Add Amazon Bedrock Text vectorizer

.github/workflows/run_tests.yml

@@ -66,6 +66,8 @@ jobs:
         AZURE_OPENAI_ENDPOINT: ${{secrets.AZURE_OPENAI_ENDPOINT}}
         AZURE_OPENAI_DEPLOYMENT_NAME: ${{secrets.AZURE_OPENAI_DEPLOYMENT_NAME}}
         OPENAI_API_VERSION: ${{secrets.OPENAI_API_VERSION}}
+        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
       run: |
         poetry run test-cov
 
@@ -86,6 +88,8 @@ jobs:
         AZURE_OPENAI_ENDPOINT: ${{secrets.AZURE_OPENAI_ENDPOINT}}
         AZURE_OPENAI_DEPLOYMENT_NAME: ${{secrets.AZURE_OPENAI_DEPLOYMENT_NAME}}
         OPENAI_API_VERSION: ${{secrets.OPENAI_API_VERSION}}
+        AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
+        AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
       run: |
         cd docs/ && poetry run treon -v --exclude="./examples/openai_qna.ipynb"
 

conftest.py

@@ -71,6 +71,13 @@ def gcp_location():
 def gcp_project_id():
     return os.getenv("GCP_PROJECT_ID")
 
+@pytest.fixture
+def aws_credentials():
+    return {
+        "aws_access_key_id": os.getenv("AWS_ACCESS_KEY_ID"),
+        "aws_secret_access_key": os.getenv("AWS_SECRET_ACCESS_KEY"),
+        "aws_region": os.getenv("AWS_REGION", "us-east-1")
+    }
 
 @pytest.fixture
 def sample_data():

docs/api/vectorizer.rst

@@ -61,6 +61,16 @@ CohereTextVectorizer
    :show-inheritance:
    :members:
 
+BedrockTextVectorizer
+=====================
+
+.. _bedrocktextvectorizer_api:
+
+.. currentmodule:: redisvl.utils.vectorize.text.bedrock
+
+.. autoclass:: BedrockTextVectorizer
+   :show-inheritance:
+   :members:
 
 CustomTextVectorizer
 ====================

docs/user_guide/vectorizers_04.ipynb

@@ -13,7 +13,8 @@
     "3. Vertex AI\n",
     "4. Cohere\n",
     "5. Mistral AI\n",
-    "6. Bringing your own vectorizer\n",
+    "6. Amazon Bedrock\n",
+    "7. Bringing your own vectorizer\n",
     "\n",
     "Before running this notebook, be sure to\n",
     "1. Have installed ``redisvl`` and have that environment active for this notebook.\n",
@@ -541,6 +542,76 @@
     "# print(test[:10])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Amazon Bedrock\n",
+    "\n",
+    "Amazon Bedrock provides fully managed foundation models for text embeddings. Install the required dependencies:\n",
+    "\n",
+    "```bash\n",
+    "pip install 'redisvl[bedrock]'  # Installs boto3\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Configure AWS credentials:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "if \"AWS_ACCESS_KEY_ID\" not in os.environ:\n",
+    "    os.environ[\"AWS_ACCESS_KEY_ID\"] = getpass.getpass(\"Enter AWS Access Key ID: \")\n",
+    "if \"AWS_SECRET_ACCESS_KEY\" not in os.environ:\n",
+    "    os.environ[\"AWS_SECRET_ACCESS_KEY\"] = getpass.getpass(\"Enter AWS Secret Key: \")\n",
+    "\n",
+    "os.environ[\"AWS_REGION\"] = \"us-east-1\"  # Change as needed"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Create embeddings:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from redisvl.utils.vectorize import BedrockTextVectorizer\n",
+    "\n",
+    "bedrock = BedrockTextVectorizer(\n",
+    "    model=\"amazon.titan-embed-text-v2:0\"\n",
+    ")\n",
+    "\n",
+    "# Single embedding\n",
+    "text = \"This is a test sentence.\"\n",
+    "embedding = bedrock.embed(text)\n",
+    "print(f\"Vector dimensions: {len(embedding)}\")\n",
+    "\n",
+    "# Multiple embeddings\n",
+    "sentences = [\n",
+    "    \"That is a happy dog\",\n",
+    "    \"That is a happy person\",\n",
+    "    \"Today is a sunny day\"\n",
+    "]\n",
+    "embeddings = bedrock.embed_many(sentences)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -691,7 +762,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -710,9 +781,10 @@
    "source": [
     "# load expects an iterable of dictionaries where\n",
     "# the vector is stored as a bytes buffer\n",
+    "from redisvl.redis.utils import array_to_buffer\n",
     "\n",
     "data = [{\"text\": t,\n",
-    "         \"embedding\": v}\n",
+    "         \"embedding\": array_to_buffer(v, dtype=\"float32\")}\n",
     "        for t, v in zip(sentences, embeddings)]\n",
     "\n",
     "index.load(data)"