diff --git a/docs/modules/indexes/retrievers/examples/weaviate-hybrid.ipynb b/docs/modules/indexes/retrievers/examples/weaviate-hybrid.ipynb index fc6ef679..f790dd7b 100644 --- a/docs/modules/indexes/retrievers/examples/weaviate-hybrid.ipynb +++ b/docs/modules/indexes/retrievers/examples/weaviate-hybrid.ipynb @@ -16,9 +16,18 @@ "This notebook shows how to use `Weaviate hybrid search` as a LangChain retriever." ] }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "c307b082", + "metadata": {}, + "source": [ + "Set up the retriever:" + ] + }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "bba863a2-977c-4add-b5f4-bfc33a80eae5", "metadata": { "tags": [] @@ -30,7 +39,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "id": "c10dd962", "metadata": {}, "outputs": [], @@ -38,18 +47,33 @@ "import weaviate\n", "import os\n", "\n", - "WEAVIATE_URL = \"...\"\n", + "WEAVIATE_URL = os.getenv(\"WEAVIATE_URL\")\n", "client = weaviate.Client(\n", " url=WEAVIATE_URL,\n", - ")" + " auth_client_secret=weaviate.AuthApiKey(api_key=os.getenv(\"WEAVIATE_API_KEY\")),\n", + " additional_headers={\n", + " \"X-Openai-Api-Key\": os.getenv(\"OPENAI_API_KEY\"),\n", + " },\n", + ")\n", + "\n", + "# client.schema.delete_all()" ] }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 3, "id": "f47a2bfe", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/workspaces/langchain/langchain/vectorstores/analyticdb.py:20: MovedIn20Warning: The ``declarative_base()`` function is now available as sqlalchemy.orm.declarative_base(). (deprecated since: 2.0) (Background on SQLAlchemy 2.0 at: https://sqlalche.me/e/b8d9)\n", + " Base = declarative_base() # type: Any\n" + ] + } + ], "source": [ "from langchain.retrievers.weaviate_hybrid_search import WeaviateHybridSearchRetriever\n", "from langchain.schema import Document" @@ -57,37 +81,85 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 4, "id": "f2eff08e", "metadata": {}, "outputs": [], "source": [ - "retriever = WeaviateHybridSearchRetriever(client, index_name=\"LangChain\", text_key=\"text\")" + "retriever = WeaviateHybridSearchRetriever(\n", + " client, index_name=\"LangChain\", text_key=\"text\"\n", + ")" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "b68debff", + "metadata": {}, + "source": [ + "Add some data:" ] }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 5, "id": "cd8a7b17", "metadata": {}, "outputs": [], "source": [ - "docs = [Document(page_content=\"foo\")]" + "docs = [\n", + " Document(\n", + " metadata={\n", + " \"title\": \"Embracing The Future: AI Unveiled\",\n", + " \"author\": \"Dr. Rebecca Simmons\",\n", + " },\n", + " page_content=\"A comprehensive analysis of the evolution of artificial intelligence, from its inception to its future prospects. Dr. Simmons covers ethical considerations, potentials, and threats posed by AI.\",\n", + " ),\n", + " Document(\n", + " metadata={\n", + " \"title\": \"Symbiosis: Harmonizing Humans and AI\",\n", + " \"author\": \"Prof. Jonathan K. Sterling\",\n", + " },\n", + " page_content=\"Prof. Sterling explores the potential for harmonious coexistence between humans and artificial intelligence. The book discusses how AI can be integrated into society in a beneficial and non-disruptive manner.\",\n", + " ),\n", + " Document(\n", + " metadata={\"title\": \"AI: The Ethical Quandary\", \"author\": \"Dr. Rebecca Simmons\"},\n", + " page_content=\"In her second book, Dr. Simmons delves deeper into the ethical considerations surrounding AI development and deployment. It is an eye-opening examination of the dilemmas faced by developers, policymakers, and society at large.\",\n", + " ),\n", + " Document(\n", + " metadata={\n", + " \"title\": \"Conscious Constructs: The Search for AI Sentience\",\n", + " \"author\": \"Dr. Samuel Cortez\",\n", + " },\n", + " page_content=\"Dr. Cortez takes readers on a journey exploring the controversial topic of AI consciousness. The book provides compelling arguments for and against the possibility of true AI sentience.\",\n", + " ),\n", + " Document(\n", + " metadata={\n", + " \"title\": \"Invisible Routines: Hidden AI in Everyday Life\",\n", + " \"author\": \"Prof. Jonathan K. Sterling\",\n", + " },\n", + " page_content=\"In his follow-up to 'Symbiosis', Prof. Sterling takes a look at the subtle, unnoticed presence and influence of AI in our everyday lives. It reveals how AI has become woven into our routines, often without our explicit realization.\",\n", + " ),\n", + "]" ] }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 6, "id": "3c5970db", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "['3f79d151-fb84-44cf-85e0-8682bfe145e0']" + "['eda16d7d-437d-4613-84ae-c2e38705ec7a',\n", + " '04b501bf-192b-4e72-be77-2fbbe7e67ebf',\n", + " '18a1acdb-23b7-4482-ab04-a6c2ed51de77',\n", + " '88e82cc3-c020-4b5a-b3c6-ca7cf3fc6a04',\n", + " 'f6abd9d5-32ed-46c4-bd08-f8d0f7c9fc95']" ] }, - "execution_count": 5, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -96,34 +168,76 @@ "retriever.add_documents(docs)" ] }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "6e030694", + "metadata": {}, + "source": [ + "Do a hybrid search:" + ] + }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 7, "id": "bf7dbb98", "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "[Document(page_content='foo', metadata={})]" + "[Document(page_content='In her second book, Dr. Simmons delves deeper into the ethical considerations surrounding AI development and deployment. It is an eye-opening examination of the dilemmas faced by developers, policymakers, and society at large.', metadata={}),\n", + " Document(page_content='A comprehensive analysis of the evolution of artificial intelligence, from its inception to its future prospects. Dr. Simmons covers ethical considerations, potentials, and threats posed by AI.', metadata={}),\n", + " Document(page_content=\"In his follow-up to 'Symbiosis', Prof. Sterling takes a look at the subtle, unnoticed presence and influence of AI in our everyday lives. It reveals how AI has become woven into our routines, often without our explicit realization.\", metadata={}),\n", + " Document(page_content='Prof. Sterling explores the potential for harmonious coexistence between humans and artificial intelligence. The book discusses how AI can be integrated into society in a beneficial and non-disruptive manner.', metadata={})]" ] }, - "execution_count": 6, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "retriever.get_relevant_documents(\"foo\")" + "retriever.get_relevant_documents(\"the ethical implications of AI\")" + ] + }, + { + "attachments": {}, + "cell_type": "markdown", + "id": "d0c5bb4d", + "metadata": {}, + "source": [ + "Do a hybrid search with where filter:" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "b2bc87c1", "metadata": {}, - "outputs": [], - "source": [] + "outputs": [ + { + "data": { + "text/plain": [ + "[Document(page_content='Prof. Sterling explores the potential for harmonious coexistence between humans and artificial intelligence. The book discusses how AI can be integrated into society in a beneficial and non-disruptive manner.', metadata={}),\n", + " Document(page_content=\"In his follow-up to 'Symbiosis', Prof. Sterling takes a look at the subtle, unnoticed presence and influence of AI in our everyday lives. It reveals how AI has become woven into our routines, often without our explicit realization.\", metadata={})]" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "retriever.get_relevant_documents(\n", + " \"AI integration in society\",\n", + " where_filter={\n", + " \"path\": [\"author\"],\n", + " \"operator\": \"Equal\",\n", + " \"valueString\": \"Prof. Jonathan K. Sterling\",\n", + " },\n", + ")" + ] } ], "metadata": { @@ -142,7 +256,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.6" + "version": "3.9.16" } }, "nbformat": 4, diff --git a/langchain/retrievers/weaviate_hybrid_search.py b/langchain/retrievers/weaviate_hybrid_search.py index 1393a909..42157a6e 100644 --- a/langchain/retrievers/weaviate_hybrid_search.py +++ b/langchain/retrievers/weaviate_hybrid_search.py @@ -19,6 +19,7 @@ class WeaviateHybridSearchRetriever(BaseRetriever): alpha: float = 0.5, k: int = 4, attributes: Optional[List[str]] = None, + create_schema_if_missing: bool = True, ): try: import weaviate @@ -40,6 +41,19 @@ class WeaviateHybridSearchRetriever(BaseRetriever): if attributes is not None: self._query_attrs.extend(attributes) + if create_schema_if_missing: + self._create_schema_if_missing() + + def _create_schema_if_missing(self) -> None: + class_obj = { + "class": self._index_name, + "properties": [{"name": self._text_key, "dataType": ["text"]}], + "vectorizer": "text2vec-openai", + } + + if not self._client.schema.exists(self._index_name): + self._client.schema.create_class(class_obj) + class Config: """Configuration for this pydantic object."""