Harrison/official pre release (#8106)

MIGRATE.md

@@ -1,6 +1,6 @@
 # Migrating to `langchain.experimental`
 
-We are moving any experimental components of langchain, or components with vulnerability issues, into `langchain.experimental`.
+We are moving any experimental components of langchain, or components with vulnerability issues, into `langchain_experimental`.
 This guide covers how to migrate.
 
 ## Installation
@@ -11,7 +11,7 @@ Previously:
 
 Now:
 
-`pip install -U langchain langchain.experimental`
+`pip install -U langchain langchain_experimental`
 
 ## PALChain
 
@@ -21,7 +21,7 @@ Previously:
 
 Now:
 
-`from langchain.experimental.pal_chain import PALChain`
+`from langchain_experimental.pal_chain import PALChain`
 
 ## SQLDatabaseChain
 
@@ -31,7 +31,7 @@ Previously:
 
 Now:
 
-`from langchain.experimental.sql import SQLDatabaseChain`
+`from langchain_experimental.sql import SQLDatabaseChain`
 
 ## `load_prompt` for Python files
 
@@ -44,4 +44,4 @@ Previously:
 
 Now:
 
-`from langchain.experimental.prompts import load_prompt`
+`from langchain_experimental.prompts import load_prompt`

docs/extras/modules/agents/tools/integrations/apify.ipynb

@@ -1,168 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Apify\n",
-    "\n",
-    "This notebook shows how to use the [Apify integration](/docs/ecosystem/integrations/apify.html) for LangChain.\n",
-    "\n",
-    "[Apify](https://apify.com) is a cloud platform for web scraping and data extraction,\n",
-    "which provides an [ecosystem](https://apify.com/store) of more than a thousand\n",
-    "ready-made apps called *Actors* for various web scraping, crawling, and data extraction use cases.\n",
-    "For example, you can use it to extract Google Search results, Instagram and Facebook profiles, products from Amazon or Shopify, Google Maps reviews, etc. etc.\n",
-    "\n",
-    "In this example, we'll use the [Website Content Crawler](https://apify.com/apify/website-content-crawler) Actor,\n",
-    "which can deeply crawl websites such as documentation, knowledge bases, help centers, or blogs,\n",
-    "and extract text content from the web pages. Then we feed the documents into a vector index and answer questions from it.\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "#!pip install apify-client openai langchain chromadb tiktoken"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "First, import `ApifyWrapper` into your source code:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.document_loaders.base import Document\n",
-    "from langchain.indexes import VectorstoreIndexCreator\n",
-    "from langchain.utilities import ApifyWrapper"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Initialize it using your [Apify API token](https://console.apify.com/account/integrations) and for the purpose of this example, also with your OpenAI API key:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = \"Your OpenAI API key\"\n",
-    "os.environ[\"APIFY_API_TOKEN\"] = \"Your Apify API token\"\n",
-    "\n",
-    "apify = ApifyWrapper()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Then run the Actor, wait for it to finish, and fetch its results from the Apify dataset into a LangChain document loader.\n",
-    "\n",
-    "Note that if you already have some results in an Apify dataset, you can load them directly using `ApifyDatasetLoader`, as shown in [this notebook](/docs/modules/data_connection/document_loaders/integrations/apify_dataset.html). In that notebook, you'll also find the explanation of the `dataset_mapping_function`, which is used to map fields from the Apify dataset records to LangChain `Document` fields."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = apify.call_actor(\n",
-    "    actor_id=\"apify/website-content-crawler\",\n",
-    "    run_input={\"startUrls\": [{\"url\": \"https://python.langchain.com/en/latest/\"}]},\n",
-    "    dataset_mapping_function=lambda item: Document(\n",
-    "        page_content=item[\"text\"] or \"\", metadata={\"source\": item[\"url\"]}\n",
-    "    ),\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Initialize the vector index from the crawled documents:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "index = VectorstoreIndexCreator().from_loaders([loader])"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "And finally, query the vector index:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "query = \"What is LangChain?\"\n",
-    "result = index.query_with_sources(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " LangChain is a standard interface through which you can interact with a variety of large language models (LLMs). It provides modules that can be used to build language model applications, and it also provides chains and agents with memory capabilities.\n",
-      "\n",
-      "https://python.langchain.com/en/latest/modules/models/llms.html, https://python.langchain.com/en/latest/getting_started/getting_started.html\n"
-     ]
-    }
-   ],
-   "source": [
-    "print(result[\"answer\"])\n",
-    "print(result[\"sources\"])"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

libs/experimental/langchain/__init__.py

@@ -1,19 +0,0 @@
-from langchain.experimental.autonomous_agents.autogpt.agent import AutoGPT
-from langchain.experimental.autonomous_agents.baby_agi.baby_agi import BabyAGI
-from langchain.experimental.generative_agents.generative_agent import GenerativeAgent
-from langchain.experimental.generative_agents.memory import GenerativeAgentMemory
-from langchain.experimental.plan_and_execute import (
-    PlanAndExecute,
-    load_agent_executor,
-    load_chat_planner,
-)
-
-__all__ = [
-    "BabyAGI",
-    "AutoGPT",
-    "GenerativeAgent",
-    "GenerativeAgentMemory",
-    "PlanAndExecute",
-    "load_agent_executor",
-    "load_chat_planner",
-]

libs/experimental/langchain/experimental/autonomous_agents/__init__.py

@@ -1,4 +0,0 @@
-from langchain.experimental.autonomous_agents.autogpt.agent import AutoGPT
-from langchain.experimental.autonomous_agents.baby_agi.baby_agi import BabyAGI
-
-__all__ = ["BabyAGI", "AutoGPT"]

libs/experimental/langchain/experimental/llms/__init__.py

@@ -1,6 +0,0 @@
-"""Experimental LLM wrappers."""
-
-from langchain.experimental.llms.jsonformer_decoder import JsonFormer
-from langchain.experimental.llms.rellm_decoder import RELLM
-
-__all__ = ["RELLM", "JsonFormer"]

libs/experimental/langchain/experimental/plan_and_execute/__init__.py

@@ -1,9 +0,0 @@
-from langchain.experimental.plan_and_execute.agent_executor import PlanAndExecute
-from langchain.experimental.plan_and_execute.executors.agent_executor import (
-    load_agent_executor,
-)
-from langchain.experimental.plan_and_execute.planners.chat_planner import (
-    load_chat_planner,
-)
-
-__all__ = ["PlanAndExecute", "load_agent_executor", "load_chat_planner"]

libs/experimental/langchain/experimental/prompts/__init__.py

@@ -1,3 +0,0 @@
-from langchain.experimental.prompts.load import load_prompt
-
-__all__ = ["load_prompt"]

libs/experimental/langchain_experimental/__init__.py

@@ -0,0 +1,19 @@
+from langchain_experimental.autonomous_agents.autogpt.agent import AutoGPT
+from langchain_experimental.autonomous_agents.baby_agi.baby_agi import BabyAGI
+from langchain_experimental.generative_agents.generative_agent import GenerativeAgent
+from langchain_experimental.generative_agents.memory import GenerativeAgentMemory
+from langchain_experimental.plan_and_execute import (
+    PlanAndExecute,
+    load_agent_executor,
+    load_chat_planner,
+)
+
+__all__ = [
+    "BabyAGI",
+    "AutoGPT",
+    "GenerativeAgent",
+    "GenerativeAgentMemory",
+    "PlanAndExecute",
+    "load_agent_executor",
+    "load_chat_planner",
+]

libs/experimental/langchain_experimental/autonomous_agents/__init__.py

@@ -0,0 +1,4 @@
+from langchain_experimental.autonomous_agents.autogpt.agent import AutoGPT
+from langchain_experimental.autonomous_agents.baby_agi.baby_agi import BabyAGI
+
+__all__ = ["BabyAGI", "AutoGPT"]

libs/experimental/langchain_experimental/autonomous_agents/autogpt/agent.py

@@ -2,18 +2,8 @@ from __future__ import annotations
 
 from typing import List, Optional
 
-from pydantic import ValidationError
-
 from langchain.chains.llm import LLMChain
 from langchain.chat_models.base import BaseChatModel
-from langchain.experimental.autonomous_agents.autogpt.output_parser import (
-    AutoGPTOutputParser,
-    BaseAutoGPTOutputParser,
-)
-from langchain.experimental.autonomous_agents.autogpt.prompt import AutoGPTPrompt
-from langchain.experimental.autonomous_agents.autogpt.prompt_generator import (
-    FINISH_NAME,
-)
 from langchain.memory import ChatMessageHistory
 from langchain.schema import (
     BaseChatMessageHistory,
@@ -23,6 +13,16 @@ from langchain.schema.messages import AIMessage, HumanMessage, SystemMessage
 from langchain.tools.base import BaseTool
 from langchain.tools.human.tool import HumanInputRun
 from langchain.vectorstores.base import VectorStoreRetriever
+from pydantic import ValidationError
+
+from langchain_experimental.autonomous_agents.autogpt.output_parser import (
+    AutoGPTOutputParser,
+    BaseAutoGPTOutputParser,
+)
+from langchain_experimental.autonomous_agents.autogpt.prompt import AutoGPTPrompt
+from langchain_experimental.autonomous_agents.autogpt.prompt_generator import (
+    FINISH_NAME,
+)
 
 
 class AutoGPT:

libs/experimental/langchain_experimental/autonomous_agents/autogpt/memory.py

@@ -1,9 +1,8 @@
 from typing import Any, Dict, List
 
-from pydantic import Field
-
 from langchain.memory.chat_memory import BaseChatMemory, get_prompt_input_key
 from langchain.vectorstores.base import VectorStoreRetriever
+from pydantic import Field
 
 
 class AutoGPTMemory(BaseChatMemory):

libs/experimental/langchain_experimental/autonomous_agents/autogpt/prompt.py

@@ -1,15 +1,15 @@
 import time
 from typing import Any, Callable, List
 
-from pydantic import BaseModel
-
-from langchain.experimental.autonomous_agents.autogpt.prompt_generator import get_prompt
 from langchain.prompts.chat import (
     BaseChatPromptTemplate,
 )
 from langchain.schema.messages import BaseMessage, HumanMessage, SystemMessage
 from langchain.tools.base import BaseTool
 from langchain.vectorstores.base import VectorStoreRetriever
+from pydantic import BaseModel
+
+from langchain_experimental.autonomous_agents.autogpt.prompt_generator import get_prompt
 
 
 class AutoGPTPrompt(BaseChatPromptTemplate, BaseModel):

libs/experimental/langchain_experimental/autonomous_agents/baby_agi/__init__.py

@@ -1,11 +1,11 @@
-from langchain.experimental.autonomous_agents.baby_agi.baby_agi import BabyAGI
+from langchain_experimental.autonomous_agents.baby_agi.baby_agi import BabyAGI
-from langchain.experimental.autonomous_agents.baby_agi.task_creation import (
+from langchain_experimental.autonomous_agents.baby_agi.task_creation import (
     TaskCreationChain,
 )
-from langchain.experimental.autonomous_agents.baby_agi.task_execution import (
+from langchain_experimental.autonomous_agents.baby_agi.task_execution import (
     TaskExecutionChain,
 )
-from langchain.experimental.autonomous_agents.baby_agi.task_prioritization import (
+from langchain_experimental.autonomous_agents.baby_agi.task_prioritization import (
     TaskPrioritizationChain,
 )
 

libs/experimental/langchain_experimental/autonomous_agents/baby_agi/baby_agi.py

@@ -2,21 +2,21 @@
 from collections import deque
 from typing import Any, Dict, List, Optional
 
-from pydantic import BaseModel, Field
-
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
-from langchain.experimental.autonomous_agents.baby_agi.task_creation import (
-    TaskCreationChain,
-)
-from langchain.experimental.autonomous_agents.baby_agi.task_execution import (
-    TaskExecutionChain,
-)
-from langchain.experimental.autonomous_agents.baby_agi.task_prioritization import (
-    TaskPrioritizationChain,
-)
 from langchain.schema.language_model import BaseLanguageModel
 from langchain.vectorstores.base import VectorStore
+from pydantic import BaseModel, Field
+
+from langchain_experimental.autonomous_agents.baby_agi.task_creation import (
+    TaskCreationChain,
+)
+from langchain_experimental.autonomous_agents.baby_agi.task_execution import (
+    TaskExecutionChain,
+)
+from langchain_experimental.autonomous_agents.baby_agi.task_prioritization import (
+    TaskPrioritizationChain,
+)
 
 
 class BabyAGI(Chain, BaseModel):

libs/experimental/langchain_experimental/cpal/base.py

@@ -7,33 +7,33 @@ import json
 from typing import Any, ClassVar, Dict, List, Optional, Type
 
 import pydantic
-
 from langchain.base_language import BaseLanguageModel
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain
-from langchain.experimental.cpal.constants import Constant
+from langchain.output_parsers import PydanticOutputParser
-from langchain.experimental.cpal.models import (
+from langchain.prompts.prompt import PromptTemplate
+
+from langchain_experimental.cpal.constants import Constant
+from langchain_experimental.cpal.models import (
     CausalModel,
     InterventionModel,
     NarrativeModel,
     QueryModel,
     StoryModel,
 )
-from langchain.experimental.cpal.templates.univariate.causal import (
+from langchain_experimental.cpal.templates.univariate.causal import (
     template as causal_template,
 )
-from langchain.experimental.cpal.templates.univariate.intervention import (
+from langchain_experimental.cpal.templates.univariate.intervention import (
     template as intervention_template,
 )
-from langchain.experimental.cpal.templates.univariate.narrative import (
+from langchain_experimental.cpal.templates.univariate.narrative import (
     template as narrative_template,
 )
-from langchain.experimental.cpal.templates.univariate.query import (
+from langchain_experimental.cpal.templates.univariate.query import (
     template as query_template,
 )
-from langchain.output_parsers import PydanticOutputParser
-from langchain.prompts.prompt import PromptTemplate
 
 
 class _BaseStoryElementChain(Chain):

libs/experimental/langchain_experimental/cpal/models.py

@@ -5,10 +5,10 @@ from typing import Any, Optional, Union
 
 import duckdb
 import pandas as pd
+from langchain.graphs.networkx_graph import NetworkxEntityGraph
 from pydantic import BaseModel, Field, PrivateAttr, root_validator, validator
 
-from langchain.experimental.cpal.constants import Constant
+from langchain_experimental.cpal.constants import Constant
-from langchain.graphs.networkx_graph import NetworkxEntityGraph
 
 
 class NarrativeModel(BaseModel):

libs/experimental/langchain_experimental/generative_agents/__init__.py

@@ -1,5 +1,5 @@
 """Generative Agents primitives."""
-from langchain.experimental.generative_agents.generative_agent import GenerativeAgent
+from langchain_experimental.generative_agents.generative_agent import GenerativeAgent
-from langchain.experimental.generative_agents.memory import GenerativeAgentMemory
+from langchain_experimental.generative_agents.memory import GenerativeAgentMemory
 
 __all__ = ["GenerativeAgent", "GenerativeAgentMemory"]

libs/experimental/langchain_experimental/generative_agents/generative_agent.py

@@ -2,12 +2,12 @@ import re
 from datetime import datetime
 from typing import Any, Dict, List, Optional, Tuple
 
-from pydantic import BaseModel, Field
-
 from langchain.chains import LLMChain
-from langchain.experimental.generative_agents.memory import GenerativeAgentMemory
 from langchain.prompts import PromptTemplate
 from langchain.schema.language_model import BaseLanguageModel
+from pydantic import BaseModel, Field
+
+from langchain_experimental.generative_agents.memory import GenerativeAgentMemory
 
 
 class GenerativeAgent(BaseModel):

libs/experimental/langchain_experimental/llms/__init__.py

@@ -0,0 +1,6 @@
+"""Experimental LLM wrappers."""
+
+from langchain_experimental.llms.jsonformer_decoder import JsonFormer
+from langchain_experimental.llms.rellm_decoder import RELLM
+
+__all__ = ["RELLM", "JsonFormer"]

libs/experimental/langchain_experimental/llms/jsonformer_decoder.py

@@ -4,10 +4,9 @@ from __future__ import annotations
 import json
 from typing import TYPE_CHECKING, Any, List, Optional, cast
 
-from pydantic import Field, root_validator
-
 from langchain.callbacks.manager import CallbackManagerForLLMRun
 from langchain.llms.huggingface_pipeline import HuggingFacePipeline
+from pydantic import Field, root_validator
 
 if TYPE_CHECKING:
     import jsonformer

libs/experimental/langchain_experimental/llms/rellm_decoder.py

@@ -3,11 +3,10 @@ from __future__ import annotations
 
 from typing import TYPE_CHECKING, Any, List, Optional, cast
 
-from pydantic import Field, root_validator
-
 from langchain.callbacks.manager import CallbackManagerForLLMRun
 from langchain.llms.huggingface_pipeline import HuggingFacePipeline
 from langchain.llms.utils import enforce_stop_tokens
+from pydantic import Field, root_validator
 
 if TYPE_CHECKING:
     import rellm

libs/experimental/langchain_experimental/pal_chain/__init__.py

@@ -5,6 +5,6 @@ As in https://arxiv.org/pdf/2211.10435.pdf.
 This is vulnerable to arbitrary code execution:
 https://github.com/hwchase17/langchain/issues/5872
 """
-from langchain.experimental.pal_chain.base import PALChain
+from langchain_experimental.pal_chain.base import PALChain
 
 __all__ = ["PALChain"]

libs/experimental/langchain_experimental/pal_chain/base.py

@@ -11,16 +11,16 @@ import ast
 import warnings
 from typing import Any, Dict, List, Optional
 
-from pydantic import Extra, Field, root_validator
-
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain
-from langchain.chains.pal.colored_object_prompt import COLORED_OBJECT_PROMPT
-from langchain.chains.pal.math_prompt import MATH_PROMPT
 from langchain.schema import BasePromptTemplate
 from langchain.schema.language_model import BaseLanguageModel
 from langchain.utilities import PythonREPL
+from pydantic import Extra, Field, root_validator
+
+from langchain_experimental.pal_chain.colored_object_prompt import COLORED_OBJECT_PROMPT
+from langchain_experimental.pal_chain.math_prompt import MATH_PROMPT
 
 COMMAND_EXECUTION_FUNCTIONS = ["system", "exec", "execfile", "eval"]
 

libs/experimental/langchain_experimental/plan_and_execute/__init__.py

@@ -0,0 +1,9 @@
+from langchain_experimental.plan_and_execute.agent_executor import PlanAndExecute
+from langchain_experimental.plan_and_execute.executors.agent_executor import (
+    load_agent_executor,
+)
+from langchain_experimental.plan_and_execute.planners.chat_planner import (
+    load_chat_planner,
+)
+
+__all__ = ["PlanAndExecute", "load_agent_executor", "load_chat_planner"]

libs/experimental/langchain_experimental/plan_and_execute/agent_executor.py

@@ -1,12 +1,12 @@
 from typing import Any, Dict, List, Optional
 
-from pydantic import Field
-
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
-from langchain.experimental.plan_and_execute.executors.base import BaseExecutor
+from pydantic import Field
-from langchain.experimental.plan_and_execute.planners.base import BasePlanner
+
-from langchain.experimental.plan_and_execute.schema import (
+from langchain_experimental.plan_and_execute.executors.base import BaseExecutor
+from langchain_experimental.plan_and_execute.planners.base import BasePlanner
+from langchain_experimental.plan_and_execute.schema import (
     BaseStepContainer,
     ListStepContainer,
 )

libs/experimental/langchain_experimental/plan_and_execute/executors/agent_executor.py

@@ -2,10 +2,11 @@ from typing import List
 
 from langchain.agents.agent import AgentExecutor
 from langchain.agents.structured_chat.base import StructuredChatAgent
-from langchain.experimental.plan_and_execute.executors.base import ChainExecutor
 from langchain.schema.language_model import BaseLanguageModel
 from langchain.tools import BaseTool
 
+from langchain_experimental.plan_and_execute.executors.base import ChainExecutor
+
 HUMAN_MESSAGE_TEMPLATE = """Previous steps: {previous_steps}
 
 Current objective: {current_step}

libs/experimental/langchain_experimental/plan_and_execute/executors/base.py

@@ -1,11 +1,11 @@
 from abc import abstractmethod
 from typing import Any
 
-from pydantic import BaseModel
-
 from langchain.callbacks.manager import Callbacks
 from langchain.chains.base import Chain
-from langchain.experimental.plan_and_execute.schema import StepResponse
+from pydantic import BaseModel
+
+from langchain_experimental.plan_and_execute.schema import StepResponse
 
 
 class BaseExecutor(BaseModel):

libs/experimental/langchain_experimental/plan_and_execute/planners/base.py

@@ -1,11 +1,11 @@
 from abc import abstractmethod
 from typing import Any, List, Optional
 
-from pydantic import BaseModel
-
 from langchain.callbacks.manager import Callbacks
 from langchain.chains.llm import LLMChain
-from langchain.experimental.plan_and_execute.schema import Plan, PlanOutputParser
+from pydantic import BaseModel
+
+from langchain_experimental.plan_and_execute.schema import Plan, PlanOutputParser
 
 
 class BasePlanner(BaseModel):

libs/experimental/langchain_experimental/plan_and_execute/planners/chat_planner.py

@@ -1,15 +1,16 @@
 import re
 
 from langchain.chains import LLMChain
-from langchain.experimental.plan_and_execute.planners.base import LLMPlanner
+from langchain.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
-from langchain.experimental.plan_and_execute.schema import (
+from langchain.schema.language_model import BaseLanguageModel
+from langchain.schema.messages import SystemMessage
+
+from langchain_experimental.plan_and_execute.planners.base import LLMPlanner
+from langchain_experimental.plan_and_execute.schema import (
     Plan,
     PlanOutputParser,
     Step,
 )
-from langchain.prompts import ChatPromptTemplate, HumanMessagePromptTemplate
-from langchain.schema.language_model import BaseLanguageModel
-from langchain.schema.messages import SystemMessage
 
 SYSTEM_PROMPT = (
     "Let's first understand the problem and devise a plan to solve the problem."

libs/experimental/langchain_experimental/plan_and_execute/schema.py

@@ -1,9 +1,8 @@
 from abc import abstractmethod
 from typing import List, Tuple
 
-from pydantic import BaseModel, Field
-
 from langchain.schema import BaseOutputParser
+from pydantic import BaseModel, Field
 
 
 class Step(BaseModel):

libs/experimental/langchain_experimental/prompts/__init__.py

@@ -0,0 +1,3 @@
+from langchain_experimental.prompts.load import load_prompt
+
+__all__ = ["load_prompt"]

libs/experimental/langchain_experimental/prompts/load.py

@@ -5,7 +5,6 @@ from pathlib import Path
 from typing import Union
 
 import yaml
-
 from langchain.prompts.loading import load_prompt_from_config, try_load_from_hub
 from langchain.schema.prompts import BasePromptTemplate
 

libs/experimental/langchain_experimental/sql/__init__.py

@@ -1,4 +1,4 @@
 """Chain for interacting with SQL Database."""
-from langchain.experimental.sql.base import SQLDatabaseChain
+from langchain_experimental.sql.base import SQLDatabaseChain
 
 __all__ = ["SQLDatabaseChain"]

libs/experimental/langchain_experimental/sql/base.py

@@ -4,17 +4,17 @@ from __future__ import annotations
 import warnings
 from typing import Any, Dict, List, Optional
 
-from pydantic import Extra, Field, root_validator
-
 from langchain.callbacks.manager import CallbackManagerForChainRun
 from langchain.chains.base import Chain
 from langchain.chains.llm import LLMChain
-from langchain.chains.sql_database.prompt import DECIDER_PROMPT, PROMPT, SQL_PROMPTS
 from langchain.prompts.prompt import PromptTemplate
 from langchain.schema import BasePromptTemplate
 from langchain.schema.language_model import BaseLanguageModel
 from langchain.tools.sql_database.prompt import QUERY_CHECKER
 from langchain.utilities.sql_database import SQLDatabase
+from pydantic import Extra, Field, root_validator
+
+from langchain_experimental.sql.prompt import DECIDER_PROMPT, PROMPT, SQL_PROMPTS
 
 INTERMEDIATE_STEPS_KEY = "intermediate_steps"
 
@@ -25,7 +25,7 @@ class SQLDatabaseChain(Chain):
     Example:
         .. code-block:: python
 
-            from langchain.experimental.sql import SQLDatabaseChain
+            from langchain_experimental.sql import SQLDatabaseChain
             from langchain import OpenAI, SQLDatabase
             db = SQLDatabase(...)
             db_chain = SQLDatabaseChain.from_llm(OpenAI(), db)

libs/experimental/pyproject.toml

@@ -1,14 +1,11 @@
 [tool.poetry]
 name = "langchain-experimental"
-version = "0.0.1rc0"
+version = "0.0.1rc4"
 description = "Building applications with LLMs through composability"
 authors = []
 license = "MIT"
 readme = "README.md"
 repository = "https://www.github.com/hwchase17/langchain"
-packages = [
-    {include = "langchain"}
-]
 
 
 [tool.poetry.dependencies]

libs/langchain/langchain/agents/agent_toolkits/github/toolkit.py

@@ -1,8 +1,17 @@
 """GitHub Toolkit."""
-from typing import List
+from typing import Dict, List
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools import BaseTool
+from langchain.tools.github.prompt import (
+    COMMENT_ON_ISSUE_PROMPT,
+    CREATE_FILE_PROMPT,
+    DELETE_FILE_PROMPT,
+    GET_ISSUE_PROMPT,
+    GET_ISSUES_PROMPT,
+    READ_FILE_PROMPT,
+    UPDATE_FILE_PROMPT,
+)
 from langchain.tools.github.tool import GitHubAction
 from langchain.utilities.github import GitHubAPIWrapper
 
@@ -16,7 +25,43 @@ class GitHubToolkit(BaseToolkit):
     def from_github_api_wrapper(
         cls, github_api_wrapper: GitHubAPIWrapper
     ) -> "GitHubToolkit":
-        actions = github_api_wrapper.list()
+        operations: List[Dict] = [
+            {
+                "mode": "get_issues",
+                "name": "Get Issues",
+                "description": GET_ISSUES_PROMPT,
+            },
+            {
+                "mode": "get_issue",
+                "name": "Get Issue",
+                "description": GET_ISSUE_PROMPT,
+            },
+            {
+                "mode": "comment_on_issue",
+                "name": "Comment on Issue",
+                "description": COMMENT_ON_ISSUE_PROMPT,
+            },
+            {
+                "mode": "create_file",
+                "name": "Create File",
+                "description": CREATE_FILE_PROMPT,
+            },
+            {
+                "mode": "read_file",
+                "name": "Read File",
+                "description": READ_FILE_PROMPT,
+            },
+            {
+                "mode": "update_file",
+                "name": "Update File",
+                "description": UPDATE_FILE_PROMPT,
+            },
+            {
+                "mode": "delete_file",
+                "name": "Delete File",
+                "description": DELETE_FILE_PROMPT,
+            },
+        ]
         tools = [
             GitHubAction(
                 name=action["name"],
@@ -24,7 +69,7 @@ class GitHubToolkit(BaseToolkit):
                 mode=action["mode"],
                 api_wrapper=github_api_wrapper,
             )
-            for action in actions
+            for action in operations
         ]
         return cls(tools=tools)
 

libs/langchain/langchain/agents/agent_toolkits/jira/toolkit.py

@@ -1,7 +1,14 @@
-from typing import List
+from typing import Dict, List
 
 from langchain.agents.agent_toolkits.base import BaseToolkit
 from langchain.tools import BaseTool
+from langchain.tools.jira.prompt import (
+    JIRA_CATCH_ALL_PROMPT,
+    JIRA_CONFLUENCE_PAGE_CREATE_PROMPT,
+    JIRA_GET_ALL_PROJECTS_PROMPT,
+    JIRA_ISSUE_CREATE_PROMPT,
+    JIRA_JQL_PROMPT,
+)
 from langchain.tools.jira.tool import JiraAction
 from langchain.utilities.jira import JiraAPIWrapper
 
@@ -13,7 +20,33 @@ class JiraToolkit(BaseToolkit):
 
     @classmethod
     def from_jira_api_wrapper(cls, jira_api_wrapper: JiraAPIWrapper) -> "JiraToolkit":
-        actions = jira_api_wrapper.list()
+        operations: List[Dict] = [
+            {
+                "mode": "jql",
+                "name": "JQL Query",
+                "description": JIRA_JQL_PROMPT,
+            },
+            {
+                "mode": "get_projects",
+                "name": "Get Projects",
+                "description": JIRA_GET_ALL_PROJECTS_PROMPT,
+            },
+            {
+                "mode": "create_issue",
+                "name": "Create Issue",
+                "description": JIRA_ISSUE_CREATE_PROMPT,
+            },
+            {
+                "mode": "other",
+                "name": "Catch all Jira API call",
+                "description": JIRA_CATCH_ALL_PROMPT,
+            },
+            {
+                "mode": "create_page",
+                "name": "Create confluence page",
+                "description": JIRA_CONFLUENCE_PAGE_CREATE_PROMPT,
+            },
+        ]
         tools = [
             JiraAction(
                 name=action["name"],
@@ -21,7 +54,7 @@ class JiraToolkit(BaseToolkit):
                 mode=action["mode"],
                 api_wrapper=jira_api_wrapper,
             )
-            for action in actions
+            for action in operations
         ]
         return cls(tools=tools)
 

libs/langchain/langchain/utilities/__init__.py

@@ -1,6 +1,5 @@
 """General utilities."""
 from langchain.requests import TextRequestsWrapper
-from langchain.utilities.apify import ApifyWrapper
 from langchain.utilities.arxiv import ArxivAPIWrapper
 from langchain.utilities.awslambda import LambdaWrapper
 from langchain.utilities.bash import BashProcess
@@ -32,7 +31,6 @@ from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
 from langchain.utilities.zapier import ZapierNLAWrapper
 
 __all__ = [
-    "ApifyWrapper",
     "ArxivAPIWrapper",
     "GoldenQueryAPIWrapper",
     "BashProcess",

libs/langchain/langchain/utilities/apify.py

@@ -1,205 +0,0 @@
-from typing import Any, Callable, Dict, Optional
-
-from pydantic import BaseModel, root_validator
-
-from langchain.document_loaders import ApifyDatasetLoader
-from langchain.document_loaders.base import Document
-from langchain.utils import get_from_dict_or_env
-
-
-class ApifyWrapper(BaseModel):
-    """Wrapper around Apify.
-
-    To use, you should have the ``apify-client`` python package installed,
-    and the environment variable ``APIFY_API_TOKEN`` set with your API key, or pass
-    `apify_api_token` as a named parameter to the constructor.
-    """
-
-    apify_client: Any
-    apify_client_async: Any
-
-    @root_validator()
-    def validate_environment(cls, values: Dict) -> Dict:
-        """Validate environment.
-
-        Validate that an Apify API token is set and the apify-client
-        Python package exists in the current environment.
-        """
-        apify_api_token = get_from_dict_or_env(
-            values, "apify_api_token", "APIFY_API_TOKEN"
-        )
-
-        try:
-            from apify_client import ApifyClient, ApifyClientAsync
-
-            values["apify_client"] = ApifyClient(apify_api_token)
-            values["apify_client_async"] = ApifyClientAsync(apify_api_token)
-        except ImportError:
-            raise ValueError(
-                "Could not import apify-client Python package. "
-                "Please install it with `pip install apify-client`."
-            )
-
-        return values
-
-    def call_actor(
-        self,
-        actor_id: str,
-        run_input: Dict,
-        dataset_mapping_function: Callable[[Dict], Document],
-        *,
-        build: Optional[str] = None,
-        memory_mbytes: Optional[int] = None,
-        timeout_secs: Optional[int] = None,
-    ) -> ApifyDatasetLoader:
-        """Run an Actor on the Apify platform and wait for results to be ready.
-
-        Args:
-            actor_id (str): The ID or name of the Actor on the Apify platform.
-            run_input (Dict): The input object of the Actor that you're trying to run.
-            dataset_mapping_function (Callable): A function that takes a single
-                dictionary (an Apify dataset item) and converts it to an
-                instance of the Document class.
-            build (str, optional): Optionally specifies the actor build to run.
-                It can be either a build tag or build number.
-            memory_mbytes (int, optional): Optional memory limit for the run,
-                in megabytes.
-            timeout_secs (int, optional): Optional timeout for the run, in seconds.
-
-        Returns:
-            ApifyDatasetLoader: A loader that will fetch the records from the
-                Actor run's default dataset.
-        """
-        actor_call = self.apify_client.actor(actor_id).call(
-            run_input=run_input,
-            build=build,
-            memory_mbytes=memory_mbytes,
-            timeout_secs=timeout_secs,
-        )
-
-        return ApifyDatasetLoader(
-            dataset_id=actor_call["defaultDatasetId"],
-            dataset_mapping_function=dataset_mapping_function,
-        )
-
-    async def acall_actor(
-        self,
-        actor_id: str,
-        run_input: Dict,
-        dataset_mapping_function: Callable[[Dict], Document],
-        *,
-        build: Optional[str] = None,
-        memory_mbytes: Optional[int] = None,
-        timeout_secs: Optional[int] = None,
-    ) -> ApifyDatasetLoader:
-        """Run an Actor on the Apify platform and wait for results to be ready.
-
-        Args:
-            actor_id (str): The ID or name of the Actor on the Apify platform.
-            run_input (Dict): The input object of the Actor that you're trying to run.
-            dataset_mapping_function (Callable): A function that takes a single
-                dictionary (an Apify dataset item) and converts it to
-                an instance of the Document class.
-            build (str, optional): Optionally specifies the actor build to run.
-                It can be either a build tag or build number.
-            memory_mbytes (int, optional): Optional memory limit for the run,
-                in megabytes.
-            timeout_secs (int, optional): Optional timeout for the run, in seconds.
-
-        Returns:
-            ApifyDatasetLoader: A loader that will fetch the records from the
-                Actor run's default dataset.
-        """
-        actor_call = await self.apify_client_async.actor(actor_id).call(
-            run_input=run_input,
-            build=build,
-            memory_mbytes=memory_mbytes,
-            timeout_secs=timeout_secs,
-        )
-
-        return ApifyDatasetLoader(
-            dataset_id=actor_call["defaultDatasetId"],
-            dataset_mapping_function=dataset_mapping_function,
-        )
-
-    def call_actor_task(
-        self,
-        task_id: str,
-        task_input: Dict,
-        dataset_mapping_function: Callable[[Dict], Document],
-        *,
-        build: Optional[str] = None,
-        memory_mbytes: Optional[int] = None,
-        timeout_secs: Optional[int] = None,
-    ) -> ApifyDatasetLoader:
-        """Run a saved Actor task on Apify and wait for results to be ready.
-
-        Args:
-            task_id (str): The ID or name of the task on the Apify platform.
-            task_input (Dict): The input object of the task that you're trying to run.
-                Overrides the task's saved input.
-            dataset_mapping_function (Callable): A function that takes a single
-                dictionary (an Apify dataset item) and converts it to an
-                instance of the Document class.
-            build (str, optional): Optionally specifies the actor build to run.
-                It can be either a build tag or build number.
-            memory_mbytes (int, optional): Optional memory limit for the run,
-                in megabytes.
-            timeout_secs (int, optional): Optional timeout for the run, in seconds.
-
-        Returns:
-            ApifyDatasetLoader: A loader that will fetch the records from the
-                task run's default dataset.
-        """
-        task_call = self.apify_client.task(task_id).call(
-            task_input=task_input,
-            build=build,
-            memory_mbytes=memory_mbytes,
-            timeout_secs=timeout_secs,
-        )
-
-        return ApifyDatasetLoader(
-            dataset_id=task_call["defaultDatasetId"],
-            dataset_mapping_function=dataset_mapping_function,
-        )
-
-    async def acall_actor_task(
-        self,
-        task_id: str,
-        task_input: Dict,
-        dataset_mapping_function: Callable[[Dict], Document],
-        *,
-        build: Optional[str] = None,
-        memory_mbytes: Optional[int] = None,
-        timeout_secs: Optional[int] = None,
-    ) -> ApifyDatasetLoader:
-        """Run a saved Actor task on Apify and wait for results to be ready.
-
-        Args:
-            task_id (str): The ID or name of the task on the Apify platform.
-            task_input (Dict): The input object of the task that you're trying to run.
-                Overrides the task's saved input.
-            dataset_mapping_function (Callable): A function that takes a single
-                dictionary (an Apify dataset item) and converts it to an
-                instance of the Document class.
-            build (str, optional): Optionally specifies the actor build to run.
-                It can be either a build tag or build number.
-            memory_mbytes (int, optional): Optional memory limit for the run,
-                in megabytes.
-            timeout_secs (int, optional): Optional timeout for the run, in seconds.
-
-        Returns:
-            ApifyDatasetLoader: A loader that will fetch the records from the
-                task run's default dataset.
-        """
-        task_call = await self.apify_client_async.task(task_id).call(
-            task_input=task_input,
-            build=build,
-            memory_mbytes=memory_mbytes,
-            timeout_secs=timeout_secs,
-        )
-
-        return ApifyDatasetLoader(
-            dataset_id=task_call["defaultDatasetId"],
-            dataset_mapping_function=dataset_mapping_function,
-        )

libs/langchain/langchain/utilities/github.py

@@ -4,15 +4,6 @@ from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Extra, root_validator
 
-from langchain.tools.github.prompt import (
-    COMMENT_ON_ISSUE_PROMPT,
-    CREATE_FILE_PROMPT,
-    DELETE_FILE_PROMPT,
-    GET_ISSUE_PROMPT,
-    GET_ISSUES_PROMPT,
-    READ_FILE_PROMPT,
-    UPDATE_FILE_PROMPT,
-)
 from langchain.utils import get_from_dict_or_env
 
 
@@ -26,52 +17,11 @@ class GitHubAPIWrapper(BaseModel):
     github_app_private_key: Optional[str] = None
     github_branch: Optional[str] = None
 
-    operations: List[Dict] = [
-        {
-            "mode": "get_issues",
-            "name": "Get Issues",
-            "description": GET_ISSUES_PROMPT,
-        },
-        {
-            "mode": "get_issue",
-            "name": "Get Issue",
-            "description": GET_ISSUE_PROMPT,
-        },
-        {
-            "mode": "comment_on_issue",
-            "name": "Comment on Issue",
-            "description": COMMENT_ON_ISSUE_PROMPT,
-        },
-        {
-            "mode": "create_file",
-            "name": "Create File",
-            "description": CREATE_FILE_PROMPT,
-        },
-        {
-            "mode": "read_file",
-            "name": "Read File",
-            "description": READ_FILE_PROMPT,
-        },
-        {
-            "mode": "update_file",
-            "name": "Update File",
-            "description": UPDATE_FILE_PROMPT,
-        },
-        {
-            "mode": "delete_file",
-            "name": "Delete File",
-            "description": DELETE_FILE_PROMPT,
-        },
-    ]
-
     class Config:
         """Configuration for this pydantic object."""
 
         extra = Extra.forbid
 
-    def list(self) -> List[Dict]:
-        return self.operations
-
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""

libs/langchain/langchain/utilities/jira.py

@@ -3,13 +3,6 @@ from typing import Any, Dict, List, Optional
 
 from pydantic import BaseModel, Extra, root_validator
 
-from langchain.tools.jira.prompt import (
-    JIRA_CATCH_ALL_PROMPT,
-    JIRA_CONFLUENCE_PAGE_CREATE_PROMPT,
-    JIRA_GET_ALL_PROJECTS_PROMPT,
-    JIRA_ISSUE_CREATE_PROMPT,
-    JIRA_JQL_PROMPT,
-)
 from langchain.utils import get_from_dict_or_env
 
 
@@ -23,42 +16,11 @@ class JiraAPIWrapper(BaseModel):
     jira_api_token: Optional[str] = None
     jira_instance_url: Optional[str] = None
 
-    operations: List[Dict] = [
-        {
-            "mode": "jql",
-            "name": "JQL Query",
-            "description": JIRA_JQL_PROMPT,
-        },
-        {
-            "mode": "get_projects",
-            "name": "Get Projects",
-            "description": JIRA_GET_ALL_PROJECTS_PROMPT,
-        },
-        {
-            "mode": "create_issue",
-            "name": "Create Issue",
-            "description": JIRA_ISSUE_CREATE_PROMPT,
-        },
-        {
-            "mode": "other",
-            "name": "Catch all Jira API call",
-            "description": JIRA_CATCH_ALL_PROMPT,
-        },
-        {
-            "mode": "create_page",
-            "name": "Create confluence page",
-            "description": JIRA_CONFLUENCE_PAGE_CREATE_PROMPT,
-        },
-    ]
-
     class Config:
         """Configuration for this pydantic object."""
 
         extra = Extra.forbid
 
-    def list(self) -> List[Dict]:
-        return self.operations
-
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""

libs/langchain/langchain/utilities/openweathermap.py

@@ -1,9 +1,8 @@
 """Util that calls OpenWeatherMap using PyOWM."""
 from typing import Any, Dict, Optional
 
-from pydantic import Extra, root_validator
+from pydantic import BaseModel, Extra, root_validator
 
-from langchain.tools.base import BaseModel
 from langchain.utils import get_from_dict_or_env
 
 

libs/langchain/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain"
-version = "0.0.240rc0"
+version = "0.0.240rc4"
 description = "Building applications with LLMs through composability"
 authors = []
 license = "MIT"