ibm: Add support for Embedding Models (#20647)

--------- Co-authored-by: Erick Friis <[email protected]>
langchain-ai · Apr 19, 2024 · 75ffe51 · 75ffe51
1 parent 7380981
commit 75ffe51
Show file tree

Hide file tree

Showing 9 changed files with 804 additions and 246 deletions.
diff --git a/docs/docs/integrations/providers/ibm.mdx b/docs/docs/integrations/providers/ibm.mdx
@@ -37,3 +37,13 @@ See a [usage example](/docs/integrations/llms/ibm_watsonx).
 ```python
 from langchain_ibm import WatsonxLLM
 ```
+
+## Embedding Models
+
+### WatsonxEmbeddings
+
+See a [usage example](/docs/integrations/text_embedding/ibm_watsonx).
+
+```python
+from langchain_ibm import WatsonxEmbeddings
+```
diff --git a/docs/docs/integrations/text_embedding/ibm_watsonx.ipynb b/docs/docs/integrations/text_embedding/ibm_watsonx.ipynb
@@ -0,0 +1,243 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# IBM watsonx.ai\n",
+    "\n",
+    ">WatsonxEmbeddings is a wrapper for IBM [watsonx.ai](https://www.ibm.com/products/watsonx-ai) foundation models.\n",
+    "\n",
+    "This example shows how to communicate with `watsonx.ai` models using `LangChain`."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setting up\n",
+    "\n",
+    "Install the package `langchain-ibm`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -qU langchain-ibm"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This cell defines the WML credentials required to work with watsonx Embeddings.\n",
+    "\n",
+    "**Action:** Provide the IBM Cloud user API key. For details, see\n",
+    "[documentation](https://cloud.ibm.com/docs/account?topic=account-userapikey&interface=ui)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "watsonx_api_key = getpass()\n",
+    "os.environ[\"WATSONX_APIKEY\"] = watsonx_api_key"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Additionaly you are able to pass additional secrets as an environment variable. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"WATSONX_URL\"] = \"your service instance url\"\n",
+    "os.environ[\"WATSONX_TOKEN\"] = \"your token for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_PASSWORD\"] = \"your password for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_USERNAME\"] = \"your username for accessing the CPD cluster\"\n",
+    "os.environ[\"WATSONX_INSTANCE_ID\"] = \"your instance_id for accessing the CPD cluster\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load the model\n",
+    "\n",
+    "You might need to adjust model `parameters` for different models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from ibm_watsonx_ai.metanames import EmbedTextParamsMetaNames\n",
+    "\n",
+    "embed_params = {\n",
+    "    EmbedTextParamsMetaNames.TRUNCATE_INPUT_TOKENS: 3,\n",
+    "    EmbedTextParamsMetaNames.RETURN_OPTIONS: {\"input_text\": True},\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Initialize the `WatsonxEmbeddings` class with previously set parameters.\n",
+    "\n",
+    "\n",
+    "**Note**: \n",
+    "\n",
+    "- To provide context for the API call, you must add `project_id` or `space_id`. For more information see [documentation](https://www.ibm.com/docs/en/watsonx-as-a-service?topic=projects).\n",
+    "- Depending on the region of your provisioned service instance, use one of the urls described [here](https://ibm.github.io/watsonx-ai-python-sdk/setup_cloud.html#authentication).\n",
+    "\n",
+    "In this example, we’ll use the `project_id` and Dallas url.\n",
+    "\n",
+    "\n",
+    "You need to specify `model_id` that will be used for inferencing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_ibm import WatsonxEmbeddings\n",
+    "\n",
+    "watsonx_embedding = WatsonxEmbeddings(\n",
+    "    model_id=\"ibm/slate-125m-english-rtrvr\",\n",
+    "    url=\"https://us-south.ml.cloud.ibm.com\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=embed_params,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Alternatively you can use Cloud Pak for Data credentials. For details, see [documentation](https://ibm.github.io/watsonx-ai-python-sdk/setup_cpd.html).    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "watsonx_embedding = WatsonxEmbeddings(\n",
+    "    model_id=\"ibm/slate-125m-english-rtrvr\",\n",
+    "    url=\"PASTE YOUR URL HERE\",\n",
+    "    username=\"PASTE YOUR USERNAME HERE\",\n",
+    "    password=\"PASTE YOUR PASSWORD HERE\",\n",
+    "    instance_id=\"openshift\",\n",
+    "    version=\"5.0\",\n",
+    "    project_id=\"PASTE YOUR PROJECT_ID HERE\",\n",
+    "    params=embed_params,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
+    "\n",
+    "### Embed query"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[0.0094472, -0.024981909, -0.026013248, -0.040483925, -0.057804465]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "text = \"This is a test document.\"\n",
+    "\n",
+    "query_result = watsonx_embedding.embed_query(text)\n",
+    "query_result[:5]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Embed documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[0.009447193, -0.024981918, -0.026013244, -0.040483937, -0.057804447]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "texts = [\"This is a content of the document\", \"This is another document\"]\n",
+    "\n",
+    "doc_result = watsonx_embedding.embed_documents(texts)\n",
+    "doc_result[0][:5]"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "langchain",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/libs/partners/ibm/langchain_ibm/__init__.py b/libs/partners/ibm/langchain_ibm/__init__.py
@@ -1,3 +1,4 @@
+from langchain_ibm.embeddings import WatsonxEmbeddings
 from langchain_ibm.llms import WatsonxLLM
 
-__all__ = ["WatsonxLLM"]
+__all__ = ["WatsonxLLM", "WatsonxEmbeddings"]