community: fixed critical bugs at Writer provider (#27879)

langchain-ai · Nov 25, 2024 · c60695a · c60695a
1 parent 6ed2d38
commit c60695a
Show file tree

Hide file tree

Showing 8 changed files with 1,170 additions and 507 deletions.
diff --git a/docs/docs/integrations/chat/writer.ipynb b/docs/docs/integrations/chat/writer.ipynb
diff --git a/docs/docs/integrations/llms/writer.ipynb b/docs/docs/integrations/llms/writer.ipynb
@@ -4,120 +4,161 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Writer\n",
+    "# Writer LLM\n",
     "\n",
     "[Writer](https://writer.com/) is a platform to generate different language content.\n",
     "\n",
     "This example goes over how to use LangChain to interact with `Writer` [models](https://dev.writer.com/docs/models).\n",
     "\n",
-    "You have to get the WRITER_API_KEY [here](https://dev.writer.com/docs)."
+    "## Setup\n",
+    "\n",
+    "To access Writer models you'll need to create a Writer account, get an API key, and install the `writer-sdk` and `langchain-community` packages.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Head to [Writer AI Studio](https://app.writer.com/aistudio/signup?utm_campaign=devrel) to sign up to OpenAI and generate an API key. Once you've done this set the WRITER_API_KEY environment variable:"
    ]
   },
   {
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-11-14T11:10:46.824961Z",
+     "start_time": "2024-11-14T11:10:44.864137Z"
+    }
+   },
    "cell_type": "code",
-   "execution_count": 4,
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.environ.get(\"WRITER_API_KEY\"):\n",
+    "    os.environ[\"WRITER_API_KEY\"] = getpass.getpass(\"Enter your Writer API key:\")"
+   ],
+   "outputs": [],
+   "execution_count": 1
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": [
+    "## Installation\n",
+    "\n",
+    "The LangChain Writer integration lives in the `langchain-community` package:"
+   ]
+  },
+  {
    "metadata": {
-    "tags": []
+    "ExecuteTime": {
+     "end_time": "2024-11-14T11:10:48.297429Z",
+     "start_time": "2024-11-14T11:10:46.843983Z"
+    }
    },
+   "cell_type": "code",
+   "source": "%pip install -qU langchain-community writer-sdk",
    "outputs": [
     {
-     "name": "stdin",
+     "name": "stdout",
      "output_type": "stream",
      "text": [
-      " ········\n"
+      "\r\n",
+      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m A new release of pip is available: \u001B[0m\u001B[31;49m24.2\u001B[0m\u001B[39;49m -> \u001B[0m\u001B[32;49m24.3.1\u001B[0m\r\n",
+      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m To update, run: \u001B[0m\u001B[32;49mpip install --upgrade pip\u001B[0m\r\n",
+      "Note: you may need to restart the kernel to use updated packages.\n"
      ]
     }
    ],
-   "source": [
-    "from getpass import getpass\n",
-    "\n",
-    "WRITER_API_KEY = getpass()"
-   ]
+   "execution_count": 2
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "Now we can initialize our model object to interact with writer LLMs"
   },
   {
-   "cell_type": "code",
-   "execution_count": 5,
    "metadata": {
-    "tags": []
+    "ExecuteTime": {
+     "end_time": "2024-11-14T11:10:49.818902Z",
+     "start_time": "2024-11-14T11:10:48.580516Z"
+    }
    },
-   "outputs": [],
+   "cell_type": "code",
    "source": [
-    "import os\n",
+    "from langchain_community.llms import Writer as WriterLLM\n",
     "\n",
-    "os.environ[\"WRITER_API_KEY\"] = WRITER_API_KEY"
-   ]
+    "llm = WriterLLM(\n",
+    "    temperature=0.7,\n",
+    "    max_tokens=1000,\n",
+    "    # other params...\n",
+    ")"
+   ],
+   "outputs": [],
+   "execution_count": 3
   },
   {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.chains import LLMChain\n",
-    "from langchain_community.llms import Writer\n",
-    "from langchain_core.prompts import PromptTemplate"
-   ]
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## Invocation"
   },
   {
-   "cell_type": "code",
-   "execution_count": 7,
    "metadata": {
-    "tags": []
+    "jupyter": {
+     "is_executing": true
+    },
+    "ExecuteTime": {
+     "start_time": "2024-11-14T11:10:49.832822Z"
+    }
    },
+   "cell_type": "code",
+   "source": "response_text = llm.invoke(input=\"Write a poem\")",
    "outputs": [],
-   "source": [
-    "template = \"\"\"Question: {question}\n",
-    "\n",
-    "Answer: Let's think step by step.\"\"\"\n",
-    "\n",
-    "prompt = PromptTemplate.from_template(template)"
-   ]
+   "execution_count": null
   },
   {
+   "metadata": {},
    "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {
-    "tags": []
-   },
+   "source": "print(response_text)",
    "outputs": [],
-   "source": [
-    "# If you get an error, probably, you need to set up the \"base_url\" parameter that can be taken from the error log.\n",
-    "\n",
-    "llm = Writer()"
-   ]
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
+   "source": "## Streaming"
   },
   {
+   "metadata": {},
    "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {
-    "tags": []
-   },
+   "source": "stream_response = llm.stream(input=\"Tell me a fairytale\")",
    "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
-   ]
+   "execution_count": null
   },
   {
+   "metadata": {},
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "tags": []
-   },
+   "source": [
+    "for chunk in stream_response:\n",
+    "    print(chunk, end=\"\")"
+   ],
    "outputs": [],
+   "execution_count": null
+  },
+  {
+   "metadata": {},
+   "cell_type": "markdown",
    "source": [
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
+    "## Async\n",
     "\n",
-    "llm_chain.run(question)"
+    "Writer support asynchronous calls via **ainvoke()** and **astream()** methods"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "cell_type": "markdown",
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all Writer features, head to our [API reference](https://dev.writer.com/api-guides/api-reference/completion-api/text-generation#text-generation)."
+   ]
   }
  ],
  "metadata": {