outputs.version }}
+        run: |
+          echo "TAG_NAME=${TAG_NAME}"
+          echo "RELEASE_NAME=${RELEASE_NAME}"

.github/workflows/_test_doc_imports.yml

@@ -0,0 +1,50 @@
+name: test_doc_imports
+
+on:
+  workflow_call:
+
+env:
+  POETRY_VERSION: "1.7.1"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.11"
+    name: "check doc imports #${{ 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: ${{ env.POETRY_VERSION }}
+          cache-key: core
+
+      - name: Install dependencies
+        shell: bash
+        run: poetry install --with test
+
+      - name: Install langchain editable
+        run: |
+          poetry run pip install -e libs/core libs/langchain libs/community libs/experimental
+
+      - name: Check doc imports
+        shell: bash
+        run: |
+          poetry run python docs/scripts/check_imports.py
+
+      - name: Ensure the test did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(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_release.yml

@@ -48,7 +48,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
 
       - name: Upload build
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/
@@ -76,7 +76,7 @@ jobs:
     steps:
       - uses: actions/checkout@v4
 
-      - uses: actions/download-artifact@v3
+      - uses: actions/download-artifact@v4
         with:
           name: test-dist
           path: ${{ inputs.working-directory }}/dist/

.github/workflows/api_doc_build.yml

@@ -1,52 +0,0 @@
-name: API docs build
-
-on:
-  workflow_dispatch:
-  schedule:
-    - cron:  '0 13 * * *'
-env:
-  POETRY_VERSION: "1.7.1"
-  PYTHON_VERSION: "3.10"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-        with:
-          ref: bagatur/api_docs_build
-
-      - name: Set Git config
-        run: |
-          git config --local user.email "actions@github.com"
-          git config --local user.name "Github Actions"
-
-      - name: Merge master
-        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: "./.github/actions/poetry_setup"
-        with:
-          python-version: ${{ env.PYTHON_VERSION }}
-          poetry-version: ${{ env.POETRY_VERSION }}
-          cache-key: api-docs
-
-      - name: Install dependencies
-        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
-          poetry run python -m pip install ./libs/partners/*
-          poetry run python -m pip install --exists-action=w --no-cache-dir -r docs/api_reference/requirements.txt
-
-      - name: Build docs
-        run: |
-          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:
-          message: 'Update API docs build'

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

@@ -0,0 +1,24 @@
+name: Check Broken Links
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron:  '0 13 * * *'
+
+jobs:
+  check-links:
+    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_diffs.yml

@@ -16,6 +16,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+env:
+  POETRY_VERSION: "1.7.1"
+
 jobs:
   build:
     runs-on: ubuntu-latest
@@ -30,15 +33,126 @@ jobs:
         run: |
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
-      dirs-to-run: ${{ steps.set-matrix.outputs.dirs-to-run }}
-  ci:
+      dirs-to-lint: ${{ steps.set-matrix.outputs.dirs-to-lint }}
+      dirs-to-test: ${{ steps.set-matrix.outputs.dirs-to-test }}
+      dirs-to-extended-test: ${{ steps.set-matrix.outputs.dirs-to-extended-test }}
+      docs-edited: ${{ steps.set-matrix.outputs.docs-edited }}
+  lint:
     name: cd ${{ matrix.working-directory }}
     needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-lint != '[]' }}
     strategy:
       matrix:
-        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-run) }}
-    uses: ./.github/workflows/_all_ci.yml
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-lint) }}
+    uses: ./.github/workflows/_lint.yml
     with:
       working-directory: ${{ matrix.working-directory }}
+    secrets: inherit
 
+  test:
+    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/_test.yml
+    with:
+      working-directory: ${{ matrix.working-directory }}
+    secrets: inherit
 
+  test-doc-imports:
+    needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' || needs.build.outputs.docs-edited }}
+    uses: ./.github/workflows/_test_doc_imports.yml
+    secrets: inherit
+
+  compile-integration-tests:
+    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/_compile_integration_test.yml
+    with:
+      working-directory: ${{ matrix.working-directory }}
+    secrets: inherit
+
+  dependencies:
+    name: cd ${{ matrix.working-directory }}
+    needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-test != '[]' }}
+    strategy:
+      matrix:
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-test) }}
+    uses: ./.github/workflows/_dependencies.yml
+    with:
+      working-directory: ${{ matrix.working-directory }}
+    secrets: inherit
+
+  extended-tests:
+    name: "cd ${{ matrix.working-directory }} / make extended_tests #${{ matrix.python-version }}"
+    needs: [ build ]
+    if: ${{ needs.build.outputs.dirs-to-extended-test != '[]' }}
+    strategy:
+      matrix:
+        # note different variable for extended test dirs
+        working-directory: ${{ fromJson(needs.build.outputs.dirs-to-extended-test) }}
+        python-version:
+          - "3.8"
+          - "3.9"
+          - "3.10"
+          - "3.11"
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: ${{ matrix.working-directory }}
+    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: ${{ matrix.working-directory }}
+          cache-key: extended
+
+      - name: Install dependencies
+        shell: bash
+        run: |
+          echo "Running extended tests, installing dependencies with poetry..."
+          poetry install -E extended_testing --with test
+
+      - name: Run extended tests
+        run: make extended_tests
+
+      - name: Ensure the tests did not create any additional files
+        shell: bash
+        run: |
+          set -eu
+
+          STATUS="$(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'
+  ci_success:
+    name: "CI Success"
+    needs: [build, lint, test, compile-integration-tests, dependencies, extended-tests, test-doc-imports]
+    if: |
+      always()
+    runs-on: ubuntu-latest
+    env:
+      JOBS_JSON: ${{ toJSON(needs) }}
+      RESULTS_JSON: ${{ toJSON(needs.*.result) }}
+      EXIT_CODE: ${{!contains(needs.*.result, 'failure') && !contains(needs.*.result, 'cancelled') && '0' || '1'}}
+    steps:
+      - name: "CI Success"
+        run: |
+          echo $JOBS_JSON
+          echo $RESULTS_JSON
+          echo "Exiting with $EXIT_CODE"
+          exit $EXIT_CODE

.github/workflows/codespell.yml

@@ -32,6 +32,6 @@ jobs:
       - name: Codespell
         uses: codespell-project/actions-codespell@v2
         with:
-          skip: guide_imports.json
+          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: libs/community/langchain_community/llms/yuan2.py

.github/workflows/doc_lint.yml

@@ -1,37 +0,0 @@
----
-name: CI / cd .
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    paths:
-      - 'docs/**'
-      - 'templates/**'
-      - 'cookbook/**'
-      - '.github/workflows/_lint.yml'
-      - '.github/workflows/doc_lint.yml'
-  workflow_dispatch:
-
-jobs:
-  check:
-    name: Check for "from langchain import x" imports
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout repository
-      uses: actions/checkout@v4
-
-    - name: Run import check
-      run: |
-        # We should not encourage imports directly from main init file
-        # Expect for hub
-        git grep 'from langchain import' {docs/docs,templates,cookbook} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
-
-  lint:
-      name: "-"
-      uses:
-        ./.github/workflows/_lint.yml
-      with:
-        working-directory: "."
-      secrets: inherit

.github/workflows/people.yml

@@ -0,0 +1,36 @@
+name: LangChain People
+
+on:
+  schedule:
+    - cron: "0 14 1 * *"
+  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'
+    runs-on: ubuntu-latest
+    steps:
+      - name: Dump GitHub context
+        env:
+          GITHUB_CONTEXT: ${{ toJson(github) }}
+        run: echo "$GITHUB_CONTEXT"
+      - uses: actions/checkout@v4
+      # 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/scheduled_test.yml

@@ -10,19 +10,21 @@ env:
 
 jobs:
   build:
-    defaults:
-      run:
-        working-directory: libs/langchain
     runs-on: ubuntu-latest
-    environment: Scheduled testing
     strategy:
       matrix:
         python-version:
           - "3.8"
-          - "3.9"
-          - "3.10"
           - "3.11"
-    name: Python ${{ matrix.python-version }}
+        working-directory:
+          - "libs/partners/openai"
+          - "libs/partners/anthropic"
+          # - "libs/partners/ai21"  # standard-tests broken
+          - "libs/partners/fireworks"
+          # - "libs/partners/groq"  # rate-limited
+          - "libs/partners/mistralai"
+          # - "libs/partners/together"  # rate-limited
+    name: Python ${{ matrix.python-version }} - ${{ matrix.working-directory }}
     steps:
       - uses: actions/checkout@v4
 
@@ -31,7 +33,7 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
           poetry-version: ${{ env.POETRY_VERSION }}
-          working-directory: libs/langchain
+          working-directory: ${{ matrix.working-directory }}
           cache-key: scheduled
 
       - name: 'Authenticate to Google Cloud'
@@ -40,26 +42,15 @@ jobs:
         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: ${{ vars.AWS_REGION }}
-
       - name: Install dependencies
-        working-directory: libs/langchain
+        working-directory: ${{ matrix.working-directory }}
         shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
           poetry install --with=test_integration,test
 
-      - 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 tests
+      - name: Run integration tests
+        working-directory: ${{ matrix.working-directory }}
         shell: bash
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -70,11 +61,16 @@ jobs:
           AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
           AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
           AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
+          AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
           FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
+          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
         run: |
-          make scheduled_tests
+          make integration_test
 
       - name: Ensure the tests did not create any additional files
+        working-directory: ${{ matrix.working-directory }}
         shell: bash
         run: |
           set -eu

.gitignore

@@ -115,13 +115,11 @@ celerybeat.pid
 # Environments
 .env
 .envrc
-.venv
-.venvs
+.venv*
+venv*
 env/
-venv/
 ENV/
 env.bak/
-venv.bak/
 
 # Spyder project settings
 .spyderproject
@@ -177,4 +175,6 @@ docs/docs/build
 docs/docs/node_modules
 docs/docs/yarn.lock
 _dist
-docs/docs/templates
+docs/docs/templates
+
+prof

Makefile

@@ -1,44 +1,56 @@
-.PHONY: all clean docs_build docs_clean docs_linkcheck api_docs_build api_docs_clean api_docs_linkcheck
+.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
 
-# Default target executed when no arguments are given to make.
+## 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.
 all: help
 
+## clean: Clean documentation and API documentation artifacts.
+clean: docs_clean api_docs_clean
 
 ######################
 # DOCUMENTATION
 ######################
 
-clean: docs_clean api_docs_clean
-
-
+## docs_build: Build the documentation.
 docs_build:
 	docs/.local_build.sh
 
+## docs_clean: Clean the documentation build artifacts.
 docs_clean:
 	@if [ -d _dist ]; then \
-			rm -r _dist; \
-			echo "Directory _dist has been cleaned."; \
+		rm -r _dist; \
+		echo "Directory _dist has been cleaned."; \
 	else \
-			echo "Nothing to clean."; \
+		echo "Nothing to clean."; \
 	fi
 
+## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
 	poetry run linkchecker _dist/docs/ --ignore-url node_modules
 
+## api_docs_build: Build the API Reference documentation.
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
 	cd docs/api_reference && poetry run make html
 
+## api_docs_clean: Clean the API Reference documentation build artifacts.
 api_docs_clean:
-	rm -f docs/api_reference/api_reference.rst
+	find ./docs/api_reference -name '*_api_reference.rst' -delete
 	cd docs/api_reference && poetry run make clean
 
+## api_docs_linkcheck: Run linkchecker on the API Reference documentation.
 api_docs_linkcheck:
 	poetry run linkchecker docs/api_reference/_build/html/index.html
 
+## spell_check: Run codespell on the project.
 spell_check:
 	poetry run codespell --toml pyproject.toml
 
+## spell_fix: Run codespell on the project and fix the errors.
 spell_fix:
 	poetry run codespell --toml pyproject.toml -w
 
@@ -46,29 +58,14 @@ spell_fix:
 # LINTING AND FORMATTING
 ######################
 
+## lint: Run linting on the project.
 lint lint_package lint_tests:
 	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:
 	poetry run ruff format docs templates cookbook
 	poetry run ruff --select I --fix docs templates cookbook
-
-######################
-# 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

@@ -34,34 +34,40 @@ conda install langchain -c conda-forge
 
 ## 🤔 What is LangChain?
 
-**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.)
+**LangChain** is a framework for developing applications powered by large language models (LLMs).
 
-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. 
+For these applications, LangChain simplifies the entire application lifecycle:
 
-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.
+- **Open-source libraries**: Build your applications using LangChain's [modular building blocks](https://python.langchain.com/docs/expression_language/) and [components](https://python.langchain.com/docs/modules/). Integrate with hundreds of [third-party providers](https://python.langchain.com/docs/integrations/platforms/).
+- **Productionization**: Inspect, monitor, and evaluate your apps with [LangSmith](https://python.langchain.com/docs/langsmith/) so that you can constantly optimize and deploy with confidence.
+- **Deployment**: Turn any chain into a REST API with [LangServe](https://python.langchain.com/docs/langserve).
 
-![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")
+### Open-source libraries
+- **`langchain-core`**: Base abstractions and LangChain Expression Language.
+- **`langchain-community`**: Third party integrations.
+  - Some integrations have been further split into **partner packages** that only rely on **`langchain-core`**. Examples include **`langchain_openai`** and **`langchain_anthropic`**.
+- **`langchain`**: Chains, agents, and retrieval strategies that make up an application's cognitive architecture.
+- **[LangGraph](https://python.langchain.com/docs/langgraph)**: A library for building robust and stateful multi-actor applications with LLMs by modeling steps as edges and nodes in a graph.
+
+### Productionization:
+- **[LangSmith](https://python.langchain.com/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
+
+### Deployment:
+- **[LangServe](https://python.langchain.com/docs/langserve)**: A library for deploying LangChain chains as REST APIs.
+
+![Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.](docs/static/svg/langchain_stack.svg "LangChain Architecture Overview")
 
 ## 🧱 What can you build with LangChain?
-**❓ Retrieval augmented generation**
+
+**❓ Question answering with RAG**
 
 - [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**
+**🧱 Extracting structured output**
 
-- [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)
+- [Documentation](https://python.langchain.com/docs/use_cases/extraction/)
+- End-to-end Example: [SQL Llama2 Template](https://github.com/langchain-ai/langchain-extract/)
 
 **🤖 Chatbots**
 
@@ -72,34 +78,51 @@ And much more! Head to the [Use cases](https://python.langchain.com/docs/use_cas
 
 ## 🚀 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
+1. **Components**: composable building blocks, tools and integrations for working with language models. Components are modular and easy-to-use, whether you are using the rest of the LangChain framework or not
 2. **Off-the-shelf chains**: built-in assemblages of components for accomplishing higher-level tasks
 
 Off-the-shelf chains make it easy to get started. Components make it easy to customize existing chains and build new ones. 
 
+## LangChain Expression Language (LCEL)
+
+LCEL is the foundation of many of LangChain's components, and is a declarative way to compose chains. LCEL was designed from day 1 to support putting prototypes in production, with no code changes, from the simplest “prompt + LLM” chain to the most complex chains.
+
+- **[Overview](https://python.langchain.com/docs/expression_language/)**: LCEL and its benefits
+- **[Interface](https://python.langchain.com/docs/expression_language/interface)**: The standard interface for LCEL objects
+- **[Primitives](https://python.langchain.com/docs/expression_language/primitives)**: More on the primitives LCEL includes
+
+## Components
+
 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.
+This includes [prompt management](https://python.langchain.com/docs/modules/model_io/prompts/), [prompt optimization](https://python.langchain.com/docs/modules/model_io/prompts/example_selectors/), a generic interface for [chat models](https://python.langchain.com/docs/modules/model_io/chat/) and [LLMs](https://python.langchain.com/docs/modules/model_io/llms/), and common utilities for working with [model outputs](https://python.langchain.com/docs/modules/model_io/output_parsers/).
 
 **📚 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.
+Retrieval Augmented Generation involves [loading data](https://python.langchain.com/docs/modules/data_connection/document_loaders/) from a variety of sources, [preparing it](https://python.langchain.com/docs/modules/data_connection/document_loaders/), [then retrieving it](https://python.langchain.com/docs/modules/data_connection/retrievers/) for use in the generation step.
 
 **🤖 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.
+Agents allow an LLM autonomy over how a task is accomplished. Agents make decisions about which Actions to take, then take that Action, observe the result, and repeat until the task is complete done. LangChain provides a [standard interface for agents](https://python.langchain.com/docs/modules/agents/), a [selection of agents](https://python.langchain.com/docs/modules/agents/agent_types/) 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
+- [Use case](https://python.langchain.com/docs/use_cases/) walkthroughs and best practice [guides](https://python.langchain.com/docs/guides/)
+- Overviews of the [interfaces](https://python.langchain.com/docs/expression_language/), [components](https://python.langchain.com/docs/modules/), and [integrations](https://python.langchain.com/docs/integrations/providers)
+
+You can also check out the full [API Reference docs](https://api.python.langchain.com).
+
+## 🌐 Ecosystem
+
+- [🦜🛠️ LangSmith](https://python.langchain.com/docs/langsmith/): Tracing and evaluating your language model applications and intelligent agents to help you move from prototype to production.
+- [🦜🕸️ LangGraph](https://python.langchain.com/docs/langgraph): Creating stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain primitives.
+- [🦜🏓 LangServe](https://python.langchain.com/docs/langserve): Deploying LangChain runnables and chains as REST APIs.
+  - [LangChain Templates](https://python.langchain.com/docs/templates/): Example applications hosted with LangServe.
 
 
 ## 💁 Contributing

SECURITY.md

@@ -1,6 +1,61 @@
 # Security Policy
 
-## Reporting a Vulnerability
+## Reporting OSS Vulnerabilities
 
-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.
+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) LangChain [security guidelines](https://python.langchain.com/docs/security) 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, bug reports to it will be marked as interesting or waste of
+  time and published with no bounty attached.
+- **tools**: Tools in either langchain or langchain-community are not eligible for bug
+  bounties. This includes the following directories
+  - langchain/tools
+  - langchain-community/tools
+  - Please review our [security guidelines](https://python.langchain.com/docs/security)
+    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 below.
+
+## 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`.

cookbook/Gemma_LangChain.ipynb

@@ -0,0 +1,932 @@
+{
+ "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 it 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](https://python.langchain.com/docs/integrations/chat/ollama) for details on installation and setup.\n",
+    "See [here](/docs/integrations/chat/ollama) for details on installation and setup.\n",
     "\n",
-    "Also, see [here](https://python.langchain.com/docs/guides/local_llms) for our full guide on local LLMs.\n",
+    "Also, see [here](/docs/guides/development/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

@@ -116,7 +116,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "from unstructured.partition.pdf import partition_pdf\n",
     "\n",
     "\n",

cookbook/README.md

@@ -8,6 +8,7 @@ Notebook | Description
 [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.

cookbook/Semi_structured_multi_modal_RAG_LLaMA2.ipynb

@@ -191,15 +191,15 @@
    "source": [
     "## Multi-vector retriever\n",
     "\n",
-    "Use [multi-vector-retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector#summary).\n",
+    "Use [multi-vector-retriever](/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.ai to run LLaMA2 locally. \n",
+    "Here, we use Ollama to run LLaMA2 locally. \n",
     "\n",
-    "See details on installation [here](https://python.langchain.com/docs/guides/local_llms)."
+    "See details on installation [here](/docs/guides/development/local_llms)."
    ]
   },
   {

cookbook/advanced_rag_eval.ipynb

@@ -68,7 +68,7 @@
     "pdf_pages = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
     "all_splits_pypdf = text_splitter.split_documents(pdf_pages)\n",
@@ -520,7 +520,7 @@
    "source": [
     "import re\n",
     "\n",
-    "from langchain.schema import Document\n",
+    "from langchain_core.documents import Document\n",
     "from langchain_core.runnables import RunnableLambda\n",
     "\n",
     "\n",

cookbook/agent_vectorstore.ipynb

@@ -28,9 +28,9 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\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

@@ -0,0 +1,200 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install -qU langchain-airbyte"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "\n",
+    "GITHUB_TOKEN = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_airbyte import AirbyteLoader\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "\n",
+    "loader = AirbyteLoader(\n",
+    "    source=\"source-github\",\n",
+    "    stream=\"pull_requests\",\n",
+    "    config={\n",
+    "        \"credentials\": {\"personal_access_token\": GITHUB_TOKEN},\n",
+    "        \"repositories\": [\"langchain-ai/langchain\"],\n",
+    "    },\n",
+    "    template=PromptTemplate.from_template(\n",
+    "        \"\"\"# {title}\n",
+    "by {user[login]}\n",
+    "\n",
+    "{body}\"\"\"\n",
+    "    ),\n",
+    "    include_metadata=False,\n",
+    ")\n",
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "# Updated partners/ibm README\n",
+      "by williamdevena\n",
+      "\n",
+      "## PR title\n",
+      "partners: changed the README file for the IBM Watson AI integration in the libs/partners/ibm folder.\n",
+      "\n",
+      "## PR message\n",
+      "Description: Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\n",
+      "\n",
+      "The README includes:\n",
+      "\n",
+      "- Brief description\n",
+      "- Installation\n",
+      "- Setting-up instructions (API key, project id, ...)\n",
+      "- Basic usage:\n",
+      "  - Loading the model\n",
+      "  - Direct inference\n",
+      "  - Chain invoking\n",
+      "  - Streaming the model output\n",
+      "  \n",
+      "Issue: https://github.com/langchain-ai/langchain/issues/17545\n",
+      "\n",
+      "Dependencies: None\n",
+      "\n",
+      "Twitter handle: None\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(docs[-2].page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "10283"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(docs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import tiktoken\n",
+    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "enc = tiktoken.get_encoding(\"cl100k_base\")\n",
+    "\n",
+    "vectorstore = Chroma.from_documents(\n",
+    "    docs,\n",
+    "    embedding=OpenAIEmbeddings(\n",
+    "        disallowed_special=(enc.special_tokens_set - {\"<|endofprompt|>\"})\n",
+    "    ),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vectorstore.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='# Updated partners/ibm README\\nby williamdevena\\n\\n## PR title\\r\\npartners: changed the README file for the IBM Watson AI integration in the libs/partners/ibm folder.\\r\\n\\r\\n## PR message\\r\\nDescription: Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\\r\\n\\r\\nThe README includes:\\r\\n\\r\\n- Brief description\\r\\n- Installation\\r\\n- Setting-up instructions (API key, project id, ...)\\r\\n- Basic usage:\\r\\n  - Loading the model\\r\\n  - Direct inference\\r\\n  - Chain invoking\\r\\n  - Streaming the model output\\r\\n  \\r\\nIssue: https://github.com/langchain-ai/langchain/issues/17545\\r\\n\\r\\nDependencies: None\\r\\n\\r\\nTwitter handle: None'),\n",
+       " Document(page_content='# Updated partners/ibm README\\nby williamdevena\\n\\n## PR title\\r\\npartners: changed the README file for the IBM Watson AI integration in the `libs/partners/ibm` folder. \\r\\n\\r\\n\\r\\n\\r\\n## PR message\\r\\n- **Description:** Changed the README file of partners/ibm following the docs on https://python.langchain.com/docs/integrations/llms/ibm_watsonx\\r\\n\\r\\n    The README includes:\\r\\n    - Brief description\\r\\n    - Installation\\r\\n    - Setting-up instructions (API key, project id, ...)\\r\\n    - Basic usage:\\r\\n        - Loading the model\\r\\n        - Direct inference\\r\\n        - Chain invoking\\r\\n        - Streaming the model output\\r\\n\\r\\n\\r\\n- **Issue:** #17545\\r\\n- **Dependencies:** None\\r\\n- **Twitter handle:** None'),\n",
+       " Document(page_content='# IBM: added partners package `langchain_ibm`, added llm\\nby MateuszOssGit\\n\\n  - **Description:** Added `langchain_ibm` as an langchain partners package of IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) LLM provider (`WatsonxLLM`)\\r\\n  - **Dependencies:** [ibm-watsonx-ai](https://pypi.org/project/ibm-watsonx-ai/),\\r\\n  - **Tag maintainer:** : \\r\\n\\r\\nPlease make sure your PR is passing linting and testing before submitting. Run `make format`, `make lint` and `make test` to check this locally. ✅'),\n",
+       " Document(page_content='# Add WatsonX support\\nby baptistebignaud\\n\\nIt is a connector to use a LLM from WatsonX.\\r\\nIt requires python SDK \"ibm-generative-ai\"\\r\\n\\r\\n(It might not be perfect since it is my first PR on a public repository 😄)')]"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.invoke(\"pull requests related to IBM\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "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": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

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 nework.\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",
     "\n",
-    "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)."
+    "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)."
    ]
   },
   {
@@ -167,7 +167,7 @@
     "from langchain.llms import LlamaCpp\n",
     "from langchain.memory import ConversationTokenBufferMemory\n",
     "from langchain.prompts import PromptTemplate, load_prompt\n",
-    "from langchain.schema import SystemMessage\n",
+    "from langchain_core.messages import SystemMessage\n",
     "from langchain_experimental.chat_models import Llama2Chat\n",
     "from quixstreams import Application, State, message_key\n",
     "\n",
@@ -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 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."
+    "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."
    ]
   },
   {
@@ -272,7 +272,7 @@
    },
    "outputs": [],
    "source": [
-    "# Load the model with the apporiate parameters:\n",
+    "# Load the model with the appropriate 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, 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",
+    "  * **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",
     "\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

@@ -40,7 +40,9 @@
     "import nest_asyncio\n",
     "import pandas as pd\n",
     "from langchain.docstore.document import Document\n",
-    "from langchain_community.agent_toolkits.pandas.base import create_pandas_dataframe_agent\n",
+    "from langchain_experimental.agents.agent_toolkits.pandas.base import (\n",
+    "    create_pandas_dataframe_agent,\n",
+    ")\n",
     "from langchain_experimental.autonomous_agents import AutoGPT\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
@@ -57,7 +59,7 @@
    },
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=1.0)"
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=1.0)"
    ]
   },
   {
@@ -227,8 +229,8 @@
     "    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/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_splitter.CharacterTextSplitter`.\n",
+    "   2. Split all documents to chunks using the `langchain_text_splitters.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",
@@ -621,7 +621,7 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "texts = text_splitter.split_documents(docs)\n",
@@ -933,7 +933,7 @@
       "**Answer**: The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureCognitiveSearchRetriever\n",
+      "- AzureAISearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",
@@ -993,7 +993,7 @@
     {
      "data": {
       "text/plain": [
-       "{'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'}"
+       "{'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'}"
       ]
      },
      "execution_count": 31,
@@ -1117,7 +1117,7 @@
       "The LangChain class includes various types of retrievers such as:\n",
       "\n",
       "- ArxivRetriever\n",
-      "- AzureCognitiveSearchRetriever\n",
+      "- AzureAISearchRetriever\n",
       "- BM25Retriever\n",
       "- ChaindeskRetriever\n",
       "- ChatGPTPluginRetriever\n",

cookbook/custom_agent_with_plugin_retrieval.ipynb

@@ -42,9 +42,9 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.prompts import StringPromptTemplate\n",
-    "from langchain.schema import AgentAction, AgentFinish\n",
     "from langchain_community.agent_toolkits import NLAToolkit\n",
     "from langchain_community.tools.plugin import AIPlugin\n",
+    "from langchain_core.agents import AgentAction, AgentFinish\n",
     "from langchain_openai import OpenAI"
    ]
   },
@@ -114,8 +114,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.schema import Document\n",
     "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings"
    ]
   },

cookbook/custom_agent_with_plugin_retrieval_using_plugnplai.ipynb

@@ -67,9 +67,9 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.prompts import StringPromptTemplate\n",
-    "from langchain.schema import AgentAction, AgentFinish\n",
     "from langchain_community.agent_toolkits import NLAToolkit\n",
     "from langchain_community.tools.plugin import AIPlugin\n",
+    "from langchain_core.agents import AgentAction, AgentFinish\n",
     "from langchain_openai import OpenAI"
    ]
   },
@@ -138,8 +138,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.schema import Document\n",
     "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings"
    ]
   },

cookbook/custom_agent_with_tool_retrieval.ipynb

@@ -40,8 +40,8 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.prompts import StringPromptTemplate\n",
-    "from langchain.schema import AgentAction, AgentFinish\n",
     "from langchain_community.utilities import SerpAPIWrapper\n",
+    "from langchain_core.agents import AgentAction, AgentFinish\n",
     "from langchain_openai import OpenAI"
    ]
   },
@@ -103,8 +103,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.schema import Document\n",
     "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_core.documents import Document\n",
     "from langchain_openai import OpenAIEmbeddings"
    ]
   },

cookbook/custom_multi_action_agent.ipynb

@@ -72,7 +72,7 @@
    "source": [
     "from typing import Any, List, Tuple, Union\n",
     "\n",
-    "from langchain.schema import AgentAction, AgentFinish\n",
+    "from langchain_core.agents import AgentAction, AgentFinish\n",
     "\n",
     "\n",
     "class FakeAgent(BaseMultiActionAgent):\n",

cookbook/deeplake_semantic_search_over_chat.ipynb

@@ -52,12 +52,12 @@
     "import os\n",
     "\n",
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import (\n",
+    "from langchain_community.vectorstores import DeepLake\n",
+    "from langchain_openai import OpenAI, OpenAIEmbeddings\n",
+    "from langchain_text_splitters 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/elasticsearch_db_qa.ipynb

@@ -84,7 +84,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
     "chain = ElasticsearchDatabaseChain.from_llm(llm=llm, database=db, verbose=True)"
    ]
   },

cookbook/fake_llm.ipynb

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

cookbook/fireworks_rag.ipynb

@@ -0,0 +1,245 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0fc0309d-4d49-4bb5-bec0-bd92c6fddb28",
+   "metadata": {},
+   "source": [
+    "## Fireworks.AI + LangChain + RAG\n",
+    " \n",
+    "[Fireworks AI](https://python.langchain.com/docs/integrations/llms/fireworks) wants to provide the best experience when working with LangChain, and here is an example of Fireworks + LangChain doing RAG\n",
+    "\n",
+    "See [our models page](https://fireworks.ai/models) for the full list of models. We use `accounts/fireworks/models/mixtral-8x7b-instruct` for RAG In this tutorial.\n",
+    "\n",
+    "For the RAG target, we will use the Gemma technical report https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d12fb75a-f707-48d5-82a5-efe2d041813c",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n",
+      "Found existing installation: langchain-fireworks 0.0.1\n",
+      "Uninstalling langchain-fireworks-0.0.1:\n",
+      "  Successfully uninstalled langchain-fireworks-0.0.1\n",
+      "Note: you may need to restart the kernel to use updated packages.\n",
+      "Obtaining file:///mnt/disks/data/langchain/libs/partners/fireworks\n",
+      "  Installing build dependencies ... \u001b[?25ldone\n",
+      "\u001b[?25h  Checking if build backend supports build_editable ... \u001b[?25ldone\n",
+      "\u001b[?25h  Getting requirements to build editable ... \u001b[?25ldone\n",
+      "\u001b[?25h  Preparing editable metadata (pyproject.toml) ... \u001b[?25ldone\n",
+      "\u001b[?25hRequirement already satisfied: aiohttp<4.0.0,>=3.9.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (3.9.3)\n",
+      "Requirement already satisfied: fireworks-ai<0.13.0,>=0.12.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (0.12.0)\n",
+      "Requirement already satisfied: langchain-core<0.2,>=0.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (0.1.23)\n",
+      "Requirement already satisfied: requests<3,>=2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-fireworks==0.0.1) (2.31.0)\n",
+      "Requirement already satisfied: aiosignal>=1.1.2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (1.3.1)\n",
+      "Requirement already satisfied: attrs>=17.3.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (23.1.0)\n",
+      "Requirement already satisfied: frozenlist>=1.1.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (1.4.0)\n",
+      "Requirement already satisfied: multidict<7.0,>=4.5 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (6.0.4)\n",
+      "Requirement already satisfied: yarl<2.0,>=1.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (1.9.2)\n",
+      "Requirement already satisfied: async-timeout<5.0,>=4.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from aiohttp<4.0.0,>=3.9.1->langchain-fireworks==0.0.1) (4.0.3)\n",
+      "Requirement already satisfied: httpx in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.26.0)\n",
+      "Requirement already satisfied: httpx-sse in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.4.0)\n",
+      "Requirement already satisfied: pydantic in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (2.4.2)\n",
+      "Requirement already satisfied: Pillow in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (10.2.0)\n",
+      "Requirement already satisfied: PyYAML>=5.3 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (6.0.1)\n",
+      "Requirement already satisfied: anyio<5,>=3 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (3.7.1)\n",
+      "Requirement already satisfied: jsonpatch<2.0,>=1.33 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (1.33)\n",
+      "Requirement already satisfied: langsmith<0.2.0,>=0.1.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (0.1.5)\n",
+      "Requirement already satisfied: packaging<24.0,>=23.2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (23.2)\n",
+      "Requirement already satisfied: tenacity<9.0.0,>=8.1.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (8.2.3)\n",
+      "Requirement already satisfied: charset-normalizer<4,>=2 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (3.3.0)\n",
+      "Requirement already satisfied: idna<4,>=2.5 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (3.4)\n",
+      "Requirement already satisfied: urllib3<3,>=1.21.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (2.0.6)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from requests<3,>=2->langchain-fireworks==0.0.1) (2023.7.22)\n",
+      "Requirement already satisfied: sniffio>=1.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (1.3.0)\n",
+      "Requirement already satisfied: exceptiongroup in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from anyio<5,>=3->langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (1.1.3)\n",
+      "Requirement already satisfied: jsonpointer>=1.9 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from jsonpatch<2.0,>=1.33->langchain-core<0.2,>=0.1->langchain-fireworks==0.0.1) (2.4)\n",
+      "Requirement already satisfied: annotated-types>=0.4.0 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from pydantic->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.5.0)\n",
+      "Requirement already satisfied: pydantic-core==2.10.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from pydantic->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (2.10.1)\n",
+      "Requirement already satisfied: typing-extensions>=4.6.1 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from pydantic->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (4.8.0)\n",
+      "Requirement already satisfied: httpcore==1.* in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from httpx->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (1.0.2)\n",
+      "Requirement already satisfied: h11<0.15,>=0.13 in /mnt/disks/data/langchain/.venv/lib/python3.9/site-packages (from httpcore==1.*->httpx->fireworks-ai<0.13.0,>=0.12.0->langchain-fireworks==0.0.1) (0.14.0)\n",
+      "Building wheels for collected packages: langchain-fireworks\n",
+      "  Building editable for langchain-fireworks (pyproject.toml) ... \u001b[?25ldone\n",
+      "\u001b[?25h  Created wheel for langchain-fireworks: filename=langchain_fireworks-0.0.1-py3-none-any.whl size=2228 sha256=564071b120b09ec31f2dc737733448a33bbb26e40b49fcde0c129ad26045259d\n",
+      "  Stored in directory: /tmp/pip-ephem-wheel-cache-oz368vdk/wheels/e0/ad/31/d7e76dd73d61905ff7f369f5b0d21a4b5e7af4d3cb7487aece\n",
+      "Successfully built langchain-fireworks\n",
+      "Installing collected packages: langchain-fireworks\n",
+      "Successfully installed langchain-fireworks-0.0.1\n",
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
+     ]
+    }
+   ],
+   "source": [
+    "%pip install --quiet pypdf chromadb tiktoken openai \n",
+    "%pip uninstall -y langchain-fireworks\n",
+    "%pip install --editable /mnt/disks/data/langchain/libs/partners/fireworks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "cf719376",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<module 'fireworks' from '/mnt/disks/data/langchain/.venv/lib/python3.9/site-packages/fireworks/__init__.py'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "import fireworks\n",
+    "\n",
+    "print(fireworks)\n",
+    "import fireworks.client"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ab49327-0532-4480-804c-d066c302a322",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load\n",
+    "import requests\n",
+    "from langchain_community.document_loaders import PyPDFLoader\n",
+    "\n",
+    "# Download the PDF from a URL and save it to a temporary location\n",
+    "url = \"https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf\"\n",
+    "response = requests.get(url, stream=True)\n",
+    "file_name = \"temp_file.pdf\"\n",
+    "with open(file_name, \"wb\") as pdf:\n",
+    "    pdf.write(response.content)\n",
+    "\n",
+    "loader = PyPDFLoader(file_name)\n",
+    "data = loader.load()\n",
+    "\n",
+    "# Split\n",
+    "from langchain_text_splitters 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_community.vectorstores import Chroma\n",
+    "from langchain_fireworks.embeddings import FireworksEmbeddings\n",
+    "\n",
+    "vectorstore = Chroma.from_documents(\n",
+    "    documents=all_splits,\n",
+    "    collection_name=\"rag-chroma\",\n",
+    "    embedding=FireworksEmbeddings(),\n",
+    ")\n",
+    "\n",
+    "retriever = vectorstore.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4efaddd9-3dbb-455c-ba54-0ad7f2d2ce0f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.pydantic_v1 import BaseModel\n",
+    "from langchain_core.runnables import RunnableParallel, RunnablePassthrough\n",
+    "\n",
+    "# RAG prompt\n",
+    "template = \"\"\"Answer the question based only on the following context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "\n",
+    "# LLM\n",
+    "from langchain_together import Together\n",
+    "\n",
+    "llm = Together(\n",
+    "    model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\",\n",
+    "    temperature=0.0,\n",
+    "    max_tokens=2000,\n",
+    "    top_k=1,\n",
+    ")\n",
+    "\n",
+    "# RAG chain\n",
+    "chain = (\n",
+    "    RunnableParallel({\"context\": retriever, \"question\": RunnablePassthrough()})\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "88b1ee51-1b0f-4ebf-bb32-e50e843f0eeb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\nAnswer: The architectural details of Mixtral are as follows:\\n- Dimension (dim): 4096\\n- Number of layers (n\\\\_layers): 32\\n- Dimension of each head (head\\\\_dim): 128\\n- Hidden dimension (hidden\\\\_dim): 14336\\n- Number of heads (n\\\\_heads): 32\\n- Number of kv heads (n\\\\_kv\\\\_heads): 8\\n- Context length (context\\\\_len): 32768\\n- Vocabulary size (vocab\\\\_size): 32000\\n- Number of experts (num\\\\_experts): 8\\n- Number of top k experts (top\\\\_k\\\\_experts): 2\\n\\nMixtral is based on a transformer architecture and uses the same modifications as described in [18], with the notable exceptions that Mixtral supports a fully dense context length of 32k tokens, and the feedforward block picks from a set of 8 distinct groups of parameters. At every layer, for every token, a router network chooses two of these groups (the “experts”) to process the token and combine their output additively. This technique increases the number of parameters of a model while controlling cost and latency, as the model only uses a fraction of the total set of parameters per token. Mixtral is pretrained with multilingual data using a context size of 32k tokens. It either matches or exceeds the performance of Llama 2 70B and GPT-3.5, over several benchmarks. In particular, Mixtral vastly outperforms Llama 2 70B on mathematics, code generation, and multilingual benchmarks.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"What are the Architectural details of Mixtral?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "755cf871-26b7-4e30-8b91-9ffd698470f4",
+   "metadata": {},
+   "source": [
+    "Trace: \n",
+    "\n",
+    "https://smith.langchain.com/public/935fd642-06a6-4b42-98e3-6074f93115cd/r"
+   ]
+  }
+ ],
+ "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": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -73,8 +73,9 @@
     "    AsyncCallbackManagerForRetrieverRun,\n",
     "    CallbackManagerForRetrieverRun,\n",
     ")\n",
-    "from langchain.schema import BaseRetriever, Document\n",
     "from langchain_community.utilities import GoogleSerperAPIWrapper\n",
+    "from langchain_core.documents import Document\n",
+    "from langchain_core.retrievers import BaseRetriever\n",
     "from langchain_openai import ChatOpenAI, OpenAI"
    ]
   },

cookbook/hypothetical_document_embeddings.ipynb

@@ -170,8 +170,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_text_splitters import CharacterTextSplitter\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.run(text)"
+    "bash_chain.invoke(text)"
    ]
   },
   {
@@ -135,7 +135,7 @@
     "\n",
     "text = \"Please write a bash script that prints 'Hello World' to the console.\"\n",
     "\n",
-    "bash_chain.run(text)"
+    "bash_chain.invoke(text)"
    ]
   },
   {
@@ -190,7 +190,7 @@
     "\n",
     "text = \"List the current directory then move up a level.\"\n",
     "\n",
-    "bash_chain.run(text)"
+    "bash_chain.invoke(text)"
    ]
   },
   {
@@ -231,7 +231,7 @@
    ],
    "source": [
     "# Run the same command again and see that the state is maintained between calls\n",
-    "bash_chain.run(text)"
+    "bash_chain.invoke(text)"
    ]
   }
  ],

cookbook/llm_checker.ipynb

@@ -50,7 +50,7 @@
     "\n",
     "checker_chain = LLMCheckerChain.from_llm(llm, verbose=True)\n",
     "\n",
-    "checker_chain.run(text)"
+    "checker_chain.invoke(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.run(\"What is 13 raised to the .3432 power?\")"
+    "llm_math.invoke(\"What is 13 raised to the .3432 power?\")"
    ]
   },
   {

cookbook/llm_symbolic_math.ipynb

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

cookbook/mongodb-langchain-cache-memory.ipynb

@@ -0,0 +1,818 @@
+{
+ "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[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "os.environ[\"LANGCHAIN_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 enviornment:\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/nomic_embedding_rag.ipynb

@@ -124,7 +124,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter.from_tiktoken_encoder(\n",
     "    chunk_size=7500, chunk_overlap=100\n",

cookbook/openai_functions_retrieval_qa.ipynb

@@ -20,10 +20,10 @@
    "outputs": [],
    "source": [
     "from langchain.chains import RetrievalQA\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain_community.document_loaders import TextLoader\n",
     "from langchain_community.vectorstores import Chroma\n",
-    "from langchain_openai import OpenAIEmbeddings"
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "from langchain_text_splitters import CharacterTextSplitter"
    ]
   },
   {
@@ -358,7 +358,7 @@
     "\n",
     "from langchain.chains.openai_functions import create_qa_with_structure_chain\n",
     "from langchain.prompts.chat import ChatPromptTemplate, HumanMessagePromptTemplate\n",
-    "from langchain.schema import HumanMessage, SystemMessage\n",
+    "from langchain_core.messages import HumanMessage, SystemMessage\n",
     "from pydantic import BaseModel, Field"
    ]
   },

cookbook/optimization.ipynb

@@ -0,0 +1,648 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c7fe38bc",
+   "metadata": {},
+   "source": [
+    "# Optimization\n",
+    "\n",
+    "This notebook goes over how to optimize chains using LangChain and [LangSmith](https://smith.langchain.com)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f87ccd5",
+   "metadata": {},
+   "source": [
+    "## Set up\n",
+    "\n",
+    "We will set an environment variable for LangSmith, and load the relevant data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "236bedc5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"LANGCHAIN_PROJECT\"] = \"movie-qa\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a3fed0dd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "7cfff337",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"data/imdb_top_1000.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2d20fb9c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df[\"Released_Year\"] = df[\"Released_Year\"].astype(int, errors=\"ignore\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09fc8fe2",
+   "metadata": {},
+   "source": [
+    "## Create the initial retrieval chain\n",
+    "\n",
+    "We will use a self-query retriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "f71e24e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.schema import Document\n",
+    "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_openai import OpenAIEmbeddings\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8881ea8e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "records = df.to_dict(\"records\")\n",
+    "documents = [Document(page_content=d[\"Overview\"], metadata=d) for d in records]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "8f495423",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vectorstore = Chroma.from_documents(documents, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "31d33d62",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains.query_constructor.base import AttributeInfo\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "metadata_field_info = [\n",
+    "    AttributeInfo(\n",
+    "        name=\"Released_Year\",\n",
+    "        description=\"The year the movie was released\",\n",
+    "        type=\"int\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"Series_Title\",\n",
+    "        description=\"The title of the movie\",\n",
+    "        type=\"str\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"Genre\",\n",
+    "        description=\"The genre of the movie\",\n",
+    "        type=\"string\",\n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"IMDB_Rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
+    "    ),\n",
+    "]\n",
+    "document_content_description = \"Brief summary of a movie\"\n",
+    "llm = ChatOpenAI(temperature=0)\n",
+    "retriever = SelfQueryRetriever.from_llm(\n",
+    "    llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "a731533b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnablePassthrough"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "05181849",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "feed4be6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"\"\"Answer the user's question based on the below information:\n",
+    "\n",
+    "Information:\n",
+    "\n",
+    "{info}\n",
+    "\n",
+    "Question: {question}\"\"\"\n",
+    ")\n",
+    "generator = (prompt | ChatOpenAI() | StrOutputParser()).with_config(\n",
+    "    run_name=\"generator\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "eb16cc9a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = (\n",
+    "    RunnablePassthrough.assign(info=(lambda x: x[\"question\"]) | retriever) | generator\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c70911cc",
+   "metadata": {},
+   "source": [
+    "## Run examples\n",
+    "\n",
+    "Run examples through the chain. This can either be manually, or using a list of examples, or production traffic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "19a88d13",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'One of the horror movies released in the early 2000s is \"The Ring\" (2002), directed by Gore Verbinski.'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"question\": \"what is a horror movie released in early 2000s\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "17f9cdae",
+   "metadata": {},
+   "source": [
+    "## Annotate\n",
+    "\n",
+    "Now, go to LangSmitha and annotate those examples as correct or incorrect"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5e211da6",
+   "metadata": {},
+   "source": [
+    "## Create Dataset\n",
+    "\n",
+    "We can now create a dataset from those runs.\n",
+    "\n",
+    "What we will do is find the runs marked as correct, then grab the sub-chains from them. Specifically, the query generator sub chain and the final generation step"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "e4024267",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langsmith import Client\n",
+    "\n",
+    "client = Client()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "3814efc5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "14"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "runs = list(\n",
+    "    client.list_runs(\n",
+    "        project_name=\"movie-qa\",\n",
+    "        execution_order=1,\n",
+    "        filter=\"and(eq(feedback_key, 'correctness'), eq(feedback_score, 1))\",\n",
+    "    )\n",
+    ")\n",
+    "\n",
+    "len(runs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "3eb123e0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gen_runs = []\n",
+    "query_runs = []\n",
+    "for r in runs:\n",
+    "    gen_runs.extend(\n",
+    "        list(\n",
+    "            client.list_runs(\n",
+    "                project_name=\"movie-qa\",\n",
+    "                filter=\"eq(name, 'generator')\",\n",
+    "                trace_id=r.trace_id,\n",
+    "            )\n",
+    "        )\n",
+    "    )\n",
+    "    query_runs.extend(\n",
+    "        list(\n",
+    "            client.list_runs(\n",
+    "                project_name=\"movie-qa\",\n",
+    "                filter=\"eq(name, 'query_constructor')\",\n",
+    "                trace_id=r.trace_id,\n",
+    "            )\n",
+    "        )\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "a4397026",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'what is a high school comedy released in early 2000s'}"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "runs[0].inputs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "3fa6ad2a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'output': 'One high school comedy released in the early 2000s is \"Mean Girls\" starring Lindsay Lohan, Rachel McAdams, and Tina Fey.'}"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "runs[0].outputs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "1fda5b4b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'query': 'what is a high school comedy released in early 2000s'}"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query_runs[0].inputs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "1a1a51e6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'output': {'query': 'high school comedy',\n",
+       "  'filter': {'operator': 'and',\n",
+       "   'arguments': [{'comparator': 'eq', 'attribute': 'Genre', 'value': 'comedy'},\n",
+       "    {'operator': 'and',\n",
+       "     'arguments': [{'comparator': 'gte',\n",
+       "       'attribute': 'Released_Year',\n",
+       "       'value': 2000},\n",
+       "      {'comparator': 'lt', 'attribute': 'Released_Year', 'value': 2010}]}]}}}"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "query_runs[0].outputs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "e9d9966b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'what is a high school comedy released in early 2000s',\n",
+       " 'info': []}"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gen_runs[0].inputs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "bc113f3d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'output': 'One high school comedy released in the early 2000s is \"Mean Girls\" starring Lindsay Lohan, Rachel McAdams, and Tina Fey.'}"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "gen_runs[0].outputs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6cca74e5",
+   "metadata": {},
+   "source": [
+    "## Create datasets\n",
+    "\n",
+    "We can now create datasets for the query generation and final generation step.\n",
+    "We do this so that (1) we can inspect the datapoints, (2) we can edit them if needed, (3) we can add to them over time"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "69966f0e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "client.create_dataset(\"movie-query_constructor\")\n",
+    "\n",
+    "inputs = [r.inputs for r in query_runs]\n",
+    "outputs = [r.outputs for r in query_runs]\n",
+    "\n",
+    "client.create_examples(\n",
+    "    inputs=inputs, outputs=outputs, dataset_name=\"movie-query_constructor\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "7e15770e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "client.create_dataset(\"movie-generator\")\n",
+    "\n",
+    "inputs = [r.inputs for r in gen_runs]\n",
+    "outputs = [r.outputs for r in gen_runs]\n",
+    "\n",
+    "client.create_examples(inputs=inputs, outputs=outputs, dataset_name=\"movie-generator\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61cf9bcd",
+   "metadata": {},
+   "source": [
+    "## Use as few shot examples\n",
+    "\n",
+    "We can now pull down a dataset and use them as few shot examples in a future chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "d9c79173",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "examples = list(client.list_examples(dataset_name=\"movie-query_constructor\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "a1771dd0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "\n",
+    "def filter_to_string(_filter):\n",
+    "    if \"operator\" in _filter:\n",
+    "        args = [filter_to_string(f) for f in _filter[\"arguments\"]]\n",
+    "        return f\"{_filter['operator']}({','.join(args)})\"\n",
+    "    else:\n",
+    "        comparator = _filter[\"comparator\"]\n",
+    "        attribute = json.dumps(_filter[\"attribute\"])\n",
+    "        value = json.dumps(_filter[\"value\"])\n",
+    "        return f\"{comparator}({attribute}, {value})\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "e67a3530",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_examples = []\n",
+    "\n",
+    "for e in examples:\n",
+    "    if \"filter\" in e.outputs[\"output\"]:\n",
+    "        string_filter = filter_to_string(e.outputs[\"output\"][\"filter\"])\n",
+    "    else:\n",
+    "        string_filter = \"NO_FILTER\"\n",
+    "    model_examples.append(\n",
+    "        (\n",
+    "            e.inputs[\"query\"],\n",
+    "            {\"query\": e.outputs[\"output\"][\"query\"], \"filter\": string_filter},\n",
+    "        )\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "84593135",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever1 = SelfQueryRetriever.from_llm(\n",
+    "    llm,\n",
+    "    vectorstore,\n",
+    "    document_content_description,\n",
+    "    metadata_field_info,\n",
+    "    verbose=True,\n",
+    "    chain_kwargs={\"examples\": model_examples},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "4ec9bb92",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain1 = (\n",
+    "    RunnablePassthrough.assign(info=(lambda x: x[\"question\"]) | retriever1) | generator\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "64eb88e2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'1. \"Saving Private Ryan\" (1998) - Directed by Steven Spielberg, this war film follows a group of soldiers during World War II as they search for a missing paratrooper.\\n\\n2. \"The Matrix\" (1999) - Directed by the Wachowskis, this science fiction action film follows a computer hacker who discovers the truth about the reality he lives in.\\n\\n3. \"Lethal Weapon 4\" (1998) - Directed by Richard Donner, this action-comedy film follows two mismatched detectives as they investigate a Chinese immigrant smuggling ring.\\n\\n4. \"The Fifth Element\" (1997) - Directed by Luc Besson, this science fiction action film follows a cab driver who must protect a mysterious woman who holds the key to saving the world.\\n\\n5. \"The Rock\" (1996) - Directed by Michael Bay, this action thriller follows a group of rogue military men who take over Alcatraz and threaten to launch missiles at San Francisco.'"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain1.invoke(\n",
+    "    {\"question\": \"what are good action movies made before 2000 but after 1997?\"}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e1ee8b55",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/press_releases.ipynb

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

cookbook/qianfan_baidu_elasticesearch_RAG.ipynb

@@ -59,13 +59,13 @@
     "from baidubce.auth.bce_credentials import BceCredentials\n",
     "from baidubce.bce_client_configuration import BceClientConfiguration\n",
     "from langchain.chains.retrieval_qa import RetrievalQA\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders.baiducloud_bos_directory import (\n",
     "    BaiduBOSDirectoryLoader,\n",
     ")\n",
     "from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings\n",
     "from langchain_community.llms.baidu_qianfan_endpoint import QianfanLLMEndpoint\n",
-    "from langchain_community.vectorstores import BESVectorStore"
+    "from langchain_community.vectorstores import BESVectorStore\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter"
    ]
   },
   {

cookbook/rag_fusion.ipynb

@@ -19,7 +19,9 @@
    "source": [
     "## Setup\n",
     "\n",
-    "For this example, we will use Pinecone and some fake data"
+    "For this example, we will use Pinecone and some fake data. To configure Pinecone, set the following environment variable:\n",
+    "\n",
+    "- `PINECONE_API_KEY`: Your Pinecone API key"
    ]
   },
   {
@@ -29,11 +31,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pinecone\n",
-    "from langchain_community.vectorstores import Pinecone\n",
     "from langchain_openai import OpenAIEmbeddings\n",
-    "\n",
-    "pinecone.init(api_key=\"...\", environment=\"...\")"
+    "from langchain_pinecone import PineconeVectorStore"
    ]
   },
   {
@@ -64,7 +63,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "vectorstore = Pinecone.from_texts(\n",
+    "vectorstore = PineconeVectorStore.from_texts(\n",
     "    list(all_documents.values()), OpenAIEmbeddings(), index_name=\"rag-fusion\"\n",
     ")"
    ]
@@ -162,7 +161,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "vectorstore = Pinecone.from_existing_index(\"rag-fusion\", OpenAIEmbeddings())\n",
+    "vectorstore = PineconeVectorStore.from_existing_index(\"rag-fusion\", OpenAIEmbeddings())\n",
     "retriever = vectorstore.as_retriever()"
    ]
   },

cookbook/rag_with_quantized_embeddings.ipynb

@@ -36,9 +36,6 @@
     "from bs4 import BeautifulSoup as Soup\n",
     "from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
     "from langchain.storage import InMemoryByteStore, LocalFileStore\n",
-    "\n",
-    "# For our example, we'll load docs from the web\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter  # noqa\n",
     "from langchain_community.document_loaders.recursive_url_loader import (\n",
     "    RecursiveUrlLoader,\n",
     ")\n",
@@ -46,6 +43,9 @@
     "# noqa\n",
     "from langchain_community.vectorstores import Chroma\n",
     "\n",
+    "# For our example, we'll load docs from the web\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter  # noqa\n",
+    "\n",
     "DOCSTORE_DIR = \".\"\n",
     "DOCSTORE_ID_KEY = \"doc_id\""
    ]

cookbook/retrieval_in_sql.ipynb

@@ -274,7 +274,7 @@
     "db = SQLDatabase.from_uri(\n",
     "    CONNECTION_STRING\n",
     ")  # We reconnect to db so the new columns are loaded as well.\n",
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)\n",
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)\n",
     "\n",
     "sql_query_chain = (\n",
     "    RunnablePassthrough.assign(schema=get_schema)\n",

cookbook/rewrite.ipynb

@@ -245,7 +245,7 @@
     "\n",
     "\n",
     "def _parse(text):\n",
-    "    return text.strip(\"**\")"
+    "    return text.strip('\"').strip(\"**\")"
    ]
   },
   {

cookbook/sales_agent_with_context.ipynb

@@ -1,28 +1,32 @@
 {
  "cells": [
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# SalesGPT - Your Context-Aware AI Sales Assistant With Knowledge Base\n",
+    "# SalesGPT - Context-Aware AI Sales Assistant With Knowledge Base and Ability Generate Stripe Payment Links\n",
     "\n",
-    "This notebook demonstrates an implementation of a **Context-Aware** AI Sales agent with a Product Knowledge Base. \n",
+    "This notebook demonstrates an implementation of a **Context-Aware** AI Sales agent with a Product Knowledge Base which can actually close sales. \n",
     "\n",
     "This notebook was originally published at [filipmichalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) by [@FilipMichalsky](https://twitter.com/FilipMichalsky).\n",
     "\n",
     "SalesGPT is context-aware, which means it can understand what section of a sales conversation it is in and act accordingly.\n",
     " \n",
-    "As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activities, such as outbound sales calls. \n",
+    "As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activites, such as outbound sales calls. \n",
     "\n",
     "Additionally, the AI Sales agent has access to tools, which allow it to interact with other systems.\n",
     "\n",
     "Here, we show how the AI Sales Agent can use a **Product Knowledge Base** to speak about a particular's company offerings,\n",
     "hence increasing relevance and reducing hallucinations.\n",
     "\n",
-    "We leverage the [`langchain`](https://github.com/langchain-ai/langchain) library in this implementation, specifically [Custom Agent Configuration](https://langchain-langchain.vercel.app/docs/modules/agents/how_to/custom_agent_with_tool_retrieval) and are inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) architecture ."
+    "Furthermore, we show how our AI Sales Agent can **generate sales** by integration with the AI Agent Highway called [Mindware](https://www.mindware.co/). In practice, this allows the agent to autonomously generate a payment link for your customers **to pay for your products via Stripe**.\n",
+    "\n",
+    "We leverage the [`langchain`](https://github.com/hwchase17/langchain) library in this implementation, specifically [Custom Agent Configuration](https://langchain-langchain.vercel.app/docs/modules/agents/how_to/custom_agent_with_tool_retrieval) and are inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) architecture ."
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -38,9 +42,10 @@
     "import os\n",
     "import re\n",
     "\n",
-    "# import your OpenAI key\n",
-    "OPENAI_API_KEY = \"sk-xx\"\n",
-    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY\n",
+    "# make sure you have .env file saved locally with your API keys\n",
+    "from dotenv import load_dotenv\n",
+    "\n",
+    "load_dotenv()\n",
     "\n",
     "from typing import Any, Callable, Dict, List, Union\n",
     "\n",
@@ -49,27 +54,18 @@
     "from langchain.agents.conversational.prompt import FORMAT_INSTRUCTIONS\n",
     "from langchain.chains import LLMChain, RetrievalQA\n",
     "from langchain.chains.base import Chain\n",
+    "from langchain.llms import BaseLLM\n",
     "from langchain.prompts import PromptTemplate\n",
     "from langchain.prompts.base import StringPromptTemplate\n",
     "from langchain.schema import AgentAction, AgentFinish\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain_community.llms import BaseLLM\n",
-    "from langchain_community.vectorstores import Chroma\n",
-    "from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
     "from pydantic import BaseModel, Field"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# install additional dependencies\n",
-    "# ! pip install chromadb openai tiktoken"
-   ]
-  },
-  {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -77,19 +73,21 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "1. Seed the SalesGPT agent\n",
     "2. Run Sales Agent to decide what to do:\n",
     "\n",
-    "    a) Use a tool, such as look up Product Information in a Knowledge Base\n",
+    "    a) Use a tool, such as look up Product Information in a Knowledge Base or Generate a Payment Link\n",
     "    \n",
     "    b) Output a response to a user \n",
     "3. Run Sales Stage Recognition Agent to recognize which stage is the sales agent at and adjust their behaviour accordingly."
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -98,15 +96,17 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "### Architecture diagram\n",
     "\n",
-    "<img src=\"https://singularity-assets-public.s3.amazonaws.com/new_flow.png\"  width=\"800\" height=\"440\"/>\n"
+    "<img src=\"https://demo-bucket-45.s3.amazonaws.com/new_flow2.png\"  width=\"800\" height=\"440\">\n"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -131,7 +131,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -149,7 +149,7 @@
     "            {conversation_history}\n",
     "            ===\n",
     "\n",
-    "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
+    "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
     "            1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
     "            2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
     "            3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",
@@ -171,7 +171,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -223,7 +223,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -240,13 +240,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
     "# test the intermediate chains\n",
     "verbose = True\n",
-    "llm = ChatOpenAI(temperature=0.9)\n",
+    "llm = ChatOpenAI(\n",
+    "    model=\"gpt-4-turbo-preview\",\n",
+    "    temperature=0.9,\n",
+    "    openai_api_key=os.getenv(\"OPENAI_API_KEY\"),\n",
+    ")\n",
     "\n",
     "stage_analyzer_chain = StageAnalyzerChain.from_llm(llm, verbose=verbose)\n",
     "\n",
@@ -257,7 +261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -276,7 +280,7 @@
       "            \n",
       "            ===\n",
       "\n",
-      "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
+      "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
       "            1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
       "            2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
       "            3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",
@@ -296,21 +300,21 @@
     {
      "data": {
       "text/plain": [
-       "'1'"
+       "{'conversation_history': '', 'text': '1'}"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "stage_analyzer_chain.run(conversation_history=\"\")"
+    "stage_analyzer_chain.invoke({\"conversation_history\": \"\"})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -352,32 +356,44 @@
     {
      "data": {
       "text/plain": [
-       "\"I'm doing great, thank you for asking! As a Business Development Representative at Sleep Haven, I wanted to reach out to see if you are looking to achieve a better night's sleep. We provide premium mattresses that offer the most comfortable and supportive sleeping experience possible. Are you interested in exploring our sleep solutions? <END_OF_TURN>\""
+       "{'salesperson_name': 'Ted Lasso',\n",
+       " 'salesperson_role': 'Business Development Representative',\n",
+       " 'company_name': 'Sleep Haven',\n",
+       " 'company_business': 'Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.',\n",
+       " 'company_values': \"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
+       " 'conversation_purpose': 'find out whether they are looking to achieve better sleep via buying a premier mattress.',\n",
+       " 'conversation_history': 'Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>',\n",
+       " 'conversation_type': 'call',\n",
+       " 'conversation_stage': 'Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional. Your greeting should be welcoming. Always clarify in your greeting the reason why you are contacting the prospect.',\n",
+       " 'text': \"I'm doing well, thank you for asking. The reason I'm calling is to discuss how Sleep Haven can help enhance your sleep quality with our premium mattresses. Are you currently looking for ways to achieve a better night's sleep? <END_OF_TURN>\"}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "sales_conversation_utterance_chain.run(\n",
-    "    salesperson_name=\"Ted Lasso\",\n",
-    "    salesperson_role=\"Business Development Representative\",\n",
-    "    company_name=\"Sleep Haven\",\n",
-    "    company_business=\"Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.\",\n",
-    "    company_values=\"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
-    "    conversation_purpose=\"find out whether they are looking to achieve better sleep via buying a premier mattress.\",\n",
-    "    conversation_history=\"Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>\",\n",
-    "    conversation_type=\"call\",\n",
-    "    conversation_stage=conversation_stages.get(\n",
-    "        \"1\",\n",
-    "        \"Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\",\n",
-    "    ),\n",
+    "sales_conversation_utterance_chain.invoke(\n",
+    "    {\n",
+    "        \"salesperson_name\": \"Ted Lasso\",\n",
+    "        \"salesperson_role\": \"Business Development Representative\",\n",
+    "        \"company_name\": \"Sleep Haven\",\n",
+    "        \"company_business\": \"Sleep Haven is a premium mattress company that provides customers with the most comfortable and supportive sleeping experience possible. We offer a range of high-quality mattresses, pillows, and bedding accessories that are designed to meet the unique needs of our customers.\",\n",
+    "        \"company_values\": \"Our mission at Sleep Haven is to help people achieve a better night's sleep by providing them with the best possible sleep solutions. We believe that quality sleep is essential to overall health and well-being, and we are committed to helping our customers achieve optimal sleep by offering exceptional products and customer service.\",\n",
+    "        \"conversation_purpose\": \"find out whether they are looking to achieve better sleep via buying a premier mattress.\",\n",
+    "        \"conversation_history\": \"Hello, this is Ted Lasso from Sleep Haven. How are you doing today? <END_OF_TURN>\\nUser: I am well, howe are you?<END_OF_TURN>\",\n",
+    "        \"conversation_type\": \"call\",\n",
+    "        \"conversation_stage\": conversation_stages.get(\n",
+    "            \"1\",\n",
+    "            \"Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\",\n",
+    "        ),\n",
+    "    }\n",
     ")"
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -385,6 +401,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -395,7 +412,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -429,7 +446,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -445,7 +462,7 @@
     "    text_splitter = CharacterTextSplitter(chunk_size=10, chunk_overlap=0)\n",
     "    texts = text_splitter.split_text(product_catalog)\n",
     "\n",
-    "    llm = OpenAI(temperature=0)\n",
+    "    llm = ChatOpenAI(temperature=0)\n",
     "    embeddings = OpenAIEmbeddings()\n",
     "    docsearch = Chroma.from_texts(\n",
     "        texts, embeddings, collection_name=\"product-knowledge-base\"\n",
@@ -454,29 +471,12 @@
     "    knowledge_base = RetrievalQA.from_chain_type(\n",
     "        llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever()\n",
     "    )\n",
-    "    return knowledge_base\n",
-    "\n",
-    "\n",
-    "def get_tools(product_catalog):\n",
-    "    # query to get_tools can be used to be embedded and relevant tools found\n",
-    "    # see here: https://langchain-langchain.vercel.app/docs/use_cases/agents/custom_agent_with_plugin_retrieval#tool-retriever\n",
-    "\n",
-    "    # we only use one tool for now, but this is highly extensible!\n",
-    "    knowledge_base = setup_knowledge_base(product_catalog)\n",
-    "    tools = [\n",
-    "        Tool(\n",
-    "            name=\"ProductSearch\",\n",
-    "            func=knowledge_base.run,\n",
-    "            description=\"useful for when you need to answer questions about product information\",\n",
-    "        )\n",
-    "    ]\n",
-    "\n",
-    "    return tools"
+    "    return knowledge_base"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -485,16 +485,18 @@
      "text": [
       "Created a chunk of size 940, which is longer than the specified 10\n",
       "Created a chunk of size 844, which is longer than the specified 10\n",
-      "Created a chunk of size 837, which is longer than the specified 10\n"
+      "Created a chunk of size 837, which is longer than the specified 10\n",
+      "/Users/filipmichalsky/Odyssey/sales_bot/SalesGPT/env/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The function `run` was deprecated in LangChain 0.1.0 and will be removed in 0.2.0. Use invoke instead.\n",
+      "  warn_deprecated(\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "' We have four products available: the Classic Harmony Spring Mattress, the Plush Serenity Bamboo Mattress, the Luxury Cloud-Comfort Memory Foam Mattress, and the EcoGreen Hybrid Latex Mattress. Each product is available in different sizes, with the Classic Harmony Spring Mattress available in Queen and King sizes, the Plush Serenity Bamboo Mattress available in King size, the Luxury Cloud-Comfort Memory Foam Mattress available in Twin, Queen, and King sizes, and the EcoGreen Hybrid Latex Mattress available in Twin and Full sizes.'"
+       "'The Sleep Haven products available are:\\n\\n1. Luxury Cloud-Comfort Memory Foam Mattress\\n2. Classic Harmony Spring Mattress\\n3. EcoGreen Hybrid Latex Mattress\\n4. Plush Serenity Bamboo Mattress\\n\\nEach product has its unique features and price point.'"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -508,12 +510,199 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Set up the SalesGPT Controller with the Sales Agent and Stage Analyzer and a Knowledge Base"
+    "### Payment gateway"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In order to set up your AI agent to use a payment gateway to generate payment links for your users you need two things:\n",
+    "\n",
+    "1. Sign up for a Stripe account and obtain a STRIPE API KEY\n",
+    "2. Create products you would like to sell in the Stripe UI. Then follow out example of `example_product_price_id_mapping.json`\n",
+    "to feed the product name to price_id mapping which allows you to generate the payment links."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "from litellm import completion\n",
+    "\n",
+    "# set GPT model env variable\n",
+    "os.environ[\"GPT_MODEL\"] = \"gpt-4-turbo-preview\"\n",
+    "\n",
+    "product_price_id_mapping = {\n",
+    "    \"ai-consulting-services\": \"price_1Ow8ofB795AYY8p1goWGZi6m\",\n",
+    "    \"Luxury Cloud-Comfort Memory Foam Mattress\": \"price_1Owv99B795AYY8p1mjtbKyxP\",\n",
+    "    \"Classic Harmony Spring Mattress\": \"price_1Owv9qB795AYY8p1tPcxCM6T\",\n",
+    "    \"EcoGreen Hybrid Latex Mattress\": \"price_1OwvLDB795AYY8p1YBAMBcbi\",\n",
+    "    \"Plush Serenity Bamboo Mattress\": \"price_1OwvMQB795AYY8p1hJN2uS3S\",\n",
+    "}\n",
+    "with open(\"example_product_price_id_mapping.json\", \"w\") as f:\n",
+    "    json.dump(product_price_id_mapping, f)\n",
+    "\n",
+    "\n",
+    "def get_product_id_from_query(query, product_price_id_mapping_path):\n",
+    "    # Load product_price_id_mapping from a JSON file\n",
+    "    with open(product_price_id_mapping_path, \"r\") as f:\n",
+    "        product_price_id_mapping = json.load(f)\n",
+    "\n",
+    "    # Serialize the product_price_id_mapping to a JSON string for inclusion in the prompt\n",
+    "    product_price_id_mapping_json_str = json.dumps(product_price_id_mapping)\n",
+    "\n",
+    "    # Dynamically create the enum list from product_price_id_mapping keys\n",
+    "    enum_list = list(product_price_id_mapping.values()) + [\n",
+    "        \"No relevant product id found\"\n",
+    "    ]\n",
+    "    enum_list_str = json.dumps(enum_list)\n",
+    "\n",
+    "    prompt = f\"\"\"\n",
+    "    You are an expert data scientist and you are working on a project to recommend products to customers based on their needs.\n",
+    "    Given the following query:\n",
+    "    {query}\n",
+    "    and the following product price id mapping:\n",
+    "    {product_price_id_mapping_json_str}\n",
+    "    return the price id that is most relevant to the query.\n",
+    "    ONLY return the price id, no other text. If no relevant price id is found, return 'No relevant price id found'.\n",
+    "    Your output will follow this schema:\n",
+    "    {{\n",
+    "    \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n",
+    "    \"title\": \"Price ID Response\",\n",
+    "    \"type\": \"object\",\n",
+    "    \"properties\": {{\n",
+    "        \"price_id\": {{\n",
+    "        \"type\": \"string\",\n",
+    "        \"enum\": {enum_list_str}\n",
+    "        }}\n",
+    "    }},\n",
+    "    \"required\": [\"price_id\"]\n",
+    "    }}\n",
+    "    Return a valid directly parsable json, dont return in it within a code snippet or add any kind of explanation!!\n",
+    "    \"\"\"\n",
+    "    prompt += \"{\"\n",
+    "    response = completion(\n",
+    "        model=os.getenv(\"GPT_MODEL\", \"gpt-3.5-turbo-1106\"),\n",
+    "        messages=[{\"content\": prompt, \"role\": \"user\"}],\n",
+    "        max_tokens=1000,\n",
+    "        temperature=0,\n",
+    "    )\n",
+    "\n",
+    "    product_id = response.choices[0].message.content.strip()\n",
+    "    return product_id"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "import requests\n",
+    "\n",
+    "\n",
+    "def generate_stripe_payment_link(query: str) -> str:\n",
+    "    \"\"\"Generate a stripe payment link for a customer based on a single query string.\"\"\"\n",
+    "\n",
+    "    # example testing payment gateway url\n",
+    "    PAYMENT_GATEWAY_URL = os.getenv(\n",
+    "        \"PAYMENT_GATEWAY_URL\", \"https://agent-payments-gateway.vercel.app/payment\"\n",
+    "    )\n",
+    "    PRODUCT_PRICE_MAPPING = \"example_product_price_id_mapping.json\"\n",
+    "\n",
+    "    # use LLM to get the price_id from query\n",
+    "    price_id = get_product_id_from_query(query, PRODUCT_PRICE_MAPPING)\n",
+    "    price_id = json.loads(price_id)\n",
+    "    payload = json.dumps(\n",
+    "        {\"prompt\": query, **price_id, \"stripe_key\": os.getenv(\"STRIPE_API_KEY\")}\n",
+    "    )\n",
+    "    headers = {\n",
+    "        \"Content-Type\": \"application/json\",\n",
+    "    }\n",
+    "\n",
+    "    response = requests.request(\n",
+    "        \"POST\", PAYMENT_GATEWAY_URL, headers=headers, data=payload\n",
+    "    )\n",
+    "    return response.text"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'{\"response\":\"https://buy.stripe.com/test_6oEbLS8JB1F9bv229d\"}'"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "generate_stripe_payment_link(\n",
+    "    query=\"Please generate a payment link for John Doe to buy two mattresses - the Classic Harmony Spring Mattress\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup agent tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_tools(product_catalog):\n",
+    "    # query to get_tools can be used to be embedded and relevant tools found\n",
+    "    # see here: https://langchain-langchain.vercel.app/docs/use_cases/agents/custom_agent_with_plugin_retrieval#tool-retriever\n",
+    "\n",
+    "    # we only use one tool for now, but this is highly extensible!\n",
+    "    knowledge_base = setup_knowledge_base(product_catalog)\n",
+    "    tools = [\n",
+    "        Tool(\n",
+    "            name=\"ProductSearch\",\n",
+    "            func=knowledge_base.run,\n",
+    "            description=\"useful for when you need to answer questions about product information or services offered, availability and their costs.\",\n",
+    "        ),\n",
+    "        Tool(\n",
+    "            name=\"GeneratePaymentLink\",\n",
+    "            func=generate_stripe_payment_link,\n",
+    "            description=\"useful to close a transaction with a customer. You need to include product name and quantity and customer name in the query input.\",\n",
+    "        ),\n",
+    "    ]\n",
+    "\n",
+    "    return tools"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Set up the SalesGPT Controller with the Sales Agent and Stage Analyzer\n",
+    "\n",
+    "#### The Agent has access to a Knowledge Base and can autonomously sell your products via Stripe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -563,19 +752,11 @@
     "            print(\"TEXT\")\n",
     "            print(text)\n",
     "            print(\"-------\")\n",
-    "        if f\"{self.ai_prefix}:\" in text:\n",
-    "            return AgentFinish(\n",
-    "                {\"output\": text.split(f\"{self.ai_prefix}:\")[-1].strip()}, text\n",
-    "            )\n",
     "        regex = r\"Action: (.*?)[\\n]*Action Input: (.*)\"\n",
     "        match = re.search(regex, text)\n",
     "        if not match:\n",
-    "            ## TODO - this is not entirely reliable, sometimes results in an error.\n",
     "            return AgentFinish(\n",
-    "                {\n",
-    "                    \"output\": \"I apologize, I was unable to find the answer to your question. Is there anything else I can help with?\"\n",
-    "                },\n",
-    "                text,\n",
+    "                {\"output\": text.split(f\"{self.ai_prefix}:\")[-1].strip()}, text\n",
     "            )\n",
     "            # raise OutputParserException(f\"Could not parse LLM output: `{text}`\")\n",
     "        action = match.group(1)\n",
@@ -589,7 +770,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -647,18 +828,18 @@
     "Previous conversation history:\n",
     "{conversation_history}\n",
     "\n",
-    "{salesperson_name}:\n",
+    "Thought:\n",
     "{agent_scratchpad}\n",
     "\"\"\""
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
-    "class SalesGPT(Chain, BaseModel):\n",
+    "class SalesGPT(Chain):\n",
     "    \"\"\"Controller model for the Sales Agent.\"\"\"\n",
     "\n",
     "    conversation_history: List[str] = []\n",
@@ -804,7 +985,9 @@
     "\n",
     "            # WARNING: this output parser is NOT reliable yet\n",
     "            ## It makes assumptions about output from LLM which can break and throw an error\n",
-    "            output_parser = SalesConvoOutputParser(ai_prefix=kwargs[\"salesperson_name\"])\n",
+    "            output_parser = SalesConvoOutputParser(\n",
+    "                ai_prefix=kwargs[\"salesperson_name\"], verbose=verbose\n",
+    "            )\n",
     "\n",
     "            sales_agent_with_tools = LLMSingleActionAgent(\n",
     "                llm_chain=llm_chain,\n",
@@ -828,6 +1011,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -835,6 +1019,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -843,7 +1028,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -880,6 +1065,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {},
    "source": [
@@ -888,7 +1074,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -897,7 +1083,9 @@
      "text": [
       "Created a chunk of size 940, which is longer than the specified 10\n",
       "Created a chunk of size 844, which is longer than the specified 10\n",
-      "Created a chunk of size 837, which is longer than the specified 10\n"
+      "Created a chunk of size 837, which is longer than the specified 10\n",
+      "/Users/filipmichalsky/Odyssey/sales_bot/SalesGPT/env/lib/python3.10/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: The class `langchain.agents.agent.LLMSingleActionAgent` was deprecated in langchain 0.1.0 and will be removed in 0.2.0. Use Use new agent constructor methods like create_react_agent, create_json_agent, create_structured_chat_agent, etc. instead.\n",
+      "  warn_deprecated(\n"
      ]
     }
    ],
@@ -907,7 +1095,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -917,7 +1105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -934,14 +1122,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Ted Lasso:  Hello, this is Ted Lasso from Sleep Haven. How are you doing today?\n"
+      "Ted Lasso:  Good day! This is Ted Lasso from Sleep Haven. How are you doing today?\n"
      ]
     }
    ],
@@ -951,18 +1139,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [],
    "source": [
     "sales_agent.human_step(\n",
-    "    \"I am well, how are you? I would like to learn more about your mattresses.\"\n",
+    "    \"I am well, how are you? I would like to learn more about your services.\"\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
@@ -977,92 +1165,32 @@
     "sales_agent.determine_conversation_stage()"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Ted Lasso:  I'm glad to hear that you're doing well! As for our mattresses, at Sleep Haven, we provide customers with the most comfortable and supportive sleeping experience possible. Our high-quality mattresses are designed to meet the unique needs of our customers. Can I ask what specifically you'd like to learn more about? \n"
-     ]
-    }
-   ],
-   "source": [
-    "sales_agent.step()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "sales_agent.human_step(\"Yes, what materials are you mattresses made from?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 24,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Conversation Stage: Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen carefully to their responses and take notes.\n"
-     ]
-    }
-   ],
-   "source": [
-    "sales_agent.determine_conversation_stage()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Ted Lasso:  Our mattresses are made from a variety of materials, depending on the model. We have the EcoGreen Hybrid Latex Mattress, which is made from 100% natural latex harvested from eco-friendly plantations. The Plush Serenity Bamboo Mattress features a layer of plush, adaptive foam and a base of high-resilience support foam, with a bamboo-infused top layer. The Luxury Cloud-Comfort Memory Foam Mattress has an innovative, temperature-sensitive memory foam layer and a high-density foam base with cooling gel-infused particles. Finally, the Classic Harmony Spring Mattress has a robust inner spring construction and layers of plush padding, with a quilted top layer and a natural cotton cover. Is there anything specific you'd like to know about these materials?\n"
-     ]
-    }
-   ],
-   "source": [
-    "sales_agent.step()"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 26,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ted Lasso:  I'm doing great, thank you for asking! I'm glad to hear you're interested. Sleep Haven is a premium mattress company, and we're all about offering the best sleep solutions, including top-notch mattresses, pillows, and bedding accessories. Our mission is to help you achieve a better night's sleep. May I know if you're looking to enhance your sleep experience with a new mattress or bedding accessories? \n"
+     ]
+    }
+   ],
    "source": [
-    "sales_agent.human_step(\n",
-    "    \"Yes, I am looking for a queen sized mattress. Do you have any mattresses in queen size?\"\n",
-    ")"
+    "sales_agent.step()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 27,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Conversation Stage: Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen carefully to their responses and take notes.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "sales_agent.determine_conversation_stage()"
+    "sales_agent.human_step(\n",
+    "    \"Yes, I would like to improve my sleep. Can you tell me more about your products?\"\n",
+    ")"
    ]
   },
   {
@@ -1074,7 +1202,24 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Ted Lasso:  Yes, we do have queen-sized mattresses available. We offer the Luxury Cloud-Comfort Memory Foam Mattress and the Classic Harmony Spring Mattress in queen size. Both mattresses provide exceptional comfort and support. Is there anything specific you would like to know about these options?\n"
+      "Conversation Stage: Needs analysis: Ask open-ended questions to uncover the prospect's needs and pain points. Listen carefully to their responses and take notes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sales_agent.determine_conversation_stage()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ted Lasso:  Absolutely, I'd be happy to share more about our products. At Sleep Haven, we offer a variety of high-quality mattresses designed to cater to different sleeping preferences and needs. Whether you're looking for memory foam's comfort, the support of hybrid mattresses, or the breathability of natural latex, we have options for everyone. Our pillows and bedding accessories are similarly curated to enhance your sleep quality. Every product is built with the aim of helping you achieve the restful night's sleep you deserve. What specific features are you looking for in a mattress? \n"
      ]
     }
    ],
@@ -1084,16 +1229,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 31,
    "metadata": {},
    "outputs": [],
    "source": [
-    "sales_agent.human_step(\"Yea, compare and contrast those two options, please.\")"
+    "sales_agent.human_step(\"What mattresses do you have and how much do they cost?\")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 32,
    "metadata": {},
    "outputs": [
     {
@@ -1110,14 +1255,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Ted Lasso:  The Luxury Cloud-Comfort Memory Foam Mattress is priced at $999 and is available in Twin, Queen, and King sizes. It features an innovative, temperature-sensitive memory foam layer and a high-density foam base. On the other hand, the Classic Harmony Spring Mattress is priced at $1,299 and is available in Queen and King sizes. It features a robust inner spring construction and layers of plush padding. Both mattresses provide exceptional comfort and support, but the Classic Harmony Spring Mattress may be a better option if you prefer the traditional feel of an inner spring mattress. Do you have any other questions about these options?\n"
+      "Ted Lasso:  We offer two primary types of mattresses at Sleep Haven. The first is our Luxury Cloud-Comfort Memory Foam Mattress, which is priced at $999 and comes in Twin, Queen, and King sizes. The second is our Classic Harmony Spring Mattress, priced at $1,299, available in Queen and King sizes. Both are designed to provide exceptional comfort and support for a better night's sleep. Which type of mattress would you be interested in learning more about? \n"
      ]
     }
    ],
@@ -1127,14 +1272,66 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [],
    "source": [
     "sales_agent.human_step(\n",
-    "    \"Great, thanks, that's it. I will talk to my wife and call back if she is onboard. Have a good day!\"\n",
+    "    \"Okay.I would like to order two Memory Foam mattresses in Twin size please.\"\n",
     ")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Conversation Stage: Close: Ask for the sale by proposing a next step. This could be a demo, a trial or a meeting with decision-makers. Ensure to summarize what has been discussed and reiterate the benefits.\n"
+     ]
+    }
+   ],
+   "source": [
+    "sales_agent.determine_conversation_stage()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ted Lasso:  Fantastic choice! You're on your way to a better night's sleep with our Luxury Cloud-Comfort Memory Foam Mattresses. I've generated a payment link for two Twin size mattresses for you. Here is the link to complete your purchase: https://buy.stripe.com/test_6oEg28e3V97BdDabJn. Is there anything else I can assist you with today? \n"
+     ]
+    }
+   ],
+   "source": [
+    "sales_agent.step()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sales_agent.human_step(\n",
+    "    \"Great, thanks! I will discuss with my wife and will buy it if she is onboard. Have a good day!\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -1153,9 +1350,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

cookbook/self_query_hotel_search.ipynb

@@ -31,7 +31,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install langchain lark openai elasticsearch pandas"
+    "!pip install langchain langchain-elasticsearch lark openai elasticsearch pandas"
    ]
   },
   {
@@ -1083,7 +1083,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.vectorstores import ElasticsearchStore\n",
+    "from langchain_elasticsearch import ElasticsearchStore\n",
     "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
     "embeddings = OpenAIEmbeddings()"

cookbook/sharedmemory_for_tools.ipynb

@@ -22,7 +22,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent\n",
+    "from langchain import hub\n",
+    "from langchain.agents import AgentExecutor, Tool, ZeroShotAgent, create_react_agent\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
     "from langchain.prompts import PromptTemplate\n",
@@ -84,19 +85,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
-    "suffix = \"\"\"Begin!\"\n",
-    "\n",
-    "{chat_history}\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\"\n",
-    "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools,\n",
-    "    prefix=prefix,\n",
-    "    suffix=suffix,\n",
-    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
-    ")"
+    "prompt = hub.pull(\"hwchase17/react\")"
    ]
   },
   {
@@ -114,16 +103,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
-    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
-    ")"
+    "model = OpenAI()\n",
+    "agent = create_react_agent(model, tools, prompt)\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 36,
    "id": "ca4bc1fb",
    "metadata": {},
    "outputs": [
@@ -133,15 +120,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
+      "Action Input: \"ChatGPT\"\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -153,10 +140,40 @@
      "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
+    },
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m                         Traceback (most recent call last)",
+      "Cell \u001B[0;32mIn[36], line 1\u001B[0m\n\u001B[0;32m----> 1\u001B[0m \u001B[43magent_executor\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43minvoke\u001B[49m\u001B[43m(\u001B[49m\u001B[43m{\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43minput\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m:\u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mWhat is ChatGPT?\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m}\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:163\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    162\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_chain_error(e)\n\u001B[0;32m--> 163\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    164\u001B[0m run_manager\u001B[38;5;241m.\u001B[39mon_chain_end(outputs)\n\u001B[1;32m    166\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m include_run_info:\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/chains/base.py:153\u001B[0m, in \u001B[0;36mChain.invoke\u001B[0;34m(self, input, config, **kwargs)\u001B[0m\n\u001B[1;32m    150\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    151\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_validate_inputs(inputs)\n\u001B[1;32m    152\u001B[0m     outputs \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 153\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call\u001B[49m\u001B[43m(\u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    154\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    155\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_call(inputs)\n\u001B[1;32m    156\u001B[0m     )\n\u001B[1;32m    158\u001B[0m     final_outputs: Dict[\u001B[38;5;28mstr\u001B[39m, Any] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mprep_outputs(\n\u001B[1;32m    159\u001B[0m         inputs, outputs, return_only_outputs\n\u001B[1;32m    160\u001B[0m     )\n\u001B[1;32m    161\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mBaseException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1432\u001B[0m, in \u001B[0;36mAgentExecutor._call\u001B[0;34m(self, inputs, run_manager)\u001B[0m\n\u001B[1;32m   1430\u001B[0m \u001B[38;5;66;03m# We now enter the agent loop (until it returns something).\u001B[39;00m\n\u001B[1;32m   1431\u001B[0m \u001B[38;5;28;01mwhile\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_should_continue(iterations, time_elapsed):\n\u001B[0;32m-> 1432\u001B[0m     next_step_output \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_take_next_step\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1433\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1434\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1435\u001B[0m \u001B[43m        \u001B[49m\u001B[43minputs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1436\u001B[0m \u001B[43m        \u001B[49m\u001B[43mintermediate_steps\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1437\u001B[0m \u001B[43m        \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1438\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1439\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28misinstance\u001B[39m(next_step_output, AgentFinish):\n\u001B[1;32m   1440\u001B[0m         \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_return(\n\u001B[1;32m   1441\u001B[0m             next_step_output, intermediate_steps, run_manager\u001B[38;5;241m=\u001B[39mrun_manager\n\u001B[1;32m   1442\u001B[0m         )\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36mAgentExecutor._take_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1138\u001B[0m, in \u001B[0;36m<listcomp>\u001B[0;34m(.0)\u001B[0m\n\u001B[1;32m   1129\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21m_take_next_step\u001B[39m(\n\u001B[1;32m   1130\u001B[0m     \u001B[38;5;28mself\u001B[39m,\n\u001B[1;32m   1131\u001B[0m     name_to_tool_map: Dict[\u001B[38;5;28mstr\u001B[39m, BaseTool],\n\u001B[0;32m   (...)\u001B[0m\n\u001B[1;32m   1135\u001B[0m     run_manager: Optional[CallbackManagerForChainRun] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m   1136\u001B[0m ) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Union[AgentFinish, List[Tuple[AgentAction, \u001B[38;5;28mstr\u001B[39m]]]:\n\u001B[1;32m   1137\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_consume_next_step(\n\u001B[0;32m-> 1138\u001B[0m         [\n\u001B[1;32m   1139\u001B[0m             a\n\u001B[1;32m   1140\u001B[0m             \u001B[38;5;28;01mfor\u001B[39;00m a \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_iter_next_step(\n\u001B[1;32m   1141\u001B[0m                 name_to_tool_map,\n\u001B[1;32m   1142\u001B[0m                 color_mapping,\n\u001B[1;32m   1143\u001B[0m                 inputs,\n\u001B[1;32m   1144\u001B[0m                 intermediate_steps,\n\u001B[1;32m   1145\u001B[0m                 run_manager,\n\u001B[1;32m   1146\u001B[0m             )\n\u001B[1;32m   1147\u001B[0m         ]\n\u001B[1;32m   1148\u001B[0m     )\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1223\u001B[0m, in \u001B[0;36mAgentExecutor._iter_next_step\u001B[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001B[0m\n\u001B[1;32m   1221\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m agent_action\n\u001B[1;32m   1222\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m agent_action \u001B[38;5;129;01min\u001B[39;00m actions:\n\u001B[0;32m-> 1223\u001B[0m     \u001B[38;5;28;01myield\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_perform_agent_action\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1224\u001B[0m \u001B[43m        \u001B[49m\u001B[43mname_to_tool_map\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcolor_mapping\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43magent_action\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\n\u001B[1;32m   1225\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/langchain/libs/langchain/langchain/agents/agent.py:1245\u001B[0m, in \u001B[0;36mAgentExecutor._perform_agent_action\u001B[0;34m(self, name_to_tool_map, color_mapping, agent_action, run_manager)\u001B[0m\n\u001B[1;32m   1243\u001B[0m         tool_run_kwargs[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mllm_prefix\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1244\u001B[0m     \u001B[38;5;66;03m# We then call the tool on the tool input to get an observation\u001B[39;00m\n\u001B[0;32m-> 1245\u001B[0m     observation \u001B[38;5;241m=\u001B[39m \u001B[43mtool\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrun\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1246\u001B[0m \u001B[43m        \u001B[49m\u001B[43magent_action\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mtool_input\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1247\u001B[0m \u001B[43m        \u001B[49m\u001B[43mverbose\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mverbose\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1248\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcolor\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mcolor\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1249\u001B[0m \u001B[43m        \u001B[49m\u001B[43mcallbacks\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mget_child\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mif\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43;01melse\u001B[39;49;00m\u001B[43m \u001B[49m\u001B[38;5;28;43;01mNone\u001B[39;49;00m\u001B[43m,\u001B[49m\n\u001B[1;32m   1250\u001B[0m \u001B[43m        \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_run_kwargs\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1251\u001B[0m \u001B[43m    \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1252\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m   1253\u001B[0m     tool_run_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39magent\u001B[38;5;241m.\u001B[39mtool_run_logging_kwargs()\n",
+      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:422\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    420\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m (\u001B[38;5;167;01mException\u001B[39;00m, \u001B[38;5;167;01mKeyboardInterrupt\u001B[39;00m) \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    421\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_error(e)\n\u001B[0;32m--> 422\u001B[0m     \u001B[38;5;28;01mraise\u001B[39;00m e\n\u001B[1;32m    423\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[1;32m    424\u001B[0m     run_manager\u001B[38;5;241m.\u001B[39mon_tool_end(observation, color\u001B[38;5;241m=\u001B[39mcolor, name\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mname, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs)\n",
+      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:381\u001B[0m, in \u001B[0;36mBaseTool.run\u001B[0;34m(self, tool_input, verbose, start_color, color, callbacks, tags, metadata, run_name, run_id, **kwargs)\u001B[0m\n\u001B[1;32m    378\u001B[0m     parsed_input \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_parse_input(tool_input)\n\u001B[1;32m    379\u001B[0m     tool_args, tool_kwargs \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_to_args_and_kwargs(parsed_input)\n\u001B[1;32m    380\u001B[0m     observation \u001B[38;5;241m=\u001B[39m (\n\u001B[0;32m--> 381\u001B[0m         \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_run\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_args\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrun_manager\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43mrun_manager\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mtool_kwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    382\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_arg_supported\n\u001B[1;32m    383\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_run(\u001B[38;5;241m*\u001B[39mtool_args, \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mtool_kwargs)\n\u001B[1;32m    384\u001B[0m     )\n\u001B[1;32m    385\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m ValidationError \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m    386\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;129;01mnot\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhandle_validation_error:\n",
+      "File \u001B[0;32m~/code/langchain/libs/core/langchain_core/tools.py:588\u001B[0m, in \u001B[0;36mTool._run\u001B[0;34m(self, run_manager, *args, **kwargs)\u001B[0m\n\u001B[1;32m    579\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc:\n\u001B[1;32m    580\u001B[0m     new_argument_supported \u001B[38;5;241m=\u001B[39m signature(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc)\u001B[38;5;241m.\u001B[39mparameters\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcallbacks\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n\u001B[1;32m    581\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m (\n\u001B[1;32m    582\u001B[0m         \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfunc(\n\u001B[1;32m    583\u001B[0m             \u001B[38;5;241m*\u001B[39margs,\n\u001B[1;32m    584\u001B[0m             callbacks\u001B[38;5;241m=\u001B[39mrun_manager\u001B[38;5;241m.\u001B[39mget_child() \u001B[38;5;28;01mif\u001B[39;00m run_manager \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m,\n\u001B[1;32m    585\u001B[0m             \u001B[38;5;241m*\u001B[39m\u001B[38;5;241m*\u001B[39mkwargs,\n\u001B[1;32m    586\u001B[0m         )\n\u001B[1;32m    587\u001B[0m         \u001B[38;5;28;01mif\u001B[39;00m new_argument_supported\n\u001B[0;32m--> 588\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mfunc\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    589\u001B[0m     )\n\u001B[1;32m    590\u001B[0m \u001B[38;5;28;01mraise\u001B[39;00m \u001B[38;5;167;01mNotImplementedError\u001B[39;00m(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mTool does not support sync\u001B[39m\u001B[38;5;124m\"\u001B[39m)\n",
+      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:94\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper.run\u001B[0;34m(self, query)\u001B[0m\n\u001B[1;32m     92\u001B[0m \u001B[38;5;250m\u001B[39m\u001B[38;5;124;03m\"\"\"Run query through GoogleSearch and parse result.\"\"\"\u001B[39;00m\n\u001B[1;32m     93\u001B[0m snippets \u001B[38;5;241m=\u001B[39m []\n\u001B[0;32m---> 94\u001B[0m results \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_google_search_results\u001B[49m\u001B[43m(\u001B[49m\u001B[43mquery\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mnum\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mk\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     95\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mlen\u001B[39m(results) \u001B[38;5;241m==\u001B[39m \u001B[38;5;241m0\u001B[39m:\n\u001B[1;32m     96\u001B[0m     \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mNo good Google Search Result was found\u001B[39m\u001B[38;5;124m\"\u001B[39m\n",
+      "File \u001B[0;32m~/code/langchain/libs/community/langchain_community/utilities/google_search.py:62\u001B[0m, in \u001B[0;36mGoogleSearchAPIWrapper._google_search_results\u001B[0;34m(self, search_term, **kwargs)\u001B[0m\n\u001B[1;32m     60\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msiterestrict:\n\u001B[1;32m     61\u001B[0m     cse \u001B[38;5;241m=\u001B[39m cse\u001B[38;5;241m.\u001B[39msiterestrict()\n\u001B[0;32m---> 62\u001B[0m res \u001B[38;5;241m=\u001B[39m \u001B[43mcse\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mlist\u001B[49m\u001B[43m(\u001B[49m\u001B[43mq\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[43msearch_term\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcx\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mgoogle_cse_id\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mexecute\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m     63\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m res\u001B[38;5;241m.\u001B[39mget(\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mitems\u001B[39m\u001B[38;5;124m\"\u001B[39m, [])\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/_helpers.py:130\u001B[0m, in \u001B[0;36mpositional.<locals>.positional_decorator.<locals>.positional_wrapper\u001B[0;34m(*args, **kwargs)\u001B[0m\n\u001B[1;32m    128\u001B[0m     \u001B[38;5;28;01melif\u001B[39;00m positional_parameters_enforcement \u001B[38;5;241m==\u001B[39m POSITIONAL_WARNING:\n\u001B[1;32m    129\u001B[0m         logger\u001B[38;5;241m.\u001B[39mwarning(message)\n\u001B[0;32m--> 130\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mwrapped\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:923\u001B[0m, in \u001B[0;36mHttpRequest.execute\u001B[0;34m(self, http, num_retries)\u001B[0m\n\u001B[1;32m    920\u001B[0m     \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mheaders[\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124mcontent-length\u001B[39m\u001B[38;5;124m\"\u001B[39m] \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mstr\u001B[39m(\u001B[38;5;28mlen\u001B[39m(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mbody))\n\u001B[1;32m    922\u001B[0m \u001B[38;5;66;03m# Handle retries for server-side errors.\u001B[39;00m\n\u001B[0;32m--> 923\u001B[0m resp, content \u001B[38;5;241m=\u001B[39m \u001B[43m_retry_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m    924\u001B[0m \u001B[43m    \u001B[49m\u001B[43mhttp\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    925\u001B[0m \u001B[43m    \u001B[49m\u001B[43mnum_retries\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    926\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[38;5;124;43mrequest\u001B[39;49m\u001B[38;5;124;43m\"\u001B[39;49m\u001B[43m,\u001B[49m\n\u001B[1;32m    927\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_sleep\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    928\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_rand\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    929\u001B[0m \u001B[43m    \u001B[49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43muri\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    930\u001B[0m \u001B[43m    \u001B[49m\u001B[43mmethod\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mstr\u001B[39;49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mmethod\u001B[49m\u001B[43m)\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    931\u001B[0m \u001B[43m    \u001B[49m\u001B[43mbody\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    932\u001B[0m \u001B[43m    \u001B[49m\u001B[43mheaders\u001B[49m\u001B[38;5;241;43m=\u001B[39;49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m    933\u001B[0m \u001B[43m\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    935\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m callback \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mresponse_callbacks:\n\u001B[1;32m    936\u001B[0m     callback(resp)\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/googleapiclient/http.py:191\u001B[0m, in \u001B[0;36m_retry_request\u001B[0;34m(http, num_retries, req_type, sleep, rand, uri, method, *args, **kwargs)\u001B[0m\n\u001B[1;32m    189\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m    190\u001B[0m     exception \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n\u001B[0;32m--> 191\u001B[0m     resp, content \u001B[38;5;241m=\u001B[39m \u001B[43mhttp\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mrequest\u001B[49m\u001B[43m(\u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m    192\u001B[0m \u001B[38;5;66;03m# Retry on SSL errors and socket timeout errors.\u001B[39;00m\n\u001B[1;32m    193\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m _ssl_SSLError \u001B[38;5;28;01mas\u001B[39;00m ssl_error:\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1724\u001B[0m, in \u001B[0;36mHttp.request\u001B[0;34m(self, uri, method, body, headers, redirections, connection_type)\u001B[0m\n\u001B[1;32m   1722\u001B[0m             content \u001B[38;5;241m=\u001B[39m \u001B[38;5;124mb\u001B[39m\u001B[38;5;124m\"\u001B[39m\u001B[38;5;124m\"\u001B[39m\n\u001B[1;32m   1723\u001B[0m         \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m-> 1724\u001B[0m             (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_request\u001B[49m\u001B[43m(\u001B[49m\n\u001B[1;32m   1725\u001B[0m \u001B[43m                \u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mauthority\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43muri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mredirections\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcachekey\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m   1726\u001B[0m \u001B[43m            \u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1727\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m \u001B[38;5;167;01mException\u001B[39;00m \u001B[38;5;28;01mas\u001B[39;00m e:\n\u001B[1;32m   1728\u001B[0m     is_timeout \u001B[38;5;241m=\u001B[39m \u001B[38;5;28misinstance\u001B[39m(e, socket\u001B[38;5;241m.\u001B[39mtimeout)\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1444\u001B[0m, in \u001B[0;36mHttp._request\u001B[0;34m(self, conn, host, absolute_uri, request_uri, method, body, headers, redirections, cachekey)\u001B[0m\n\u001B[1;32m   1441\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1442\u001B[0m     auth\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, headers, body)\n\u001B[0;32m-> 1444\u001B[0m (response, content) \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_conn_request\u001B[49m\u001B[43m(\u001B[49m\u001B[43mconn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mrequest_uri\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mmethod\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbody\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mheaders\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1446\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m auth:\n\u001B[1;32m   1447\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m auth\u001B[38;5;241m.\u001B[39mresponse(response, body):\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1366\u001B[0m, in \u001B[0;36mHttp._conn_request\u001B[0;34m(self, conn, request_uri, method, body, headers)\u001B[0m\n\u001B[1;32m   1364\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m   1365\u001B[0m     \u001B[38;5;28;01mif\u001B[39;00m conn\u001B[38;5;241m.\u001B[39msock \u001B[38;5;129;01mis\u001B[39;00m \u001B[38;5;28;01mNone\u001B[39;00m:\n\u001B[0;32m-> 1366\u001B[0m         \u001B[43mconn\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1367\u001B[0m     conn\u001B[38;5;241m.\u001B[39mrequest(method, request_uri, body, headers)\n\u001B[1;32m   1368\u001B[0m \u001B[38;5;28;01mexcept\u001B[39;00m socket\u001B[38;5;241m.\u001B[39mtimeout:\n",
+      "File \u001B[0;32m~/code/langchain/.venv/lib/python3.10/site-packages/httplib2/__init__.py:1156\u001B[0m, in \u001B[0;36mHTTPSConnectionWithTimeout.connect\u001B[0;34m(self)\u001B[0m\n\u001B[1;32m   1154\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m has_timeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout):\n\u001B[1;32m   1155\u001B[0m     sock\u001B[38;5;241m.\u001B[39msettimeout(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mtimeout)\n\u001B[0;32m-> 1156\u001B[0m \u001B[43msock\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconnect\u001B[49m\u001B[43m(\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mhost\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mport\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m   1158\u001B[0m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39msock \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_context\u001B[38;5;241m.\u001B[39mwrap_socket(sock, server_hostname\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mhost)\n\u001B[1;32m   1160\u001B[0m \u001B[38;5;66;03m# Python 3.3 compatibility: emulate the check_hostname behavior\u001B[39;00m\n",
+      "\u001B[0;31mKeyboardInterrupt\u001B[0m: "
+     ]
     }
    ],
    "source": [
-    "agent_chain.run(input=\"What is ChatGPT?\")"
+    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
    ]
   },
   {
@@ -179,15 +196,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
+      "Action Input: Who developed ChatGPT\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -202,7 +219,7 @@
     }
    ],
    "source": [
-    "agent_chain.run(input=\"Who developed it?\")"
+    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
    ]
   },
   {
@@ -217,14 +234,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001b[0m\n",
+      "Action Input: My daughter 5 years old\u001B[0m\n",
       "\n",
-      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
       "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -232,16 +249,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001b[0m\n",
+      "\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n",
       "\n",
-      "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001b[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -256,8 +273,8 @@
     }
    ],
    "source": [
-    "agent_chain.run(\n",
-    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
+    "agent_executor.invoke(\n",
+    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
     ")"
    ]
   },
@@ -289,9 +306,17 @@
     }
    ],
    "source": [
-    "print(agent_chain.memory.buffer)"
+    "print(agent_executor.memory.buffer)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "84ca95c30e262e00",
+   "metadata": {
+    "collapsed": false
+   },
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "id": "cc3d0aa4",
@@ -340,25 +365,9 @@
     "    ),\n",
     "]\n",
     "\n",
-    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
-    "suffix = \"\"\"Begin!\"\n",
-    "\n",
-    "{chat_history}\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\"\n",
-    "\n",
-    "prompt = ZeroShotAgent.create_prompt(\n",
-    "    tools,\n",
-    "    prefix=prefix,\n",
-    "    suffix=suffix,\n",
-    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"],\n",
-    ")\n",
-    "\n",
-    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
-    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
-    "agent_chain = AgentExecutor.from_agent_and_tools(\n",
-    "    agent=agent, tools=tools, verbose=True, memory=memory\n",
-    ")"
+    "prompt = hub.pull(\"hwchase17/react\")\n",
+    "agent = create_react_agent(model, tools, prompt)\n",
+    "agent_executor = AgentExecutor(agent=agent, tools=tools, memory=memory)"
    ]
   },
   {
@@ -373,15 +382,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I should research ChatGPT to answer this question.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I should research ChatGPT to answer this question.\n",
       "Action: Search\n",
-      "Action Input: \"ChatGPT\"\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
+      "Action Input: \"ChatGPT\"\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -396,7 +405,7 @@
     }
    ],
    "source": [
-    "agent_chain.run(input=\"What is ChatGPT?\")"
+    "agent_executor.invoke({\"input\": \"What is ChatGPT?\"})"
    ]
   },
   {
@@ -411,15 +420,15 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to find out who developed ChatGPT\n",
       "Action: Search\n",
-      "Action Input: Who developed ChatGPT\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
-      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
+      "Action Input: Who developed ChatGPT\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -434,7 +443,7 @@
     }
    ],
    "source": [
-    "agent_chain.run(input=\"Who developed it?\")"
+    "agent_executor.invoke({\"input\": \"Who developed it?\"})"
    ]
   },
   {
@@ -449,14 +458,14 @@
      "text": [
       "\n",
       "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
       "Action: Summary\n",
-      "Action Input: My daughter 5 years old\u001b[0m\n",
+      "Action Input: My daughter 5 years old\u001B[0m\n",
       "\n",
-      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
       "Prompt after formatting:\n",
-      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
+      "\u001B[32;1m\u001B[1;3mThis is a conversation between a human and a bot:\n",
       "\n",
       "Human: What is ChatGPT?\n",
       "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
@@ -464,16 +473,16 @@
       "AI: ChatGPT was developed by OpenAI.\n",
       "\n",
       "Write a summary of the conversation for My daughter 5 years old:\n",
-      "\u001b[0m\n",
+      "\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n",
       "\n",
-      "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
-      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001b[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001B[0m\n",
       "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
+      "\u001B[1m> Finished chain.\u001B[0m\n"
      ]
     },
     {
@@ -488,8 +497,8 @@
     }
    ],
    "source": [
-    "agent_chain.run(\n",
-    "    input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\"\n",
+    "agent_executor.invoke(\n",
+    "    {\"input\": \"Thanks. Summarize the conversation, for my daughter 5 years old.\"}\n",
     ")"
    ]
   },
@@ -524,7 +533,7 @@
     }
    ],
    "source": [
-    "print(agent_chain.memory.buffer)"
+    "print(agent_executor.memory.buffer)"
    ]
   }
  ],

cookbook/smart_llm.ipynb

@@ -209,7 +209,7 @@
     }
    ],
    "source": [
-    "chain.run({})"
+    "chain.invoke({})"
    ]
   },
   {

cookbook/together_ai.ipynb

@@ -9,7 +9,7 @@
     " \n",
     "[Together AI](https://python.langchain.com/docs/integrations/llms/together) has a broad set of OSS LLMs via inference API.\n",
     "\n",
-    "See [here](https://api.together.xyz/playground). We use `\"mistralai/Mixtral-8x7B-Instruct-v0.1` for RAG on the Mixtral paper.\n",
+    "See [here](https://docs.together.ai/docs/inference-models). We use `\"mistralai/Mixtral-8x7B-Instruct-v0.1` for RAG on the Mixtral paper.\n",
     "\n",
     "Download the paper:\n",
     "https://arxiv.org/pdf/2401.04088.pdf"
@@ -39,7 +39,7 @@
     "data = loader.load()\n",
     "\n",
     "# Split\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=0)\n",
     "all_splits = text_splitter.split_documents(data)\n",
@@ -148,7 +148,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.16"
+   "version": "3.9.6"
   }
  },
  "nbformat": 4,

cookbook/tool_call_messages.ipynb

@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c48812ed-35bd-4fbe-9a2c-6c7335e5645e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_anthropic import ChatAnthropic\n",
+    "from langchain_core.runnables import ConfigurableField\n",
+    "from langchain_core.tools import tool\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def multiply(x: float, y: float) -> float:\n",
+    "    \"\"\"Multiply 'x' times 'y'.\"\"\"\n",
+    "    return x * y\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def exponentiate(x: float, y: float) -> float:\n",
+    "    \"\"\"Raise 'x' to the 'y'.\"\"\"\n",
+    "    return x**y\n",
+    "\n",
+    "\n",
+    "@tool\n",
+    "def add(x: float, y: float) -> float:\n",
+    "    \"\"\"Add 'x' and 'y'.\"\"\"\n",
+    "    return x + y\n",
+    "\n",
+    "\n",
+    "tools = [multiply, exponentiate, add]\n",
+    "\n",
+    "gpt35 = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0).bind_tools(tools)\n",
+    "claude3 = ChatAnthropic(model=\"claude-3-sonnet-20240229\").bind_tools(tools)\n",
+    "llm_with_tools = gpt35.configurable_alternatives(\n",
+    "    ConfigurableField(id=\"llm\"), default_key=\"gpt35\", claude3=claude3\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c186263-1b98-4cb2-b6d1-71f65eb0d811",
+   "metadata": {},
+   "source": [
+    "# LangGraph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "28fc2c60-7dbc-428a-8983-1a6a15ea30d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import operator\n",
+    "from typing import Annotated, Sequence, TypedDict\n",
+    "\n",
+    "from langchain_core.messages import AIMessage, BaseMessage, HumanMessage, ToolMessage\n",
+    "from langchain_core.runnables import RunnableLambda\n",
+    "from langgraph.graph import END, StateGraph\n",
+    "\n",
+    "\n",
+    "class AgentState(TypedDict):\n",
+    "    messages: Annotated[Sequence[BaseMessage], operator.add]\n",
+    "\n",
+    "\n",
+    "def should_continue(state):\n",
+    "    return \"continue\" if state[\"messages\"][-1].tool_calls else \"end\"\n",
+    "\n",
+    "\n",
+    "def call_model(state, config):\n",
+    "    return {\"messages\": [llm_with_tools.invoke(state[\"messages\"], config=config)]}\n",
+    "\n",
+    "\n",
+    "def _invoke_tool(tool_call):\n",
+    "    tool = {tool.name: tool for tool in tools}[tool_call[\"name\"]]\n",
+    "    return ToolMessage(tool.invoke(tool_call[\"args\"]), tool_call_id=tool_call[\"id\"])\n",
+    "\n",
+    "\n",
+    "tool_executor = RunnableLambda(_invoke_tool)\n",
+    "\n",
+    "\n",
+    "def call_tools(state):\n",
+    "    last_message = state[\"messages\"][-1]\n",
+    "    return {\"messages\": tool_executor.batch(last_message.tool_calls)}\n",
+    "\n",
+    "\n",
+    "workflow = StateGraph(AgentState)\n",
+    "workflow.add_node(\"agent\", call_model)\n",
+    "workflow.add_node(\"action\", call_tools)\n",
+    "workflow.set_entry_point(\"agent\")\n",
+    "workflow.add_conditional_edges(\n",
+    "    \"agent\",\n",
+    "    should_continue,\n",
+    "    {\n",
+    "        \"continue\": \"action\",\n",
+    "        \"end\": END,\n",
+    "    },\n",
+    ")\n",
+    "workflow.add_edge(\"action\", \"agent\")\n",
+    "graph = workflow.compile()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3710e724-2595-4625-ba3a-effb81e66e4a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
+       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc', 'function': {'arguments': '{\"x\": 8, \"y\": 2.743}', 'name': 'exponentiate'}, 'type': 'function'}, {'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp', 'function': {'arguments': '{\"x\": 17.24, \"y\": -918.1241}', 'name': 'add'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 58, 'prompt_tokens': 168, 'total_tokens': 226}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-528302fc-7acf-4c11-82c4-119ccf40c573-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8, 'y': 2.743}, 'id': 'call_6yMU2WsS4Bqgi1WxFHxtfJRc'}, {'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'call_GAL3dQiKFF9XEV0RrRLPTvVp'}]),\n",
+       "  ToolMessage(content='300.03770462067547', tool_call_id='call_6yMU2WsS4Bqgi1WxFHxtfJRc'),\n",
+       "  ToolMessage(content='-900.8841', tool_call_id='call_GAL3dQiKFF9XEV0RrRLPTvVp'),\n",
+       "  AIMessage(content='The result of \\\\(3 + 5^{2.743}\\\\) is approximately 300.04, and the result of \\\\(17.24 - 918.1241\\\\) is approximately -900.88.', response_metadata={'token_usage': {'completion_tokens': 44, 'prompt_tokens': 251, 'total_tokens': 295}, 'model_name': 'gpt-3.5-turbo-0125', 'system_fingerprint': 'fp_b28b39ffa8', 'finish_reason': 'stop', 'logprobs': None}, id='run-d1161669-ed09-4b18-94bd-6d8530df5aa8-0')]}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "graph.invoke(\n",
+    "    {\n",
+    "        \"messages\": [\n",
+    "            HumanMessage(\n",
+    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
+    "            )\n",
+    "        ]\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "073c074e-d722-42e0-85ec-c62c079207e4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'messages': [HumanMessage(content=\"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"),\n",
+       "  AIMessage(content=[{'text': \"Okay, let's break this down into two parts:\", 'type': 'text'}, {'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC', 'input': {'x': 3, 'y': 5}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_01AkLGH8sxMHaH15yewmjwkF', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 450, 'output_tokens': 81}}, id='run-f35bfae8-8ded-4f8a-831b-0940d6ad16b6-0', tool_calls=[{'name': 'add', 'args': {'x': 3, 'y': 5}, 'id': 'toolu_01DEhqcXkXTtzJAiZ7uMBeDC'}]),\n",
+       "  ToolMessage(content='8.0', tool_call_id='toolu_01DEhqcXkXTtzJAiZ7uMBeDC'),\n",
+       "  AIMessage(content=[{'id': 'toolu_013DyMLrvnrto33peAKMGMr1', 'input': {'x': 8.0, 'y': 2.743}, 'name': 'exponentiate', 'type': 'tool_use'}], response_metadata={'id': 'msg_015Fmp8aztwYcce2JDAFfce3', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 545, 'output_tokens': 75}}, id='run-48aaeeeb-a1e5-48fd-a57a-6c3da2907b47-0', tool_calls=[{'name': 'exponentiate', 'args': {'x': 8.0, 'y': 2.743}, 'id': 'toolu_013DyMLrvnrto33peAKMGMr1'}]),\n",
+       "  ToolMessage(content='300.03770462067547', tool_call_id='toolu_013DyMLrvnrto33peAKMGMr1'),\n",
+       "  AIMessage(content=[{'text': 'So 3 plus 5 raised to the 2.743 power is 300.04.\\n\\nFor the second part:', 'type': 'text'}, {'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46', 'input': {'x': 17.24, 'y': -918.1241}, 'name': 'add', 'type': 'tool_use'}], response_metadata={'id': 'msg_015TkhfRBENPib2RWAxkieH6', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'tool_use', 'stop_sequence': None, 'usage': {'input_tokens': 638, 'output_tokens': 105}}, id='run-45fb62e3-d102-4159-881d-241c5dbadeed-0', tool_calls=[{'name': 'add', 'args': {'x': 17.24, 'y': -918.1241}, 'id': 'toolu_01UTmMrGTmLpPrPCF1rShN46'}]),\n",
+       "  ToolMessage(content='-900.8841', tool_call_id='toolu_01UTmMrGTmLpPrPCF1rShN46'),\n",
+       "  AIMessage(content='Therefore, 17.24 - 918.1241 = -900.8841', response_metadata={'id': 'msg_01LgKnRuUcSyADCpxv9tPoYD', 'model': 'claude-3-sonnet-20240229', 'stop_reason': 'end_turn', 'stop_sequence': None, 'usage': {'input_tokens': 759, 'output_tokens': 24}}, id='run-1008254e-ccd1-497c-8312-9550dd77bd08-0')]}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "graph.invoke(\n",
+    "    {\n",
+    "        \"messages\": [\n",
+    "            HumanMessage(\n",
+    "                \"what's 3 plus 5 raised to the 2.743. also what's 17.24 - 918.1241\"\n",
+    "            )\n",
+    "        ]\n",
+    "    },\n",
+    "    config={\"configurable\": {\"llm\": \"claude3\"}},\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": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/twitter-the-algorithm-analysis-deeplake.ipynb

@@ -2610,7 +2610,7 @@
     }
    ],
    "source": [
-    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain_text_splitters import CharacterTextSplitter\n",
     "\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "texts = text_splitter.split_documents(docs)"
@@ -3811,7 +3811,7 @@
     "from langchain.chains import ConversationalRetrievalChain\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo-0613\")  # switch to 'gpt-4'\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo-0613\")  # switch to 'gpt-4'\n",
     "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
    ]
   },

cookbook/two_agent_debate_tools.ipynb

@@ -424,7 +424,7 @@
     "    DialogueAgentWithTools(\n",
     "        name=name,\n",
     "        system_message=SystemMessage(content=system_message),\n",
-    "        model=ChatOpenAI(model_name=\"gpt-4\", temperature=0.2),\n",
+    "        model=ChatOpenAI(model=\"gpt-4\", temperature=0.2),\n",
     "        tool_names=tools,\n",
     "        top_k_results=2,\n",
     "    )\n",

cookbook/video_captioning/video_captioning.ipynb

@@ -0,0 +1,174 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Video Captioning\n",
+    "This notebook shows how to use VideoCaptioningChain, which is implemented using Langchain's ImageCaptionLoader and AssemblyAI to produce .srt files.\n",
+    "\n",
+    "This system autogenerates both subtitles and closed captions from a video URL."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Installing Dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install ffmpeg-python\n",
+    "# !pip install assemblyai\n",
+    "# !pip install opencv-python\n",
+    "# !pip install torch\n",
+    "# !pip install pillow\n",
+    "# !pip install transformers\n",
+    "# !pip install langchain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-30T03:39:14.078232Z",
+     "start_time": "2023-11-30T03:39:12.534410Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "\n",
+    "from langchain.chains.video_captioning import VideoCaptioningChain\n",
+    "from langchain.chat_models.openai import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setting up API Keys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2023-11-30T03:39:17.423806Z",
+     "start_time": "2023-11-30T03:39:17.417945Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "OPENAI_API_KEY = getpass.getpass(\"OpenAI API Key:\")\n",
+    "\n",
+    "ASSEMBLYAI_API_KEY = getpass.getpass(\"AssemblyAI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Required parameters:**\n",
+    "\n",
+    "* llm: The language model this chain will use to get suggestions on how to refine the closed-captions\n",
+    "* assemblyai_key: The API key for AssemblyAI, used to generate the subtitles\n",
+    "\n",
+    "**Optional Parameters:**\n",
+    "\n",
+    "* verbose (Default: True): Sets verbose mode for downstream chain calls\n",
+    "* use_logging (Default: True): Log the chain's processes in run manager\n",
+    "* frame_skip (Default: None): Choose how many video frames to skip during processing. Increasing it results in faster execution, but less accurate results. If None, frame skip is calculated manually based on the framerate Set this to 0 to sample all frames\n",
+    "* image_delta_threshold (Default: 3000000): Set the sensitivity for what the image processor considers a change in scenery in the video, used to delimit closed captions. Higher = less sensitive\n",
+    "* closed_caption_char_limit (Default: 20): Sets the character limit on closed captions\n",
+    "* closed_caption_similarity_threshold (Default: 80): Sets the percentage value to how similar two closed caption models should be in order to be clustered into one longer closed caption\n",
+    "* use_unclustered_video_models (Default: False): If true, closed captions that could not be clustered will be included. May result in spontaneous behaviour from closed captions such as very short lasting captions or fast-changing captions. Enabling this is experimental and not recommended"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example run"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# https://ia804703.us.archive.org/27/items/uh-oh-here-we-go-again/Uh-Oh%2C%20Here%20we%20go%20again.mp4\n",
+    "# https://ia601200.us.archive.org/9/items/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb.mp4\n",
+    "\n",
+    "chain = VideoCaptioningChain(\n",
+    "    llm=ChatOpenAI(model=\"gpt-4\", max_tokens=4000, openai_api_key=OPENAI_API_KEY),\n",
+    "    assemblyai_key=ASSEMBLYAI_API_KEY,\n",
+    ")\n",
+    "\n",
+    "srt_content = chain.run(\n",
+    "    video_file_path=\"https://ia601200.us.archive.org/9/items/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb/f58703d4-61e6-4f8f-8c08-b42c7e16f7cb.mp4\"\n",
+    ")\n",
+    "\n",
+    "print(srt_content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Writing output to .srt file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open(\"output.srt\", \"w\") as file:\n",
+    "    file.write(srt_content)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "myenv",
+   "language": "python",
+   "name": "myenv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.6"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

cookbook/wikibase_agent.ipynb

@@ -401,7 +401,7 @@
     ")\n",
     "from langchain.chains import LLMChain\n",
     "from langchain.prompts import StringPromptTemplate\n",
-    "from langchain.schema import AgentAction, AgentFinish"
+    "from langchain_core.agents import AgentAction, AgentFinish"
    ]
   },
   {
@@ -601,7 +601,7 @@
    "source": [
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model_name=\"gpt-4\", temperature=0)"
+    "llm = ChatOpenAI(model=\"gpt-4\", temperature=0)"
    ]
   },
   {

docker/docker-compose.yml

@@ -1,12 +1,17 @@
 # docker-compose to make it easier to spin up integration tests.
 # Services should use NON standard ports to avoid collision with
+# any existing services that might be used for development.
+# ATTENTION: When adding a service below use a non-standard port
+# increment by one from the preceding port.
+# For credentials always use `langchain` and `langchain` for the
+# username and password.
 version: "3"
 name: langchain-tests
 
 services:
   redis:
     image: redis/redis-stack-server:latest
-    # We use non standard ports since 
+    # We use non standard ports since
     # these instances are used for testing
     # and users may already have existing
     # redis instances set up locally
@@ -19,3 +24,61 @@ services:
     image: graphdb
     ports:
       - "6021:7200"
+  mongo:
+    image: mongo:latest
+    container_name: mongo_container
+    ports:
+      - "6022:27017"
+    environment:
+      MONGO_INITDB_ROOT_USERNAME: langchain
+      MONGO_INITDB_ROOT_PASSWORD: langchain
+  postgres:
+    image: postgres:16
+    environment:
+      POSTGRES_DB: langchain
+      POSTGRES_USER: langchain
+      POSTGRES_PASSWORD: langchain
+    ports:
+      - "6023:5432"
+    command: |
+      postgres -c log_statement=all
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          "psql postgresql://langchain:langchain@localhost/langchain --command 'SELECT 1;' || exit 1",
+        ]
+      interval: 5s
+      retries: 60
+    volumes:
+      - postgres_data:/var/lib/postgresql/data
+  pgvector:
+    # postgres with the pgvector extension
+    image: ankane/pgvector
+    environment:
+      POSTGRES_DB: langchain
+      POSTGRES_USER: langchain
+      POSTGRES_PASSWORD: langchain
+    ports:
+      - "6024:5432"
+    command: |
+      postgres -c log_statement=all
+    healthcheck:
+      test:
+        [
+          "CMD-SHELL",
+          "psql postgresql://langchain:langchain@localhost/langchain --command 'SELECT 1;' || exit 1",
+        ]
+      interval: 5s
+      retries: 60
+    volumes:
+      - postgres_data_pgvector:/var/lib/postgresql/data
+  vdms:
+    image: intellabs/vdms:latest
+    container_name: vdms_container
+    ports:
+      - "6025:55555"
+
+volumes:
+  postgres_data:
+  postgres_data_pgvector:

docs/.gitignore

@@ -0,0 +1,2 @@
+/.quarto/
+src/supabase.d.ts

docs/.yarnrc.yml

@@ -0,0 +1 @@
+nodeLinker: node-modules

docs/api_reference/conf.py

@@ -1,4 +1,5 @@
 """Configuration file for the Sphinx documentation builder."""
+
 # Configuration file for the Sphinx documentation builder.
 #
 # This file only contains a selection of the most common options. For a full
@@ -49,7 +50,7 @@ class ExampleLinksDirective(SphinxDirective):
         class_or_func_name = self.arguments[0]
         links = imported_classes.get(class_or_func_name, {})
         list_node = nodes.bullet_list()
-        for doc_name, link in links.items():
+        for doc_name, link in sorted(links.items()):
             item_node = nodes.list_item()
             para_node = nodes.paragraph()
             link_node = nodes.reference()
@@ -114,8 +115,8 @@ autodoc_pydantic_field_signature_prefix = "param"
 autodoc_member_order = "groupwise"
 autoclass_content = "both"
 autodoc_typehints_format = "short"
+autodoc_typehints = "both"
 
-# autodoc_typehints = "description"
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ["templates"]
 
@@ -174,3 +175,6 @@ myst_enable_extensions = ["colon_fence"]
 
 # generate autosummary even if no references
 autosummary_generate = True
+
+html_copy_source = False
+html_show_sourcelink = False

docs/api_reference/create_api_rst.py

@@ -3,6 +3,7 @@
 import importlib
 import inspect
 import os
+import sys
 import typing
 from enum import Enum
 from pathlib import Path
@@ -217,8 +218,8 @@ def _construct_doc(
 
     for module in namespaces:
         _members = members_by_namespace[module]
-        classes = _members["classes_"]
-        functions = _members["functions"]
+        classes = [el for el in _members["classes_"] if el["is_public"]]
+        functions = [el for el in _members["functions"] if el["is_public"]]
         if not (classes or functions):
             continue
         section = f":mod:`{package_namespace}.{module}`"
@@ -244,9 +245,6 @@ Classes
 """
 
             for class_ in sorted(classes, key=lambda c: c["qualified_name"]):
-                if not class_["is_public"]:
-                    continue
-
                 if class_["kind"] == "TypedDict":
                     template = "typeddict.rst"
                 elif class_["kind"] == "enum":
@@ -264,7 +262,7 @@ Classes
 """
 
         if functions:
-            _functions = [f["qualified_name"] for f in functions if f["is_public"]]
+            _functions = [f["qualified_name"] for f in functions]
             fstring = "\n    ".join(sorted(_functions))
             full_doc += f"""\
 Functions
@@ -309,7 +307,14 @@ def _package_namespace(package_name: str) -> str:
 
 def _package_dir(package_name: str = "langchain") -> Path:
     """Return the path to the directory containing the documentation."""
-    if package_name in ("langchain", "experimental", "community", "core", "cli"):
+    if package_name in (
+        "langchain",
+        "experimental",
+        "community",
+        "core",
+        "cli",
+        "text-splitters",
+    ):
         return ROOT_DIR / "libs" / package_name / _package_namespace(package_name)
     else:
         return (
@@ -347,28 +352,29 @@ def _doc_first_line(package_name: str) -> str:
     return f".. {package_name.replace('-', '_')}_api_reference:\n\n"
 
 
-def main() -> None:
+def main(dirs: Optional[list] = None) -> None:
     """Generate the api_reference.rst file for each package."""
     print("Starting to build API reference files.")
-    for dir in os.listdir(ROOT_DIR / "libs"):
+    if not dirs:
+        dirs = [
+            dir_
+            for dir_ in os.listdir(ROOT_DIR / "libs")
+            if dir_ not in ("cli", "partners")
+        ]
+        dirs += os.listdir(ROOT_DIR / "libs" / "partners")
+    for dir_ in dirs:
         # Skip any hidden directories
         # Some of these could be present by mistake in the code base
         # e.g., .pytest_cache from running tests from the wrong location.
-        if not dir.startswith("."):
-            print("Skipping dir:", dir)
-            continue
-
-        if dir in ("cli", "partners"):
+        if dir_.startswith("."):
+            print("Skipping dir:", dir_)
             continue
         else:
-            print("Building package:", dir)
-            _build_rst_file(package_name=dir)
-    partner_packages = os.listdir(ROOT_DIR / "libs" / "partners")
-    print("Building partner packages:", partner_packages)
-    for dir in partner_packages:
-        _build_rst_file(package_name=dir)
+            print("Building package:", dir_)
+            _build_rst_file(package_name=dir_)
     print("API reference files built.")
 
 
 if __name__ == "__main__":
-    main()
+    dirs = sys.argv[1:] or None
+    main(dirs=dirs)

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

@@ -43,6 +43,9 @@
         <li class="nav-item">
           <a class="sk-nav-link nav-link" href="{{ pathto('experimental_api_reference') }}">Experimental</a>
         </li>
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link" href="{{ pathto('text_splitters_api_reference') }}">Text splitters</a>
+        </li>
         {%- for title, pathname in partners %}
         <li class="nav-item">
           <a class="sk-nav-link nav-link nav-more-item-mobile-items" href="{{ pathto(pathname) }}">{{ title }}</a>

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

@@ -5,7 +5,7 @@
   <script type="text/javascript" src="{{ pathto('_static/doctools.js', 1) }}"></script>
   <script type="text/javascript" src="{{ pathto('_static/language_data.js', 1) }}"></script>
   <script type="text/javascript" src="{{ pathto('_static/searchtools.js', 1) }}"></script>
-  <!-- <script type="text/javascript" src="{{ pathto('_static/sphinx_highlight.js', 1) }}"></script> -->
+  <script type="text/javascript" src="{{ pathto('_static/sphinx_highlight.js', 1) }}"></script>
   <script type="text/javascript">
     $(document).ready(function() {
       if (!Search.out) {

docs/docs/additional_resources/dependents.mdx

@@ -241,7 +241,6 @@ Dependents stats for `langchain-ai/langchain`
 |[alejandro-ao/langchain-ask-pdf](https://github.com/alejandro-ao/langchain-ask-pdf) | 514 |
 |[sajjadium/ctf-archives](https://github.com/sajjadium/ctf-archives) | 507 |
 |[continuum-llms/chatgpt-memory](https://github.com/continuum-llms/chatgpt-memory) | 502 |
-|[llmOS/opencopilot](https://github.com/llmOS/opencopilot) | 495 |
 |[steamship-core/steamship-langchain](https://github.com/steamship-core/steamship-langchain) | 494 |
 |[mpaepper/content-chatbot](https://github.com/mpaepper/content-chatbot) | 493 |
 |[langchain-ai/langchain-aiplugin](https://github.com/langchain-ai/langchain-aiplugin) | 492 |
@@ -455,7 +454,6 @@ Dependents stats for `langchain-ai/langchain`
 |[Teahouse-Studios/akari-bot](https://github.com/Teahouse-Studios/akari-bot) | 149 |
 |[realminchoi/babyagi-ui](https://github.com/realminchoi/babyagi-ui) | 148 |
 |[ssheng/BentoChain](https://github.com/ssheng/BentoChain) | 148 |
-|[lmstudio-ai/examples](https://github.com/lmstudio-ai/examples) | 147 |
 |[solana-labs/chatgpt-plugin](https://github.com/solana-labs/chatgpt-plugin) | 147 |
 |[aurelio-labs/arxiv-bot](https://github.com/aurelio-labs/arxiv-bot) | 147 |
 |[Jaseci-Labs/jaseci](https://github.com/Jaseci-Labs/jaseci) | 146 |

docs/docs/additional_resources/tutorials.mdx

@@ -1,155 +1,55 @@
 # Tutorials
 
-Below are links to tutorials and courses on LangChain. For written guides on common use cases for LangChain, check out the [use cases guides](/docs/use_cases).
+## Books and Handbooks
 
-⛓ icon marks a new addition [last update 2024-02-06]
+- [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
+- [LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
+- [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
 
----------------------
-
-### [LangChain](https://en.wikipedia.org/wiki/LangChain) on Wikipedia
-
-### Books
-
-#### [Generative AI with LangChain](https://www.amazon.com/Generative-AI-LangChain-language-ChatGPT/dp/1835083463/ref=sr_1_1?crid=1GMOMH0G7GLR&keywords=generative+ai+with+langchain&qid=1703247181&sprefix=%2Caps%2C298&sr=8-1) by [Ben Auffrath](https://www.amazon.com/stores/Ben-Auffarth/author/B08JQKSZ7D?ref=ap_rdr&store_ref=ap_rdr&isDramIntegrated=true&shoppingPortalEnabled=true), ©️ 2023 Packt Publishing
-
-
-### DeepLearning.AI courses
- by [Harrison Chase](https://en.wikipedia.org/wiki/LangChain) and [Andrew Ng](https://en.wikipedia.org/wiki/Andrew_Ng)
-- [LangChain for LLM Application Development](https://learn.deeplearning.ai/langchain)
-- [LangChain Chat with Your Data](https://learn.deeplearning.ai/langchain-chat-with-your-data)
-- [Functions, Tools and Agents with LangChain](https://learn.deeplearning.ai/functions-tools-agents-langchain)
-
-### Handbook
-[LangChain AI Handbook](https://www.pinecone.io/learn/langchain/) By **James Briggs** and **Francisco Ingham**
-
-⛓ [LangChain Cheatsheet](https://pub.towardsai.net/langchain-cheatsheet-all-secrets-on-a-single-page-8be26b721cde) by **Ivan Reznikov**
-
-### Short Tutorials
-[LangChain Explained in 13 Minutes | QuickStart Tutorial for Beginners](https://youtu.be/aywZrzNaKjs) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-
-[LangChain Crash Course: Build an AutoGPT app in 25 minutes](https://youtu.be/MlK6SIjcjE8) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
-
-[LangChain Crash Course - Build apps with language models](https://youtu.be/LbT1yp6quS8) by [Patrick Loeber](https://www.youtube.com/@patloeber)
-
-⛓ [LangChain 101 Course](https://medium.com/@ivanreznikov/langchain-101-course-updated-668f7b41d6cb) by **Ivan Reznikov**
 
 ##  Tutorials
 
-### [LangChain for Gen AI and LLMs](https://www.youtube.com/playlist?list=PLIUOU7oqGTLieV9uTIFMm6_4PXg-hlN6F) by [James Briggs](https://www.youtube.com/@jamesbriggs)
-- #1 [Getting Started with `GPT-3` vs. Open Source LLMs](https://youtu.be/nE2skSRWTTs)
-- #2 [Prompt Templates for `GPT 3.5` and other LLMs](https://youtu.be/RflBcK0oDH0)
-- #3 [LLM Chains using `GPT 3.5` and other LLMs](https://youtu.be/S8j9Tk0lZHU)
-- [LangChain Data Loaders, Tokenizers, Chunking, and Datasets - Data Prep 101](https://youtu.be/eqOfr4AGLk8)
-- #4 [Chatbot Memory for `Chat-GPT`, `Davinci` + other LLMs](https://youtu.be/X05uK0TZozM)
-- #5 [Chat with OpenAI in LangChain](https://youtu.be/CnAgB3A5OlU)
-- #6 [Fixing LLM Hallucinations with Retrieval Augmentation in LangChain](https://youtu.be/kvdVduIJsc8)
-- #7 [LangChain Agents Deep Dive with `GPT 3.5`](https://youtu.be/jSP-gSEyVeI)
-- #8 [Create Custom Tools for Chatbots in LangChain](https://youtu.be/q-HNphrWsDE)
-- #9 [Build Conversational Agents with Vector DBs](https://youtu.be/H6bCqqw9xyI)
-- [Using NEW `MPT-7B` in Hugging Face and LangChain](https://youtu.be/DXpk9K7DgMo)
-- [`MPT-30B` Chatbot with LangChain](https://youtu.be/pnem-EhT6VI)
-- [Fine-tuning OpenAI's `GPT 3.5` for LangChain Agents](https://youtu.be/boHXgQ5eQic?si=OOOfK-GhsgZGBqSr)
-- [Chatbots with `RAG`: LangChain Full Walkthrough](https://youtu.be/LhnCsygAvzY?si=N7k6xy4RQksbWwsQ)
+### [LangChain v 0.1 by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae0gBSJ9T0w7cu7iJZbH3T31)
+### [Build with Langchain - Advanced by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae06tclDATrMYY0idsTdLg9v)
+### [LangGraph by LangChain.ai](https://www.youtube.com/playlist?list=PLfaIDFEXuae16n2TWUkKq5PgJ0w6Pkwtg)
+
+### [by Greg Kamradt](https://www.youtube.com/playlist?list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5)
+### [by Sam Witteveen](https://www.youtube.com/playlist?list=PL8motc6AQftk1Bs42EW45kwYbyJ4jOdiZ)
+### [by James Briggs](https://www.youtube.com/playlist?list=PLIUOU7oqGTLieV9uTIFMm6_4PXg-hlN6F)
+### [by Prompt Engineering](https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr)
+### [by Mayo Oshin](https://www.youtube.com/@chatwithdata/search?query=langchain)
+### [by 1 little Coder](https://www.youtube.com/playlist?list=PLpdmBGJ6ELUK-v0MK-t4wZmVEbxM5xk6L)
 
 
-### [LangChain 101](https://www.youtube.com/playlist?list=PLqZXAkvF1bPNQER9mLmDbntNfSpzdDIU5) by [Greg Kamradt (Data Indy)](https://www.youtube.com/@DataIndependent)
-- [What Is LangChain? - LangChain + `ChatGPT` Overview](https://youtu.be/_v_fgW2SkkQ)
-- [Quickstart Guide](https://youtu.be/kYRB-vJFy38)
-- [Beginner's Guide To 7 Essential Concepts](https://youtu.be/2xxziIWmaSA)
-- [Beginner's Guide To 9 Use Cases](https://youtu.be/vGP4pQdCocw)
-- [Agents Overview + Google Searches](https://youtu.be/Jq9Sf68ozk0)
-- [`OpenAI` + `Wolfram Alpha`](https://youtu.be/UijbzCIJ99g)
-- [Ask Questions On Your Custom (or Private) Files](https://youtu.be/EnT-ZTrcPrg)
-- [Connect `Google Drive Files` To `OpenAI`](https://youtu.be/IqqHqDcXLww)
-- [`YouTube Transcripts` + `OpenAI`](https://youtu.be/pNcQ5XXMgH4)
-- [Question A 300 Page Book (w/ `OpenAI` + `Pinecone`)](https://youtu.be/h0DHDp1FbmQ)
-- [Workaround `OpenAI's` Token Limit With Chain Types](https://youtu.be/f9_BWhCI4Zo)
-- [Build Your Own OpenAI + LangChain Web App in 23 Minutes](https://youtu.be/U_eV8wfMkXU)
-- [Working With The New `ChatGPT API`](https://youtu.be/e9P7FLi5Zy8)
-- [OpenAI + LangChain Wrote Me 100 Custom Sales Emails](https://youtu.be/y1pyAQM-3Bo)
-- [Structured Output From `OpenAI` (Clean Dirty Data)](https://youtu.be/KwAXfey-xQk)
-- [Connect `OpenAI` To +5,000 Tools (LangChain + `Zapier`)](https://youtu.be/7tNm0yiDigU)
-- [Use LLMs To Extract Data From Text (Expert Mode)](https://youtu.be/xZzvwR9jdPA)
-- [Extract Insights From Interview Transcripts Using LLMs](https://youtu.be/shkMOHwJ4SM)
-- [5 Levels Of LLM Summarizing: Novice to Expert](https://youtu.be/qaPMdcCqtWk)
-- [Control Tone & Writing Style Of Your LLM Output](https://youtu.be/miBG-a3FuhU)
-- [Build Your Own `AI Twitter Bot` Using LLMs](https://youtu.be/yLWLDjT01q8)
-- [ChatGPT made my interview questions for me (`Streamlit` + LangChain)](https://youtu.be/zvoAMx0WKkw)
-- [Function Calling via ChatGPT API - First Look With LangChain](https://youtu.be/0-zlUy7VUjg)
-- [Extract Topics From Video/Audio With LLMs (Topic Modeling w/ LangChain)](https://youtu.be/pEkxRQFNAs4)
+## Courses
 
+### Featured courses on Deeplearning.AI
 
-### [LangChain How to and guides](https://www.youtube.com/playlist?list=PL8motc6AQftk1Bs42EW45kwYbyJ4jOdiZ) by [Sam Witteveen](https://www.youtube.com/@samwitteveenai)
-- [LangChain Basics - LLMs & PromptTemplates with Colab](https://youtu.be/J_0qvRt4LNk)
-- [LangChain Basics - Tools and Chains](https://youtu.be/hI2BY7yl_Ac)
-- [`ChatGPT API` Announcement & Code Walkthrough with LangChain](https://youtu.be/phHqvLHCwH4)
-- [Conversations with Memory (explanation & code walkthrough)](https://youtu.be/X550Zbz_ROE)
-- [Chat with `Flan20B`](https://youtu.be/VW5LBavIfY4)
-- [Using `Hugging Face Models` locally (code walkthrough)](https://youtu.be/Kn7SX2Mx_Jk)
-- [`PAL`: Program-aided Language Models with LangChain code](https://youtu.be/dy7-LvDu-3s)
-- [Building a Summarization System with LangChain and `GPT-3` - Part 1](https://youtu.be/LNq_2s_H01Y)
-- [Building a Summarization System with LangChain and `GPT-3` - Part 2](https://youtu.be/d-yeHDLgKHw)
-- [Microsoft's `Visual ChatGPT` using LangChain](https://youtu.be/7YEiEyfPF5U)
-- [LangChain Agents - Joining Tools and Chains with Decisions](https://youtu.be/ziu87EXZVUE)
-- [Comparing LLMs with LangChain](https://youtu.be/rFNG0MIEuW0)
-- [Using `Constitutional AI` in LangChain](https://youtu.be/uoVqNFDwpX4)
-- [Talking to `Alpaca` with LangChain - Creating an Alpaca Chatbot](https://youtu.be/v6sF8Ed3nTE)
-- [Talk to your `CSV` & `Excel` with LangChain](https://youtu.be/xQ3mZhw69bc)
-- [`BabyAGI`: Discover the Power of Task-Driven Autonomous Agents!](https://youtu.be/QBcDLSE2ERA)
-- [Improve your `BabyAGI` with LangChain](https://youtu.be/DRgPyOXZ-oE)
-- [Master `PDF` Chat with LangChain - Your essential guide to queries on documents](https://youtu.be/ZzgUqFtxgXI)
-- [Using LangChain with `DuckDuckGO`, `Wikipedia` & `PythonREPL` Tools](https://youtu.be/KerHlb8nuVc)
-- [Building Custom Tools and Agents with LangChain (gpt-3.5-turbo)](https://youtu.be/biS8G8x8DdA)
-- [LangChain Retrieval QA Over Multiple Files with `ChromaDB`](https://youtu.be/3yPBVii7Ct0)
-- [LangChain Retrieval QA with Instructor Embeddings & `ChromaDB` for PDFs](https://youtu.be/cFCGUjc33aU)
-- [LangChain + Retrieval Local LLMs for Retrieval QA - No OpenAI!!!](https://youtu.be/9ISVjh8mdlA)
-- [`Camel` + LangChain for Synthetic Data & Market Research](https://youtu.be/GldMMK6-_-g)
-- [Information Extraction with LangChain & `Kor`](https://youtu.be/SW1ZdqH0rRQ)
-- [Converting a LangChain App from OpenAI to OpenSource](https://youtu.be/KUDn7bVyIfc)
-- [Using LangChain `Output Parsers` to get what you want out of LLMs](https://youtu.be/UVn2NroKQCw)
-- [Building a LangChain Custom Medical Agent with Memory](https://youtu.be/6UFtRwWnHws)
-- [Understanding `ReACT` with LangChain](https://youtu.be/Eug2clsLtFs)
-- [`OpenAI Functions` + LangChain : Building a Multi Tool Agent](https://youtu.be/4KXK6c6TVXQ)
-- [What can you do with 16K tokens in LangChain?](https://youtu.be/z2aCZBAtWXs)
-- [Tagging and Extraction - Classification using `OpenAI Functions`](https://youtu.be/a8hMgIcUEnE)
-- [HOW to Make Conversational Form with LangChain](https://youtu.be/IT93On2LB5k)
-- [`Claude-2` meets LangChain!](https://youtu.be/Hb_D3p0bK2U?si=j96Kc7oJoeRI5-iC)
-- [`PaLM 2` Meets LangChain](https://youtu.be/orPwLibLqm4?si=KgJjpEbAD9YBPqT4)
-- [`LLaMA2` with LangChain - Basics | LangChain TUTORIAL](https://youtu.be/cIRzwSXB4Rc?si=v3Hwxk1m3fksBIHN)
-- [Serving `LLaMA2` with `Replicate`](https://youtu.be/JIF4nNi26DE?si=dSazFyC4UQmaR-rJ)
-- [NEW LangChain Expression Language](https://youtu.be/ud7HJ2p3gp0?si=8pJ9O6hGbXrCX5G9)
-- [Building a RCI Chain for Agents with LangChain Expression Language](https://youtu.be/QaKM5s0TnsY?si=0miEj-o17AHcGfLG)
-- [How to Run `LLaMA-2-70B` on the `Together AI`](https://youtu.be/Tc2DHfzHeYE?si=Xku3S9dlBxWQukpe)
-- [`RetrievalQA` with `LLaMA 2 70b` & `Chroma` DB](https://youtu.be/93yueQQnqpM?si=ZMwj-eS_CGLnNMXZ)
-- [How to use `BGE Embeddings` for LangChain](https://youtu.be/sWRvSG7vL4g?si=85jnvnmTCF9YIWXI)
-- [How to use Custom Prompts for `RetrievalQA` on `LLaMA-2 7B`](https://youtu.be/PDwUKves9GY?si=sMF99TWU0p4eiK80)
+- [LangChain for LLM Application Development](https://www.deeplearning.ai/short-courses/langchain-for-llm-application-development/)
+- [LangChain Chat with Your Data](https://www.deeplearning.ai/short-courses/langchain-chat-with-your-data/)
+- [Functions, Tools and Agents with LangChain](https://www.deeplearning.ai/short-courses/functions-tools-agents-langchain/)
+- [Build LLM Apps with LangChain.js](https://www.deeplearning.ai/short-courses/build-llm-apps-with-langchain-js/)
 
+### Online courses
 
-### [LangChain](https://www.youtube.com/playlist?list=PLVEEucA9MYhOu89CX8H3MBZqayTbcCTMr) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
-- [LangChain Crash Course — All You Need to Know to Build Powerful Apps with LLMs](https://youtu.be/5-fc4Tlgmro)
-- [Working with MULTIPLE `PDF` Files in LangChain: `ChatGPT` for your Data](https://youtu.be/s5LhRdh5fu4)
-- [`ChatGPT` for YOUR OWN `PDF` files with LangChain](https://youtu.be/TLf90ipMzfE)
-- [Talk to YOUR DATA without OpenAI APIs: LangChain](https://youtu.be/wrD-fZvT6UI)
-- [LangChain: `PDF` Chat App (GUI) | `ChatGPT` for Your `PDF` FILES](https://youtu.be/RIWbalZ7sTo)
-- [`LangFlow`: Build Chatbots without Writing Code](https://youtu.be/KJ-ux3hre4s)
-- [LangChain: Giving Memory to LLMs](https://youtu.be/dxO6pzlgJiY)
-- [BEST OPEN Alternative to `OPENAI's EMBEDDINGs` for Retrieval QA: LangChain](https://youtu.be/ogEalPMUCSY)
-- [LangChain: Run Language Models Locally - `Hugging Face Models`](https://youtu.be/Xxxuw4_iCzw) 
-- [Slash API Costs: Mastering Caching for LLM Applications](https://youtu.be/EQOznhaJWR0?si=AXoI7f3-SVFRvQUl)
-- [Avoid PROMPT INJECTION with `Constitutional AI` - LangChain](https://youtu.be/tyKSkPFHVX8?si=9mgcB5Y1kkotkBGB)
+- [Udemy](https://www.udemy.com/courses/search/?q=langchain)
+- [Pluralsight](https://www.pluralsight.com/search?q=langchain)
+- [Coursera](https://www.coursera.org/search?query=langchain)
+- [Maven](https://maven.com/courses?query=langchain)
+- [Udacity](https://www.udacity.com/catalog/all/any-price/any-school/any-skill/any-difficulty/any-duration/any-type/relevance/page-1?searchValue=langchain)
+- [LinkedIn Learning](https://www.linkedin.com/search/results/learning/?keywords=langchain)
+- [edX](https://www.edx.org/search?q=langchain)
+- [freeCodeCamp](https://www.youtube.com/@freecodecamp/search?query=langchain)
 
+## Short Tutorials
 
-### LangChain by [Chat with data](https://www.youtube.com/@chatwithdata)
-- [LangChain Beginner's Tutorial for `Typescript`/`Javascript`](https://youtu.be/bH722QgRlhQ)
-- [`GPT-4` Tutorial: How to Chat With Multiple `PDF` Files (~1000 pages of Tesla's 10-K Annual Reports)](https://youtu.be/Ix9WIZpArm0)
-- [`GPT-4` & LangChain Tutorial: How to Chat With A 56-Page `PDF` Document (w/`Pinecone`)](https://youtu.be/ih9PBGVVOO4)
-- [LangChain & `Supabase` Tutorial: How to Build a ChatGPT Chatbot For Your Website](https://youtu.be/R2FMzcsmQY8)
-- [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI)
-
-
-### Codebase Analysis
-- [Codebase Analysis: Langchain Agents](https://carbonated-yacht-2c5.notion.site/Codebase-Analysis-Langchain-Agents-0b0587acd50647ca88aaae7cff5df1f2)
+- [by Nicholas Renotte](https://youtu.be/MlK6SIjcjE8)
+- [by Patrick Loeber](https://youtu.be/LbT1yp6quS8)
+- [by Rabbitmetrics](https://youtu.be/aywZrzNaKjs)
+- [by Ivan Reznikov](https://medium.com/@ivanreznikov/langchain-101-course-updated-668f7b41d6cb)
 
+## [Documentation: Use cases](/docs/use_cases)
 
 ---------------------
-⛓ icon marks a new addition [last update 2024-02-061]
+
+

docs/docs/additional_resources/youtube.mdx

@@ -7,7 +7,7 @@
 ### Introduction to LangChain with Harrison Chase, creator of LangChain
 - [Building the Future with LLMs, `LangChain`, & `Pinecone`](https://youtu.be/nMniwlGyX-c) by [Pinecone](https://www.youtube.com/@pinecone-io)
 - [LangChain and Weaviate with Harrison Chase and Bob van Luijt - Weaviate Podcast #36](https://youtu.be/lhby7Ql7hbk) by [Weaviate • Vector Database](https://www.youtube.com/@Weaviate)
-- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@FullStackDeepLearning)
+- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@The_Full_Stack)
 - [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI) by [Chat with data](https://www.youtube.com/@chatwithdata)
 
 ## Videos (sorted by views)
@@ -15,8 +15,8 @@
 - [Using `ChatGPT` with YOUR OWN Data. This is magical. (LangChain OpenAI API)](https://youtu.be/9AXP7tCI9PI) by [TechLead](https://www.youtube.com/@TechLead)
 - [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson) 
 - [LangChain explained - The hottest new Python framework](https://youtu.be/RoR4XJw8wIc) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
-- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
-- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
+- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DaveShap)
+- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DaveShap)
 - [Build your own LLM Apps with LangChain & `GPT-Index`](https://youtu.be/-75p09zFUJY) by [1littlecoder](https://www.youtube.com/@1littlecoder)
 - [`BabyAGI` - New System of Autonomous AI Agents with LangChain](https://youtu.be/lg3kJvf1kXo) by [1littlecoder](https://www.youtube.com/@1littlecoder)
 - [Run `BabyAGI` with Langchain Agents (with Python Code)](https://youtu.be/WosPGHPObx8) by [1littlecoder](https://www.youtube.com/@1littlecoder)
@@ -37,15 +37,15 @@
 - [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
 - [`ChatGPT` with any `YouTube` video using langchain and `chromadb`](https://youtu.be/TQZfB2bzVwU) by [echohive](https://www.youtube.com/@echohive)
 - [How to Talk to a `PDF` using LangChain and `ChatGPT`](https://youtu.be/v2i1YDtrIwk) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
-- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@merksworld) 
-- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nick_daigs)
+- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@heymichaeldaigler) 
+- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nickdaigler)
 - [LangChain. Crear aplicaciones Python impulsadas por GPT](https://youtu.be/DkW_rDndts8) by [Jesús Conde](https://www.youtube.com/@0utKast)
 - [Easiest Way to Use GPT In Your Products | LangChain Basics Tutorial](https://youtu.be/fLy0VenZyGc) by [Rachel Woods](https://www.youtube.com/@therachelwoods)
 - [`BabyAGI` + `GPT-4` Langchain Agent with Internet Access](https://youtu.be/wx1z_hs5P6E) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
 - [Learning LLM Agents. How does it actually work? LangChain, AutoGPT & OpenAI](https://youtu.be/mb_YAABSplk) by [Arnoldas Kemeklis](https://www.youtube.com/@processusAI)
 - [Get Started with LangChain in `Node.js`](https://youtu.be/Wxx1KUWJFv4) by [Developers Digest](https://www.youtube.com/@DevelopersDigest)
 - [LangChain + `OpenAI` tutorial: Building a Q&A system w/ own text data](https://youtu.be/DYOU_Z0hAwo) by [Samuel Chan](https://www.youtube.com/@SamuelChan)
-- [Langchain + `Zapier` Agent](https://youtu.be/yribLAb-pxA) by [Merk](https://www.youtube.com/@merksworld)
+- [Langchain + `Zapier` Agent](https://youtu.be/yribLAb-pxA) by [Merk](https://www.youtube.com/@heymichaeldaigler)
 - [Connecting the Internet with `ChatGPT` (LLMs) using Langchain And Answers Your Questions](https://youtu.be/9Y0TBC63yZg) by [Kamalraj M M](https://www.youtube.com/@insightbuilder)
 - [Build More Powerful LLM Applications for Business’s with LangChain (Beginners Guide)](https://youtu.be/sp3-WLKEcBg) by[ No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
 - [LangFlow LLM Agent Demo for 🦜🔗LangChain](https://youtu.be/zJxDHaWt-6o) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
@@ -82,7 +82,7 @@
 - [Build a LangChain-based Semantic PDF Search App with No-Code Tools Bubble and Flowise](https://youtu.be/s33v5cIeqA4) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
 - [LangChain Memory Tutorial | Building a ChatGPT Clone in Python](https://youtu.be/Cwq91cj2Pnc) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
 - [ChatGPT For Your DATA | Chat with Multiple Documents Using LangChain](https://youtu.be/TeDgIDqQmzs) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
-- [`Llama Index`: Chat with Documentation using URL Loader](https://youtu.be/XJRoDEctAwA) by [Merk](https://www.youtube.com/@merksworld)
+- [`Llama Index`: Chat with Documentation using URL Loader](https://youtu.be/XJRoDEctAwA) by [Merk](https://www.youtube.com/@heymichaeldaigler)
 - [Using OpenAI, LangChain, and `Gradio` to Build Custom GenAI Applications](https://youtu.be/1MsmqMg3yUc) by [David Hundley](https://www.youtube.com/@dkhundley)
 - [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0)
 - [Build AI chatbot with custom knowledge base using OpenAI API and GPT Index](https://youtu.be/vDZAZuaXf48) by [Irina Nik](https://www.youtube.com/@irina_nik)
@@ -93,7 +93,7 @@
 - [Build a Custom Chatbot with OpenAI: `GPT-Index` & LangChain | Step-by-Step Tutorial](https://youtu.be/FIDv6nc4CgU) by [Fabrikod](https://www.youtube.com/@fabrikod)
 - [`Flowise` is an open-source no-code UI visual tool to build 🦜🔗LangChain applications](https://youtu.be/CovAPtQPU0k) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
 - [LangChain & GPT 4 For Data Analysis: The `Pandas` Dataframe Agent](https://youtu.be/rFQ5Kmkd4jc) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
-- [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Toolfinder AI](https://www.youtube.com/@toolfinderai)
+- [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Girlfriend GPT](https://www.youtube.com/@girlfriendGPT)
 - [How to build with Langchain 10x easier | ⛓️ LangFlow & `Flowise`](https://youtu.be/Ya1oGL7ZTvU) by [AI Jason](https://www.youtube.com/@AIJasonZ)
 - [Getting Started With LangChain In 20 Minutes- Build Celebrity Search Application](https://youtu.be/_FpT1cwcSLg) by [Krish Naik](https://www.youtube.com/@krishnaik06)
 - ⛓ [Vector Embeddings Tutorial – Code Your Own AI Assistant with `GPT-4 API` + LangChain + NLP](https://youtu.be/yfHHvmaMkcA?si=5uJhxoh2tvdnOXok) by [FreeCodeCamp.org](https://www.youtube.com/@freecodecamp)
@@ -109,7 +109,7 @@
 - ⛓ [PyData Heidelberg #11 - TimeSeries Forecasting & LLM Langchain](https://www.youtube.com/live/Glbwb5Hxu18?si=PIEY8Raq_C9PCHuW) by [PyData](https://www.youtube.com/@PyDataTV)
 - ⛓ [Prompt Engineering in Web Development | Using LangChain and Templates with OpenAI](https://youtu.be/pK6WzlTOlYw?si=fkcDQsBG2h-DM8uQ) by [Akamai Developer
 ](https://www.youtube.com/@AkamaiDeveloper)
-- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIDataScienceOnAWS)
+- ⛓ [Retrieval-Augmented Generation (RAG) using LangChain and `Pinecone` - The RAG Special Episode](https://youtu.be/J_tCD_J6w3s?si=60Mnr5VD9UED9bGG) by [Generative AI and Data Science On AWS](https://www.youtube.com/@GenerativeAIOnAWS)
 - ⛓ [`LLAMA2 70b-chat` Multiple Documents Chatbot with Langchain & Streamlit |All OPEN SOURCE|Replicate API](https://youtu.be/vhghB81vViM?si=dszzJnArMeac7lyc) by [DataInsightEdge](https://www.youtube.com/@DataInsightEdge01)
 - ⛓ [Chatting with 44K Fashion Products: LangChain Opportunities and Pitfalls](https://youtu.be/Zudgske0F_s?si=8HSshHoEhh0PemJA) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
 - ⛓ [Structured Data Extraction from `ChatGPT` with LangChain](https://youtu.be/q1lYg8JISpQ?si=0HctzOHYZvq62sve) by [MG](https://www.youtube.com/@MG_cafe)

docs/docs/contributing/code.mdx

@@ -98,7 +98,7 @@ To run unit tests in Docker:
 make docker_tests
 ```
 
-There are also [integration tests and code-coverage](./testing) available.
+There are also [integration tests and code-coverage](/docs/contributing/testing/) available.
 
 ### Only develop langchain_core or langchain_experimental
 

docs/docs/contributing/documentation.mdx

@@ -1,66 +0,0 @@
----
-sidebar_position: 3
----
-# Contribute Documentation
-
-The docs directory contains Documentation and API Reference.
-
-Documentation is built using [Quarto](https://quarto.org) and [Docusaurus 2](https://docusaurus.io/).
-
-API Reference are largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code and are hosted by [Read the Docs](https://readthedocs.org/).
-For that reason, we ask that you add good documentation to all classes and methods.
-
-Similar to linting, we recognize documentation can be annoying. If you do not want to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
-
-## Build Documentation Locally
-
-### Install dependencies
-
-- [Quarto](https://quarto.org) - package that converts Jupyter notebooks (`.ipynb` files) into mdx files for serving in Docusaurus.
-- `poetry install --with lint,docs --no-root` from the monorepo root.
-
-### Building
-
-In the following commands, the prefix `api_` indicates that those are operations for the API Reference.
-
-Before building the documentation, it is always a good idea to clean the build directory:
-
-```bash
-make docs_clean
-make api_docs_clean
-```
-
-Next, you can build the documentation as outlined below:
-
-```bash
-make docs_build
-make api_docs_build
-```
-
-Finally, run the link checker to ensure all links are valid:
-
-```bash
-make docs_linkcheck
-make api_docs_linkcheck
-```
-
-### Linting and Formatting
-
-The docs are linted from the monorepo root. To lint the docs, run the following from there:
-
-```bash
-make lint
-```
-
-If you have formatting-related errors, you can fix them automatically with:
-
-```bash
-make format
-``` 
-
-## Verify Documentation changes
-
-After pushing documentation changes to the repository, you can preview and verify that the changes are
-what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page.
-This will take you to a preview of the documentation changes.
-This preview is created by [Vercel](https://vercel.com/docs/getting-started-with-vercel).

docs/docs/contributing/documentation/_category_.yml

@@ -0,0 +1,2 @@
+label: 'Documentation'
+position: 3

docs/docs/contributing/documentation/style_guide.mdx

@@ -0,0 +1,138 @@
+---
+sidebar_label: "Style guide"
+---
+
+# LangChain Documentation Style Guide
+
+## Introduction
+
+As LangChain continues to grow, the surface area of documentation required to cover it continues to grow too.
+This page provides guidelines for anyone writing documentation for LangChain, as well as some of our philosophies around
+organization and structure.
+
+## Philosophy
+
+LangChain's documentation aspires to follow the [Diataxis framework](https://diataxis.fr).
+Under this framework, all documentation falls under one of four categories:
+
+- **Tutorials**: Lessons that take the reader by the hand through a series of conceptual steps to complete a project.
+  - An example of this is our [LCEL streaming guide](/docs/expression_language/streaming).
+  - Our guides on [custom components](/docs/modules/model_io/chat/custom_chat_model) is another one.
+- **How-to guides**: Guides that take the reader through the steps required to solve a real-world problem.
+  - The clearest examples of this are our [Use case](/docs/use_cases/) quickstart pages.
+- **Reference**: Technical descriptions of the machinery and how to operate it.
+  - Our [Runnable interface](/docs/expression_language/interface) page is an example of this.
+  - The [API reference pages](https://api.python.langchain.com/) are another.
+- **Explanation**: Explanations that clarify and illuminate a particular topic.
+  - The [LCEL primitives pages](/docs/expression_language/primitives/sequence) are an example of this.
+
+Each category serves a distinct purpose and requires a specific approach to writing and structuring the content.
+
+## Taxonomy
+
+Keeping the above in mind, we have sorted LangChain's docs into categories. It is helpful to think in these terms
+when contributing new documentation:
+
+### Getting started
+
+The [getting started section](/docs/get_started/introduction) includes a high-level introduction to LangChain, a quickstart that
+tours LangChain's various features, and logistical instructions around installation and project setup.
+
+It contains elements of **How-to guides** and **Explanations**.
+
+### Use cases
+
+[Use cases](/docs/use_cases/) are guides that are meant to show how to use LangChain to accomplish a specific task (RAG, information extraction, etc.).
+The quickstarts should be good entrypoints for first-time LangChain developers who prefer to learn by getting something practical prototyped,
+then taking the pieces apart retrospectively. These should mirror what LangChain is good at.
+
+The quickstart pages here should fit the **How-to guide** category, with the other pages intended to be **Explanations** of more
+in-depth concepts and strategies that accompany the main happy paths.
+
+:::note
+The below sections are listed roughly in order of increasing level of abstraction.
+:::
+
+### Expression Language
+
+[LangChain Expression Language (LCEL)](/docs/expression_language/) is the fundamental way that most LangChain components fit together, and this section is designed to teach
+developers how to use it to build with LangChain's primitives effectively.
+
+This section should contains **Tutorials** that teach how to stream and use LCEL primitives for more abstract tasks, **Explanations** of specific behaviors,
+and some **References** for how to use different methods in the Runnable interface.
+
+### Components
+
+The [components section](/docs/modules) covers concepts one level of abstraction higher than LCEL.
+Abstract base classes like `BaseChatModel` and `BaseRetriever` should be covered here, as well as core implementations of these base classes,
+such as `ChatPromptTemplate` and `RecursiveCharacterTextSplitter`. Customization guides belong here too.
+
+This section should contain mostly conceptual **Tutorials**, **References**, and **Explanations** of the components they cover.
+
+:::note
+As a general rule of thumb, everything covered in the `Expression Language` and `Components` sections (with the exception of the `Composition` section of components) should
+cover only components that exist in `langchain_core`.
+:::
+
+### Integrations
+
+The [integrations](/docs/integrations/platforms/) are specific implementations of components. These often involve third-party APIs and services.
+If this is the case, as a general rule, these are maintained by the third-party partner.
+
+This section should contain mostly **Explanations** and **References**, though the actual content here is more flexible than other sections and more at the
+discretion of the third-party provider.
+
+:::note
+Concepts covered in `Integrations` should generally exist in `langchain_community` or specific partner packages.
+:::
+
+### Guides and Ecosystem
+
+The [Guides](/docs/guides) and [Ecosystem](/docs/langsmith/) sections should contain guides that address higher-level problems than the sections above.
+This includes, but is not limited to, considerations around productionization and development workflows.
+
+These should contain mostly **How-to guides**, **Explanations**, and **Tutorials**.
+
+### API references
+
+LangChain's API references. Should act as **References** (as the name implies) with some **Explanation**-focused content as well. 
+
+## Sample developer journey
+
+We have set up our docs to assist a new developer to LangChain. Let's walk through the intended path:
+
+- The developer lands on https://python.langchain.com, and reads through the introduction and the diagram.
+- If they are just curious, they may be drawn to the [Quickstart](/docs/get_started/quickstart) to get a high-level tour of what LangChain contains.
+- If they have a specific task in mind that they want to accomplish, they will be drawn to the Use-Case section. The use-case should provide a good, concrete hook that shows the value LangChain can provide them and be a good entrypoint to the framework.
+- They can then move to learn more about the fundamentals of LangChain through the Expression Language sections.
+- Next, they can learn about LangChain's various components and integrations.
+- Finally, they can get additional knowledge through the Guides.
+
+This is only an ideal of course - sections will inevitably reference lower or higher-level concepts that are documented in other sections.
+
+## Guidelines
+
+Here are some other guidelines you should think about when writing and organizing documentation.
+
+### Linking to other sections
+
+Because sections of the docs do not exist in a vacuum, it is important to link to other sections as often as possible
+to allow a developer to learn more about an unfamiliar topic inline.
+
+This includes linking to the API references as well as conceptual sections!
+
+### Conciseness
+
+In general, take a less-is-more approach. If a section with a good explanation of a concept already exists, you should link to it rather than
+re-explain it, unless the concept you are documenting presents some new wrinkle.
+
+Be concise, including in code samples.
+
+### General style
+
+- Use active voice and present tense whenever possible.
+- Use examples and code snippets to illustrate concepts and usage.
+- Use appropriate header levels (`#`, `##`, `###`, etc.) to organize the content hierarchically.
+- Use bullet points and numbered lists to break down information into easily digestible chunks.
+- Use tables (especially for **Reference** sections) and diagrams often to present information visually.
+- Include the table of contents for longer documentation pages to help readers navigate the content, but hide it for shorter pages.

docs/docs/contributing/documentation/technical_logistics.mdx

@@ -0,0 +1,171 @@
+# Technical logistics
+
+LangChain documentation consists of two components:
+
+1. Main Documentation: Hosted at [python.langchain.com](https://python.langchain.com/),
+this comprehensive resource serves as the primary user-facing documentation.
+It covers a wide array of topics, including tutorials, use cases, integrations,
+and more, offering extensive guidance on building with LangChain.
+The content for this documentation lives in the `/docs` directory of the monorepo.
+2. In-code Documentation: This is documentation of the codebase itself, which is also
+used to generate the externally facing [API Reference](https://api.python.langchain.com/en/latest/langchain_api_reference.html).
+The content for the API reference is autogenerated by scanning the docstrings in the codebase. For this reason we ask that
+developers document their code well.
+
+The main documentation is built using [Quarto](https://quarto.org) and [Docusaurus 2](https://docusaurus.io/).
+
+The `API Reference` is largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/)
+from the code and is hosted by [Read the Docs](https://readthedocs.org/).
+
+We appreciate all contributions to the documentation, whether it be fixing a typo,
+adding a new tutorial or example and whether it be in the main documentation or the API Reference.
+
+Similar to linting, we recognize documentation can be annoying. If you do not want
+to do it, please contact a project maintainer, and they can help you with it. We do not want this to be a blocker for good code getting contributed.
+
+## 📜 Main Documentation
+
+The content for the main documentation is located in the `/docs` directory of the monorepo.
+
+The documentation is written using a combination of ipython notebooks (`.ipynb` files)
+and markdown (`.mdx` files). The notebooks are converted to markdown
+using [Quarto](https://quarto.org) and then built using [Docusaurus 2](https://docusaurus.io/).
+
+Feel free to make contributions to the main documentation! 🥰
+
+After modifying the documentation:
+
+1. Run the linting and formatting commands (see below) to ensure that the documentation is well-formatted and free of errors.
+2. Optionally build the documentation locally to verify that the changes look good.
+3. Make a pull request with the changes.
+4. You can preview and verify that the changes are what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page. This will take you to a preview of the documentation changes.
+
+## ⚒️ Linting and Building Documentation Locally
+
+After writing up the documentation, you may want to lint and build the documentation
+locally to ensure that it looks good and is free of errors.
+
+If you're unable to build it locally that's okay as well, as you will be able to
+see a preview of the documentation on the pull request page.
+
+### Install dependencies
+
+- [Quarto](https://quarto.org) - package that converts Jupyter notebooks (`.ipynb` files) into mdx files for serving in Docusaurus. [Download link](https://quarto.org/docs/download/).
+
+From the **monorepo root**, run the following command to install the dependencies:
+
+```bash
+poetry install --with lint,docs --no-root
+````
+
+### Building
+
+The code that builds the documentation is located in the `/docs` directory of the monorepo.
+
+In the following commands, the prefix `api_` indicates that those are operations for the API Reference.
+
+Before building the documentation, it is always a good idea to clean the build directory:
+
+```bash
+make docs_clean
+make api_docs_clean
+```
+
+Next, you can build the documentation as outlined below:
+
+```bash
+make docs_build
+make api_docs_build
+```
+
+Finally, run the link checker to ensure all links are valid:
+
+```bash
+make docs_linkcheck
+make api_docs_linkcheck
+```
+
+### Linting and Formatting
+
+The Main Documentation is linted from the **monorepo root**. To lint the main documentation, run the following from there:
+
+```bash
+make lint
+```
+
+If you have formatting-related errors, you can fix them automatically with:
+
+```bash
+make format
+```
+
+## ⌨️ In-code Documentation
+
+The in-code documentation is largely autogenerated by [sphinx](https://www.sphinx-doc.org/en/master/) from the code and is hosted by [Read the Docs](https://readthedocs.org/).
+
+For the API reference to be useful, the codebase must be well-documented. This means that all functions, classes, and methods should have a docstring that explains what they do, what the arguments are, and what the return value is. This is a good practice in general, but it is especially important for LangChain because the API reference is the primary resource for developers to understand how to use the codebase.
+
+We generally follow the [Google Python Style Guide](https://google.github.io/styleguide/pyguide.html#38-comments-and-docstrings) for docstrings.
+
+Here is an example of a well-documented function:
+
+```python
+
+def my_function(arg1: int, arg2: str) -> float:
+    """This is a short description of the function. (It should be a single sentence.)
+
+    This is a longer description of the function. It should explain what
+    the function does, what the arguments are, and what the return value is.
+    It should wrap at 88 characters.
+
+    Examples:
+        This is a section for examples of how to use the function.
+
+        .. code-block:: python
+
+            my_function(1, "hello")
+
+    Args:
+        arg1: This is a description of arg1. We do not need to specify the type since
+            it is already specified in the function signature.
+        arg2: This is a description of arg2.
+
+    Returns:
+        This is a description of the return value.
+    """
+    return 3.14
+```
+
+### Linting and Formatting
+
+The in-code documentation is linted from the directories belonging to the packages
+being documented.
+
+For example, if you're working on the `langchain-community` package, you would change
+the working directory to the `langchain-community` directory:
+
+```bash
+cd [root]/libs/langchain-community
+```
+
+Set up a virtual environment for the package if you haven't done so already.
+
+Install the dependencies for the package.
+
+```bash
+poetry install --with lint
+```
+
+Then you can run the following commands to lint and format the in-code documentation:
+
+```bash
+make format
+make lint
+```
+
+## Verify Documentation Changes
+
+After pushing documentation changes to the repository, you can preview and verify that the changes are
+what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page.
+This will take you to a preview of the documentation changes.
+This preview is created by [Vercel](https://vercel.com/docs/getting-started-with-vercel).

docs/docs/contributing/index.mdx

@@ -12,7 +12,7 @@ As an open-source project in a rapidly developing field, we are extremely open t
 
 There are many ways to contribute to LangChain. Here are some common ways people contribute:
 
-- [**Documentation**](./documentation.mdx): Help improve our docs, including this one!
+- [**Documentation**](/docs/contributing/documentation/style_guide): Help improve our docs, including this one!
 - [**Code**](./code.mdx): Help us write code, fix bugs, or improve our infrastructure.
 - [**Integrations**](integrations.mdx): Help us integrate with your favorite vendors and tools.
 - [**Discussions**](https://github.com/langchain-ai/langchain/discussions): Help answer usage questions and discuss issues with users.

docs/docs/contributing/integrations.mdx

@@ -3,7 +3,7 @@ sidebar_position: 5
 ---
 # Contribute Integrations
 
-To begin, make sure you have all the dependencies outlined in guide on [Contributing Code](./code).
+To begin, make sure you have all the dependencies outlined in guide on [Contributing Code](/docs/contributing/code/).
 
 There are a few different places you can contribute integrations for LangChain:
 
@@ -14,19 +14,20 @@ For the most part, new integrations should be added to the Community package. Pa
 
 In the following sections, we'll walk through how to contribute to each of these packages from a fake company, `Parrot Link AI`.
 
-## Community Package
+## Community package
 
 The `langchain-community` package is in `libs/community` and contains most integrations.
 
-It is installed by users with `pip install langchain-community`, and exported members can be imported with code like 
+It can be installed with `pip install langchain-community`, and exported members can be imported with code like 
 
 ```python
-from langchain_community.chat_models import ParrotLinkLLM
-from langchain_community.llms import ChatParrotLink
+from langchain_community.chat_models import ChatParrotLink
+from langchain_community.llms import ParrotLinkLLM
 from langchain_community.vectorstores import ParrotLinkVectorStore
 ```
 
-The community package relies on manually-installed dependent packages, so you will see errors if you try to import a package that is not installed. In our fake example, if you tried to import `ParrotLinkLLM` without installing `parrot-link-sdk`, you will see an `ImportError` telling you to install it when trying to use it.
+The `community` package relies on manually-installed dependent packages, so you will see errors 
+if you try to import a package that is not installed. In our fake example, if you tried to import `ParrotLinkLLM` without installing `parrot-link-sdk`, you will see an `ImportError` telling you to install it when trying to use it.
 
 Let's say we wanted to implement a chat model for Parrot Link AI. We would create a new file in `libs/community/langchain_community/chat_models/parrot_link.py` with the following code:
 
@@ -39,7 +40,7 @@ class ChatParrotLink(BaseChatModel):
     Example:
         .. code-block:: python
 
-            from langchain_parrot_link import ChatParrotLink
+            from langchain_community.chat_models import ChatParrotLink
 
             model = ChatParrotLink()
     """
@@ -56,9 +57,16 @@ And add documentation to:
 
 - `docs/docs/integrations/chat/parrot_link.ipynb`
 
-## Partner Packages
+## Partner package in LangChain repo
 
-Partner packages are in `libs/partners/*` and are installed by users with `pip install langchain-{partner}`, and exported members can be imported with code like 
+Partner packages can be hosted in the `LangChain` monorepo or in an external repo.
+
+Partner package in the `LangChain` repo is placed in `libs/partners/{partner}` 
+and the package source code is in `libs/partners/{partner}/langchain_{partner}`.
+
+A package is 
+installed by users with `pip install langchain-{partner}`, and the package members 
+can be imported with code like:
 
 ```python
 from langchain_{partner} import X
@@ -123,13 +131,49 @@ By default, this will include stubs for a Chat Model, an LLM, and/or a Vector St
 
 ### Write Unit and Integration Tests
 
-Some basic tests are generated in the tests/ directory. You should add more tests to cover your package's functionality.
+Some basic tests are presented in the `tests/` directory. You should add more tests to cover your package's functionality.
 
-For information on running and implementing tests, see the [Testing guide](./testing).
+For information on running and implementing tests, see the [Testing guide](/docs/contributing/testing/).
 
 ### Write documentation
 
-Documentation is generated from Jupyter notebooks in the `docs/` directory. You should move the generated notebooks to the relevant `docs/docs/integrations` directory in the monorepo root.
+Documentation is generated from Jupyter notebooks in the `docs/` directory. You should place the notebooks with examples
+to the relevant `docs/docs/integrations` directory in the monorepo root.
+
+### (If Necessary) Deprecate community integration
+
+Note: this is only necessary if you're migrating an existing community integration into 
+a partner package. If the component you're integrating is net-new to LangChain (i.e. 
+not already in the `community` package), you can skip this step.
+
+Let's pretend we migrated our `ChatParrotLink` chat model from the community package to 
+the partner package. We would need to deprecate the old model in the community package.
+
+We would do that by adding a `@deprecated` decorator to the old model as follows, in
+`libs/community/langchain_community/chat_models/parrot_link.py`.
+
+Before our change, our chat model might look like this:
+
+```python
+class ChatParrotLink(BaseChatModel):
+  ...
+```
+
+After our change, it would look like this:
+
+```python
+from langchain_core._api.deprecation import deprecated
+
+@deprecated(
+    since="0.0.<next community version>", 
+    removal="0.2.0", 
+    alternative_import="langchain_parrot_link.ChatParrotLink"
+)
+class ChatParrotLink(BaseChatModel):
+  ...
+```
+
+You should do this for *each* component that you're migrating to the partner package.
 
 ### Additional steps
 
@@ -143,3 +187,12 @@ Maintainer steps (Contributors should **not** do these):
 - [ ] set up pypi and test pypi projects
 - [ ] add credential secrets to Github Actions
 - [ ] add package to conda-forge
+
+## Partner package in external repo
+
+Partner packages in external repos must be coordinated between the LangChain team and
+the partner organization to ensure that they are maintained and updated.
+
+If you're interested in creating a partner package in an external repo, please start
+with one in the LangChain repo, and then reach out to the LangChain team to discuss
+how to move it to an external repo.

docs/docs/contributing/repo_structure.mdx

@@ -41,7 +41,7 @@ There are other files in the root directory level, but their presence should be
 The `/docs` directory contains the content for the documentation that is shown
 at https://python.langchain.com/ and the associated API Reference https://api.python.langchain.com/en/latest/langchain_api_reference.html.
 
-See the [documentation](./documentation) guidelines to learn how to contribute to the documentation.
+See the [documentation](/docs/contributing/documentation/style_guide) guidelines to learn how to contribute to the documentation.
 
 ## Code
 

docs/docs/expression_language/cookbook/agent.ipynb

@@ -1,205 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "e89f490d",
-   "metadata": {},
-   "source": [
-    "# Agents\n",
-    "\n",
-    "You can pass a Runnable into an agent."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "af4381de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.agents import AgentExecutor, tool\n",
-    "from langchain.agents.output_parsers import XMLAgentOutputParser\n",
-    "from langchain_community.chat_models import ChatAnthropic"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "24cc8134",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "model = ChatAnthropic(model=\"claude-2\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "67c0b0e4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "@tool\n",
-    "def search(query: str) -> str:\n",
-    "    \"\"\"Search things about current events.\"\"\"\n",
-    "    return \"32 degrees\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "7203b101",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tool_list = [search]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "b68e756d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Get the prompt to use - you can modify this!\n",
-    "prompt = hub.pull(\"hwchase17/xml-agent-convo\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "61ab3e9a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Logic for going from intermediate steps to a string to pass into model\n",
-    "# This is pretty tied to the prompt\n",
-    "def convert_intermediate_steps(intermediate_steps):\n",
-    "    log = \"\"\n",
-    "    for action, observation in intermediate_steps:\n",
-    "        log += (\n",
-    "            f\"<tool>{action.tool}</tool><tool_input>{action.tool_input}\"\n",
-    "            f\"</tool_input><observation>{observation}</observation>\"\n",
-    "        )\n",
-    "    return log\n",
-    "\n",
-    "\n",
-    "# Logic for converting tools to string to go in prompt\n",
-    "def convert_tools(tools):\n",
-    "    return \"\\n\".join([f\"{tool.name}: {tool.description}\" for tool in tools])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "260f5988",
-   "metadata": {},
-   "source": [
-    "Building an agent from a runnable usually involves a few things:\n",
-    "\n",
-    "1. Data processing for the intermediate steps. These need to represented in a way that the language model can recognize them. This should be pretty tightly coupled to the instructions in the prompt\n",
-    "\n",
-    "2. The prompt itself\n",
-    "\n",
-    "3. The model, complete with stop tokens if needed\n",
-    "\n",
-    "4. The output parser - should be in sync with how the prompt specifies things to be formatted."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "e92f1d6f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent = (\n",
-    "    {\n",
-    "        \"input\": lambda x: x[\"input\"],\n",
-    "        \"agent_scratchpad\": lambda x: convert_intermediate_steps(\n",
-    "            x[\"intermediate_steps\"]\n",
-    "        ),\n",
-    "    }\n",
-    "    | prompt.partial(tools=convert_tools(tool_list))\n",
-    "    | model.bind(stop=[\"</tool_input>\", \"</final_answer>\"])\n",
-    "    | XMLAgentOutputParser()\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "6ce6ec7a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor(agent=agent, tools=tool_list, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "fb5cb2e3",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m <tool>search</tool><tool_input>weather in New York\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m <tool>search</tool>\n",
-      "<tool_input>weather in New York\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m <final_answer>The weather in New York is 32 degrees\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'whats the weather in New york?',\n",
-       " 'output': 'The weather in New York is 32 degrees'}"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.invoke({\"input\": \"whats the weather in New york?\"})"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bce86dd8",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}