Merge pull request #41 from deepset-ai/chroma-rename-retriever

Chroma: rename retriever
deepset-ai · Feb 14, 2024 · cbc081d · cbc081d
2 parents 7ac9de8 + a000e05
commit cbc081d
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 32 deletions.
diff --git a/notebooks/amazon_sagemaker_and_chroma_for_qa.ipynb b/notebooks/amazon_sagemaker_and_chroma_for_qa.ipynb
@@ -31,16 +31,16 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "EX5oCws-etEH",
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
+        "id": "EX5oCws-etEH",
         "outputId": "4d46055f-4d58-4d67-b895-ad701c2eb306"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "Requirement already satisfied: chroma-haystack in /usr/local/lib/python3.10/dist-packages (0.11.0)\n",
             "Requirement already satisfied: amazon-sagemaker-haystack in /usr/local/lib/python3.10/dist-packages (0.1.0)\n",
@@ -153,6 +153,9 @@
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "Eg9lSuAJM6MJ"
+      },
       "source": [
         "## Deploy a model on Sagemaker\n",
         "\n",
@@ -162,10 +165,7 @@
         "- Amazon Sagemaker Jumpstart [documentation](https://docs.aws.amazon.com/sagemaker/latest/dg/jumpstart-foundation-models-use.html).\n",
         "- [This notebook](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart-foundation-models/text-generation-falcon.ipynb) on how to deploy Falcon models programmatically with a notebook\n",
         "- [This blogpost](https://aws.amazon.com/blogs/machine-learning/build-production-ready-generative-ai-applications-for-enterprise-search-using-haystack-pipelines-and-amazon-sagemaker-jumpstart-with-llms/) about deploying models on Sagemaker for Haystack 1.x\n"
-      ],
-      "metadata": {
-        "id": "Eg9lSuAJM6MJ"
-      }
+      ]
     },
     {
       "cell_type": "markdown",
@@ -182,10 +182,10 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tZTz7cHwhZ-9",
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
+        "id": "tZTz7cHwhZ-9",
         "outputId": "72a5b7af-5d81-4c2f-e922-f35ee1dda94e"
       },
       "outputs": [
@@ -210,19 +210,24 @@
     },
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "k-CF7LUSy2T7"
+      },
       "source": [
         "## Load data from Wikipedia\n",
         "\n",
         "We are going to download the Wikipedia pages related to NASA's martian rovers using the python library `wikipedia`.\n",
         "\n",
         "These pages are converted into Haystack Documents."
-      ],
-      "metadata": {
-        "id": "k-CF7LUSy2T7"
-      }
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-Nz9MRVgxcfW"
+      },
+      "outputs": [],
       "source": [
         "import wikipedia\n",
         "from haystack.dataclasses import Document\n",
@@ -241,12 +246,7 @@
         "    page = wikipedia.page(title=title, auto_suggest=False)\n",
         "    doc = Document(content=page.content, meta={\"title\": page.title, \"url\":page.url})\n",
         "    raw_docs.append(doc)"
-      ],
-      "metadata": {
-        "id": "-Nz9MRVgxcfW"
-      },
-      "execution_count": null,
-      "outputs": []
+      ]
     },
     {
       "cell_type": "markdown",
@@ -309,29 +309,29 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "X7HrON1PFHos",
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
+        "id": "X7HrON1PFHos",
         "outputId": "22a57096-f22a-4333-cd85-9ea9ea4b52e0"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stderr",
+          "output_type": "stream",
           "text": [
             "/root/.cache/chroma/onnx_models/all-MiniLM-L6-v2/onnx.tar.gz: 100%|██████████| 79.3M/79.3M [00:06<00:00, 12.6MiB/s]\n"
           ]
         },
         {
-          "output_type": "execute_result",
           "data": {
             "text/plain": [
               "{'writer': {'documents_written': None}}"
             ]
           },
+          "execution_count": 5,
           "metadata": {},
-          "execution_count": 5
+          "output_type": "execute_result"
         }
       ],
       "source": [
@@ -346,7 +346,7 @@
       "source": [
         "## Building the Query Pipeline\n",
         "\n",
-        "Let’s create another pipeline to query our application. In this pipeline, we’ll use [ChromaQueryRetriever](https://docs.haystack.deepset.ai/v2.0/docs/chromaqueryretriever) to retrieve relevant information from the ChromaDocumentStore and a Falcon 7B Instruct BF16 model to generate answers with [SagemakerGenerator](https://docs.haystack.deepset.ai/v2.0/docs/sagemakergenerator).\n",
+        "Let’s create another pipeline to query our application. In this pipeline, we’ll use [ChromaQueryTextRetriever](https://docs.haystack.deepset.ai/v2.0/docs/chromaqueryretriever) to retrieve relevant information from the ChromaDocumentStore and a Falcon 7B Instruct BF16 model to generate answers with [SagemakerGenerator](https://docs.haystack.deepset.ai/v2.0/docs/sagemakergenerator).\n",
         "\n",
         "Next, we'll create a prompt for our task using the Retrieval-Augmented Generation (RAG) approach with [PromptBuilder](https://docs.haystack.deepset.ai/v2.0/docs/promptbuilder). This prompt will help generate answers by considering the provided context. Finally, we'll connect these three components to complete the pipeline."
       ]
@@ -362,10 +362,10 @@
         "from haystack.pipeline import Pipeline\n",
         "from haystack.components.builders import PromptBuilder\n",
         "from haystack_integrations.components.generators.amazon_sagemaker import SagemakerGenerator\n",
-        "from haystack_integrations.components.retrievers.chroma import ChromaQueryRetriever\n",
+        "from haystack_integrations.components.retrievers.chroma import ChromaQueryTextRetriever\n",
         "\n",
         "# Create pipeline components\n",
-        "retriever = ChromaQueryRetriever(document_store=document_store, top_k=3)\n",
+        "retriever = ChromaQueryTextRetriever(document_store=document_store, top_k=3)\n",
         "\n",
         "# Initialize the AmazonSagemakerGenerator with an Amazon Sagemaker model\n",
         "# You may need to change the model name if it differs from your endpoint name.\n",
@@ -404,16 +404,16 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "mDYCSRRtiAy5",
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
+        "id": "mDYCSRRtiAy5",
         "outputId": "b644aeb8-c9eb-4dbf-ed28-ad3080826410"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "\n",
             "Opportunity landed on Mars on January 24, 2004.\n"
@@ -431,16 +431,16 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "giSWajzyAcNp",
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
+        "id": "giSWajzyAcNp",
         "outputId": "ac240c1a-657d-447a-8f08-8558616d71e9"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "\n",
             "Yes, the Ingenuity mission is over. The helicopter made a total of 72 flights over a period of about 3 years until rotor damage sustained in January 2024 forced an end to the mission.\n"
@@ -458,16 +458,16 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "ROhJ8VL_JdHc",
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
+        "id": "ROhJ8VL_JdHc",
         "outputId": "4c77f458-d472-4644-b073-304986bf7a6c"
       },
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "\n",
             "The first NASA rover to land on Mars was called Sojourner.\n"

diff --git a/notebooks/chroma-indexing-and-rag-examples.ipynb b/notebooks/chroma-indexing-and-rag-examples.ipynb
@@ -145,7 +145,7 @@
       },
       "outputs": [],
       "source": [
-        "from haystack_integrations.components.retrievers.chroma import ChromaQueryRetriever\n",
+        "from haystack_integrations.components.retrievers.chroma import ChromaQueryTextRetriever\n",
         "from haystack.components.generators import HuggingFaceTGIGenerator\n",
         "from haystack.components.builders import PromptBuilder\n",
         "\n",
@@ -163,7 +163,7 @@
         "\n",
         "llm = HuggingFaceTGIGenerator(model=\"mistralai/Mixtral-8x7B-Instruct-v0.1\")\n",
         "llm.warm_up()\n",
-        "retriever = ChromaQueryRetriever(document_store)\n",
+        "retriever = ChromaQueryTextRetriever(document_store)\n",
         "\n",
         "querying = Pipeline()\n",
         "querying.add_component(\"retriever\", retriever)\n",