update notebooks (#275)

docs/examples/chains/llm_bash.ipynb

@@ -24,16 +24,17 @@
       "\n",
       "```bash\n",
       "echo \"Hello World\"\n",
-      "```\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3m{'success': True, 'outputs': ['Hello World\\n']}\u001b[0m\n",
+      "```\u001b[0m['```bash', 'echo \"Hello World\"', '```']\n",
+      "\n",
+      "Answer: \u001b[33;1m\u001b[1;3mHello World\n",
+      "\u001b[0m\n",
       "\u001b[1m> Finished LLMBashChain chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "{'commands': ['echo \"Hello World\"'],\n",
-       " 'output': {'success': True, 'outputs': ['Hello World\\n']}}"
+       "'Hello World\\n'"
       ]
      },
      "execution_count": 2,
@@ -42,7 +43,7 @@
     }
    ],
    "source": [
-    "from langchain.chains.llm_bash.base import LLMBashChain\n",
+    "from langchain.chains import LLMBashChain\n",
     "from langchain.llms import OpenAI\n",
     "\n",
     "llm = OpenAI(temperature=0)\n",
@@ -78,9 +79,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.10.8"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}

docs/examples/chains/llm_requests.ipynb

@@ -115,7 +115,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.8"
   }
  },
  "nbformat": 4,

docs/examples/chains/map_reduce.ipynb

@@ -85,7 +85,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.7"
+   "version": "3.10.8"
   }
  },
  "nbformat": 4,

docs/examples/chains/transformation.ipynb

@@ -0,0 +1,130 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "872bb8b5",
+   "metadata": {},
+   "source": [
+    "# Transformation Chain\n",
+    "\n",
+    "This notebook showcases using a generic transformation chain.\n",
+    "\n",
+    "As an example, we will create a dummy transformation that takes in a super long text, filters the text to only the first 3 paragraphs, and then passes that into an LLMChain to summarize those."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "bbbb4330",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import TransformChain, LLMChain, SimpleSequentialChain\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.prompts import PromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "8ae5937c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('../state_of_the_union.txt') as f:\n",
+    "    state_of_the_union = f.read()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "98739592",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def transform_func(inputs: dict) -> dict:\n",
+    "    text = inputs[\"text\"]\n",
+    "    shortened_text = \"\\n\\n\".join(text.split(\"\\n\\n\")[:3])\n",
+    "    return {\"output_text\": shortened_text}\n",
+    "\n",
+    "transform_chain = TransformChain(input_variables=[\"text\"], output_variables=[\"output_text\"], transform=transform_func)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e9397934",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Summarize this text:\n",
+    "\n",
+    "{output_text}\n",
+    "\n",
+    "Summary:\"\"\"\n",
+    "prompt = PromptTemplate(input_variables=[\"output_text\"], template=template)\n",
+    "llm_chain = LLMChain(llm=OpenAI(), prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "06f51f17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sequential_chain = SimpleSequentialChain(chains=[transform_chain, llm_chain])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "f7caa1ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' This speech addresses the American people and acknowledges the difficulties of last year due to COVID-19. It emphasizes the importance of coming together regardless of political affiliation and encourages a sense of unity as Americans.'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sequential_chain.run(state_of_the_union)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3ca6409",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

langchain/chains/__init__.py

@@ -10,6 +10,7 @@ from langchain.chains.qa_with_sources.base import QAWithSourcesChain
 from langchain.chains.qa_with_sources.vector_db import VectorDBQAWithSourcesChain
 from langchain.chains.sequential import SequentialChain, SimpleSequentialChain
 from langchain.chains.sql_database.base import SQLDatabaseChain
+from langchain.chains.transform import TransformChain
 from langchain.chains.vector_db_qa.base import VectorDBQA
 
 __all__ = [
@@ -27,4 +28,5 @@ __all__ = [
     "VectorDBQAWithSourcesChain",
     "APIChain",
     "LLMRequestsChain",
+    "TransformChain",
 ]