MSUSAzureAccelerators · minhvu10 · Jul 26, 2023 · Jul 26, 2023 · Jul 26, 2023 · Jul 26, 2023
diff --git a/00-Resource-Validation.ipynb b/00-Resource-Validation.ipynb
diff --git a/01-Load-Data-ACogSearch.ipynb b/01-Load-Data-ACogSearch.ipynb
diff --git a/02-LoadCSVOneToMany-ACogSearch.ipynb b/02-LoadCSVOneToMany-ACogSearch.ipynb
diff --git a/03-Quering-AOpenAI.ipynb b/03-Quering-AOpenAI.ipynb
diff --git a/04-Adding_Memory.ipynb b/04-Adding_Memory.ipynb
diff --git a/04-Complex-Docs.ipynb b/04-Complex-Docs.ipynb
diff --git a/05-Adding_Memory.ipynb b/05-Adding_Memory.ipynb
diff --git a/05-TabularDataQA.ipynb b/05-TabularDataQA.ipynb
diff --git a/06-SQLDB_QA.ipynb b/06-SQLDB_QA.ipynb
diff --git a/06-TabularDataQA.ipynb b/06-TabularDataQA.ipynb
diff --git a/07-BingChatClone.ipynb b/07-BingChatClone.ipynb
diff --git a/07-SQLDB_QA.ipynb b/07-SQLDB_QA.ipynb
diff --git a/08-BingChatClone.ipynb b/08-BingChatClone.ipynb
diff --git a/08-Smart_Agent.ipynb b/08-Smart_Agent.ipynb
diff --git a/09-Smart_Agent.ipynb b/09-Smart_Agent.ipynb
diff --git a/09-Building-Apps.ipynb → 10-Building-Apps.ipynb b/09-Building-Apps.ipynb → 10-Building-Apps.ipynb
diff --git a/11-VectorDB_Load.ipynb b/11-VectorDB_Load.ipynb
diff --git a/12-VectorDB_QA.ipynb b/12-VectorDB_QA.ipynb
@@ -0,0 +1,274 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "# Question and answer LLM using the Vector Database data as context"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "Prerequites: \n",
+        "\n",
+        "1. This notebook assumes you've completed the previous notebook and have data loaded into your vector store. \n",
+        "\n",
+        "2. Azure openAI endpoint\n",
+        "    Confirm that you've deployed both an embedding model and a LLM. https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/create-resource?pivots=web-portal\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "jupyter": {
+          "outputs_hidden": true,
+          "source_hidden": false
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [],
+      "source": [
+        "%pip install weaviate-client\n",
+        "%pip install langchain\n",
+        "%pip install openai[datalib]\n",
+        "%pip install tiktoken\n",
+        "%pip install python-dotenv"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "gather": {
+          "logged": 1694446501722
+        },
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "from dotenv import load_dotenv\n",
+        "load_dotenv(\"credentials.env\", override=True)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "gather": {
+          "logged": 1694446501905
+        },
+        "jupyter": {
+          "outputs_hidden": true
+        }
+      },
+      "outputs": [],
+      "source": [
+        "from langchain.vectorstores import Weaviate\n",
+        "import weaviate\n",
+        "\n",
+        "WEAVIATE_URL = os.environ[\"VECTOR_DB_WEAVIATE_URL\"]\n",
+        "WEAVIATE_API_KEY = os.environ[\"WEAVIATE_API_KEY\"]\n",
+        "\n",
+        "#create client to inte ract with Weaviate\n",
+        "client = weaviate.Client(url=WEAVIATE_URL, auth_client_secret=weaviate.AuthApiKey(WEAVIATE_API_KEY))\n",
+        "#Print schemas in weaviate, you should see your index from the previous notebook named \"arxivcs_index\"\n",
+        "client.schema.get()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "### Set embedding parameters and LLM paramters"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "source": [
+        "We are not embedding documents into Weaviate but we still need the embedding model to convert our prompt into a vector and do a similarity search. Make sure you are using the same embedding model here as you did to write data to the vector database.  "
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "gather": {
+          "logged": 1694446502048
+        },
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [],
+      "source": [
+        "#embedding parameters, should be the same as what was used to embed documents into weaviate\n",
+        "import openai\n",
+        "\n",
+        "openai.api_type = \"azure\"\n",
+        "openai.api_key = os.environ['openai_api_key']\n",
+        "openai.api_base = os.environ[\"AZURE_OPENAI_ENDPOINT\"]\n",
+        "openai.api_version = os.environ[\"AZURE_OPENAI_API_VERSION\"]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "gather": {
+          "logged": 1694446502196
+        },
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [],
+      "source": [
+        "#LLM Paramaters\n",
+        "from langchain.chat_models import AzureChatOpenAI\n",
+        "\n",
+        "llm = AzureChatOpenAI(\n",
+        "    openai_api_base=os.environ[\"AZURE_OPENAI_ENDPOINT\"],\n",
+        "    openai_api_version=os.environ[\"AZURE_OPENAI_API_VERSION\"],\n",
+        "    deployment_name=os.environ[\"AZURE_OPENAI_LLM_DEPLOYMENT\"],\n",
+        "    openai_api_key=os.environ['openai_api_key'],\n",
+        "    openai_api_type=\"azure\",\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "gather": {
+          "logged": 1694446250628
+        },
+        "jupyter": {
+          "outputs_hidden": false,
+          "source_hidden": false
+        },
+        "nteract": {
+          "transient": {
+            "deleting": false
+          }
+        }
+      },
+      "outputs": [],
+      "source": [
+        "from langchain import PromptTemplate, LLMChain\n",
+        "\n",
+        "# Prompt\n",
+        "prompt = PromptTemplate.from_template(\n",
+        "    \"Summarize the main themes in these retrieved docs: {docs}\"\n",
+        ")\n",
+        "\n",
+        "# Chain\n",
+        "llm_chain = LLMChain(llm=llm, prompt=prompt)\n",
+        "\n",
+        "#Converting our input question to an Embedding to use for search\n",
+        "response = openai.Embedding.create(\n",
+        "    input=\"What is Quantum mechanics?\",\n",
+        "    engine=\"textembedding\"\n",
+        ")\n",
+        "embeddings = response['data'][0]['embedding']\n",
+        "\n",
+        "# Run\n",
+        "db = Weaviate(client=client, index_name=\"arxivcs_index\", text_key=\"text\")\n",
+        "docs = db.similarity_search_by_vector(embedding=embeddings)\n",
+        "result = llm_chain(docs)\n",
+        "\n",
+        "# Output\n",
+        "result['text']"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernel_info": {
+      "name": "python310-sdkv2"
+    },
+    "kernelspec": {
+      "display_name": "Python 3.10 - SDK v2",
+      "language": "python",
+      "name": "python310-sdkv2"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.10.11"
+    },
+    "microsoft": {
+      "host": {
+        "AzureML": {
+          "notebookHasBeenCompleted": true
+        }
+      },
+      "ms_spell_check": {
+        "ms_spell_check_language": "en"
+      }
+    },
+    "nteract": {
+      "version": "nteract-front-end@1.0.0"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 2
+}
diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md
@@ -0,0 +1,9 @@
+# Microsoft Open Source Code of Conduct
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+
+Resources:
+
+- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
+- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
+- Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -0,0 +1,14 @@
+# Contributing
+
+This project welcomes contributions and suggestions. Most contributions require you to
+agree to a Contributor License Agreement (CLA) declaring that you have the right to,
+and actually do, grant us the rights to use your contribution. For details, visit
+https://cla.microsoft.com.
+
+When you submit a pull request, a CLA-bot will automatically determine whether you need
+to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the
+instructions provided by the bot. You will only need to do this once across all repositories using our CLA.
+
+This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
+For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
+or contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.
diff --git a/LICENSE.txt b/LICENSE.txt
@@ -0,0 +1,21 @@
+Copyright (c) Microsoft Corporation.
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED *AS IS*, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.