script

.scripts/community_split/libs/community/langchain_community/agent_toolkits/conversational_retrieval/openai_functions.py

@@ -0,0 +1,88 @@
+from __future__ import annotations
+
+from typing import Any, List, Optional, TYPE_CHECKING
+
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.memory import BaseMemory
+from langchain_core.messages import SystemMessage
+from langchain_core.prompts.chat import MessagesPlaceholder
+from langchain_core.tools import BaseTool
+
+if TYPE_CHECKING:
+    from langchain.agents.agent import AgentExecutor
+
+
+def _get_default_system_message() -> SystemMessage:
+    return SystemMessage(
+        content=(
+            "Do your best to answer the questions. "
+            "Feel free to use any tools available to look up "
+            "relevant information, only if necessary"
+        )
+    )
+
+def create_conversational_retrieval_agent(
+    llm: BaseLanguageModel,
+    tools: List[BaseTool],
+    remember_intermediate_steps: bool = True,
+    memory_key: str = "chat_history",
+    system_message: Optional[SystemMessage] = None,
+    verbose: bool = False,
+    max_token_limit: int = 2000,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """A convenience method for creating a conversational retrieval agent.
+
+    Args:
+        llm: The language model to use, should be ChatOpenAI
+        tools: A list of tools the agent has access to
+        remember_intermediate_steps: Whether the agent should remember intermediate
+            steps or not. Intermediate steps refer to prior action/observation
+            pairs from previous questions. The benefit of remembering these is if
+            there is relevant information in there, the agent can use it to answer
+            follow up questions. The downside is it will take up more tokens.
+        memory_key: The name of the memory key in the prompt.
+        system_message: The system message to use. By default, a basic one will
+            be used.
+        verbose: Whether or not the final AgentExecutor should be verbose or not,
+            defaults to False.
+        max_token_limit: The max number of tokens to keep around in memory.
+            Defaults to 2000.
+
+    Returns:
+        An agent executor initialized appropriately
+    """
+    from langchain.agents.agent import AgentExecutor
+    from langchain.agents.openai_functions_agent.agent_token_buffer_memory import (
+        AgentTokenBufferMemory,
+    )
+    from langchain.agents.openai_functions_agent.base import OpenAIFunctionsAgent
+    from langchain.memory.token_buffer import ConversationTokenBufferMemory
+
+    if remember_intermediate_steps:
+        memory: BaseMemory = AgentTokenBufferMemory(
+            memory_key=memory_key, llm=llm, max_token_limit=max_token_limit
+        )
+    else:
+        memory = ConversationTokenBufferMemory(
+            memory_key=memory_key,
+            return_messages=True,
+            output_key="output",
+            llm=llm,
+            max_token_limit=max_token_limit,
+        )
+
+    _system_message = system_message or _get_default_system_message()
+    prompt = OpenAIFunctionsAgent.create_prompt(
+        system_message=_system_message,
+        extra_prompt_messages=[MessagesPlaceholder(variable_name=memory_key)],
+    )
+    agent = OpenAIFunctionsAgent(llm=llm, tools=tools, prompt=prompt)
+    return AgentExecutor(
+        agent=agent,
+        tools=tools,
+        memory=memory,
+        verbose=verbose,
+        return_intermediate_steps=remember_intermediate_steps,
+        **kwargs,
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/json/base.py

@@ -0,0 +1,53 @@
+"""Json agent."""
+from __future__ import annotations
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models import BaseLanguageModel
+
+from langchain_community.agent_toolkits.json.prompt import JSON_PREFIX, JSON_SUFFIX
+from langchain_community.agent_toolkits.json.toolkit import JsonToolkit
+
+if TYPE_CHECKING:
+    from langchain.agents.agent import AgentExecutor
+
+
+def create_json_agent(
+    llm: BaseLanguageModel,
+    toolkit: JsonToolkit,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    prefix: str = JSON_PREFIX,
+    suffix: str = JSON_SUFFIX,
+    format_instructions: Optional[str] = None,
+    input_variables: Optional[List[str]] = None,
+    verbose: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct a json agent from an LLM and tools."""
+    from langchain.agents.agent import AgentExecutor
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.chains.llm import LLMChain
+    tools = toolkit.get_tools()
+    prompt_params = {"format_instructions": format_instructions} if format_instructions is not None else {}
+    prompt = ZeroShotAgent.create_prompt(
+        tools,
+        prefix=prefix,
+        suffix=suffix,
+        input_variables=input_variables,
+        **prompt_params,
+    )
+    llm_chain = LLMChain(
+        llm=llm,
+        prompt=prompt,
+        callback_manager=callback_manager,
+    )
+    tool_names = [tool.name for tool in tools]
+    agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        verbose=verbose,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/nla/tool.py

@@ -0,0 +1,57 @@
+"""Tool for interacting with a single API with natural language definition."""
+
+from __future__ import annotations
+from typing import Any, Optional, TYPE_CHECKING
+
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.tools import Tool
+
+from langchain_community.tools.openapi.utils.api_models import APIOperation
+from langchain_community.tools.openapi.utils.openapi_utils import OpenAPISpec
+from langchain_community.utilities.requests import Requests
+
+if TYPE_CHECKING:
+    from langchain.chains.api.openapi.chain import OpenAPIEndpointChain
+
+
+class NLATool(Tool):
+    """Natural Language API Tool."""
+
+    @classmethod
+    def from_open_api_endpoint_chain(
+        cls, chain: OpenAPIEndpointChain, api_title: str
+    ) -> "NLATool":
+        """Convert an endpoint chain to an API endpoint tool."""
+        expanded_name = (
+            f'{api_title.replace(" ", "_")}.{chain.api_operation.operation_id}'
+        )
+        description = (
+            f"I'm an AI from {api_title}. Instruct what you want,"
+            " and I'll assist via an API with description:"
+            f" {chain.api_operation.description}"
+        )
+        return cls(name=expanded_name, func=chain.run, description=description)
+
+    @classmethod
+    def from_llm_and_method(
+        cls,
+        llm: BaseLanguageModel,
+        path: str,
+        method: str,
+        spec: OpenAPISpec,
+        requests: Optional[Requests] = None,
+        verbose: bool = False,
+        return_intermediate_steps: bool = False,
+        **kwargs: Any,
+    ) -> "NLATool":
+        """Instantiate the tool from the specified path and method."""
+        api_operation = APIOperation.from_openapi_spec(spec, path, method)
+        chain = OpenAPIEndpointChain.from_api_operation(
+            api_operation,
+            llm,
+            requests=requests,
+            verbose=verbose,
+            return_intermediate_steps=return_intermediate_steps,
+            **kwargs,
+        )
+        return cls.from_open_api_endpoint_chain(chain, spec.info.title)

.scripts/community_split/libs/community/langchain_community/agent_toolkits/openapi/base.py

@@ -0,0 +1,77 @@
+"""OpenAPI spec agent."""
+from __future__ import annotations
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models import BaseLanguageModel
+
+from langchain_community.agent_toolkits.openapi.prompt import (
+    OPENAPI_PREFIX,
+    OPENAPI_SUFFIX,
+)
+from langchain_community.agent_toolkits.openapi.toolkit import OpenAPIToolkit
+
+if TYPE_CHECKING:
+    from langchain.agents.agent import AgentExecutor
+
+
+def create_openapi_agent(
+    llm: BaseLanguageModel,
+    toolkit: OpenAPIToolkit,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    prefix: str = OPENAPI_PREFIX,
+    suffix: str = OPENAPI_SUFFIX,
+    format_instructions: Optional[str] = None,
+    input_variables: Optional[List[str]] = None,
+    max_iterations: Optional[int] = 15,
+    max_execution_time: Optional[float] = None,
+    early_stopping_method: str = "force",
+    verbose: bool = False,
+    return_intermediate_steps: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct an OpenAPI agent from an LLM and tools.
+
+    *Security Note*: When creating an OpenAPI agent, check the permissions
+        and capabilities of the underlying toolkit.
+
+        For example, if the default implementation of OpenAPIToolkit
+        uses the RequestsToolkit which contains tools to make arbitrary
+        network requests against any URL (e.g., GET, POST, PATCH, PUT, DELETE),
+
+        Control access to who can submit issue requests using this toolkit and
+        what network access it has.
+
+        See https://python.langchain.com/docs/security for more information.
+    """
+    from langchain.agents.agent import AgentExecutor
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.chains.llm import LLMChain
+    tools = toolkit.get_tools()
+    prompt_params = {"format_instructions": format_instructions} if format_instructions is not None else {}
+    prompt = ZeroShotAgent.create_prompt(
+        tools,
+        prefix=prefix,
+        suffix=suffix,
+        input_variables=input_variables,
+        **prompt_params
+    )
+    llm_chain = LLMChain(
+        llm=llm,
+        prompt=prompt,
+        callback_manager=callback_manager,
+    )
+    tool_names = [tool.name for tool in tools]
+    agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        verbose=verbose,
+        return_intermediate_steps=return_intermediate_steps,
+        max_iterations=max_iterations,
+        max_execution_time=max_execution_time,
+        early_stopping_method=early_stopping_method,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/openapi/planner.py

@@ -0,0 +1,366 @@
+"""Agent that interacts with OpenAPI APIs via a hierarchical planning approach."""
+import json
+import re
+from functools import partial
+from typing import Any, Callable, Dict, List, Optional, TYPE_CHECKING
+
+import yaml
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.prompts import BasePromptTemplate, PromptTemplate
+from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseTool, Tool
+from langchain_openai.llms import OpenAI
+
+from langchain_community.agent_toolkits.openapi.planner_prompt import (
+    API_CONTROLLER_PROMPT,
+    API_CONTROLLER_TOOL_DESCRIPTION,
+    API_CONTROLLER_TOOL_NAME,
+    API_ORCHESTRATOR_PROMPT,
+    API_PLANNER_PROMPT,
+    API_PLANNER_TOOL_DESCRIPTION,
+    API_PLANNER_TOOL_NAME,
+    PARSING_DELETE_PROMPT,
+    PARSING_GET_PROMPT,
+    PARSING_PATCH_PROMPT,
+    PARSING_POST_PROMPT,
+    PARSING_PUT_PROMPT,
+    REQUESTS_DELETE_TOOL_DESCRIPTION,
+    REQUESTS_GET_TOOL_DESCRIPTION,
+    REQUESTS_PATCH_TOOL_DESCRIPTION,
+    REQUESTS_POST_TOOL_DESCRIPTION,
+    REQUESTS_PUT_TOOL_DESCRIPTION,
+)
+from langchain_community.agent_toolkits.openapi.spec import ReducedOpenAPISpec
+from langchain_community.output_parsers.json import parse_json_markdown
+from langchain_community.tools.requests.tool import BaseRequestsTool
+from langchain_community.utilities.requests import RequestsWrapper
+
+if TYPE_CHECKING:
+    from langchain.agents.agent import AgentExecutor
+    from langchain.chains.llm import LLMChain
+    from langchain.memory import ReadOnlySharedMemory
+
+#
+# Requests tools with LLM-instructed extraction of truncated responses.
+#
+# Of course, truncating so bluntly may lose a lot of valuable
+# information in the response.
+# However, the goal for now is to have only a single inference step.
+MAX_RESPONSE_LENGTH = 5000
+"""Maximum length of the response to be returned."""
+
+
+def _get_default_llm_chain(prompt: BasePromptTemplate) -> LLMChain:
+    from langchain.chains.llm import LLMChain
+    return LLMChain(
+        llm=OpenAI(),
+        prompt=prompt,
+    )
+
+
+def _get_default_llm_chain_factory(
+    prompt: BasePromptTemplate,
+) -> Callable[[], LLMChain]:
+    """Returns a default LLMChain factory."""
+    return partial(_get_default_llm_chain, prompt)
+
+
+class RequestsGetToolWithParsing(BaseRequestsTool, BaseTool):
+    """Requests GET tool with LLM-instructed extraction of truncated responses."""
+
+    name: str = "requests_get"
+    """Tool name."""
+    description = REQUESTS_GET_TOOL_DESCRIPTION
+    """Tool description."""
+    response_length: Optional[int] = MAX_RESPONSE_LENGTH
+    """Maximum length of the response to be returned."""
+    llm_chain: Any = Field(
+        default_factory=_get_default_llm_chain_factory(PARSING_GET_PROMPT)
+    )
+    """LLMChain used to extract the response."""
+
+    def _run(self, text: str) -> str:
+        try:
+            data = parse_json_markdown(text)
+        except json.JSONDecodeError as e:
+            raise e
+        data_params = data.get("params")
+        response = self.requests_wrapper.get(data["url"], params=data_params)
+        response = response[: self.response_length]
+        return self.llm_chain.predict(
+            response=response, instructions=data["output_instructions"]
+        ).strip()
+
+    async def _arun(self, text: str) -> str:
+        raise NotImplementedError()
+
+
+class RequestsPostToolWithParsing(BaseRequestsTool, BaseTool):
+    """Requests POST tool with LLM-instructed extraction of truncated responses."""
+
+    name: str = "requests_post"
+    """Tool name."""
+    description = REQUESTS_POST_TOOL_DESCRIPTION
+    """Tool description."""
+    response_length: Optional[int] = MAX_RESPONSE_LENGTH
+    """Maximum length of the response to be returned."""
+    llm_chain: Any = Field(
+        default_factory=_get_default_llm_chain_factory(PARSING_POST_PROMPT)
+    )
+    """LLMChain used to extract the response."""
+
+    def _run(self, text: str) -> str:
+        try:
+            data = parse_json_markdown(text)
+        except json.JSONDecodeError as e:
+            raise e
+        response = self.requests_wrapper.post(data["url"], data["data"])
+        response = response[: self.response_length]
+        return self.llm_chain.predict(
+            response=response, instructions=data["output_instructions"]
+        ).strip()
+
+    async def _arun(self, text: str) -> str:
+        raise NotImplementedError()
+
+
+class RequestsPatchToolWithParsing(BaseRequestsTool, BaseTool):
+    """Requests PATCH tool with LLM-instructed extraction of truncated responses."""
+
+    name: str = "requests_patch"
+    """Tool name."""
+    description = REQUESTS_PATCH_TOOL_DESCRIPTION
+    """Tool description."""
+    response_length: Optional[int] = MAX_RESPONSE_LENGTH
+    """Maximum length of the response to be returned."""
+    llm_chain: Any = Field(
+        default_factory=_get_default_llm_chain_factory(PARSING_PATCH_PROMPT)
+    )
+    """LLMChain used to extract the response."""
+
+    def _run(self, text: str) -> str:
+        try:
+            data = parse_json_markdown(text)
+        except json.JSONDecodeError as e:
+            raise e
+        response = self.requests_wrapper.patch(data["url"], data["data"])
+        response = response[: self.response_length]
+        return self.llm_chain.predict(
+            response=response, instructions=data["output_instructions"]
+        ).strip()
+
+    async def _arun(self, text: str) -> str:
+        raise NotImplementedError()
+
+
+class RequestsPutToolWithParsing(BaseRequestsTool, BaseTool):
+    """Requests PUT tool with LLM-instructed extraction of truncated responses."""
+
+    name: str = "requests_put"
+    """Tool name."""
+    description = REQUESTS_PUT_TOOL_DESCRIPTION
+    """Tool description."""
+    response_length: Optional[int] = MAX_RESPONSE_LENGTH
+    """Maximum length of the response to be returned."""
+    llm_chain: Any = Field(
+        default_factory=_get_default_llm_chain_factory(PARSING_PUT_PROMPT)
+    )
+    """LLMChain used to extract the response."""
+
+    def _run(self, text: str) -> str:
+        try:
+            data = parse_json_markdown(text)
+        except json.JSONDecodeError as e:
+            raise e
+        response = self.requests_wrapper.put(data["url"], data["data"])
+        response = response[: self.response_length]
+        return self.llm_chain.predict(
+            response=response, instructions=data["output_instructions"]
+        ).strip()
+
+    async def _arun(self, text: str) -> str:
+        raise NotImplementedError()
+
+
+class RequestsDeleteToolWithParsing(BaseRequestsTool, BaseTool):
+    """A tool that sends a DELETE request and parses the response."""
+
+    name: str = "requests_delete"
+    """The name of the tool."""
+    description = REQUESTS_DELETE_TOOL_DESCRIPTION
+    """The description of the tool."""
+
+    response_length: Optional[int] = MAX_RESPONSE_LENGTH
+    """The maximum length of the response."""
+    llm_chain: Any = Field(
+        default_factory=_get_default_llm_chain_factory(PARSING_DELETE_PROMPT)
+    )
+    """The LLM chain used to parse the response."""
+
+    def _run(self, text: str) -> str:
+        try:
+            data = parse_json_markdown(text)
+        except json.JSONDecodeError as e:
+            raise e
+        response = self.requests_wrapper.delete(data["url"])
+        response = response[: self.response_length]
+        return self.llm_chain.predict(
+            response=response, instructions=data["output_instructions"]
+        ).strip()
+
+    async def _arun(self, text: str) -> str:
+        raise NotImplementedError()
+
+
+#
+# Orchestrator, planner, controller.
+#
+def _create_api_planner_tool(
+    api_spec: ReducedOpenAPISpec, llm: BaseLanguageModel
+) -> Tool:
+    from langchain.chains.llm import LLMChain
+    endpoint_descriptions = [
+        f"{name} {description}" for name, description, _ in api_spec.endpoints
+    ]
+    prompt = PromptTemplate(
+        template=API_PLANNER_PROMPT,
+        input_variables=["query"],
+        partial_variables={"endpoints": "- " + "- ".join(endpoint_descriptions)},
+    )
+    chain = LLMChain(llm=llm, prompt=prompt)
+    tool = Tool(
+        name=API_PLANNER_TOOL_NAME,
+        description=API_PLANNER_TOOL_DESCRIPTION,
+        func=chain.run,
+    )
+    return tool
+
+
+def _create_api_controller_agent(
+    api_url: str,
+    api_docs: str,
+    requests_wrapper: RequestsWrapper,
+    llm: BaseLanguageModel,
+) -> AgentExecutor:
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.agents.agent import AgentExecutor
+    from langchain.chains.llm import LLMChain
+    get_llm_chain = LLMChain(llm=llm, prompt=PARSING_GET_PROMPT)
+    post_llm_chain = LLMChain(llm=llm, prompt=PARSING_POST_PROMPT)
+    tools: List[BaseTool] = [
+        RequestsGetToolWithParsing(
+            requests_wrapper=requests_wrapper, llm_chain=get_llm_chain
+        ),
+        RequestsPostToolWithParsing(
+            requests_wrapper=requests_wrapper, llm_chain=post_llm_chain
+        ),
+    ]
+    prompt = PromptTemplate(
+        template=API_CONTROLLER_PROMPT,
+        input_variables=["input", "agent_scratchpad"],
+        partial_variables={
+            "api_url": api_url,
+            "api_docs": api_docs,
+            "tool_names": ", ".join([tool.name for tool in tools]),
+            "tool_descriptions": "\n".join(
+                [f"{tool.name}: {tool.description}" for tool in tools]
+            ),
+        },
+    )
+    agent = ZeroShotAgent(
+        llm_chain=LLMChain(llm=llm, prompt=prompt),
+        allowed_tools=[tool.name for tool in tools],
+    )
+    return AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)
+
+
+def _create_api_controller_tool(
+    api_spec: ReducedOpenAPISpec,
+    requests_wrapper: RequestsWrapper,
+    llm: BaseLanguageModel,
+) -> Tool:
+    """Expose controller as a tool.
+
+    The tool is invoked with a plan from the planner, and dynamically
+    creates a controller agent with relevant documentation only to
+    constrain the context.
+    """
+
+    base_url = api_spec.servers[0]["url"]  # TODO: do better.
+
+    def _create_and_run_api_controller_agent(plan_str: str) -> str:
+        pattern = r"\b(GET|POST|PATCH|DELETE)\s+(/\S+)*"
+        matches = re.findall(pattern, plan_str)
+        endpoint_names = [
+            "{method} {route}".format(method=method, route=route.split("?")[0])
+            for method, route in matches
+        ]
+        docs_str = ""
+        for endpoint_name in endpoint_names:
+            found_match = False
+            for name, _, docs in api_spec.endpoints:
+                regex_name = re.compile(re.sub("\{.*?\}", ".*", name))
+                if regex_name.match(endpoint_name):
+                    found_match = True
+                    docs_str += f"== Docs for {endpoint_name} == \n{yaml.dump(docs)}\n"
+            if not found_match:
+                raise ValueError(f"{endpoint_name} endpoint does not exist.")
+
+        agent = _create_api_controller_agent(base_url, docs_str, requests_wrapper, llm)
+        return agent.run(plan_str)
+
+    return Tool(
+        name=API_CONTROLLER_TOOL_NAME,
+        func=_create_and_run_api_controller_agent,
+        description=API_CONTROLLER_TOOL_DESCRIPTION,
+    )
+
+
+def create_openapi_agent(
+    api_spec: ReducedOpenAPISpec,
+    requests_wrapper: RequestsWrapper,
+    llm: BaseLanguageModel,
+    shared_memory: Optional[ReadOnlySharedMemory] = None,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    verbose: bool = True,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Instantiate OpenAI API planner and controller for a given spec.
+
+    Inject credentials via requests_wrapper.
+
+    We use a top-level "orchestrator" agent to invoke the planner and controller,
+    rather than a top-level planner
+    that invokes a controller with its plan. This is to keep the planner simple.
+    """
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.agents.agent import AgentExecutor
+    from langchain.chains.llm import LLMChain
+    tools = [
+        _create_api_planner_tool(api_spec, llm),
+        _create_api_controller_tool(api_spec, requests_wrapper, llm),
+    ]
+    prompt = PromptTemplate(
+        template=API_ORCHESTRATOR_PROMPT,
+        input_variables=["input", "agent_scratchpad"],
+        partial_variables={
+            "tool_names": ", ".join([tool.name for tool in tools]),
+            "tool_descriptions": "\n".join(
+                [f"{tool.name}: {tool.description}" for tool in tools]
+            ),
+        },
+    )
+    agent = ZeroShotAgent(
+        llm_chain=LLMChain(llm=llm, prompt=prompt, memory=shared_memory),
+        allowed_tools=[tool.name for tool in tools],
+        **kwargs,
+    )
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        verbose=verbose,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/openapi/toolkit.py

@@ -0,0 +1,90 @@
+"""Requests toolkit."""
+from __future__ import annotations
+
+from typing import Any, List
+
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.tools import Tool
+
+from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_community.agent_toolkits.json.base import create_json_agent
+from langchain_community.agent_toolkits.json.toolkit import JsonToolkit
+from langchain_community.agent_toolkits.openapi.prompt import DESCRIPTION
+from langchain_community.tools import BaseTool
+from langchain_community.tools.json.tool import JsonSpec
+from langchain_community.tools.requests.tool import (
+    RequestsDeleteTool,
+    RequestsGetTool,
+    RequestsPatchTool,
+    RequestsPostTool,
+    RequestsPutTool,
+)
+from langchain_community.utilities.requests import TextRequestsWrapper
+
+
+class RequestsToolkit(BaseToolkit):
+    """Toolkit for making REST requests.
+
+    *Security Note*: This toolkit contains tools to make GET, POST, PATCH, PUT,
+        and DELETE requests to an API.
+
+        Exercise care in who is allowed to use this toolkit. If exposing
+        to end users, consider that users will be able to make arbitrary
+        requests on behalf of the server hosting the code. For example,
+        users could ask the server to make a request to a private API
+        that is only accessible from the server.
+
+        Control access to who can submit issue requests using this toolkit and
+        what network access it has.
+
+        See https://python.langchain.com/docs/security for more information.
+    """
+
+    requests_wrapper: TextRequestsWrapper
+
+    def get_tools(self) -> List[BaseTool]:
+        """Return a list of tools."""
+        return [
+            RequestsGetTool(requests_wrapper=self.requests_wrapper),
+            RequestsPostTool(requests_wrapper=self.requests_wrapper),
+            RequestsPatchTool(requests_wrapper=self.requests_wrapper),
+            RequestsPutTool(requests_wrapper=self.requests_wrapper),
+            RequestsDeleteTool(requests_wrapper=self.requests_wrapper),
+        ]
+
+
+class OpenAPIToolkit(BaseToolkit):
+    """Toolkit for interacting with an OpenAPI API.
+
+    *Security Note*: This toolkit contains tools that can read and modify
+        the state of a service; e.g., by creating, deleting, or updating,
+        reading underlying data.
+
+        For example, this toolkit can be used to delete data exposed via
+        an OpenAPI compliant API.
+    """
+
+    json_agent: Any
+    requests_wrapper: TextRequestsWrapper
+
+    def get_tools(self) -> List[BaseTool]:
+        """Get the tools in the toolkit."""
+        json_agent_tool = Tool(
+            name="json_explorer",
+            func=self.json_agent.run,
+            description=DESCRIPTION,
+        )
+        request_toolkit = RequestsToolkit(requests_wrapper=self.requests_wrapper)
+        return [*request_toolkit.get_tools(), json_agent_tool]
+
+    @classmethod
+    def from_llm(
+        cls,
+        llm: BaseLanguageModel,
+        json_spec: JsonSpec,
+        requests_wrapper: TextRequestsWrapper,
+        **kwargs: Any,
+    ) -> OpenAPIToolkit:
+        """Create json agent from llm, then initialize."""
+        json_agent = create_json_agent(llm, JsonToolkit(spec=json_spec), **kwargs)
+        return cls(json_agent=json_agent, requests_wrapper=requests_wrapper)

.scripts/community_split/libs/community/langchain_community/agent_toolkits/powerbi/base.py

@@ -0,0 +1,68 @@
+"""Power BI agent."""
+from __future__ import annotations
+
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models import BaseLanguageModel
+
+from langchain_community.agent_toolkits.powerbi.prompt import (
+    POWERBI_PREFIX,
+    POWERBI_SUFFIX,
+)
+from langchain_community.agent_toolkits.powerbi.toolkit import PowerBIToolkit
+from langchain_community.utilities.powerbi import PowerBIDataset
+
+if TYPE_CHECKING:
+    from langchain.agents import AgentExecutor
+
+
+def create_pbi_agent(
+    llm: BaseLanguageModel,
+    toolkit: Optional[PowerBIToolkit] = None,
+    powerbi: Optional[PowerBIDataset] = None,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    prefix: str = POWERBI_PREFIX,
+    suffix: str = POWERBI_SUFFIX,
+    format_instructions: Optional[str] = None,
+    examples: Optional[str] = None,
+    input_variables: Optional[List[str]] = None,
+    top_k: int = 10,
+    verbose: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct a Power BI agent from an LLM and tools."""
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.agents import AgentExecutor
+    from langchain.chains.llm import LLMChain
+    if toolkit is None:
+        if powerbi is None:
+            raise ValueError("Must provide either a toolkit or powerbi dataset")
+        toolkit = PowerBIToolkit(powerbi=powerbi, llm=llm, examples=examples)
+    tools = toolkit.get_tools()
+    tables = powerbi.table_names if powerbi else toolkit.powerbi.table_names
+    prompt_params = {"format_instructions": format_instructions} if format_instructions is not None else {}
+    agent = ZeroShotAgent(
+        llm_chain=LLMChain(
+            llm=llm,
+            prompt=ZeroShotAgent.create_prompt(
+                tools,
+                prefix=prefix.format(top_k=top_k).format(tables=tables),
+                suffix=suffix,
+                input_variables=input_variables,
+                **prompt_params,
+            ),
+            callback_manager=callback_manager,  # type: ignore
+            verbose=verbose,
+        ),
+        allowed_tools=[tool.name for tool in tools],
+        **kwargs,
+    )
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        verbose=verbose,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/powerbi/chat_base.py

@@ -0,0 +1,69 @@
+"""Power BI agent."""
+from __future__ import annotations
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models.chat_models import BaseChatModel
+
+from langchain_community.agent_toolkits.powerbi.prompt import (
+    POWERBI_CHAT_PREFIX,
+    POWERBI_CHAT_SUFFIX,
+)
+from langchain_community.agent_toolkits.powerbi.toolkit import PowerBIToolkit
+from langchain_community.utilities.powerbi import PowerBIDataset
+
+if TYPE_CHECKING:
+    from langchain.agents import AgentExecutor
+    from langchain.agents.agent import AgentOutputParser
+    from langchain.memory.chat_memory import BaseChatMemory
+
+
+def create_pbi_chat_agent(
+    llm: BaseChatModel,
+    toolkit: Optional[PowerBIToolkit] = None,
+    powerbi: Optional[PowerBIDataset] = None,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    output_parser: Optional[AgentOutputParser] = None,
+    prefix: str = POWERBI_CHAT_PREFIX,
+    suffix: str = POWERBI_CHAT_SUFFIX,
+    examples: Optional[str] = None,
+    input_variables: Optional[List[str]] = None,
+    memory: Optional[BaseChatMemory] = None,
+    top_k: int = 10,
+    verbose: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct a Power BI agent from a Chat LLM and tools.
+
+    If you supply only a toolkit and no Power BI dataset, the same LLM is used for both.
+    """
+    from langchain.agents import AgentExecutor
+    from langchain.agents.conversational_chat.base import ConversationalChatAgent
+    from langchain.memory import ConversationBufferMemory
+    if toolkit is None:
+        if powerbi is None:
+            raise ValueError("Must provide either a toolkit or powerbi dataset")
+        toolkit = PowerBIToolkit(powerbi=powerbi, llm=llm, examples=examples)
+    tools = toolkit.get_tools()
+    tables = powerbi.table_names if powerbi else toolkit.powerbi.table_names
+    agent = ConversationalChatAgent.from_llm_and_tools(
+        llm=llm,
+        tools=tools,
+        system_message=prefix.format(top_k=top_k).format(tables=tables),
+        human_message=suffix,
+        input_variables=input_variables,
+        callback_manager=callback_manager,
+        output_parser=output_parser,
+        verbose=verbose,
+        **kwargs,
+    )
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        memory=memory
+        or ConversationBufferMemory(memory_key="chat_history", return_messages=True),
+        verbose=verbose,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/powerbi/toolkit.py

@@ -0,0 +1,106 @@
+"""Toolkit for interacting with a Power BI dataset."""
+from __future__ import annotations
+from typing import List, Optional, Union, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.language_models.chat_models import BaseChatModel
+from langchain_core.prompts import PromptTemplate
+from langchain_core.prompts.chat import (
+    ChatPromptTemplate,
+    HumanMessagePromptTemplate,
+    SystemMessagePromptTemplate,
+)
+from langchain_core.pydantic_v1 import Field
+
+from langchain_community.agent_toolkits.base import BaseToolkit
+from langchain_community.tools import BaseTool
+from langchain_community.tools.powerbi.prompt import (
+    QUESTION_TO_QUERY_BASE,
+    SINGLE_QUESTION_TO_QUERY,
+    USER_INPUT,
+)
+from langchain_community.tools.powerbi.tool import (
+    InfoPowerBITool,
+    ListPowerBITool,
+    QueryPowerBITool,
+)
+from langchain_community.utilities.powerbi import PowerBIDataset
+
+if TYPE_CHECKING:
+    from langchain.chains.llm import LLMChain
+
+
+class PowerBIToolkit(BaseToolkit):
+    """Toolkit for interacting with Power BI dataset.
+
+    *Security Note*: This toolkit interacts with an external service.
+
+        Control access to who can use this toolkit.
+
+        Make sure that the capabilities given by this toolkit to the calling
+        code are appropriately scoped to the application.
+
+        See https://python.langchain.com/docs/security for more information.
+    """
+
+    powerbi: PowerBIDataset = Field(exclude=True)
+    llm: Union[BaseLanguageModel, BaseChatModel] = Field(exclude=True)
+    examples: Optional[str] = None
+    max_iterations: int = 5
+    callback_manager: Optional[BaseCallbackManager] = None
+    output_token_limit: Optional[int] = None
+    tiktoken_model_name: Optional[str] = None
+
+    class Config:
+        """Configuration for this pydantic object."""
+
+        arbitrary_types_allowed = True
+
+    def get_tools(self) -> List[BaseTool]:
+        """Get the tools in the toolkit."""
+        return [
+            QueryPowerBITool(
+                llm_chain=self._get_chain(),
+                powerbi=self.powerbi,
+                examples=self.examples,
+                max_iterations=self.max_iterations,
+                output_token_limit=self.output_token_limit,
+                tiktoken_model_name=self.tiktoken_model_name,
+            ),
+            InfoPowerBITool(powerbi=self.powerbi),
+            ListPowerBITool(powerbi=self.powerbi),
+        ]
+
+    def _get_chain(self) -> LLMChain:
+        """Construct the chain based on the callback manager and model type."""
+        from langchain.chains.llm import LLMChain
+        if isinstance(self.llm, BaseLanguageModel):
+            return LLMChain(
+                llm=self.llm,
+                callback_manager=self.callback_manager
+                if self.callback_manager
+                else None,
+                prompt=PromptTemplate(
+                    template=SINGLE_QUESTION_TO_QUERY,
+                    input_variables=["tool_input", "tables", "schemas", "examples"],
+                ),
+            )
+
+        system_prompt = SystemMessagePromptTemplate(
+            prompt=PromptTemplate(
+                template=QUESTION_TO_QUERY_BASE,
+                input_variables=["tables", "schemas", "examples"],
+            )
+        )
+        human_prompt = HumanMessagePromptTemplate(
+            prompt=PromptTemplate(
+                template=USER_INPUT,
+                input_variables=["tool_input"],
+            )
+        )
+        return LLMChain(
+            llm=self.llm,
+            callback_manager=self.callback_manager if self.callback_manager else None,
+            prompt=ChatPromptTemplate.from_messages([system_prompt, human_prompt]),
+        )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/spark_sql/base.py

@@ -0,0 +1,64 @@
+"""Spark SQL agent."""
+from __future__ import annotations
+from typing import Any, Dict, List, Optional, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager, Callbacks
+from langchain_core.language_models import BaseLanguageModel
+
+from langchain_community.agent_toolkits.spark_sql.prompt import SQL_PREFIX, SQL_SUFFIX
+from langchain_community.agent_toolkits.spark_sql.toolkit import SparkSQLToolkit
+
+if TYPE_CHECKING:
+    from langchain.agents.agent import AgentExecutor
+
+
+def create_spark_sql_agent(
+    llm: BaseLanguageModel,
+    toolkit: SparkSQLToolkit,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    callbacks: Callbacks = None,
+    prefix: str = SQL_PREFIX,
+    suffix: str = SQL_SUFFIX,
+    format_instructions: Optional[str] = None,
+    input_variables: Optional[List[str]] = None,
+    top_k: int = 10,
+    max_iterations: Optional[int] = 15,
+    max_execution_time: Optional[float] = None,
+    early_stopping_method: str = "force",
+    verbose: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct a Spark SQL agent from an LLM and tools."""
+    from langchain.agents.agent import AgentExecutor
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.chains.llm import LLMChain
+    tools = toolkit.get_tools()
+    prefix = prefix.format(top_k=top_k)
+    prompt_params = {"format_instructions": format_instructions} if format_instructions is not None else {}
+    prompt = ZeroShotAgent.create_prompt(
+        tools,
+        prefix=prefix,
+        suffix=suffix,
+        input_variables=input_variables,
+        **prompt_params,
+    )
+    llm_chain = LLMChain(
+        llm=llm,
+        prompt=prompt,
+        callback_manager=callback_manager,
+        callbacks=callbacks,
+    )
+    tool_names = [tool.name for tool in tools]
+    agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        callbacks=callbacks,
+        verbose=verbose,
+        max_iterations=max_iterations,
+        max_execution_time=max_execution_time,
+        early_stopping_method=early_stopping_method,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/sql/base.py

@@ -0,0 +1,102 @@
+"""SQL agent."""
+from __future__ import annotations
+from typing import Any, Dict, List, Optional, Sequence, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.messages import AIMessage, SystemMessage
+from langchain_core.prompts.chat import (
+    ChatPromptTemplate,
+    HumanMessagePromptTemplate,
+    MessagesPlaceholder,
+)
+
+from langchain_community.agent_toolkits.sql.prompt import (
+    SQL_FUNCTIONS_SUFFIX,
+    SQL_PREFIX,
+    SQL_SUFFIX,
+)
+from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit
+from langchain_community.tools import BaseTool
+
+if TYPE_CHECKING:
+    from langchain.agents.agent import AgentExecutor
+    from langchain.agents.agent_types import AgentType
+
+
+def create_sql_agent(
+    llm: BaseLanguageModel,
+    toolkit: SQLDatabaseToolkit,
+    agent_type: Optional[AgentType] = None,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    prefix: str = SQL_PREFIX,
+    suffix: Optional[str] = None,
+    format_instructions: Optional[str] = None,
+    input_variables: Optional[List[str]] = None,
+    top_k: int = 10,
+    max_iterations: Optional[int] = 15,
+    max_execution_time: Optional[float] = None,
+    early_stopping_method: str = "force",
+    verbose: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    extra_tools: Sequence[BaseTool] = (),
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct an SQL agent from an LLM and tools."""
+    from langchain.agents.agent import AgentExecutor, BaseSingleActionAgent
+    from langchain.agents.agent_types import AgentType
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.agents.openai_functions_agent.base import OpenAIFunctionsAgent
+    from langchain.chains.llm import LLMChain
+    agent_type = agent_type or AgentType.ZERO_SHOT_REACT_DESCRIPTION
+    tools = toolkit.get_tools() + list(extra_tools)
+    prefix = prefix.format(dialect=toolkit.dialect, top_k=top_k)
+    agent: BaseSingleActionAgent
+
+    if agent_type == AgentType.ZERO_SHOT_REACT_DESCRIPTION:
+        prompt_params = {"format_instructions": format_instructions} if format_instructions is not None else {}
+        prompt = ZeroShotAgent.create_prompt(
+            tools,
+            prefix=prefix,
+            suffix=suffix or SQL_SUFFIX,
+            input_variables=input_variables,
+            **prompt_params,
+        )
+        llm_chain = LLMChain(
+            llm=llm,
+            prompt=prompt,
+            callback_manager=callback_manager,
+        )
+        tool_names = [tool.name for tool in tools]
+        agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
+
+    elif agent_type == AgentType.OPENAI_FUNCTIONS:
+        messages = [
+            SystemMessage(content=prefix),
+            HumanMessagePromptTemplate.from_template("{input}"),
+            AIMessage(content=suffix or SQL_FUNCTIONS_SUFFIX),
+            MessagesPlaceholder(variable_name="agent_scratchpad"),
+        ]
+        input_variables = ["input", "agent_scratchpad"]
+        _prompt = ChatPromptTemplate(input_variables=input_variables, messages=messages)
+
+        agent = OpenAIFunctionsAgent(
+            llm=llm,
+            prompt=_prompt,
+            tools=tools,
+            callback_manager=callback_manager,
+            **kwargs,
+        )
+    else:
+        raise ValueError(f"Agent type {agent_type} not supported at the moment.")
+
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        verbose=verbose,
+        max_iterations=max_iterations,
+        max_execution_time=max_execution_time,
+        early_stopping_method=early_stopping_method,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/agent_toolkits/vectorstore/base.py

@@ -0,0 +1,103 @@
+"""VectorStore agent."""
+from __future__ import annotations
+from typing import Any, Dict, Optional, TYPE_CHECKING
+
+from langchain_core.callbacks import BaseCallbackManager
+from langchain_core.language_models import BaseLanguageModel
+
+from langchain_community.agent_toolkits.vectorstore.prompt import PREFIX, ROUTER_PREFIX
+from langchain_community.agent_toolkits.vectorstore.toolkit import (
+    VectorStoreRouterToolkit,
+    VectorStoreToolkit,
+)
+
+if TYPE_CHECKING:
+    from langchain.agents.agent import AgentExecutor
+
+
+def create_vectorstore_agent(
+    llm: BaseLanguageModel,
+    toolkit: VectorStoreToolkit,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    prefix: str = PREFIX,
+    verbose: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct a VectorStore agent from an LLM and tools.
+
+    Args:
+        llm (BaseLanguageModel): LLM that will be used by the agent
+        toolkit (VectorStoreToolkit): Set of tools for the agent
+        callback_manager (Optional[BaseCallbackManager], optional): Object to handle the callback [ Defaults to None. ]
+        prefix (str, optional): The prefix prompt for the agent. If not provided uses default PREFIX.
+        verbose (bool, optional): If you want to see the content of the scratchpad. [ Defaults to False ]
+        agent_executor_kwargs (Optional[Dict[str, Any]], optional): If there is any other parameter you want to send to the agent. [ Defaults to None ]
+        **kwargs: Additional named parameters to pass to the ZeroShotAgent.
+
+    Returns:
+        AgentExecutor: Returns a callable AgentExecutor object. Either you can call it or use run method with the query to get the response
+    """  # noqa: E501
+    from langchain.agents.agent import AgentExecutor
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.chains.llm import LLMChain
+    tools = toolkit.get_tools()
+    prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
+    llm_chain = LLMChain(
+        llm=llm,
+        prompt=prompt,
+        callback_manager=callback_manager,
+    )
+    tool_names = [tool.name for tool in tools]
+    agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        verbose=verbose,
+        **(agent_executor_kwargs or {}),
+    )
+
+
+def create_vectorstore_router_agent(
+    llm: BaseLanguageModel,
+    toolkit: VectorStoreRouterToolkit,
+    callback_manager: Optional[BaseCallbackManager] = None,
+    prefix: str = ROUTER_PREFIX,
+    verbose: bool = False,
+    agent_executor_kwargs: Optional[Dict[str, Any]] = None,
+    **kwargs: Any,
+) -> AgentExecutor:
+    """Construct a VectorStore router agent from an LLM and tools.
+
+    Args:
+        llm (BaseLanguageModel): LLM that will be used by the agent
+        toolkit (VectorStoreRouterToolkit): Set of tools for the agent which have routing capability with multiple vector stores
+        callback_manager (Optional[BaseCallbackManager], optional): Object to handle the callback [ Defaults to None. ]
+        prefix (str, optional): The prefix prompt for the router agent. If not provided uses default ROUTER_PREFIX.
+        verbose (bool, optional): If you want to see the content of the scratchpad. [ Defaults to False ]
+        agent_executor_kwargs (Optional[Dict[str, Any]], optional): If there is any other parameter you want to send to the agent. [ Defaults to None ]
+        **kwargs: Additional named parameters to pass to the ZeroShotAgent.
+
+    Returns:
+        AgentExecutor: Returns a callable AgentExecutor object. Either you can call it or use run method with the query to get the response.
+    """  # noqa: E501
+    from langchain.agents.agent import AgentExecutor
+    from langchain.agents.mrkl.base import ZeroShotAgent
+    from langchain.chains.llm import LLMChain
+    tools = toolkit.get_tools()
+    prompt = ZeroShotAgent.create_prompt(tools, prefix=prefix)
+    llm_chain = LLMChain(
+        llm=llm,
+        prompt=prompt,
+        callback_manager=callback_manager,
+    )
+    tool_names = [tool.name for tool in tools]
+    agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names, **kwargs)
+    return AgentExecutor.from_agent_and_tools(
+        agent=agent,
+        tools=tools,
+        callback_manager=callback_manager,
+        verbose=verbose,
+        **(agent_executor_kwargs or {}),
+    )

.scripts/community_split/libs/community/langchain_community/document_loaders/base.py

@@ -0,0 +1,101 @@
+"""Abstract interface for document loader implementations."""
+from __future__ import annotations
+from abc import ABC, abstractmethod
+from typing import Iterator, List, Optional, TYPE_CHECKING
+
+from langchain_core.documents import Document
+
+from langchain_community.document_loaders.blob_loaders import Blob
+
+if TYPE_CHECKING:
+    from langchain.text_splitter import TextSplitter
+
+
+class BaseLoader(ABC):
+    """Interface for Document Loader.
+
+    Implementations should implement the lazy-loading method using generators
+    to avoid loading all Documents into memory at once.
+
+    The `load` method will remain as is for backwards compatibility, but its
+    implementation should be just `list(self.lazy_load())`.
+    """
+
+    # Sub-classes should implement this method
+    # as return list(self.lazy_load()).
+    # This method returns a List which is materialized in memory.
+    @abstractmethod
+    def load(self) -> List[Document]:
+        """Load data into Document objects."""
+
+    def load_and_split(
+        self, text_splitter: Optional[TextSplitter] = None
+    ) -> List[Document]:
+        """Load Documents and split into chunks. Chunks are returned as Documents.
+
+        Args:
+            text_splitter: TextSplitter instance to use for splitting documents.
+              Defaults to RecursiveCharacterTextSplitter.
+
+        Returns:
+            List of Documents.
+        """
+        from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+        if text_splitter is None:
+            _text_splitter: TextSplitter = RecursiveCharacterTextSplitter()
+        else:
+            _text_splitter = text_splitter
+        docs = self.load()
+        return _text_splitter.split_documents(docs)
+
+    # Attention: This method will be upgraded into an abstractmethod once it's
+    #            implemented in all the existing subclasses.
+    def lazy_load(
+        self,
+    ) -> Iterator[Document]:
+        """A lazy loader for Documents."""
+        raise NotImplementedError(
+            f"{self.__class__.__name__} does not implement lazy_load()"
+        )
+
+
+class BaseBlobParser(ABC):
+    """Abstract interface for blob parsers.
+
+    A blob parser provides a way to parse raw data stored in a blob into one
+    or more documents.
+
+    The parser can be composed with blob loaders, making it easy to reuse
+    a parser independent of how the blob was originally loaded.
+    """
+
+    @abstractmethod
+    def lazy_parse(self, blob: Blob) -> Iterator[Document]:
+        """Lazy parsing interface.
+
+        Subclasses are required to implement this method.
+
+        Args:
+            blob: Blob instance
+
+        Returns:
+            Generator of documents
+        """
+
+    def parse(self, blob: Blob) -> List[Document]:
+        """Eagerly parse the blob into a document or documents.
+
+        This is a convenience method for interactive development environment.
+
+        Production applications should favor the lazy_parse method instead.
+
+        Subclasses should generally not over-ride this parse method.
+
+        Args:
+            blob: Blob instance
+
+        Returns:
+            List of documents
+        """
+        return list(self.lazy_parse(blob))

.scripts/community_split/libs/community/langchain_community/document_loaders/generic.py

@@ -0,0 +1,182 @@
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Any, Iterator, List, Literal, Optional, Sequence, Union, \
+    TYPE_CHECKING
+
+from langchain_core.documents import Document
+
+from langchain_community.document_loaders.base import BaseBlobParser, BaseLoader
+from langchain_community.document_loaders.blob_loaders import (
+    BlobLoader,
+    FileSystemBlobLoader,
+)
+from langchain_community.document_loaders.parsers.registry import get_parser
+
+if TYPE_CHECKING:
+    from langchain.text_splitter import TextSplitter
+
+_PathLike = Union[str, Path]
+
+DEFAULT = Literal["default"]
+
+
+class GenericLoader(BaseLoader):
+    """Generic Document Loader.
+
+    A generic document loader that allows combining an arbitrary blob loader with
+    a blob parser.
+
+    Examples:
+
+        Parse a specific PDF file:
+
+        .. code-block:: python
+
+            from langchain_community.document_loaders import GenericLoader
+            from langchain_community.document_loaders.parsers.pdf import PyPDFParser
+
+            # Recursively load all text files in a directory.
+            loader = GenericLoader.from_filesystem(
+                "my_lovely_pdf.pdf",
+                parser=PyPDFParser()
+            )
+
+       .. code-block:: python
+
+            from langchain_community.document_loaders import GenericLoader
+            from langchain_community.document_loaders.blob_loaders import FileSystemBlobLoader
+
+
+            loader = GenericLoader.from_filesystem(
+                path="path/to/directory",
+                glob="**/[!.]*",
+                suffixes=[".pdf"],
+                show_progress=True,
+            )
+
+            docs = loader.lazy_load()
+            next(docs)
+
+    Example instantiations to change which files are loaded:
+
+    .. code-block:: python
+
+        # Recursively load all text files in a directory.
+        loader = GenericLoader.from_filesystem("/path/to/dir", glob="**/*.txt")
+
+        # Recursively load all non-hidden files in a directory.
+        loader = GenericLoader.from_filesystem("/path/to/dir", glob="**/[!.]*")
+
+        # Load all files in a directory without recursion.
+        loader = GenericLoader.from_filesystem("/path/to/dir", glob="*")
+
+    Example instantiations to change which parser is used:
+
+    .. code-block:: python
+
+        from langchain_community.document_loaders.parsers.pdf import PyPDFParser
+
+        # Recursively load all text files in a directory.
+        loader = GenericLoader.from_filesystem(
+            "/path/to/dir",
+            glob="**/*.pdf",
+            parser=PyPDFParser()
+        )
+
+    """
+
+    def __init__(
+        self,
+        blob_loader: BlobLoader,
+        blob_parser: BaseBlobParser,
+    ) -> None:
+        """A generic document loader.
+
+        Args:
+            blob_loader: A blob loader which knows how to yield blobs
+            blob_parser: A blob parser which knows how to parse blobs into documents
+        """
+        self.blob_loader = blob_loader
+        self.blob_parser = blob_parser
+
+    def lazy_load(
+        self,
+    ) -> Iterator[Document]:
+        """Load documents lazily. Use this when working at a large scale."""
+        for blob in self.blob_loader.yield_blobs():
+            yield from self.blob_parser.lazy_parse(blob)
+
+    def load(self) -> List[Document]:
+        """Load all documents."""
+        return list(self.lazy_load())
+
+    def load_and_split(
+        self, text_splitter: Optional[TextSplitter] = None
+    ) -> List[Document]:
+        """Load all documents and split them into sentences."""
+        raise NotImplementedError(
+            "Loading and splitting is not yet implemented for generic loaders. "
+            "When they will be implemented they will be added via the initializer. "
+            "This method should not be used going forward."
+        )
+
+    @classmethod
+    def from_filesystem(
+        cls,
+        path: _PathLike,
+        *,
+        glob: str = "**/[!.]*",
+        exclude: Sequence[str] = (),
+        suffixes: Optional[Sequence[str]] = None,
+        show_progress: bool = False,
+        parser: Union[DEFAULT, BaseBlobParser] = "default",
+        parser_kwargs: Optional[dict] = None,
+    ) -> GenericLoader:
+        """Create a generic document loader using a filesystem blob loader.
+
+        Args:
+            path: The path to the directory to load documents from OR the path to a
+                  single file to load. If this is a file, glob, exclude, suffixes
+                    will be ignored.
+            glob: The glob pattern to use to find documents.
+            suffixes: The suffixes to use to filter documents. If None, all files
+                      matching the glob will be loaded.
+            exclude: A list of patterns to exclude from the loader.
+            show_progress: Whether to show a progress bar or not (requires tqdm).
+                           Proxies to the file system loader.
+            parser: A blob parser which knows how to parse blobs into documents,
+                    will instantiate a default parser if not provided.
+                    The default can be overridden by either passing a parser or
+                    setting the class attribute `blob_parser` (the latter
+                    should be used with inheritance).
+            parser_kwargs: Keyword arguments to pass to the parser.
+
+        Returns:
+            A generic document loader.
+        """
+        blob_loader = FileSystemBlobLoader(
+            path,
+            glob=glob,
+            exclude=exclude,
+            suffixes=suffixes,
+            show_progress=show_progress,
+        )
+        if isinstance(parser, str):
+            if parser == "default":
+                try:
+                    # If there is an implementation of get_parser on the class, use it.
+                    blob_parser = cls.get_parser(**(parser_kwargs or {}))
+                except NotImplementedError:
+                    # if not then use the global registry.
+                    blob_parser = get_parser(parser)
+            else:
+                blob_parser = get_parser(parser)
+        else:
+            blob_parser = parser
+        return cls(blob_loader, blob_parser)
+
+    @staticmethod
+    def get_parser(**kwargs: Any) -> BaseBlobParser:
+        """Override this method to associate a default parser with the class."""
+        raise NotImplementedError()

.scripts/community_split/libs/community/langchain_community/document_loaders/parsers/language/language_parser.py

@@ -0,0 +1,157 @@
+from __future__ import annotations
+
+from typing import Any, Dict, Iterator, Optional, TYPE_CHECKING
+
+from langchain_core.documents import Document
+
+from langchain_community.document_loaders.base import BaseBlobParser
+from langchain_community.document_loaders.blob_loaders import Blob
+from langchain_community.document_loaders.parsers.language.cobol import CobolSegmenter
+from langchain_community.document_loaders.parsers.language.javascript import (
+    JavaScriptSegmenter,
+)
+from langchain_community.document_loaders.parsers.language.python import PythonSegmenter
+
+if TYPE_CHECKING:
+    from langchain.text_splitter import Language
+
+try:
+    from langchain.text_splitter import Language
+    LANGUAGE_EXTENSIONS: Dict[str, str] = {
+        "py": Language.PYTHON,
+        "js": Language.JS,
+        "cobol": Language.COBOL,
+    }
+
+    LANGUAGE_SEGMENTERS: Dict[str, Any] = {
+        Language.PYTHON: PythonSegmenter,
+        Language.JS: JavaScriptSegmenter,
+        Language.COBOL: CobolSegmenter,
+    }
+except ImportError:
+    LANGUAGE_EXTENSIONS = {}
+    LANGUAGE_SEGMENTERS = {}
+
+
+class LanguageParser(BaseBlobParser):
+    """Parse using the respective programming language syntax.
+
+    Each top-level function and class in the code is loaded into separate documents.
+    Furthermore, an extra document is generated, containing the remaining top-level code
+    that excludes the already segmented functions and classes.
+
+    This approach can potentially improve the accuracy of QA models over source code.
+
+    Currently, the supported languages for code parsing are Python and JavaScript.
+
+    The language used for parsing can be configured, along with the minimum number of
+    lines required to activate the splitting based on syntax.
+
+    Examples:
+
+       .. code-block:: python
+
+            from langchain.text_splitter.Language
+            from langchain_community.document_loaders.generic import GenericLoader
+            from langchain_community.document_loaders.parsers import LanguageParser
+
+            loader = GenericLoader.from_filesystem(
+                "./code",
+                glob="**/*",
+                suffixes=[".py", ".js"],
+                parser=LanguageParser()
+            )
+            docs = loader.load()
+
+        Example instantiations to manually select the language:
+
+        .. code-block:: python
+
+            from langchain.text_splitter import Language
+
+            loader = GenericLoader.from_filesystem(
+                "./code",
+                glob="**/*",
+                suffixes=[".py"],
+                parser=LanguageParser(language=Language.PYTHON)
+            )
+
+        Example instantiations to set number of lines threshold:
+
+        .. code-block:: python
+
+            loader = GenericLoader.from_filesystem(
+                "./code",
+                glob="**/*",
+                suffixes=[".py"],
+                parser=LanguageParser(parser_threshold=200)
+            )
+    """
+
+    def __init__(self, language: Optional[Language] = None, parser_threshold: int = 0):
+        """
+        Language parser that split code using the respective language syntax.
+
+        Args:
+            language: If None (default), it will try to infer language from source.
+            parser_threshold: Minimum lines needed to activate parsing (0 by default).
+        """
+        self.language = language
+        self.parser_threshold = parser_threshold
+
+    def lazy_parse(self, blob: Blob) -> Iterator[Document]:
+        code = blob.as_string()
+
+        language = self.language or (
+            LANGUAGE_EXTENSIONS.get(blob.source.rsplit(".", 1)[-1])
+            if isinstance(blob.source, str)
+            else None
+        )
+
+        if language is None:
+            yield Document(
+                page_content=code,
+                metadata={
+                    "source": blob.source,
+                },
+            )
+            return
+
+        if self.parser_threshold >= len(code.splitlines()):
+            yield Document(
+                page_content=code,
+                metadata={
+                    "source": blob.source,
+                    "language": language,
+                },
+            )
+            return
+
+        self.Segmenter = LANGUAGE_SEGMENTERS[language]
+        segmenter = self.Segmenter(blob.as_string())
+        if not segmenter.is_valid():
+            yield Document(
+                page_content=code,
+                metadata={
+                    "source": blob.source,
+                },
+            )
+            return
+
+        for functions_classes in segmenter.extract_functions_classes():
+            yield Document(
+                page_content=functions_classes,
+                metadata={
+                    "source": blob.source,
+                    "content_type": "functions_classes",
+                    "language": language,
+                },
+            )
+        yield Document(
+            page_content=segmenter.simplify_code(),
+            metadata={
+                "source": blob.source,
+                "content_type": "simplified_code",
+                "language": language,
+            },
+        )

.scripts/community_split/libs/community/langchain_community/document_loaders/telegram.py

@@ -0,0 +1,262 @@
+from __future__ import annotations
+
+import asyncio
+import json
+from pathlib import Path
+from typing import TYPE_CHECKING, Dict, List, Optional, Union
+
+from langchain_core.documents import Document
+
+from langchain_community.document_loaders.base import BaseLoader
+
+if TYPE_CHECKING:
+    import pandas as pd
+    from telethon.hints import EntityLike
+
+
+def concatenate_rows(row: dict) -> str:
+    """Combine message information in a readable format ready to be used."""
+    date = row["date"]
+    sender = row["from"]
+    text = row["text"]
+    return f"{sender} on {date}: {text}\n\n"
+
+
+class TelegramChatFileLoader(BaseLoader):
+    """Load from `Telegram chat` dump."""
+
+    def __init__(self, path: str):
+        """Initialize with a path."""
+        self.file_path = path
+
+    def load(self) -> List[Document]:
+        """Load documents."""
+        p = Path(self.file_path)
+
+        with open(p, encoding="utf8") as f:
+            d = json.load(f)
+
+        text = "".join(
+            concatenate_rows(message)
+            for message in d["messages"]
+            if message["type"] == "message" and isinstance(message["text"], str)
+        )
+        metadata = {"source": str(p)}
+
+        return [Document(page_content=text, metadata=metadata)]
+
+
+def text_to_docs(text: Union[str, List[str]]) -> List[Document]:
+    """Convert a string or list of strings to a list of Documents with metadata."""
+    from langchain.text_splitter import RecursiveCharacterTextSplitter
+    if isinstance(text, str):
+        # Take a single string as one page
+        text = [text]
+    page_docs = [Document(page_content=page) for page in text]
+
+    # Add page numbers as metadata
+    for i, doc in enumerate(page_docs):
+        doc.metadata["page"] = i + 1
+
+    # Split pages into chunks
+    doc_chunks = []
+
+    for doc in page_docs:
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=800,
+            separators=["\n\n", "\n", ".", "!", "?", ",", " ", ""],
+            chunk_overlap=20,
+        )
+        chunks = text_splitter.split_text(doc.page_content)
+        for i, chunk in enumerate(chunks):
+            doc = Document(
+                page_content=chunk, metadata={"page": doc.metadata["page"], "chunk": i}
+            )
+            # Add sources a metadata
+            doc.metadata["source"] = f"{doc.metadata['page']}-{doc.metadata['chunk']}"
+            doc_chunks.append(doc)
+    return doc_chunks
+
+
+class TelegramChatApiLoader(BaseLoader):
+    """Load `Telegram` chat json directory dump."""
+
+    def __init__(
+        self,
+        chat_entity: Optional[EntityLike] = None,
+        api_id: Optional[int] = None,
+        api_hash: Optional[str] = None,
+        username: Optional[str] = None,
+        file_path: str = "telegram_data.json",
+    ):
+        """Initialize with API parameters.
+
+        Args:
+            chat_entity: The chat entity to fetch data from.
+            api_id: The API ID.
+            api_hash: The API hash.
+            username: The username.
+            file_path: The file path to save the data to. Defaults to
+                 "telegram_data.json".
+        """
+        self.chat_entity = chat_entity
+        self.api_id = api_id
+        self.api_hash = api_hash
+        self.username = username
+        self.file_path = file_path
+
+    async def fetch_data_from_telegram(self) -> None:
+        """Fetch data from Telegram API and save it as a JSON file."""
+        from telethon.sync import TelegramClient
+
+        data = []
+        async with TelegramClient(self.username, self.api_id, self.api_hash) as client:
+            async for message in client.iter_messages(self.chat_entity):
+                is_reply = message.reply_to is not None
+                reply_to_id = message.reply_to.reply_to_msg_id if is_reply else None
+                data.append(
+                    {
+                        "sender_id": message.sender_id,
+                        "text": message.text,
+                        "date": message.date.isoformat(),
+                        "message.id": message.id,
+                        "is_reply": is_reply,
+                        "reply_to_id": reply_to_id,
+                    }
+                )
+
+        with open(self.file_path, "w", encoding="utf-8") as f:
+            json.dump(data, f, ensure_ascii=False, indent=4)
+
+    def _get_message_threads(self, data: pd.DataFrame) -> dict:
+        """Create a dictionary of message threads from the given data.
+
+        Args:
+            data (pd.DataFrame): A DataFrame containing the conversation \
+                data with columns:
+                - message.sender_id
+                - text
+                - date
+                - message.id
+                - is_reply
+                - reply_to_id
+
+        Returns:
+            dict: A dictionary where the key is the parent message ID and \
+                the value is a list of message IDs in ascending order.
+        """
+
+        def find_replies(parent_id: int, reply_data: pd.DataFrame) -> List[int]:
+            """
+            Recursively find all replies to a given parent message ID.
+
+            Args:
+                parent_id (int): The parent message ID.
+                reply_data (pd.DataFrame): A DataFrame containing reply messages.
+
+            Returns:
+                list: A list of message IDs that are replies to the parent message ID.
+            """
+            # Find direct replies to the parent message ID
+            direct_replies = reply_data[reply_data["reply_to_id"] == parent_id][
+                "message.id"
+            ].tolist()
+
+            # Recursively find replies to the direct replies
+            all_replies = []
+            for reply_id in direct_replies:
+                all_replies += [reply_id] + find_replies(reply_id, reply_data)
+
+            return all_replies
+
+        # Filter out parent messages
+        parent_messages = data[~data["is_reply"]]
+
+        # Filter out reply messages and drop rows with NaN in 'reply_to_id'
+        reply_messages = data[data["is_reply"]].dropna(subset=["reply_to_id"])
+
+        # Convert 'reply_to_id' to integer
+        reply_messages["reply_to_id"] = reply_messages["reply_to_id"].astype(int)
+
+        # Create a dictionary of message threads with parent message IDs as keys and \
+        # lists of reply message IDs as values
+        message_threads = {
+            parent_id: [parent_id] + find_replies(parent_id, reply_messages)
+            for parent_id in parent_messages["message.id"]
+        }
+
+        return message_threads
+
+    def _combine_message_texts(
+        self, message_threads: Dict[int, List[int]], data: pd.DataFrame
+    ) -> str:
+        """
+        Combine the message texts for each parent message ID based \
+            on the list of message threads.
+
+        Args:
+            message_threads (dict): A dictionary where the key is the parent message \
+                ID and the value is a list of message IDs in ascending order.
+            data (pd.DataFrame): A DataFrame containing the conversation data:
+                - message.sender_id
+                - text
+                - date
+                - message.id
+                - is_reply
+                - reply_to_id
+
+        Returns:
+            str: A combined string of message texts sorted by date.
+        """
+        combined_text = ""
+
+        # Iterate through sorted parent message IDs
+        for parent_id, message_ids in message_threads.items():
+            # Get the message texts for the message IDs and sort them by date
+            message_texts = (
+                data[data["message.id"].isin(message_ids)]
+                .sort_values(by="date")["text"]
+                .tolist()
+            )
+            message_texts = [str(elem) for elem in message_texts]
+
+            # Combine the message texts
+            combined_text += " ".join(message_texts) + ".\n"
+
+        return combined_text.strip()
+
+    def load(self) -> List[Document]:
+        """Load documents."""
+
+        if self.chat_entity is not None:
+            try:
+                import nest_asyncio
+
+                nest_asyncio.apply()
+                asyncio.run(self.fetch_data_from_telegram())
+            except ImportError:
+                raise ImportError(
+                    """`nest_asyncio` package not found.
+                    please install with `pip install nest_asyncio`
+                    """
+                )
+
+        p = Path(self.file_path)
+
+        with open(p, encoding="utf8") as f:
+            d = json.load(f)
+        try:
+            import pandas as pd
+        except ImportError:
+            raise ImportError(
+                """`pandas` package not found. 
+                please install with `pip install pandas`
+                """
+            )
+        normalized_messages = pd.json_normalize(d)
+        df = pd.DataFrame(normalized_messages)
+
+        message_threads = self._get_message_threads(df)
+        combined_texts = self._combine_message_texts(message_threads, df)
+
+        return text_to_docs(combined_texts)

.scripts/community_split/libs/community/langchain_community/document_transformers/openai_functions.py

@@ -0,0 +1,140 @@
+"""Document transformers that use OpenAI Functions models"""
+from typing import Any, Dict, Optional, Sequence, Type, Union
+
+from langchain_core.documents import BaseDocumentTransformer, Document
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.pydantic_v1 import BaseModel
+
+
+class OpenAIMetadataTagger(BaseDocumentTransformer, BaseModel):
+    """Extract metadata tags from document contents using OpenAI functions.
+
+    Example:
+        .. code-block:: python
+
+                from langchain_community.chat_models import ChatOpenAI
+                from langchain_community.document_transformers import OpenAIMetadataTagger
+                from langchain_core.documents import Document
+
+                schema = {
+                    "properties": {
+                        "movie_title": { "type": "string" },
+                        "critic": { "type": "string" },
+                        "tone": {
+                            "type": "string",
+                            "enum": ["positive", "negative"]
+                        },
+                        "rating": {
+                            "type": "integer",
+                            "description": "The number of stars the critic rated the movie"
+                        }
+                    },
+                    "required": ["movie_title", "critic", "tone"]
+                }
+
+                # Must be an OpenAI model that supports functions
+                llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
+                tagging_chain = create_tagging_chain(schema, llm)
+                document_transformer = OpenAIMetadataTagger(tagging_chain=tagging_chain)
+                original_documents = [
+                    Document(page_content="Review of The Bee Movie\nBy Roger Ebert\n\nThis is the greatest movie ever made. 4 out of 5 stars."),
+                    Document(page_content="Review of The Godfather\nBy Anonymous\n\nThis movie was super boring. 1 out of 5 stars.", metadata={"reliable": False}),
+                ]
+
+                enhanced_documents = document_transformer.transform_documents(original_documents)
+    """  # noqa: E501
+
+    tagging_chain: Any
+    """The chain used to extract metadata from each document."""
+
+    def transform_documents(
+        self, documents: Sequence[Document], **kwargs: Any
+    ) -> Sequence[Document]:
+        """Automatically extract and populate metadata
+        for each document according to the provided schema."""
+
+        new_documents = []
+
+        for document in documents:
+            extracted_metadata: Dict = self.tagging_chain.run(document.page_content)  # type: ignore[assignment]  # noqa: E501
+            new_document = Document(
+                page_content=document.page_content,
+                metadata={**extracted_metadata, **document.metadata},
+            )
+            new_documents.append(new_document)
+        return new_documents
+
+    async def atransform_documents(
+        self, documents: Sequence[Document], **kwargs: Any
+    ) -> Sequence[Document]:
+        raise NotImplementedError
+
+
+def create_metadata_tagger(
+    metadata_schema: Union[Dict[str, Any], Type[BaseModel]],
+    llm: BaseLanguageModel,
+    prompt: Optional[ChatPromptTemplate] = None,
+    *,
+    tagging_chain_kwargs: Optional[Dict] = None,
+) -> OpenAIMetadataTagger:
+    """Create a DocumentTransformer that uses an OpenAI function chain to automatically
+        tag documents with metadata based on their content and an input schema.
+
+    Args:
+        metadata_schema: Either a dictionary or pydantic.BaseModel class. If a dictionary
+            is passed in, it's assumed to already be a valid JsonSchema.
+            For best results, pydantic.BaseModels should have docstrings describing what
+            the schema represents and descriptions for the parameters.
+        llm: Language model to use, assumed to support the OpenAI function-calling API.
+            Defaults to use "gpt-3.5-turbo-0613"
+        prompt: BasePromptTemplate to pass to the model.
+
+    Returns:
+        An LLMChain that will pass the given function to the model.
+
+    Example:
+        .. code-block:: python
+
+                from langchain_community.chat_models import ChatOpenAI
+                from langchain_community.document_transformers import create_metadata_tagger
+                from langchain_core.documents import Document
+
+                schema = {
+                    "properties": {
+                        "movie_title": { "type": "string" },
+                        "critic": { "type": "string" },
+                        "tone": {
+                            "type": "string",
+                            "enum": ["positive", "negative"]
+                        },
+                        "rating": {
+                            "type": "integer",
+                            "description": "The number of stars the critic rated the movie"
+                        }
+                    },
+                    "required": ["movie_title", "critic", "tone"]
+                }
+
+                # Must be an OpenAI model that supports functions
+                llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
+
+                document_transformer = create_metadata_tagger(schema, llm)
+                original_documents = [
+                    Document(page_content="Review of The Bee Movie\nBy Roger Ebert\n\nThis is the greatest movie ever made. 4 out of 5 stars."),
+                    Document(page_content="Review of The Godfather\nBy Anonymous\n\nThis movie was super boring. 1 out of 5 stars.", metadata={"reliable": False}),
+                ]
+
+                enhanced_documents = document_transformer.transform_documents(original_documents)
+    """  # noqa: E501
+    from langchain.chains.openai_functions import create_tagging_chain
+    metadata_schema = (
+        metadata_schema
+        if isinstance(metadata_schema, dict)
+        else metadata_schema.schema()
+    )
+    _tagging_chain_kwargs = tagging_chain_kwargs or {}
+    tagging_chain = create_tagging_chain(
+        metadata_schema, llm, prompt=prompt, **_tagging_chain_kwargs
+    )
+    return OpenAIMetadataTagger(tagging_chain=tagging_chain)

.scripts/community_split/libs/community/langchain_community/tools/amadeus/closest_airport.py

@@ -0,0 +1,50 @@
+from typing import Optional, Type
+
+from langchain_core.callbacks import CallbackManagerForToolRun
+from langchain_core.pydantic_v1 import BaseModel, Field
+
+from langchain_community.chat_models import ChatOpenAI
+from langchain_community.tools.amadeus.base import AmadeusBaseTool
+
+
+class ClosestAirportSchema(BaseModel):
+    """Schema for the AmadeusClosestAirport tool."""
+
+    location: str = Field(
+        description=(
+            " The location for which you would like to find the nearest airport "
+            " along with optional details such as country, state, region, or "
+            " province, allowing for easy processing and identification of "
+            " the closest airport. Examples of the format are the following:\n"
+            " Cali, Colombia\n "
+            " Lincoln, Nebraska, United States\n"
+            " New York, United States\n"
+            " Sydney, New South Wales, Australia\n"
+            " Rome, Lazio, Italy\n"
+            " Toronto, Ontario, Canada\n"
+        )
+    )
+
+
+class AmadeusClosestAirport(AmadeusBaseTool):
+    """Tool for finding the closest airport to a particular location."""
+
+    name: str = "closest_airport"
+    description: str = (
+        "Use this tool to find the closest airport to a particular location."
+    )
+    args_schema: Type[ClosestAirportSchema] = ClosestAirportSchema
+
+    def _run(
+        self,
+        location: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        content = (
+            f" What is the nearest airport to {location}? Please respond with the "
+            " airport's International Air Transport Association (IATA) Location "
+            ' Identifier in the following JSON format. JSON: "iataCode": "IATA '
+            ' Location Identifier" '
+        )
+
+        return ChatOpenAI(temperature=0).invoke(content)

.scripts/community_split/libs/community/langchain_community/tools/clickup/tool.py

@@ -0,0 +1,42 @@
+"""
+This tool allows agents to interact with the clickup library
+and operate on a Clickup instance.
+To use this tool, you must first set as environment variables:
+    client_secret
+    client_id
+    code
+
+Below is a sample script that uses the Clickup tool:
+
+```python
+from langchain_community.agent_toolkits.clickup.toolkit import ClickupToolkit
+from langchain_community.utilities.clickup import ClickupAPIWrapper
+
+clickup = ClickupAPIWrapper()
+toolkit = ClickupToolkit.from_clickup_api_wrapper(clickup)
+```
+"""
+from typing import Optional
+
+from langchain_core.callbacks import CallbackManagerForToolRun
+from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseTool
+
+from langchain_community.utilities.clickup import ClickupAPIWrapper
+
+
+class ClickupAction(BaseTool):
+    """Tool that queries the  Clickup API."""
+
+    api_wrapper: ClickupAPIWrapper = Field(default_factory=ClickupAPIWrapper)
+    mode: str
+    name: str = ""
+    description: str = ""
+
+    def _run(
+        self,
+        instructions: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Use the  Clickup API to run an operation."""
+        return self.api_wrapper.run(self.mode, instructions)

.scripts/community_split/libs/community/langchain_community/tools/jira/tool.py

@@ -0,0 +1,44 @@
+"""
+This tool allows agents to interact with the atlassian-python-api library
+and operate on a Jira instance. For more information on the
+atlassian-python-api library, see https://atlassian-python-api.readthedocs.io/jira.html
+
+To use this tool, you must first set as environment variables:
+    JIRA_API_TOKEN
+    JIRA_USERNAME
+    JIRA_INSTANCE_URL
+
+Below is a sample script that uses the Jira tool:
+
+```python
+from langchain_community.agent_toolkits.jira.toolkit import JiraToolkit
+from langchain_community.utilities.jira import JiraAPIWrapper
+
+jira = JiraAPIWrapper()
+toolkit = JiraToolkit.from_jira_api_wrapper(jira)
+```
+"""
+from typing import Optional
+
+from langchain_core.callbacks import CallbackManagerForToolRun
+from langchain_core.pydantic_v1 import Field
+from langchain_core.tools import BaseTool
+
+from langchain_community.utilities.jira import JiraAPIWrapper
+
+
+class JiraAction(BaseTool):
+    """Tool that queries the Atlassian Jira API."""
+
+    api_wrapper: JiraAPIWrapper = Field(default_factory=JiraAPIWrapper)
+    mode: str
+    name: str = ""
+    description: str = ""
+
+    def _run(
+        self,
+        instructions: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Use the Atlassian Jira API to run an operation."""
+        return self.api_wrapper.run(self.mode, instructions)

.scripts/community_split/libs/community/langchain_community/tools/powerbi/tool.py

@@ -0,0 +1,276 @@
+"""Tools for interacting with a Power BI dataset."""
+import logging
+from time import perf_counter
+from typing import Any, Dict, Optional, Tuple
+
+from langchain_core.callbacks import (
+    AsyncCallbackManagerForToolRun,
+    CallbackManagerForToolRun,
+)
+from langchain_core.pydantic_v1 import Field, validator
+from langchain_core.tools import BaseTool
+from langchain_openai.chat_models import _import_tiktoken
+
+from langchain_community.tools.powerbi.prompt import (
+    BAD_REQUEST_RESPONSE,
+    DEFAULT_FEWSHOT_EXAMPLES,
+    RETRY_RESPONSE,
+)
+from langchain_community.utilities.powerbi import PowerBIDataset, json_to_md
+
+logger = logging.getLogger(__name__)
+
+
+class QueryPowerBITool(BaseTool):
+    """Tool for querying a Power BI Dataset."""
+
+    name: str = "query_powerbi"
+    description: str = """
+    Input to this tool is a detailed question about the dataset, output is a result from the dataset. It will try to answer the question using the dataset, and if it cannot, it will ask for clarification.
+
+    Example Input: "How many rows are in table1?"
+    """  # noqa: E501
+    llm_chain: Any
+    powerbi: PowerBIDataset = Field(exclude=True)
+    examples: Optional[str] = DEFAULT_FEWSHOT_EXAMPLES
+    session_cache: Dict[str, Any] = Field(default_factory=dict, exclude=True)
+    max_iterations: int = 5
+    output_token_limit: int = 4000
+    tiktoken_model_name: Optional[str] = None  # "cl100k_base"
+
+    class Config:
+        """Configuration for this pydantic object."""
+
+        arbitrary_types_allowed = True
+
+    @validator("llm_chain")
+    def validate_llm_chain_input_variables(  # pylint: disable=E0213
+        cls, llm_chain: Any
+    ) -> Any:
+        """Make sure the LLM chain has the correct input variables."""
+        for var in llm_chain.prompt.input_variables:
+            if var not in ["tool_input", "tables", "schemas", "examples"]:
+                raise ValueError(
+                    "LLM chain for QueryPowerBITool must have input variables ['tool_input', 'tables', 'schemas', 'examples'], found %s",  # noqa: C0301 E501 # pylint: disable=C0301
+                    llm_chain.prompt.input_variables,
+                )
+        return llm_chain
+
+    def _check_cache(self, tool_input: str) -> Optional[str]:
+        """Check if the input is present in the cache.
+
+        If the value is a bad request, overwrite with the escalated version,
+        if not present return None."""
+        if tool_input not in self.session_cache:
+            return None
+        return self.session_cache[tool_input]
+
+    def _run(
+        self,
+        tool_input: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+        **kwargs: Any,
+    ) -> str:
+        """Execute the query, return the results or an error message."""
+        if cache := self._check_cache(tool_input):
+            logger.debug("Found cached result for %s: %s", tool_input, cache)
+            return cache
+
+        try:
+            logger.info("Running PBI Query Tool with input: %s", tool_input)
+            query = self.llm_chain.predict(
+                tool_input=tool_input,
+                tables=self.powerbi.get_table_names(),
+                schemas=self.powerbi.get_schemas(),
+                examples=self.examples,
+                callbacks=run_manager.get_child() if run_manager else None,
+            )
+        except Exception as exc:  # pylint: disable=broad-except
+            self.session_cache[tool_input] = f"Error on call to LLM: {exc}"
+            return self.session_cache[tool_input]
+        if query == "I cannot answer this":
+            self.session_cache[tool_input] = query
+            return self.session_cache[tool_input]
+        logger.info("PBI Query:\n%s", query)
+        start_time = perf_counter()
+        pbi_result = self.powerbi.run(command=query)
+        end_time = perf_counter()
+        logger.debug("PBI Result: %s", pbi_result)
+        logger.debug(f"PBI Query duration: {end_time - start_time:0.6f}")
+        result, error = self._parse_output(pbi_result)
+        if error is not None and "TokenExpired" in error:
+            self.session_cache[
+                tool_input
+            ] = "Authentication token expired or invalid, please try reauthenticate."
+            return self.session_cache[tool_input]
+
+        iterations = kwargs.get("iterations", 0)
+        if error and iterations < self.max_iterations:
+            return self._run(
+                tool_input=RETRY_RESPONSE.format(
+                    tool_input=tool_input, query=query, error=error
+                ),
+                run_manager=run_manager,
+                iterations=iterations + 1,
+            )
+
+        self.session_cache[tool_input] = (
+            result if result else BAD_REQUEST_RESPONSE.format(error=error)
+        )
+        return self.session_cache[tool_input]
+
+    async def _arun(
+        self,
+        tool_input: str,
+        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+        **kwargs: Any,
+    ) -> str:
+        """Execute the query, return the results or an error message."""
+        if cache := self._check_cache(tool_input):
+            logger.debug("Found cached result for %s: %s", tool_input, cache)
+            return f"{cache}, from cache, you have already asked this question."
+        try:
+            logger.info("Running PBI Query Tool with input: %s", tool_input)
+            query = await self.llm_chain.apredict(
+                tool_input=tool_input,
+                tables=self.powerbi.get_table_names(),
+                schemas=self.powerbi.get_schemas(),
+                examples=self.examples,
+                callbacks=run_manager.get_child() if run_manager else None,
+            )
+        except Exception as exc:  # pylint: disable=broad-except
+            self.session_cache[tool_input] = f"Error on call to LLM: {exc}"
+            return self.session_cache[tool_input]
+
+        if query == "I cannot answer this":
+            self.session_cache[tool_input] = query
+            return self.session_cache[tool_input]
+        logger.info("PBI Query: %s", query)
+        start_time = perf_counter()
+        pbi_result = await self.powerbi.arun(command=query)
+        end_time = perf_counter()
+        logger.debug("PBI Result: %s", pbi_result)
+        logger.debug(f"PBI Query duration: {end_time - start_time:0.6f}")
+        result, error = self._parse_output(pbi_result)
+        if error is not None and ("TokenExpired" in error or "TokenError" in error):
+            self.session_cache[
+                tool_input
+            ] = "Authentication token expired or invalid, please try to reauthenticate or check the scope of the credential."  # noqa: E501
+            return self.session_cache[tool_input]
+
+        iterations = kwargs.get("iterations", 0)
+        if error and iterations < self.max_iterations:
+            return await self._arun(
+                tool_input=RETRY_RESPONSE.format(
+                    tool_input=tool_input, query=query, error=error
+                ),
+                run_manager=run_manager,
+                iterations=iterations + 1,
+            )
+
+        self.session_cache[tool_input] = (
+            result if result else BAD_REQUEST_RESPONSE.format(error=error)
+        )
+        return self.session_cache[tool_input]
+
+    def _parse_output(
+        self, pbi_result: Dict[str, Any]
+    ) -> Tuple[Optional[str], Optional[Any]]:
+        """Parse the output of the query to a markdown table."""
+        if "results" in pbi_result:
+            rows = pbi_result["results"][0]["tables"][0]["rows"]
+            if len(rows) == 0:
+                logger.info("0 records in result, query was valid.")
+                return (
+                    None,
+                    "0 rows returned, this might be correct, but please validate if all filter values were correct?",  # noqa: E501
+                )
+            result = json_to_md(rows)
+            too_long, length = self._result_too_large(result)
+            if too_long:
+                return (
+                    f"Result too large, please try to be more specific or use the `TOPN` function. The result is {length} tokens long, the limit is {self.output_token_limit} tokens.",  # noqa: E501
+                    None,
+                )
+            return result, None
+
+        if "error" in pbi_result:
+            if (
+                "pbi.error" in pbi_result["error"]
+                and "details" in pbi_result["error"]["pbi.error"]
+            ):
+                return None, pbi_result["error"]["pbi.error"]["details"][0]["detail"]
+            return None, pbi_result["error"]
+        return None, pbi_result
+
+    def _result_too_large(self, result: str) -> Tuple[bool, int]:
+        """Tokenize the output of the query."""
+        if self.tiktoken_model_name:
+            tiktoken_ = _import_tiktoken()
+            encoding = tiktoken_.encoding_for_model(self.tiktoken_model_name)
+            length = len(encoding.encode(result))
+            logger.info("Result length: %s", length)
+            return length > self.output_token_limit, length
+        return False, 0
+
+
+class InfoPowerBITool(BaseTool):
+    """Tool for getting metadata about a PowerBI Dataset."""
+
+    name: str = "schema_powerbi"
+    description: str = """
+    Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables.
+    Be sure that the tables actually exist by calling list_tables_powerbi first!
+
+    Example Input: "table1, table2, table3"
+    """  # noqa: E501
+    powerbi: PowerBIDataset = Field(exclude=True)
+
+    class Config:
+        """Configuration for this pydantic object."""
+
+        arbitrary_types_allowed = True
+
+    def _run(
+        self,
+        tool_input: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Get the schema for tables in a comma-separated list."""
+        return self.powerbi.get_table_info(tool_input.split(", "))
+
+    async def _arun(
+        self,
+        tool_input: str,
+        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+    ) -> str:
+        return await self.powerbi.aget_table_info(tool_input.split(", "))
+
+
+class ListPowerBITool(BaseTool):
+    """Tool for getting tables names."""
+
+    name: str = "list_tables_powerbi"
+    description: str = "Input is an empty string, output is a comma separated list of tables in the database."  # noqa: E501 # pylint: disable=C0301
+    powerbi: PowerBIDataset = Field(exclude=True)
+
+    class Config:
+        """Configuration for this pydantic object."""
+
+        arbitrary_types_allowed = True
+
+    def _run(
+        self,
+        tool_input: Optional[str] = None,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Get the names of the tables."""
+        return ", ".join(self.powerbi.get_table_names())
+
+    async def _arun(
+        self,
+        tool_input: Optional[str] = None,
+        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+    ) -> str:
+        """Get the names of the tables."""
+        return ", ".join(self.powerbi.get_table_names())

.scripts/community_split/libs/community/langchain_community/tools/spark_sql/tool.py

@@ -0,0 +1,130 @@
+# flake8: noqa
+"""Tools for interacting with Spark SQL."""
+from typing import Any, Dict, Optional
+
+from langchain_core.pydantic_v1 import BaseModel, Field, root_validator
+
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.callbacks import (
+    AsyncCallbackManagerForToolRun,
+    CallbackManagerForToolRun,
+)
+from langchain_core.prompts import PromptTemplate
+from langchain_community.utilities.spark_sql import SparkSQL
+from langchain_core.tools import BaseTool
+from langchain_community.tools.spark_sql.prompt import QUERY_CHECKER
+
+
+class BaseSparkSQLTool(BaseModel):
+    """Base tool for interacting with Spark SQL."""
+
+    db: SparkSQL = Field(exclude=True)
+
+    class Config(BaseTool.Config):
+        pass
+
+
+class QuerySparkSQLTool(BaseSparkSQLTool, BaseTool):
+    """Tool for querying a Spark SQL."""
+
+    name: str = "query_sql_db"
+    description: str = """
+    Input to this tool is a detailed and correct SQL query, output is a result from the Spark SQL.
+    If the query is not correct, an error message will be returned.
+    If an error is returned, rewrite the query, check the query, and try again.
+    """
+
+    def _run(
+        self,
+        query: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Execute the query, return the results or an error message."""
+        return self.db.run_no_throw(query)
+
+
+class InfoSparkSQLTool(BaseSparkSQLTool, BaseTool):
+    """Tool for getting metadata about a Spark SQL."""
+
+    name: str = "schema_sql_db"
+    description: str = """
+    Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables.
+    Be sure that the tables actually exist by calling list_tables_sql_db first!
+
+    Example Input: "table1, table2, table3"
+    """
+
+    def _run(
+        self,
+        table_names: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Get the schema for tables in a comma-separated list."""
+        return self.db.get_table_info_no_throw(table_names.split(", "))
+
+
+class ListSparkSQLTool(BaseSparkSQLTool, BaseTool):
+    """Tool for getting tables names."""
+
+    name: str = "list_tables_sql_db"
+    description: str = "Input is an empty string, output is a comma separated list of tables in the Spark SQL."
+
+    def _run(
+        self,
+        tool_input: str = "",
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Get the schema for a specific table."""
+        return ", ".join(self.db.get_usable_table_names())
+
+
+class QueryCheckerTool(BaseSparkSQLTool, BaseTool):
+    """Use an LLM to check if a query is correct.
+    Adapted from https://www.patterns.app/blog/2023/01/18/crunchbot-sql-analyst-gpt/"""
+
+    template: str = QUERY_CHECKER
+    llm: BaseLanguageModel
+    llm_chain: Any = Field(init=False)
+    name: str = "query_checker_sql_db"
+    description: str = """
+    Use this tool to double check if your query is correct before executing it.
+    Always use this tool before executing a query with query_sql_db!
+    """
+
+    @root_validator(pre=True)
+    def initialize_llm_chain(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        if "llm_chain" not in values:
+            from langchain.chains.llm import LLMChain
+            values["llm_chain"] = LLMChain(
+                llm=values.get("llm"),
+                prompt=PromptTemplate(
+                    template=QUERY_CHECKER, input_variables=["query"]
+                ),
+            )
+
+        if values["llm_chain"].prompt.input_variables != ["query"]:
+            raise ValueError(
+                "LLM chain for QueryCheckerTool need to use ['query'] as input_variables "
+                "for the embedded prompt"
+            )
+
+        return values
+
+    def _run(
+        self,
+        query: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Use the LLM to check the query."""
+        return self.llm_chain.predict(
+            query=query, callbacks=run_manager.get_child() if run_manager else None
+        )
+
+    async def _arun(
+        self,
+        query: str,
+        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+    ) -> str:
+        return await self.llm_chain.apredict(
+            query=query, callbacks=run_manager.get_child() if run_manager else None
+        )

.scripts/community_split/libs/community/langchain_community/tools/sql_database/tool.py

@@ -0,0 +1,134 @@
+# flake8: noqa
+"""Tools for interacting with a SQL database."""
+from typing import Any, Dict, Optional
+
+from langchain_core.pydantic_v1 import BaseModel, Extra, Field, root_validator
+
+from langchain_core.language_models import BaseLanguageModel
+from langchain_core.callbacks import (
+    AsyncCallbackManagerForToolRun,
+    CallbackManagerForToolRun,
+)
+from langchain_core.prompts import PromptTemplate
+from langchain_community.utilities.sql_database import SQLDatabase
+from langchain_core.tools import BaseTool
+from langchain_community.tools.sql_database.prompt import QUERY_CHECKER
+
+
+class BaseSQLDatabaseTool(BaseModel):
+    """Base tool for interacting with a SQL database."""
+
+    db: SQLDatabase = Field(exclude=True)
+
+    class Config(BaseTool.Config):
+        pass
+
+
+class QuerySQLDataBaseTool(BaseSQLDatabaseTool, BaseTool):
+    """Tool for querying a SQL database."""
+
+    name: str = "sql_db_query"
+    description: str = """
+    Input to this tool is a detailed and correct SQL query, output is a result from the database.
+    If the query is not correct, an error message will be returned.
+    If an error is returned, rewrite the query, check the query, and try again.
+    """
+
+    def _run(
+        self,
+        query: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Execute the query, return the results or an error message."""
+        return self.db.run_no_throw(query)
+
+
+class InfoSQLDatabaseTool(BaseSQLDatabaseTool, BaseTool):
+    """Tool for getting metadata about a SQL database."""
+
+    name: str = "sql_db_schema"
+    description: str = """
+    Input to this tool is a comma-separated list of tables, output is the schema and sample rows for those tables.    
+
+    Example Input: "table1, table2, table3"
+    """
+
+    def _run(
+        self,
+        table_names: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Get the schema for tables in a comma-separated list."""
+        return self.db.get_table_info_no_throw(
+            [t.strip() for t in table_names.split(",")]
+        )
+
+
+class ListSQLDatabaseTool(BaseSQLDatabaseTool, BaseTool):
+    """Tool for getting tables names."""
+
+    name: str = "sql_db_list_tables"
+    description: str = "Input is an empty string, output is a comma separated list of tables in the database."
+
+    def _run(
+        self,
+        tool_input: str = "",
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Get the schema for a specific table."""
+        return ", ".join(self.db.get_usable_table_names())
+
+
+class QuerySQLCheckerTool(BaseSQLDatabaseTool, BaseTool):
+    """Use an LLM to check if a query is correct.
+    Adapted from https://www.patterns.app/blog/2023/01/18/crunchbot-sql-analyst-gpt/"""
+
+    template: str = QUERY_CHECKER
+    llm: BaseLanguageModel
+    llm_chain: Any = Field(init=False)
+    name: str = "sql_db_query_checker"
+    description: str = """
+    Use this tool to double check if your query is correct before executing it.
+    Always use this tool before executing a query with sql_db_query!
+    """
+
+    @root_validator(pre=True)
+    def initialize_llm_chain(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        if "llm_chain" not in values:
+            from langchain.chains.llm import LLMChain
+            values["llm_chain"] = LLMChain(
+                llm=values.get("llm"),
+                prompt=PromptTemplate(
+                    template=QUERY_CHECKER, input_variables=["dialect", "query"]
+                ),
+            )
+
+        if values["llm_chain"].prompt.input_variables != ["dialect", "query"]:
+            raise ValueError(
+                "LLM chain for QueryCheckerTool must have input variables ['query', 'dialect']"
+            )
+
+        return values
+
+    def _run(
+        self,
+        query: str,
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Use the LLM to check the query."""
+        return self.llm_chain.predict(
+            query=query,
+            dialect=self.db.dialect,
+            callbacks=run_manager.get_child() if run_manager else None,
+        )
+
+    async def _arun(
+        self,
+        query: str,
+        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+    ) -> str:
+        return await self.llm_chain.apredict(
+            query=query,
+            dialect=self.db.dialect,
+            callbacks=run_manager.get_child() if run_manager else None,
+        )

.scripts/community_split/libs/community/langchain_community/tools/zapier/tool.py

@@ -0,0 +1,215 @@
+"""[DEPRECATED]
+
+## Zapier Natural Language Actions API
+\
+Full docs here: https://nla.zapier.com/start/
+
+**Zapier Natural Language Actions** gives you access to the 5k+ apps, 20k+ actions
+on Zapier's platform through a natural language API interface.
+
+NLA supports apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot, Google Sheets,
+Microsoft Teams, and thousands more apps: https://zapier.com/apps
+
+Zapier NLA handles ALL the underlying API auth and translation from
+natural language --> underlying API call --> return simplified output for LLMs
+The key idea is you, or your users, expose a set of actions via an oauth-like setup
+window, which you can then query and execute via a REST API.
+
+NLA offers both API Key and OAuth for signing NLA API requests.
+
+1. Server-side (API Key): for quickly getting started, testing, and production scenarios
+    where LangChain will only use actions exposed in the developer's Zapier account
+    (and will use the developer's connected accounts on Zapier.com)
+
+2. User-facing (Oauth): for production scenarios where you are deploying an end-user
+    facing application and LangChain needs access to end-user's exposed actions and
+    connected accounts on Zapier.com
+
+This quick start will focus on the server-side use case for brevity.
+Review [full docs](https://nla.zapier.com/start/) for user-facing oauth developer
+support.
+
+Typically, you'd use SequentialChain, here's a basic example:
+
+    1. Use NLA to find an email in Gmail
+    2. Use LLMChain to generate a draft reply to (1)
+    3. Use NLA to send the draft reply (2) to someone in Slack via direct message
+
+In code, below:
+
+```python
+
+import os
+
+# get from https://platform.openai.com/
+os.environ["OPENAI_API_KEY"] = os.environ.get("OPENAI_API_KEY", "")
+
+# get from https://nla.zapier.com/docs/authentication/
+os.environ["ZAPIER_NLA_API_KEY"] = os.environ.get("ZAPIER_NLA_API_KEY", "")
+
+from langchain_community.agent_toolkits import ZapierToolkit
+from langchain_community.utilities.zapier import ZapierNLAWrapper
+
+## step 0. expose gmail 'find email' and slack 'send channel message' actions
+
+# first go here, log in, expose (enable) the two actions:
+#    https://nla.zapier.com/demo/start
+#    -- for this example, can leave all fields "Have AI guess"
+# in an oauth scenario, you'd get your own <provider> id (instead of 'demo')
+# which you route your users through first
+
+zapier = ZapierNLAWrapper()
+## To leverage OAuth you may pass the value `nla_oauth_access_token` to
+## the ZapierNLAWrapper. If you do this there is no need to initialize
+## the ZAPIER_NLA_API_KEY env variable
+# zapier = ZapierNLAWrapper(zapier_nla_oauth_access_token="TOKEN_HERE")
+toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)
+```
+
+"""
+from typing import Any, Dict, Optional
+
+from langchain_core._api import warn_deprecated
+from langchain_core.callbacks import (
+    AsyncCallbackManagerForToolRun,
+    CallbackManagerForToolRun,
+)
+from langchain_core.pydantic_v1 import Field, root_validator
+from langchain_core.tools import BaseTool
+
+from langchain_community.tools.zapier.prompt import BASE_ZAPIER_TOOL_PROMPT
+from langchain_community.utilities.zapier import ZapierNLAWrapper
+
+
+class ZapierNLARunAction(BaseTool):
+    """
+    Args:
+        action_id: a specific action ID (from list actions) of the action to execute
+            (the set api_key must be associated with the action owner)
+        instructions: a natural language instruction string for using the action
+            (eg. "get the latest email from Mike Knoop" for "Gmail: find email" action)
+        params: a dict, optional. Any params provided will *override* AI guesses
+            from `instructions` (see "understanding the AI guessing flow" here:
+            https://nla.zapier.com/docs/using-the-api#ai-guessing)
+
+    """
+
+    api_wrapper: ZapierNLAWrapper = Field(default_factory=ZapierNLAWrapper)
+    action_id: str
+    params: Optional[dict] = None
+    base_prompt: str = BASE_ZAPIER_TOOL_PROMPT
+    zapier_description: str
+    params_schema: Dict[str, str] = Field(default_factory=dict)
+    name: str = ""
+    description: str = ""
+
+    @root_validator
+    def set_name_description(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        zapier_description = values["zapier_description"]
+        params_schema = values["params_schema"]
+        if "instructions" in params_schema:
+            del params_schema["instructions"]
+
+        # Ensure base prompt (if overridden) contains necessary input fields
+        necessary_fields = {"{zapier_description}", "{params}"}
+        if not all(field in values["base_prompt"] for field in necessary_fields):
+            raise ValueError(
+                "Your custom base Zapier prompt must contain input fields for "
+                "{zapier_description} and {params}."
+            )
+
+        values["name"] = zapier_description
+        values["description"] = values["base_prompt"].format(
+            zapier_description=zapier_description,
+            params=str(list(params_schema.keys())),
+        )
+        return values
+
+    def _run(
+        self, instructions: str, run_manager: Optional[CallbackManagerForToolRun] = None
+    ) -> str:
+        """Use the Zapier NLA tool to return a list of all exposed user actions."""
+        warn_deprecated(
+            since="0.0.319",
+            message=(
+                "This tool will be deprecated on 2023-11-17. See "
+                "https://nla.zapier.com/sunset/ for details"
+            ),
+        )
+        return self.api_wrapper.run_as_str(self.action_id, instructions, self.params)
+
+    async def _arun(
+        self,
+        instructions: str,
+        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+    ) -> str:
+        """Use the Zapier NLA tool to return a list of all exposed user actions."""
+        warn_deprecated(
+            since="0.0.319",
+            message=(
+                "This tool will be deprecated on 2023-11-17. See "
+                "https://nla.zapier.com/sunset/ for details"
+            ),
+        )
+        return await self.api_wrapper.arun_as_str(
+            self.action_id,
+            instructions,
+            self.params,
+        )
+
+
+ZapierNLARunAction.__doc__ = (
+    ZapierNLAWrapper.run.__doc__ + ZapierNLARunAction.__doc__  # type: ignore
+)
+
+
+# other useful actions
+
+
+class ZapierNLAListActions(BaseTool):
+    """
+    Args:
+        None
+
+    """
+
+    name: str = "ZapierNLA_list_actions"
+    description: str = BASE_ZAPIER_TOOL_PROMPT + (
+        "This tool returns a list of the user's exposed actions."
+    )
+    api_wrapper: ZapierNLAWrapper = Field(default_factory=ZapierNLAWrapper)
+
+    def _run(
+        self,
+        _: str = "",
+        run_manager: Optional[CallbackManagerForToolRun] = None,
+    ) -> str:
+        """Use the Zapier NLA tool to return a list of all exposed user actions."""
+        warn_deprecated(
+            since="0.0.319",
+            message=(
+                "This tool will be deprecated on 2023-11-17. See "
+                "https://nla.zapier.com/sunset/ for details"
+            ),
+        )
+        return self.api_wrapper.list_as_str()
+
+    async def _arun(
+        self,
+        _: str = "",
+        run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+    ) -> str:
+        """Use the Zapier NLA tool to return a list of all exposed user actions."""
+        warn_deprecated(
+            since="0.0.319",
+            message=(
+                "This tool will be deprecated on 2023-11-17. See "
+                "https://nla.zapier.com/sunset/ for details"
+            ),
+        )
+        return await self.api_wrapper.alist_as_str()
+
+
+ZapierNLAListActions.__doc__ = (
+    ZapierNLAWrapper.list.__doc__ + ZapierNLAListActions.__doc__  # type: ignore
+)

.scripts/community_split/libs/community/tests/integration_tests/callbacks/test_langchain_tracer.py

@@ -0,0 +1,284 @@
+"""Integration tests for the langchain tracer module."""
+import asyncio
+import os
+
+from aiohttp import ClientSession
+from langchain_core.callbacks import atrace_as_chain_group, trace_as_chain_group
+from langchain_core.tracers.context import tracing_v2_enabled
+from langchain_core.prompts import PromptTemplate
+
+from langchain_community.callbacks import tracing_enabled
+from langchain_community.chat_models import ChatOpenAI
+from langchain_community.llms import OpenAI
+
+questions = [
+    (
+        "Who won the US Open men's final in 2019? "
+        "What is his age raised to the 0.334 power?"
+    ),
+    (
+        "Who is Olivia Wilde's boyfriend? "
+        "What is his current age raised to the 0.23 power?"
+    ),
+    (
+        "Who won the most recent formula 1 grand prix? "
+        "What is their age raised to the 0.23 power?"
+    ),
+    (
+        "Who won the US Open women's final in 2019? "
+        "What is her age raised to the 0.34 power?"
+    ),
+    ("Who is Beyonce's husband? " "What is his age raised to the 0.19 power?"),
+]
+
+
+def test_tracing_sequential() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_TRACING"] = "true"
+
+    for q in questions[:3]:
+        llm = OpenAI(temperature=0)
+        tools = load_tools(["llm-math", "serpapi"], llm=llm)
+        agent = initialize_agent(
+            tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+        )
+        agent.run(q)
+
+
+def test_tracing_session_env_var() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_TRACING"] = "true"
+    os.environ["LANGCHAIN_SESSION"] = "my_session"
+
+    llm = OpenAI(temperature=0)
+    tools = load_tools(["llm-math", "serpapi"], llm=llm)
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    agent.run(questions[0])
+    if "LANGCHAIN_SESSION" in os.environ:
+        del os.environ["LANGCHAIN_SESSION"]
+
+
+async def test_tracing_concurrent() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_TRACING"] = "true"
+    aiosession = ClientSession()
+    llm = OpenAI(temperature=0)
+    async_tools = load_tools(["llm-math", "serpapi"], llm=llm, aiosession=aiosession)
+    agent = initialize_agent(
+        async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    tasks = [agent.arun(q) for q in questions[:3]]
+    await asyncio.gather(*tasks)
+    await aiosession.close()
+
+
+async def test_tracing_concurrent_bw_compat_environ() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_HANDLER"] = "langchain"
+    if "LANGCHAIN_TRACING" in os.environ:
+        del os.environ["LANGCHAIN_TRACING"]
+    aiosession = ClientSession()
+    llm = OpenAI(temperature=0)
+    async_tools = load_tools(["llm-math", "serpapi"], llm=llm, aiosession=aiosession)
+    agent = initialize_agent(
+        async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    tasks = [agent.arun(q) for q in questions[:3]]
+    await asyncio.gather(*tasks)
+    await aiosession.close()
+    if "LANGCHAIN_HANDLER" in os.environ:
+        del os.environ["LANGCHAIN_HANDLER"]
+
+
+def test_tracing_context_manager() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    llm = OpenAI(temperature=0)
+    tools = load_tools(["llm-math", "serpapi"], llm=llm)
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    if "LANGCHAIN_TRACING" in os.environ:
+        del os.environ["LANGCHAIN_TRACING"]
+    with tracing_enabled() as session:
+        assert session
+        agent.run(questions[0])  # this should be traced
+
+    agent.run(questions[0])  # this should not be traced
+
+
+async def test_tracing_context_manager_async() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    llm = OpenAI(temperature=0)
+    async_tools = load_tools(["llm-math", "serpapi"], llm=llm)
+    agent = initialize_agent(
+        async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    if "LANGCHAIN_TRACING" in os.environ:
+        del os.environ["LANGCHAIN_TRACING"]
+
+    # start a background task
+    task = asyncio.create_task(agent.arun(questions[0]))  # this should not be traced
+    with tracing_enabled() as session:
+        assert session
+        tasks = [agent.arun(q) for q in questions[1:4]]  # these should be traced
+        await asyncio.gather(*tasks)
+
+    await task
+
+
+async def test_tracing_v2_environment_variable() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_TRACING_V2"] = "true"
+
+    aiosession = ClientSession()
+    llm = OpenAI(temperature=0)
+    async_tools = load_tools(["llm-math", "serpapi"], llm=llm, aiosession=aiosession)
+    agent = initialize_agent(
+        async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    tasks = [agent.arun(q) for q in questions[:3]]
+    await asyncio.gather(*tasks)
+    await aiosession.close()
+
+
+def test_tracing_v2_context_manager() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    llm = ChatOpenAI(temperature=0)
+    tools = load_tools(["llm-math", "serpapi"], llm=llm)
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    if "LANGCHAIN_TRACING_V2" in os.environ:
+        del os.environ["LANGCHAIN_TRACING_V2"]
+    with tracing_v2_enabled():
+        agent.run(questions[0])  # this should be traced
+
+    agent.run(questions[0])  # this should not be traced
+
+
+def test_tracing_v2_chain_with_tags() -> None:
+    from langchain.chains.llm import LLMChain
+    from langchain.chains.constitutional_ai.base import ConstitutionalChain
+    from langchain.chains.constitutional_ai.models import ConstitutionalPrinciple
+    llm = OpenAI(temperature=0)
+    chain = ConstitutionalChain.from_llm(
+        llm,
+        chain=LLMChain.from_string(llm, "Q: {question} A:"),
+        tags=["only-root"],
+        constitutional_principles=[
+            ConstitutionalPrinciple(
+                critique_request="Tell if this answer is good.",
+                revision_request="Give a better answer.",
+            )
+        ],
+    )
+    if "LANGCHAIN_TRACING_V2" in os.environ:
+        del os.environ["LANGCHAIN_TRACING_V2"]
+    with tracing_v2_enabled():
+        chain.run("what is the meaning of life", tags=["a-tag"])
+
+
+def test_tracing_v2_agent_with_metadata() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_TRACING_V2"] = "true"
+    llm = OpenAI(temperature=0)
+    chat = ChatOpenAI(temperature=0)
+    tools = load_tools(["llm-math", "serpapi"], llm=llm)
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    chat_agent = initialize_agent(
+        tools, chat, agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    agent.run(questions[0], tags=["a-tag"], metadata={"a": "b", "c": "d"})
+    chat_agent.run(questions[0], tags=["a-tag"], metadata={"a": "b", "c": "d"})
+
+
+async def test_tracing_v2_async_agent_with_metadata() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_TRACING_V2"] = "true"
+    llm = OpenAI(temperature=0, metadata={"f": "g", "h": "i"})
+    chat = ChatOpenAI(temperature=0, metadata={"f": "g", "h": "i"})
+    async_tools = load_tools(["llm-math", "serpapi"], llm=llm)
+    agent = initialize_agent(
+        async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    chat_agent = initialize_agent(
+        async_tools,
+        chat,
+        agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION,
+        verbose=True,
+    )
+    await agent.arun(questions[0], tags=["a-tag"], metadata={"a": "b", "c": "d"})
+    await chat_agent.arun(questions[0], tags=["a-tag"], metadata={"a": "b", "c": "d"})
+
+
+def test_trace_as_group() -> None:
+    from langchain.chains.llm import LLMChain
+    llm = OpenAI(temperature=0.9)
+    prompt = PromptTemplate(
+        input_variables=["product"],
+        template="What is a good name for a company that makes {product}?",
+    )
+    chain = LLMChain(llm=llm, prompt=prompt)
+    with trace_as_chain_group("my_group", inputs={"input": "cars"}) as group_manager:
+        chain.run(product="cars", callbacks=group_manager)
+        chain.run(product="computers", callbacks=group_manager)
+        final_res = chain.run(product="toys", callbacks=group_manager)
+        group_manager.on_chain_end({"output": final_res})
+
+    with trace_as_chain_group("my_group_2", inputs={"input": "toys"}) as group_manager:
+        final_res = chain.run(product="toys", callbacks=group_manager)
+        group_manager.on_chain_end({"output": final_res})
+
+
+def test_trace_as_group_with_env_set() -> None:
+    from langchain.chains.llm import LLMChain
+    os.environ["LANGCHAIN_TRACING_V2"] = "true"
+    llm = OpenAI(temperature=0.9)
+    prompt = PromptTemplate(
+        input_variables=["product"],
+        template="What is a good name for a company that makes {product}?",
+    )
+    chain = LLMChain(llm=llm, prompt=prompt)
+    with trace_as_chain_group(
+        "my_group_env_set", inputs={"input": "cars"}
+    ) as group_manager:
+        chain.run(product="cars", callbacks=group_manager)
+        chain.run(product="computers", callbacks=group_manager)
+        final_res = chain.run(product="toys", callbacks=group_manager)
+        group_manager.on_chain_end({"output": final_res})
+
+    with trace_as_chain_group(
+        "my_group_2_env_set", inputs={"input": "toys"}
+    ) as group_manager:
+        final_res = chain.run(product="toys", callbacks=group_manager)
+        group_manager.on_chain_end({"output": final_res})
+
+
+async def test_trace_as_group_async() -> None:
+    from langchain.chains.llm import LLMChain
+    llm = OpenAI(temperature=0.9)
+    prompt = PromptTemplate(
+        input_variables=["product"],
+        template="What is a good name for a company that makes {product}?",
+    )
+    chain = LLMChain(llm=llm, prompt=prompt)
+    async with atrace_as_chain_group("my_async_group") as group_manager:
+        await chain.arun(product="cars", callbacks=group_manager)
+        await chain.arun(product="computers", callbacks=group_manager)
+        await chain.arun(product="toys", callbacks=group_manager)
+
+    async with atrace_as_chain_group(
+        "my_async_group_2", inputs={"input": "toys"}
+    ) as group_manager:
+        res = await asyncio.gather(
+            *[
+                chain.arun(product="toys", callbacks=group_manager),
+                chain.arun(product="computers", callbacks=group_manager),
+                chain.arun(product="cars", callbacks=group_manager),
+            ]
+        )
+        await group_manager.on_chain_end({"output": res})

.scripts/community_split/libs/community/tests/integration_tests/callbacks/test_openai_callback.py

@@ -0,0 +1,68 @@
+"""Integration tests for the langchain tracer module."""
+import asyncio
+
+
+from langchain_community.callbacks import get_openai_callback
+from langchain_community.llms import OpenAI
+
+
+async def test_openai_callback() -> None:
+    llm = OpenAI(temperature=0)
+    with get_openai_callback() as cb:
+        llm("What is the square root of 4?")
+
+    total_tokens = cb.total_tokens
+    assert total_tokens > 0
+
+    with get_openai_callback() as cb:
+        llm("What is the square root of 4?")
+        llm("What is the square root of 4?")
+
+    assert cb.total_tokens == total_tokens * 2
+
+    with get_openai_callback() as cb:
+        await asyncio.gather(
+            *[llm.agenerate(["What is the square root of 4?"]) for _ in range(3)]
+        )
+
+    assert cb.total_tokens == total_tokens * 3
+
+    task = asyncio.create_task(llm.agenerate(["What is the square root of 4?"]))
+    with get_openai_callback() as cb:
+        await llm.agenerate(["What is the square root of 4?"])
+
+    await task
+    assert cb.total_tokens == total_tokens
+
+
+def test_openai_callback_batch_llm() -> None:
+    llm = OpenAI(temperature=0)
+    with get_openai_callback() as cb:
+        llm.generate(["What is the square root of 4?", "What is the square root of 4?"])
+
+    assert cb.total_tokens > 0
+    total_tokens = cb.total_tokens
+
+    with get_openai_callback() as cb:
+        llm("What is the square root of 4?")
+        llm("What is the square root of 4?")
+
+    assert cb.total_tokens == total_tokens
+
+
+def test_openai_callback_agent() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    llm = OpenAI(temperature=0)
+    tools = load_tools(["serpapi", "llm-math"], llm=llm)
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    with get_openai_callback() as cb:
+        agent.run(
+            "Who is Olivia Wilde's boyfriend? "
+            "What is his current age raised to the 0.23 power?"
+        )
+        print(f"Total Tokens: {cb.total_tokens}")
+        print(f"Prompt Tokens: {cb.prompt_tokens}")
+        print(f"Completion Tokens: {cb.completion_tokens}")
+        print(f"Total Cost (USD): ${cb.total_cost}")

.scripts/community_split/libs/community/tests/integration_tests/callbacks/test_streamlit_callback.py

@@ -0,0 +1,30 @@
+"""Integration tests for the StreamlitCallbackHandler module."""
+
+import pytest
+
+# Import the internal StreamlitCallbackHandler from its module - and not from
+# the `langchain_community.callbacks.streamlit` package - so that we don't end up using
+# Streamlit's externally-provided callback handler.
+from langchain_community.callbacks.streamlit.streamlit_callback_handler import (
+    StreamlitCallbackHandler,
+)
+from langchain_community.llms import OpenAI
+
+
+@pytest.mark.requires("streamlit")
+def test_streamlit_callback_agent() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    import streamlit as st
+
+    streamlit_callback = StreamlitCallbackHandler(st.container())
+
+    llm = OpenAI(temperature=0)
+    tools = load_tools(["serpapi", "llm-math"], llm=llm)
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    agent.run(
+        "Who is Olivia Wilde's boyfriend? "
+        "What is his current age raised to the 0.23 power?",
+        callbacks=[streamlit_callback],
+    )

.scripts/community_split/libs/community/tests/integration_tests/callbacks/test_wandb_tracer.py

@@ -0,0 +1,118 @@
+"""Integration tests for the langchain tracer module."""
+import asyncio
+import os
+
+from aiohttp import ClientSession
+from langchain_community.callbacks import wandb_tracing_enabled
+
+from langchain_community.llms import OpenAI
+
+questions = [
+    (
+        "Who won the US Open men's final in 2019? "
+        "What is his age raised to the 0.334 power?"
+    ),
+    (
+        "Who is Olivia Wilde's boyfriend? "
+        "What is his current age raised to the 0.23 power?"
+    ),
+    (
+        "Who won the most recent formula 1 grand prix? "
+        "What is their age raised to the 0.23 power?"
+    ),
+    (
+        "Who won the US Open women's final in 2019? "
+        "What is her age raised to the 0.34 power?"
+    ),
+    ("Who is Beyonce's husband? " "What is his age raised to the 0.19 power?"),
+]
+
+
+def test_tracing_sequential() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_WANDB_TRACING"] = "true"
+    os.environ["WANDB_PROJECT"] = "langchain-tracing"
+
+    for q in questions[:3]:
+        llm = OpenAI(temperature=0)
+        tools = load_tools(
+            ["llm-math", "serpapi"],
+            llm=llm,
+        )
+        agent = initialize_agent(
+            tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+        )
+        agent.run(q)
+
+
+def test_tracing_session_env_var() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_WANDB_TRACING"] = "true"
+
+    llm = OpenAI(temperature=0)
+    tools = load_tools(
+        ["llm-math", "serpapi"],
+        llm=llm,
+    )
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    agent.run(questions[0])
+
+
+async def test_tracing_concurrent() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    os.environ["LANGCHAIN_WANDB_TRACING"] = "true"
+    aiosession = ClientSession()
+    llm = OpenAI(temperature=0)
+    async_tools = load_tools(
+        ["llm-math", "serpapi"],
+        llm=llm,
+        aiosession=aiosession,
+    )
+    agent = initialize_agent(
+        async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    tasks = [agent.arun(q) for q in questions[:3]]
+    await asyncio.gather(*tasks)
+    await aiosession.close()
+
+
+def test_tracing_context_manager() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    llm = OpenAI(temperature=0)
+    tools = load_tools(
+        ["llm-math", "serpapi"],
+        llm=llm,
+    )
+    agent = initialize_agent(
+        tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    if "LANGCHAIN_WANDB_TRACING" in os.environ:
+        del os.environ["LANGCHAIN_WANDB_TRACING"]
+    with wandb_tracing_enabled():
+        agent.run(questions[0])  # this should be traced
+
+    agent.run(questions[0])  # this should not be traced
+
+
+async def test_tracing_context_manager_async() -> None:
+    from langchain.agents import AgentType, initialize_agent, load_tools
+    llm = OpenAI(temperature=0)
+    async_tools = load_tools(
+        ["llm-math", "serpapi"],
+        llm=llm,
+    )
+    agent = initialize_agent(
+        async_tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True
+    )
+    if "LANGCHAIN_WANDB_TRACING" in os.environ:
+        del os.environ["LANGCHAIN_TRACING"]
+
+    # start a background task
+    task = asyncio.create_task(agent.arun(questions[0]))  # this should not be traced
+    with wandb_tracing_enabled():
+        tasks = [agent.arun(q) for q in questions[1:4]]  # these should be traced
+        await asyncio.gather(*tasks)
+
+    await task

.scripts/community_split/libs/community/tests/integration_tests/chat_models/test_openai.py

@@ -0,0 +1,341 @@
+"""Test ChatOpenAI wrapper."""
+from typing import Any, Optional
+
+import pytest
+from langchain_core.callbacks import CallbackManager
+from langchain_core.messages import BaseMessage, HumanMessage, SystemMessage
+from langchain_core.outputs import (
+    ChatGeneration,
+    ChatResult,
+    LLMResult,
+)
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.pydantic_v1 import BaseModel, Field
+from langchain_openai.chat_models import ChatOpenAI
+
+from langchain_community.output_parsers.openai_functions import (
+    JsonOutputFunctionsParser,
+)
+from tests.unit_tests.callbacks.fake_callback_handler import FakeCallbackHandler
+
+
+@pytest.mark.scheduled
+def test_chat_openai() -> None:
+    """Test ChatOpenAI wrapper."""
+    chat = ChatOpenAI(
+        temperature=0.7,
+        base_url=None,
+        organization=None,
+        openai_proxy=None,
+        timeout=10.0,
+        max_retries=3,
+        http_client=None,
+        n=1,
+        max_tokens=10,
+        default_headers=None,
+        default_query=None,
+    )
+    message = HumanMessage(content="Hello")
+    response = chat([message])
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+def test_chat_openai_model() -> None:
+    """Test ChatOpenAI wrapper handles model_name."""
+    chat = ChatOpenAI(model="foo")
+    assert chat.model_name == "foo"
+    chat = ChatOpenAI(model_name="bar")
+    assert chat.model_name == "bar"
+
+
+def test_chat_openai_system_message() -> None:
+    """Test ChatOpenAI wrapper with system message."""
+    chat = ChatOpenAI(max_tokens=10)
+    system_message = SystemMessage(content="You are to chat with the user.")
+    human_message = HumanMessage(content="Hello")
+    response = chat([system_message, human_message])
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+@pytest.mark.scheduled
+def test_chat_openai_generate() -> None:
+    """Test ChatOpenAI wrapper with generate."""
+    chat = ChatOpenAI(max_tokens=10, n=2)
+    message = HumanMessage(content="Hello")
+    response = chat.generate([[message], [message]])
+    assert isinstance(response, LLMResult)
+    assert len(response.generations) == 2
+    assert response.llm_output
+    assert "system_fingerprint" in response.llm_output
+    for generations in response.generations:
+        assert len(generations) == 2
+        for generation in generations:
+            assert isinstance(generation, ChatGeneration)
+            assert isinstance(generation.text, str)
+            assert generation.text == generation.message.content
+
+
+@pytest.mark.scheduled
+def test_chat_openai_multiple_completions() -> None:
+    """Test ChatOpenAI wrapper with multiple completions."""
+    chat = ChatOpenAI(max_tokens=10, n=5)
+    message = HumanMessage(content="Hello")
+    response = chat._generate([message])
+    assert isinstance(response, ChatResult)
+    assert len(response.generations) == 5
+    for generation in response.generations:
+        assert isinstance(generation.message, BaseMessage)
+        assert isinstance(generation.message.content, str)
+
+
+@pytest.mark.scheduled
+def test_chat_openai_streaming() -> None:
+    """Test that streaming correctly invokes on_llm_new_token callback."""
+    callback_handler = FakeCallbackHandler()
+    callback_manager = CallbackManager([callback_handler])
+    chat = ChatOpenAI(
+        max_tokens=10,
+        streaming=True,
+        temperature=0,
+        callback_manager=callback_manager,
+        verbose=True,
+    )
+    message = HumanMessage(content="Hello")
+    response = chat([message])
+    assert callback_handler.llm_streams > 0
+    assert isinstance(response, BaseMessage)
+
+
+@pytest.mark.scheduled
+def test_chat_openai_streaming_generation_info() -> None:
+    """Test that generation info is preserved when streaming."""
+
+    class _FakeCallback(FakeCallbackHandler):
+        saved_things: dict = {}
+
+        def on_llm_end(
+            self,
+            *args: Any,
+            **kwargs: Any,
+        ) -> Any:
+            # Save the generation
+            self.saved_things["generation"] = args[0]
+
+    callback = _FakeCallback()
+    callback_manager = CallbackManager([callback])
+    chat = ChatOpenAI(
+        max_tokens=2,
+        temperature=0,
+        callback_manager=callback_manager,
+    )
+    list(chat.stream("hi"))
+    generation = callback.saved_things["generation"]
+    # `Hello!` is two tokens, assert that that is what is returned
+    assert generation.generations[0][0].text == "Hello!"
+
+
+def test_chat_openai_llm_output_contains_model_name() -> None:
+    """Test llm_output contains model_name."""
+    chat = ChatOpenAI(max_tokens=10)
+    message = HumanMessage(content="Hello")
+    llm_result = chat.generate([[message]])
+    assert llm_result.llm_output is not None
+    assert llm_result.llm_output["model_name"] == chat.model_name
+
+
+def test_chat_openai_streaming_llm_output_contains_model_name() -> None:
+    """Test llm_output contains model_name."""
+    chat = ChatOpenAI(max_tokens=10, streaming=True)
+    message = HumanMessage(content="Hello")
+    llm_result = chat.generate([[message]])
+    assert llm_result.llm_output is not None
+    assert llm_result.llm_output["model_name"] == chat.model_name
+
+
+def test_chat_openai_invalid_streaming_params() -> None:
+    """Test that streaming correctly invokes on_llm_new_token callback."""
+    with pytest.raises(ValueError):
+        ChatOpenAI(
+            max_tokens=10,
+            streaming=True,
+            temperature=0,
+            n=5,
+        )
+
+
+@pytest.mark.scheduled
+async def test_async_chat_openai() -> None:
+    """Test async generation."""
+    chat = ChatOpenAI(max_tokens=10, n=2)
+    message = HumanMessage(content="Hello")
+    response = await chat.agenerate([[message], [message]])
+    assert isinstance(response, LLMResult)
+    assert len(response.generations) == 2
+    assert response.llm_output
+    assert "system_fingerprint" in response.llm_output
+    for generations in response.generations:
+        assert len(generations) == 2
+        for generation in generations:
+            assert isinstance(generation, ChatGeneration)
+            assert isinstance(generation.text, str)
+            assert generation.text == generation.message.content
+
+
+@pytest.mark.scheduled
+async def test_async_chat_openai_streaming() -> None:
+    """Test that streaming correctly invokes on_llm_new_token callback."""
+    callback_handler = FakeCallbackHandler()
+    callback_manager = CallbackManager([callback_handler])
+    chat = ChatOpenAI(
+        max_tokens=10,
+        streaming=True,
+        temperature=0,
+        callback_manager=callback_manager,
+        verbose=True,
+    )
+    message = HumanMessage(content="Hello")
+    response = await chat.agenerate([[message], [message]])
+    assert callback_handler.llm_streams > 0
+    assert isinstance(response, LLMResult)
+    assert len(response.generations) == 2
+    for generations in response.generations:
+        assert len(generations) == 1
+        for generation in generations:
+            assert isinstance(generation, ChatGeneration)
+            assert isinstance(generation.text, str)
+            assert generation.text == generation.message.content
+
+
+
+
+@pytest.mark.scheduled
+async def test_async_chat_openai_bind_functions() -> None:
+    """Test ChatOpenAI wrapper with multiple completions."""
+
+    class Person(BaseModel):
+        """Identifying information about a person."""
+
+        name: str = Field(..., title="Name", description="The person's name")
+        age: int = Field(..., title="Age", description="The person's age")
+        fav_food: Optional[str] = Field(
+            default=None, title="Fav Food", description="The person's favorite food"
+        )
+
+    chat = ChatOpenAI(
+        max_tokens=30,
+        n=1,
+        streaming=True,
+    ).bind_functions(functions=[Person], function_call="Person")
+
+    prompt = ChatPromptTemplate.from_messages(
+        [
+            ("system", "Use the provided Person function"),
+            ("user", "{input}"),
+        ]
+    )
+
+    chain = prompt | chat | JsonOutputFunctionsParser(args_only=True)
+
+    message = HumanMessage(content="Sally is 13 years old")
+    response = await chain.abatch([{"input": message}])
+
+    assert isinstance(response, list)
+    assert len(response) == 1
+    for generation in response:
+        assert isinstance(generation, dict)
+        assert "name" in generation
+        assert "age" in generation
+
+
+def test_chat_openai_extra_kwargs() -> None:
+    """Test extra kwargs to chat openai."""
+    # Check that foo is saved in extra_kwargs.
+    llm = ChatOpenAI(foo=3, max_tokens=10)
+    assert llm.max_tokens == 10
+    assert llm.model_kwargs == {"foo": 3}
+
+    # Test that if extra_kwargs are provided, they are added to it.
+    llm = ChatOpenAI(foo=3, model_kwargs={"bar": 2})
+    assert llm.model_kwargs == {"foo": 3, "bar": 2}
+
+    # Test that if provided twice it errors
+    with pytest.raises(ValueError):
+        ChatOpenAI(foo=3, model_kwargs={"foo": 2})
+
+    # Test that if explicit param is specified in kwargs it errors
+    with pytest.raises(ValueError):
+        ChatOpenAI(model_kwargs={"temperature": 0.2})
+
+    # Test that "model" cannot be specified in kwargs
+    with pytest.raises(ValueError):
+        ChatOpenAI(model_kwargs={"model": "text-davinci-003"})
+
+
+@pytest.mark.scheduled
+def test_openai_streaming() -> None:
+    """Test streaming tokens from OpenAI."""
+    llm = ChatOpenAI(max_tokens=10)
+
+    for token in llm.stream("I'm Pickle Rick"):
+        assert isinstance(token.content, str)
+
+
+@pytest.mark.scheduled
+async def test_openai_astream() -> None:
+    """Test streaming tokens from OpenAI."""
+    llm = ChatOpenAI(max_tokens=10)
+
+    async for token in llm.astream("I'm Pickle Rick"):
+        assert isinstance(token.content, str)
+
+
+@pytest.mark.scheduled
+async def test_openai_abatch() -> None:
+    """Test streaming tokens from ChatOpenAI."""
+    llm = ChatOpenAI(max_tokens=10)
+
+    result = await llm.abatch(["I'm Pickle Rick", "I'm not Pickle Rick"])
+    for token in result:
+        assert isinstance(token.content, str)
+
+
+@pytest.mark.scheduled
+async def test_openai_abatch_tags() -> None:
+    """Test batch tokens from ChatOpenAI."""
+    llm = ChatOpenAI(max_tokens=10)
+
+    result = await llm.abatch(
+        ["I'm Pickle Rick", "I'm not Pickle Rick"], config={"tags": ["foo"]}
+    )
+    for token in result:
+        assert isinstance(token.content, str)
+
+
+@pytest.mark.scheduled
+def test_openai_batch() -> None:
+    """Test batch tokens from ChatOpenAI."""
+    llm = ChatOpenAI(max_tokens=10)
+
+    result = llm.batch(["I'm Pickle Rick", "I'm not Pickle Rick"])
+    for token in result:
+        assert isinstance(token.content, str)
+
+
+@pytest.mark.scheduled
+async def test_openai_ainvoke() -> None:
+    """Test invoke tokens from ChatOpenAI."""
+    llm = ChatOpenAI(max_tokens=10)
+
+    result = await llm.ainvoke("I'm Pickle Rick", config={"tags": ["foo"]})
+    assert isinstance(result.content, str)
+
+
+@pytest.mark.scheduled
+def test_openai_invoke() -> None:
+    """Test invoke tokens from ChatOpenAI."""
+    llm = ChatOpenAI(max_tokens=10)
+
+    result = llm.invoke("I'm Pickle Rick", config=dict(tags=["foo"]))
+    assert isinstance(result.content, str)

.scripts/community_split/libs/community/tests/integration_tests/chat_models/test_qianfan_endpoint.py

@@ -0,0 +1,219 @@
+"""Test Baidu Qianfan Chat Endpoint."""
+
+from typing import Any
+
+from langchain_core.callbacks import CallbackManager
+from langchain_core.messages import (
+    AIMessage,
+    BaseMessage,
+    FunctionMessage,
+    HumanMessage,
+)
+from langchain_core.outputs import ChatGeneration, LLMResult
+from langchain_core.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
+
+from langchain_community.chat_models.baidu_qianfan_endpoint import QianfanChatEndpoint
+from tests.unit_tests.callbacks.fake_callback_handler import FakeCallbackHandler
+
+_FUNCTIONS: Any = [
+    {
+        "name": "format_person_info",
+        "description": (
+            "Output formatter. Should always be used to format your response to the"
+            " user."
+        ),
+        "parameters": {
+            "title": "Person",
+            "description": "Identifying information about a person.",
+            "type": "object",
+            "properties": {
+                "name": {
+                    "title": "Name",
+                    "description": "The person's name",
+                    "type": "string",
+                },
+                "age": {
+                    "title": "Age",
+                    "description": "The person's age",
+                    "type": "integer",
+                },
+                "fav_food": {
+                    "title": "Fav Food",
+                    "description": "The person's favorite food",
+                    "type": "string",
+                },
+            },
+            "required": ["name", "age"],
+        },
+    },
+    {
+        "name": "get_current_temperature",
+        "description": ("Used to get the location's temperature."),
+        "parameters": {
+            "type": "object",
+            "properties": {
+                "location": {
+                    "type": "string",
+                    "description": "city name",
+                },
+                "unit": {
+                    "type": "string",
+                    "enum": ["centigrade", "Fahrenheit"],
+                },
+            },
+            "required": ["location", "unit"],
+        },
+        "responses": {
+            "type": "object",
+            "properties": {
+                "temperature": {
+                    "type": "integer",
+                    "description": "city temperature",
+                },
+                "unit": {
+                    "type": "string",
+                    "enum": ["centigrade", "Fahrenheit"],
+                },
+            },
+        },
+    },
+]
+
+
+def test_default_call() -> None:
+    """Test default model(`ERNIE-Bot`) call."""
+    chat = QianfanChatEndpoint()
+    response = chat(messages=[HumanMessage(content="Hello")])
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+def test_model() -> None:
+    """Test model kwarg works."""
+    chat = QianfanChatEndpoint(model="BLOOMZ-7B")
+    response = chat(messages=[HumanMessage(content="Hello")])
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+def test_model_param() -> None:
+    """Test model params works."""
+    chat = QianfanChatEndpoint()
+    response = chat(model="BLOOMZ-7B", messages=[HumanMessage(content="Hello")])
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+def test_endpoint() -> None:
+    """Test user custom model deployments like some open source models."""
+    chat = QianfanChatEndpoint(endpoint="qianfan_bloomz_7b_compressed")
+    response = chat(messages=[HumanMessage(content="Hello")])
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+def test_endpoint_param() -> None:
+    """Test user custom model deployments like some open source models."""
+    chat = QianfanChatEndpoint()
+    response = chat(
+        messages=[
+            HumanMessage(endpoint="qianfan_bloomz_7b_compressed", content="Hello")
+        ]
+    )
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+def test_multiple_history() -> None:
+    """Tests multiple history works."""
+    chat = QianfanChatEndpoint()
+
+    response = chat(
+        messages=[
+            HumanMessage(content="Hello."),
+            AIMessage(content="Hello!"),
+            HumanMessage(content="How are you doing?"),
+        ]
+    )
+    assert isinstance(response, BaseMessage)
+    assert isinstance(response.content, str)
+
+
+def test_stream() -> None:
+    """Test that stream works."""
+    chat = QianfanChatEndpoint(streaming=True)
+    callback_handler = FakeCallbackHandler()
+    callback_manager = CallbackManager([callback_handler])
+    response = chat(
+        messages=[
+            HumanMessage(content="Hello."),
+            AIMessage(content="Hello!"),
+            HumanMessage(content="Who are you?"),
+        ],
+        stream=True,
+        callbacks=callback_manager,
+    )
+    assert callback_handler.llm_streams > 0
+    assert isinstance(response.content, str)
+
+
+def test_multiple_messages() -> None:
+    """Tests multiple messages works."""
+    chat = QianfanChatEndpoint()
+    message = HumanMessage(content="Hi, how are you.")
+    response = chat.generate([[message], [message]])
+
+    assert isinstance(response, LLMResult)
+    assert len(response.generations) == 2
+    for generations in response.generations:
+        assert len(generations) == 1
+        for generation in generations:
+            assert isinstance(generation, ChatGeneration)
+            assert isinstance(generation.text, str)
+            assert generation.text == generation.message.content
+
+
+def test_functions_call_thoughts() -> None:
+    chat = QianfanChatEndpoint(model="ERNIE-Bot")
+
+    prompt_tmpl = "Use the given functions to answer following question: {input}"
+    prompt_msgs = [
+        HumanMessagePromptTemplate.from_template(prompt_tmpl),
+    ]
+    prompt = ChatPromptTemplate(messages=prompt_msgs)
+
+    chain = prompt | chat.bind(functions=_FUNCTIONS)
+
+    message = HumanMessage(content="What's the temperature in Shanghai today?")
+    response = chain.batch([{"input": message}])
+    assert isinstance(response[0], AIMessage)
+    assert "function_call" in response[0].additional_kwargs
+
+
+def test_functions_call() -> None:
+    chat = QianfanChatEndpoint(model="ERNIE-Bot")
+
+    prompt = ChatPromptTemplate(
+        messages=[
+            HumanMessage(content="What's the temperature in Shanghai today?"),
+            AIMessage(
+                content="",
+                additional_kwargs={
+                    "function_call": {
+                        "name": "get_current_temperature",
+                        "thoughts": "i will use get_current_temperature "
+                        "to resolve the questions",
+                        "arguments": '{"location":"Shanghai","unit":"centigrade"}',
+                    }
+                },
+            ),
+            FunctionMessage(
+                name="get_current_weather",
+                content='{"temperature": "25", \
+                                "unit": "摄氏度", "description": "晴朗"}',
+            ),
+        ]
+    )
+    chain = prompt | chat.bind(functions=_FUNCTIONS)
+    resp = chain.invoke({})
+    assert isinstance(resp, AIMessage)

.scripts/community_split/libs/community/tests/integration_tests/document_loaders/parsers/test_language.py

@@ -0,0 +1,182 @@
+from pathlib import Path
+
+import pytest
+
+from langchain_community.document_loaders.concurrent import ConcurrentLoader
+from langchain_community.document_loaders.generic import GenericLoader
+from langchain_community.document_loaders.parsers import LanguageParser
+
+
+def test_language_loader_for_python() -> None:
+    """Test Python loader with parser enabled."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = GenericLoader.from_filesystem(
+        file_path, glob="hello_world.py", parser=LanguageParser(parser_threshold=5)
+    )
+    docs = loader.load()
+
+    assert len(docs) == 2
+
+    metadata = docs[0].metadata
+    assert metadata["source"] == str(file_path / "hello_world.py")
+    assert metadata["content_type"] == "functions_classes"
+    assert metadata["language"] == "python"
+    metadata = docs[1].metadata
+    assert metadata["source"] == str(file_path / "hello_world.py")
+    assert metadata["content_type"] == "simplified_code"
+    assert metadata["language"] == "python"
+
+    assert (
+        docs[0].page_content
+        == """def main():
+    print("Hello World!")
+
+    return 0"""
+    )
+    assert (
+        docs[1].page_content
+        == """#!/usr/bin/env python3
+
+import sys
+
+
+# Code for: def main():
+
+
+if __name__ == "__main__":
+    sys.exit(main())"""
+    )
+
+
+def test_language_loader_for_python_with_parser_threshold() -> None:
+    """Test Python loader with parser enabled and below threshold."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = GenericLoader.from_filesystem(
+        file_path,
+        glob="hello_world.py",
+        parser=LanguageParser(language="python", parser_threshold=1000),
+    )
+    docs = loader.load()
+
+    assert len(docs) == 1
+
+
+def esprima_installed() -> bool:
+    try:
+        import esprima  # noqa: F401
+
+        return True
+    except Exception as e:
+        print(f"esprima not installed, skipping test {e}")
+        return False
+
+
+@pytest.mark.skipif(not esprima_installed(), reason="requires esprima package")
+def test_language_loader_for_javascript() -> None:
+    """Test JavaScript loader with parser enabled."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = GenericLoader.from_filesystem(
+        file_path, glob="hello_world.js", parser=LanguageParser(parser_threshold=5)
+    )
+    docs = loader.load()
+
+    assert len(docs) == 3
+
+    metadata = docs[0].metadata
+    assert metadata["source"] == str(file_path / "hello_world.js")
+    assert metadata["content_type"] == "functions_classes"
+    assert metadata["language"] == "js"
+    metadata = docs[1].metadata
+    assert metadata["source"] == str(file_path / "hello_world.js")
+    assert metadata["content_type"] == "functions_classes"
+    assert metadata["language"] == "js"
+    metadata = docs[2].metadata
+    assert metadata["source"] == str(file_path / "hello_world.js")
+    assert metadata["content_type"] == "simplified_code"
+    assert metadata["language"] == "js"
+
+    assert (
+        docs[0].page_content
+        == """class HelloWorld {
+  sayHello() {
+    console.log("Hello World!");
+  }
+}"""
+    )
+    assert (
+        docs[1].page_content
+        == """function main() {
+  const hello = new HelloWorld();
+  hello.sayHello();
+}"""
+    )
+    assert (
+        docs[2].page_content
+        == """// Code for: class HelloWorld {
+
+// Code for: function main() {
+
+main();"""
+    )
+
+
+def test_language_loader_for_javascript_with_parser_threshold() -> None:
+    """Test JavaScript loader with parser enabled and below threshold."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = GenericLoader.from_filesystem(
+        file_path,
+        glob="hello_world.js",
+        parser=LanguageParser(language="js", parser_threshold=1000),
+    )
+    docs = loader.load()
+
+    assert len(docs) == 1
+
+
+def test_concurrent_language_loader_for_javascript_with_parser_threshold() -> None:
+    """Test JavaScript ConcurrentLoader with parser enabled and below threshold."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = ConcurrentLoader.from_filesystem(
+        file_path,
+        glob="hello_world.js",
+        parser=LanguageParser(language="js", parser_threshold=1000),
+    )
+    docs = loader.load()
+
+    assert len(docs) == 1
+
+
+def test_concurrent_language_loader_for_python_with_parser_threshold() -> None:
+    """Test Python ConcurrentLoader with parser enabled and below threshold."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = ConcurrentLoader.from_filesystem(
+        file_path,
+        glob="hello_world.py",
+        parser=LanguageParser(language="python", parser_threshold=1000),
+    )
+    docs = loader.load()
+
+    assert len(docs) == 1
+
+
+@pytest.mark.skipif(not esprima_installed(), reason="requires esprima package")
+def test_concurrent_language_loader_for_javascript() -> None:
+    """Test JavaScript ConcurrentLoader with parser enabled."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = ConcurrentLoader.from_filesystem(
+        file_path, glob="hello_world.js", parser=LanguageParser(parser_threshold=5)
+    )
+    docs = loader.load()
+
+    assert len(docs) == 3
+
+
+def test_concurrent_language_loader_for_python() -> None:
+    """Test Python ConcurrentLoader with parser enabled."""
+    file_path = Path(__file__).parent.parent.parent / "examples"
+    loader = ConcurrentLoader.from_filesystem(
+        file_path, glob="hello_world.py", parser=LanguageParser(parser_threshold=5)
+    )
+    docs = loader.load()
+
+    assert len(docs) == 2

.scripts/community_split/libs/community/tests/integration_tests/llms/test_fireworks.py

@@ -0,0 +1,147 @@
+"""Test Fireworks AI API Wrapper."""
+import sys
+from typing import Generator
+
+import pytest
+from langchain_core.outputs import LLMResult
+
+from langchain_community.llms.fireworks import Fireworks
+
+if sys.version_info < (3, 9):
+    pytest.skip("fireworks-ai requires Python > 3.8", allow_module_level=True)
+
+
+@pytest.fixture
+def llm() -> Fireworks:
+    return Fireworks(model_kwargs={"temperature": 0, "max_tokens": 512})
+
+
+@pytest.mark.scheduled
+def test_fireworks_call(llm: Fireworks) -> None:
+    """Test valid call to fireworks."""
+    output = llm("How is the weather in New York today?")
+    assert isinstance(output, str)
+
+
+@pytest.mark.scheduled
+def test_fireworks_model_param() -> None:
+    """Tests model parameters for Fireworks"""
+    llm = Fireworks(model="foo")
+    assert llm.model == "foo"
+
+
+@pytest.mark.scheduled
+def test_fireworks_invoke(llm: Fireworks) -> None:
+    """Tests completion with invoke"""
+    output = llm.invoke("How is the weather in New York today?", stop=[","])
+    assert isinstance(output, str)
+    assert output[-1] == ","
+
+
+@pytest.mark.scheduled
+async def test_fireworks_ainvoke(llm: Fireworks) -> None:
+    """Tests completion with invoke"""
+    output = await llm.ainvoke("How is the weather in New York today?", stop=[","])
+    assert isinstance(output, str)
+    assert output[-1] == ","
+
+
+@pytest.mark.scheduled
+def test_fireworks_batch(llm: Fireworks) -> None:
+    """Tests completion with invoke"""
+    llm = Fireworks()
+    output = llm.batch(
+        [
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+        ],
+        stop=[","],
+    )
+    for token in output:
+        assert isinstance(token, str)
+        assert token[-1] == ","
+
+
+@pytest.mark.scheduled
+async def test_fireworks_abatch(llm: Fireworks) -> None:
+    """Tests completion with invoke"""
+    output = await llm.abatch(
+        [
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+            "How is the weather in New York today?",
+        ],
+        stop=[","],
+    )
+    for token in output:
+        assert isinstance(token, str)
+        assert token[-1] == ","
+
+
+@pytest.mark.scheduled
+def test_fireworks_multiple_prompts(
+    llm: Fireworks,
+) -> None:
+    """Test completion with multiple prompts."""
+    output = llm.generate(["How is the weather in New York today?", "I'm pickle rick"])
+    assert isinstance(output, LLMResult)
+    assert isinstance(output.generations, list)
+    assert len(output.generations) == 2
+
+
+@pytest.mark.scheduled
+def test_fireworks_streaming(llm: Fireworks) -> None:
+    """Test stream completion."""
+    generator = llm.stream("Who's the best quarterback in the NFL?")
+    assert isinstance(generator, Generator)
+
+    for token in generator:
+        assert isinstance(token, str)
+
+
+@pytest.mark.scheduled
+def test_fireworks_streaming_stop_words(llm: Fireworks) -> None:
+    """Test stream completion with stop words."""
+    generator = llm.stream("Who's the best quarterback in the NFL?", stop=[","])
+    assert isinstance(generator, Generator)
+
+    last_token = ""
+    for token in generator:
+        last_token = token
+        assert isinstance(token, str)
+    assert last_token[-1] == ","
+
+
+@pytest.mark.scheduled
+async def test_fireworks_streaming_async(llm: Fireworks) -> None:
+    """Test stream completion."""
+
+    last_token = ""
+    async for token in llm.astream(
+        "Who's the best quarterback in the NFL?", stop=[","]
+    ):
+        last_token = token
+        assert isinstance(token, str)
+    assert last_token[-1] == ","
+
+
+@pytest.mark.scheduled
+async def test_fireworks_async_agenerate(llm: Fireworks) -> None:
+    """Test async."""
+    output = await llm.agenerate(["What is the best city to live in California?"])
+    assert isinstance(output, LLMResult)
+
+
+@pytest.mark.scheduled
+async def test_fireworks_multiple_prompts_async_agenerate(llm: Fireworks) -> None:
+    output = await llm.agenerate(
+        ["How is the weather in New York today?", "I'm pickle rick"]
+    )
+    assert isinstance(output, LLMResult)
+    assert isinstance(output.generations, list)
+    assert len(output.generations) == 2

.scripts/community_split/libs/community/tests/integration_tests/llms/test_opaqueprompts.py

@@ -0,0 +1,77 @@
+import langchain_community.utilities.opaqueprompts as op
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.prompts import PromptTemplate
+from langchain_core.runnables import RunnableParallel
+
+from langchain_community.llms import OpenAI
+from langchain_community.llms.opaqueprompts import OpaquePrompts
+
+prompt_template = """
+As an AI assistant, you will answer questions according to given context.
+
+Sensitive personal information in the question is masked for privacy.
+For instance, if the original text says "Giana is good," it will be changed
+to "PERSON_998 is good."
+
+Here's how to handle these changes:
+* Consider these masked phrases just as placeholders, but still refer to
+them in a relevant way when answering.
+* It's possible that different masked terms might mean the same thing.
+Stick with the given term and don't modify it.
+* All masked terms follow the "TYPE_ID" pattern.
+* Please don't invent new masked terms. For instance, if you see "PERSON_998,"
+don't come up with "PERSON_997" or "PERSON_999" unless they're already in the question.
+
+Conversation History: ```{history}```
+Context : ```During our recent meeting on February 23, 2023, at 10:30 AM,
+John Doe provided me with his personal details. His email is johndoe@example.com
+and his contact number is 650-456-7890. He lives in New York City, USA, and
+belongs to the American nationality with Christian beliefs and a leaning towards
+the Democratic party. He mentioned that he recently made a transaction using his
+credit card 4111 1111 1111 1111 and transferred bitcoins to the wallet address
+1A1zP1eP5QGefi2DMPTfTL5SLmv7DivfNa. While discussing his European travels, he
+noted down his IBAN as GB29 NWBK 6016 1331 9268 19. Additionally, he provided
+his website as https://johndoeportfolio.com. John also discussed
+some of his US-specific details. He said his bank account number is
+1234567890123456 and his drivers license is Y12345678. His ITIN is 987-65-4321,
+and he recently renewed his passport,
+the number for which is 123456789. He emphasized not to share his SSN, which is
+669-45-6789. Furthermore, he mentioned that he accesses his work files remotely
+through the IP 192.168.1.1 and has a medical license number MED-123456. ```
+Question: ```{question}```
+"""
+
+
+def test_opaqueprompts() -> None:
+    chain = PromptTemplate.from_template(prompt_template) | OpaquePrompts(llm=OpenAI())
+    output = chain.invoke(
+        {
+            "question": "Write a text message to remind John to do password reset \
+                for his website through his email to stay secure."
+        }
+    )
+    assert isinstance(output, str)
+
+
+def test_opaqueprompts_functions() -> None:
+    prompt = (PromptTemplate.from_template(prompt_template),)
+    llm = OpenAI()
+    pg_chain = (
+        op.sanitize
+        | RunnableParallel(
+            secure_context=lambda x: x["secure_context"],  # type: ignore
+            response=(lambda x: x["sanitized_input"])  # type: ignore
+            | prompt
+            | llm
+            | StrOutputParser(),
+        )
+        | (lambda x: op.desanitize(x["response"], x["secure_context"]))
+    )
+
+    pg_chain.invoke(
+        {
+            "question": "Write a text message to remind John to do password reset\
+                 for his website through his email to stay secure.",
+            "history": "",
+        }
+    )

.scripts/community_split/libs/community/tests/integration_tests/llms/test_symblai_nebula.py

@@ -0,0 +1,42 @@
+"""Test Nebula API wrapper."""
+from langchain_community.llms.symblai_nebula import Nebula
+
+
+def test_symblai_nebula_call() -> None:
+    """Test valid call to Nebula."""
+    conversation = """Sam: Good morning, team! Let's keep this standup concise. 
+    We'll go in the usual order: what you did yesterday, 
+    what you plan to do today, and any blockers. Alex, kick us off.
+Alex: Morning! Yesterday, I wrapped up the UI for the user dashboard. 
+The new charts and widgets are now responsive. 
+I also had a sync with the design team to ensure the final touchups are in 
+line with the brand guidelines. Today, I'll start integrating the frontend with 
+the new API endpoints Rhea was working on. 
+The only blocker is waiting for some final API documentation, 
+but I guess Rhea can update on that.
+Rhea: Hey, all! Yep, about the API documentation - I completed the majority of
+ the backend work for user data retrieval yesterday. 
+ The endpoints are mostly set up, but I need to do a bit more testing today. 
+ I'll finalize the API documentation by noon, so that should unblock Alex. 
+ After that, I’ll be working on optimizing the database queries 
+ for faster data fetching. No other blockers on my end.
+Sam: Great, thanks Rhea. Do reach out if you need any testing assistance
+ or if there are any hitches with the database. 
+ Now, my update: Yesterday, I coordinated with the client to get clarity 
+ on some feature requirements. Today, I'll be updating our project roadmap 
+ and timelines based on their feedback. Additionally, I'll be sitting with 
+ the QA team in the afternoon for preliminary testing. 
+ Blocker: I might need both of you to be available for a quick call 
+ in case the client wants to discuss the changes live.
+Alex: Sounds good, Sam. Just let us know a little in advance for the call.
+Rhea: Agreed. We can make time for that.
+Sam: Perfect! Let's keep the momentum going. Reach out if there are any 
+sudden issues or support needed. Have a productive day!
+Alex: You too.
+Rhea: Thanks, bye!"""
+    llm = Nebula(nebula_api_key="<your_api_key>")
+
+    instruction = """Identify the main objectives mentioned in this 
+conversation."""
+    output = llm.invoke(f"{instruction}\n{conversation}")
+    assert isinstance(output, str)

.scripts/community_split/libs/community/tests/integration_tests/llms/test_vertexai.py

@@ -0,0 +1,151 @@
+"""Test Vertex AI API wrapper.
+In order to run this test, you need to install VertexAI SDK:
+pip install google-cloud-aiplatform>=1.36.0
+
+Your end-user credentials would be used to make the calls (make sure you've run 
+`gcloud auth login` first).
+"""
+import os
+from typing import Optional
+
+import pytest
+from langchain_core.outputs import LLMResult
+
+from langchain_community.llms import VertexAI, VertexAIModelGarden
+
+
+def test_vertex_initialization() -> None:
+    llm = VertexAI()
+    assert llm._llm_type == "vertexai"
+    assert llm.model_name == llm.client._model_id
+
+
+def test_vertex_call() -> None:
+    llm = VertexAI(temperature=0)
+    output = llm("Say foo:")
+    assert isinstance(output, str)
+
+
+@pytest.mark.scheduled
+def test_vertex_generate() -> None:
+    llm = VertexAI(temperature=0.3, n=2, model_name="text-bison@001")
+    output = llm.generate(["Say foo:"])
+    assert isinstance(output, LLMResult)
+    assert len(output.generations) == 1
+    assert len(output.generations[0]) == 2
+
+
+@pytest.mark.scheduled
+def test_vertex_generate_code() -> None:
+    llm = VertexAI(temperature=0.3, n=2, model_name="code-bison@001")
+    output = llm.generate(["generate a python method that says foo:"])
+    assert isinstance(output, LLMResult)
+    assert len(output.generations) == 1
+    assert len(output.generations[0]) == 2
+
+
+@pytest.mark.scheduled
+async def test_vertex_agenerate() -> None:
+    llm = VertexAI(temperature=0)
+    output = await llm.agenerate(["Please say foo:"])
+    assert isinstance(output, LLMResult)
+
+
+@pytest.mark.scheduled
+def test_vertex_stream() -> None:
+    llm = VertexAI(temperature=0)
+    outputs = list(llm.stream("Please say foo:"))
+    assert isinstance(outputs[0], str)
+
+
+async def test_vertex_consistency() -> None:
+    llm = VertexAI(temperature=0)
+    output = llm.generate(["Please say foo:"])
+    streaming_output = llm.generate(["Please say foo:"], stream=True)
+    async_output = await llm.agenerate(["Please say foo:"])
+    assert output.generations[0][0].text == streaming_output.generations[0][0].text
+    assert output.generations[0][0].text == async_output.generations[0][0].text
+
+
+@pytest.mark.parametrize(
+    "endpoint_os_variable_name,result_arg",
+    [("FALCON_ENDPOINT_ID", "generated_text"), ("LLAMA_ENDPOINT_ID", None)],
+)
+def test_model_garden(
+    endpoint_os_variable_name: str, result_arg: Optional[str]
+) -> None:
+    """In order to run this test, you should provide endpoint names.
+
+    Example:
+    export FALCON_ENDPOINT_ID=...
+    export LLAMA_ENDPOINT_ID=...
+    export PROJECT=...
+    """
+    endpoint_id = os.environ[endpoint_os_variable_name]
+    project = os.environ["PROJECT"]
+    location = "europe-west4"
+    llm = VertexAIModelGarden(
+        endpoint_id=endpoint_id,
+        project=project,
+        result_arg=result_arg,
+        location=location,
+    )
+    output = llm("What is the meaning of life?")
+    assert isinstance(output, str)
+    assert llm._llm_type == "vertexai_model_garden"
+
+
+@pytest.mark.parametrize(
+    "endpoint_os_variable_name,result_arg",
+    [("FALCON_ENDPOINT_ID", "generated_text"), ("LLAMA_ENDPOINT_ID", None)],
+)
+def test_model_garden_generate(
+    endpoint_os_variable_name: str, result_arg: Optional[str]
+) -> None:
+    """In order to run this test, you should provide endpoint names.
+
+    Example:
+    export FALCON_ENDPOINT_ID=...
+    export LLAMA_ENDPOINT_ID=...
+    export PROJECT=...
+    """
+    endpoint_id = os.environ[endpoint_os_variable_name]
+    project = os.environ["PROJECT"]
+    location = "europe-west4"
+    llm = VertexAIModelGarden(
+        endpoint_id=endpoint_id,
+        project=project,
+        result_arg=result_arg,
+        location=location,
+    )
+    output = llm.generate(["What is the meaning of life?", "How much is 2+2"])
+    assert isinstance(output, LLMResult)
+    assert len(output.generations) == 2
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize(
+    "endpoint_os_variable_name,result_arg",
+    [("FALCON_ENDPOINT_ID", "generated_text"), ("LLAMA_ENDPOINT_ID", None)],
+)
+async def test_model_garden_agenerate(
+    endpoint_os_variable_name: str, result_arg: Optional[str]
+) -> None:
+    endpoint_id = os.environ[endpoint_os_variable_name]
+    project = os.environ["PROJECT"]
+    location = "europe-west4"
+    llm = VertexAIModelGarden(
+        endpoint_id=endpoint_id,
+        project=project,
+        result_arg=result_arg,
+        location=location,
+    )
+    output = await llm.agenerate(["What is the meaning of life?", "How much is 2+2"])
+    assert isinstance(output, LLMResult)
+    assert len(output.generations) == 2
+
+
+def test_vertex_call_count_tokens() -> None:
+    llm = VertexAI()
+    output = llm.get_num_tokens("How are you?")
+    assert output == 4

.scripts/community_split/libs/community/tests/integration_tests/utilities/test_arxiv.py

@@ -0,0 +1,171 @@
+"""Integration test for Arxiv API Wrapper."""
+from typing import Any, List
+
+import pytest
+from langchain_core.documents import Document
+from langchain_core.tools import BaseTool
+
+from langchain_community.tools import ArxivQueryRun
+from langchain_community.utilities import ArxivAPIWrapper
+
+
+@pytest.fixture
+def api_client() -> ArxivAPIWrapper:
+    return ArxivAPIWrapper()
+
+
+def test_run_success_paper_name(api_client: ArxivAPIWrapper) -> None:
+    """Test a query of paper name that returns the correct answer"""
+
+    output = api_client.run("Heat-bath random walks with Markov bases")
+    assert "Probability distributions for Markov chains based quantum walks" in output
+    assert (
+        "Transformations of random walks on groups via Markov stopping times" in output
+    )
+    assert (
+        "Recurrence of Multidimensional Persistent Random Walks. Fourier and Series "
+        "Criteria" in output
+    )
+
+
+def test_run_success_arxiv_identifier(api_client: ArxivAPIWrapper) -> None:
+    """Test a query of an arxiv identifier returns the correct answer"""
+
+    output = api_client.run("1605.08386v1")
+    assert "Heat-bath random walks with Markov bases" in output
+
+
+def test_run_success_multiple_arxiv_identifiers(api_client: ArxivAPIWrapper) -> None:
+    """Test a query of multiple arxiv identifiers that returns the correct answer"""
+
+    output = api_client.run("1605.08386v1 2212.00794v2 2308.07912")
+    assert "Heat-bath random walks with Markov bases" in output
+    assert "Scaling Language-Image Pre-training via Masking" in output
+    assert (
+        "Ultra-low mass PBHs in the early universe can explain the PTA signal" in output
+    )
+
+
+def test_run_returns_several_docs(api_client: ArxivAPIWrapper) -> None:
+    """Test that returns several docs"""
+
+    output = api_client.run("Caprice Stanley")
+    assert "On Mixing Behavior of a Family of Random Walks" in output
+
+
+def test_run_returns_no_result(api_client: ArxivAPIWrapper) -> None:
+    """Test that gives no result."""
+
+    output = api_client.run("1605.08386WWW")
+    assert "No good Arxiv Result was found" == output
+
+
+def assert_docs(docs: List[Document]) -> None:
+    for doc in docs:
+        assert doc.page_content
+        assert doc.metadata
+        assert set(doc.metadata) == {"Published", "Title", "Authors", "Summary"}
+
+
+def test_load_success_paper_name(api_client: ArxivAPIWrapper) -> None:
+    """Test a query of paper name that returns one document"""
+
+    docs = api_client.load("Heat-bath random walks with Markov bases")
+    assert len(docs) == 3
+    assert_docs(docs)
+
+
+def test_load_success_arxiv_identifier(api_client: ArxivAPIWrapper) -> None:
+    """Test a query of an arxiv identifier that returns one document"""
+
+    docs = api_client.load("1605.08386v1")
+    assert len(docs) == 1
+    assert_docs(docs)
+
+
+def test_load_success_multiple_arxiv_identifiers(api_client: ArxivAPIWrapper) -> None:
+    """Test a query of arxiv identifiers that returns the correct answer"""
+
+    docs = api_client.load("1605.08386v1 2212.00794v2 2308.07912")
+    assert len(docs) == 3
+    assert_docs(docs)
+
+
+def test_load_returns_no_result(api_client: ArxivAPIWrapper) -> None:
+    """Test that returns no docs"""
+
+    docs = api_client.load("1605.08386WWW")
+    assert len(docs) == 0
+
+
+def test_load_returns_limited_docs() -> None:
+    """Test that returns several docs"""
+    expected_docs = 2
+    api_client = ArxivAPIWrapper(load_max_docs=expected_docs)
+    docs = api_client.load("ChatGPT")
+    assert len(docs) == expected_docs
+    assert_docs(docs)
+
+
+def test_load_returns_limited_doc_content_chars() -> None:
+    """Test that returns limited doc_content_chars_max"""
+
+    doc_content_chars_max = 100
+    api_client = ArxivAPIWrapper(doc_content_chars_max=doc_content_chars_max)
+    docs = api_client.load("1605.08386")
+    assert len(docs[0].page_content) == doc_content_chars_max
+
+
+def test_load_returns_unlimited_doc_content_chars() -> None:
+    """Test that returns unlimited doc_content_chars_max"""
+
+    doc_content_chars_max = None
+    api_client = ArxivAPIWrapper(doc_content_chars_max=doc_content_chars_max)
+    docs = api_client.load("1605.08386")
+    assert len(docs[0].page_content) == pytest.approx(54338, rel=1e-2)
+
+
+def test_load_returns_full_set_of_metadata() -> None:
+    """Test that returns several docs"""
+    api_client = ArxivAPIWrapper(load_max_docs=1, load_all_available_meta=True)
+    docs = api_client.load("ChatGPT")
+    assert len(docs) == 1
+    for doc in docs:
+        assert doc.page_content
+        assert doc.metadata
+        assert set(doc.metadata).issuperset(
+            {"Published", "Title", "Authors", "Summary"}
+        )
+        print(doc.metadata)
+        assert len(set(doc.metadata)) > 4
+
+
+def _load_arxiv_from_universal_entry(**kwargs: Any) -> BaseTool:
+    from langchain.agents.load_tools import load_tools
+    tools = load_tools(["arxiv"], **kwargs)
+    assert len(tools) == 1, "loaded more than 1 tool"
+    return tools[0]
+
+
+def test_load_arxiv_from_universal_entry() -> None:
+    arxiv_tool = _load_arxiv_from_universal_entry()
+    output = arxiv_tool("Caprice Stanley")
+    assert (
+        "On Mixing Behavior of a Family of Random Walks" in output
+    ), "failed to fetch a valid result"
+
+
+def test_load_arxiv_from_universal_entry_with_params() -> None:
+    params = {
+        "top_k_results": 1,
+        "load_max_docs": 10,
+        "load_all_available_meta": True,
+    }
+    arxiv_tool = _load_arxiv_from_universal_entry(**params)
+    assert isinstance(arxiv_tool, ArxivQueryRun)
+    wp = arxiv_tool.api_wrapper
+    assert wp.top_k_results == 1, "failed to assert top_k_results"
+    assert wp.load_max_docs == 10, "failed to assert load_max_docs"
+    assert (
+        wp.load_all_available_meta is True
+    ), "failed to assert load_all_available_meta"

.scripts/community_split/libs/community/tests/integration_tests/utilities/test_pubmed.py

@@ -0,0 +1,164 @@
+"""Integration test for PubMed API Wrapper."""
+from typing import Any, List
+
+import pytest
+from langchain_core.documents import Document
+from langchain_core.tools import BaseTool
+
+from langchain_community.tools import PubmedQueryRun
+from langchain_community.utilities import PubMedAPIWrapper
+
+xmltodict = pytest.importorskip("xmltodict")
+
+
+@pytest.fixture
+def api_client() -> PubMedAPIWrapper:
+    return PubMedAPIWrapper()
+
+
+def test_run_success(api_client: PubMedAPIWrapper) -> None:
+    """Test that returns the correct answer"""
+
+    search_string = (
+        "Examining the Validity of ChatGPT in Identifying "
+        "Relevant Nephrology Literature"
+    )
+    output = api_client.run(search_string)
+    test_string = (
+        "Examining the Validity of ChatGPT in Identifying "
+        "Relevant Nephrology Literature: Findings and Implications"
+    )
+    assert test_string in output
+    assert len(output) == api_client.doc_content_chars_max
+
+
+def test_run_returns_no_result(api_client: PubMedAPIWrapper) -> None:
+    """Test that gives no result."""
+
+    output = api_client.run("1605.08386WWW")
+    assert "No good PubMed Result was found" == output
+
+
+def test_retrieve_article_returns_book_abstract(api_client: PubMedAPIWrapper) -> None:
+    """Test that returns the excerpt of a book."""
+
+    output_nolabel = api_client.retrieve_article("25905357", "")
+    output_withlabel = api_client.retrieve_article("29262144", "")
+    test_string_nolabel = (
+        "Osteoporosis is a multifactorial disorder associated with low bone mass and "
+        "enhanced skeletal fragility. Although"
+    )
+    assert test_string_nolabel in output_nolabel["Summary"]
+    assert (
+        "Wallenberg syndrome was first described in 1808 by Gaspard Vieusseux. However,"
+        in output_withlabel["Summary"]
+    )
+
+
+def test_retrieve_article_returns_article_abstract(
+    api_client: PubMedAPIWrapper,
+) -> None:
+    """Test that returns the abstract of an article."""
+
+    output_nolabel = api_client.retrieve_article("37666905", "")
+    output_withlabel = api_client.retrieve_article("37666551", "")
+    test_string_nolabel = (
+        "This work aims to: (1) Provide maximal hand force data on six different "
+        "grasp types for healthy subjects; (2) detect grasp types with maximal "
+        "force significantly affected by hand osteoarthritis (HOA) in women; (3) "
+        "look for predictors to detect HOA from the maximal forces using discriminant "
+        "analyses."
+    )
+    assert test_string_nolabel in output_nolabel["Summary"]
+    test_string_withlabel = (
+        "OBJECTIVES: To assess across seven hospitals from six different countries "
+        "the extent to which the COVID-19 pandemic affected the volumes of orthopaedic "
+        "hospital admissions and patient outcomes for non-COVID-19 patients admitted "
+        "for orthopaedic care."
+    )
+    assert test_string_withlabel in output_withlabel["Summary"]
+
+
+def test_retrieve_article_no_abstract_available(api_client: PubMedAPIWrapper) -> None:
+    """Test that returns 'No abstract available'."""
+
+    output = api_client.retrieve_article("10766884", "")
+    assert "No abstract available" == output["Summary"]
+
+
+def assert_docs(docs: List[Document]) -> None:
+    for doc in docs:
+        assert doc.metadata
+        assert set(doc.metadata) == {
+            "Copyright Information",
+            "uid",
+            "Title",
+            "Published",
+        }
+
+
+def test_load_success(api_client: PubMedAPIWrapper) -> None:
+    """Test that returns one document"""
+
+    docs = api_client.load_docs("chatgpt")
+    assert len(docs) == api_client.top_k_results == 3
+    assert_docs(docs)
+
+
+def test_load_returns_no_result(api_client: PubMedAPIWrapper) -> None:
+    """Test that returns no docs"""
+
+    docs = api_client.load_docs("1605.08386WWW")
+    assert len(docs) == 0
+
+
+def test_load_returns_limited_docs() -> None:
+    """Test that returns several docs"""
+    expected_docs = 2
+    api_client = PubMedAPIWrapper(top_k_results=expected_docs)
+    docs = api_client.load_docs("ChatGPT")
+    assert len(docs) == expected_docs
+    assert_docs(docs)
+
+
+def test_load_returns_full_set_of_metadata() -> None:
+    """Test that returns several docs"""
+    api_client = PubMedAPIWrapper(load_max_docs=1, load_all_available_meta=True)
+    docs = api_client.load_docs("ChatGPT")
+    assert len(docs) == 3
+    for doc in docs:
+        assert doc.metadata
+        assert set(doc.metadata).issuperset(
+            {"Copyright Information", "Published", "Title", "uid"}
+        )
+
+
+def _load_pubmed_from_universal_entry(**kwargs: Any) -> BaseTool:
+    from langchain.agents.load_tools import load_tools
+    tools = load_tools(["pubmed"], **kwargs)
+    assert len(tools) == 1, "loaded more than 1 tool"
+    return tools[0]
+
+
+def test_load_pupmed_from_universal_entry() -> None:
+    pubmed_tool = _load_pubmed_from_universal_entry()
+    search_string = (
+        "Examining the Validity of ChatGPT in Identifying "
+        "Relevant Nephrology Literature"
+    )
+    output = pubmed_tool(search_string)
+    test_string = (
+        "Examining the Validity of ChatGPT in Identifying "
+        "Relevant Nephrology Literature: Findings and Implications"
+    )
+    assert test_string in output
+
+
+def test_load_pupmed_from_universal_entry_with_params() -> None:
+    params = {
+        "top_k_results": 1,
+    }
+    pubmed_tool = _load_pubmed_from_universal_entry(**params)
+    assert isinstance(pubmed_tool, PubmedQueryRun)
+    wp = pubmed_tool.api_wrapper
+    assert wp.top_k_results == 1, "failed to assert top_k_results"

.scripts/community_split/libs/community/tests/integration_tests/vectorstores/conftest.py

@@ -0,0 +1,44 @@
+import os
+from typing import Union
+
+import pytest
+from vcr.request import Request
+
+# Those environment variables turn on Deep Lake pytest mode.
+# It significantly makes tests run much faster.
+# Need to run before `import deeplake`
+os.environ["BUGGER_OFF"] = "true"
+os.environ["DEEPLAKE_DOWNLOAD_PATH"] = "./testing/local_storage"
+os.environ["DEEPLAKE_PYTEST_ENABLED"] = "true"
+
+
+# This fixture returns a dictionary containing filter_headers options
+# for replacing certain headers with dummy values during cassette playback
+# Specifically, it replaces the authorization header with a dummy value to
+# prevent sensitive data from being recorded in the cassette.
+# It also filters request to certain hosts (specified in the `ignored_hosts` list)
+# to prevent data from being recorded in the cassette.
+@pytest.fixture(scope="module")
+def vcr_config() -> dict:
+    skipped_host = ["pinecone.io"]
+
+    def before_record_response(response: dict) -> Union[dict, None]:
+        return response
+
+    def before_record_request(request: Request) -> Union[Request, None]:
+        for host in skipped_host:
+            if request.host.startswith(host) or request.host.endswith(host):
+                return None
+        return request
+
+    return {
+        "before_record_request": before_record_request,
+        "before_record_response": before_record_response,
+        "filter_headers": [
+            ("authorization", "authorization-DUMMY"),
+            ("X-OpenAI-Client-User-Agent", "X-OpenAI-Client-User-Agent-DUMMY"),
+            ("Api-Key", "Api-Key-DUMMY"),
+            ("User-Agent", "User-Agent-DUMMY"),
+        ],
+        "ignore_localhost": True,
+    }

.scripts/community_split/libs/core/langchain_core/utils/env.py

@@ -0,0 +1,45 @@
+from __future__ import annotations
+
+import os
+from typing import Any, Dict, Optional
+
+
+def env_var_is_set(env_var: str) -> bool:
+    """Check if an environment variable is set.
+
+    Args:
+        env_var (str): The name of the environment variable.
+
+    Returns:
+        bool: True if the environment variable is set, False otherwise.
+    """
+    return env_var in os.environ and os.environ[env_var] not in (
+        "",
+        "0",
+        "false",
+        "False",
+    )
+
+
+def get_from_dict_or_env(
+    data: Dict[str, Any], key: str, env_key: str, default: Optional[str] = None
+) -> str:
+    """Get a value from a dictionary or an environment variable."""
+    if key in data and data[key]:
+        return data[key]
+    else:
+        return get_from_env(key, env_key, default=default)
+
+
+def get_from_env(key: str, env_key: str, default: Optional[str] = None) -> str:
+    """Get a value from a dictionary or an environment variable."""
+    if env_key in os.environ and os.environ[env_key]:
+        return os.environ[env_key]
+    elif default is not None:
+        return default
+    else:
+        raise ValueError(
+            f"Did not find {key}, please add an environment variable"
+            f" `{env_key}` which contains it, or pass"
+            f"  `{key}` as a named parameter."
+        )