feat: allow to run the model locally with ollama and faiss (#17) (#28)

* feat: add ollama support in post-documents api (#17)

* docs: add docs on how to change ollama models

* docs: fix sample url

* docs: formatting

* chore: update lockfile

* refactor: rename function

* refactor: move http-response

* refactor: rename ollama.ts

* refactor: simplify http helpers

* refactor: add data http response

* refactor: update api.http

* chore: update packages and clean up dependencies

* refactor: rename functions and ids

* refactor: move code

* refactor: rename models to constants

* feat: persist local storage

* chore: enable streaming

* feat: implement local mode for chat api

* chore: update .gitignore

* fix: use last user message as question

* refactor: consistent error messages

* refactor: formatting

* refactor: clean up frontend

* docs: simplify api docs

* fix: generate .env file in api folder

* chore: update sample env file

README.md

@@ -1,3 +1,4 @@
+<!-- prettier-ignore -->
 <div align="center">
 
 <img src="./packages/webapp/public/favicon.png" alt="" align="center" height="64" />
@@ -68,7 +69,7 @@ You need to install following tools to work on your local machine:
 
 Then you can get the project code:
 
-1. [**Fork**](https://github.com/Azure-Samples/langchainjs-quickstart-demo/fork) the project to create your own copy of this repository.
+1. [**Fork**](https://github.com/Azure-Samples/serverless-ai-langchainjs/fork) the project to create your own copy of this repository.
 2. On your forked repository, select the **Code** button, then the **Local** tab, and copy the URL of your forked repository.
 <div align="center">
   <img src="./docs/images/clone-url.png" alt="Screenshot showing how to copy the repository URL" width="400px" />
@@ -123,15 +124,18 @@ This will start the web app and the API locally. Open the URL `http://localhost:
 
 First you need to provision the Azure resources needed to run the sample. Follow the instructions in the [Deploy the sample to Azure](#deploy-the-sample-to-azure) section to deploy the sample to Azure, then you'll be able to run the sample locally using the deployed Azure resources.
 
-Once your deployment is complete, you can run the following commands to start the application locally:
+Once your deployment is complete, you should see a `.env` file in the `src/api` folder. This file contains the environment variables needed to run the application using Azure resources.
 
-1. Run `azd env get-values > .env` to get the environment variables.
-2. Run `npm start` to start the application.
+To run the sample, you can then use the same commands as for the Ollama setup:
+
+```bash
+npm start
+```
 
 This will start the web app and the API locally. Open the URL `http://localhost:8000` in your browser to start chatting with the bot.
 
 > [!TIP]
-> You can switch back to using Ollama models by simply deleting the `.env` file and starting the application again.
+> You can switch back to using Ollama models by simply deleting the `src/api/.env` file and starting the application again. To regenerate the `.env` file, you can run `azd env get-values > src/api/.env`.
 
 ### Deploy the sample to Azure
 

azure.yaml

@@ -27,7 +27,7 @@ services:
 hooks:
   postprovision:
     shell: sh
-    run: azd env get-values > .env
+    run: azd env get-values > src/api/.env
   postup:
     windows:
       shell: pwsh

docs/faq.md

@@ -36,7 +36,7 @@ Invoke-RestMethod -Uri "http://localhost:7071/api/documents" -Method Post -InFil
 
 ### For the deployed version
 
-First you need to find the URL of the deployed function. You can either look at the `.env` file at the root of the project and search for the `API_URI` variable, or run this command to get the URL:
+First you need to find the URL of the deployed function. You can either look at the `src/api/.env` file and search for the `API_URI` variable, or run this command to get the URL:
 
 ```bash
 azd env get-values | grep API_URI
@@ -76,9 +76,22 @@ azd env set AZURE_OPENAI_API_EMBEDDINGS_MODEL_VERSION 1
 
 You may also need to adjust the capacity in `infra/main.bicep` file, depending on how much TPM your account is allowed.
 
-<!--
-TODO: how to change local models version with Ollama
--->
+### Local models
+
+To change the local models used by Ollama, you can edit the file `packages/api/src/constants.ts`:
+
+```typescript
+export const ollamaEmbeddingsModel = 'all-minilm:l6-v2';
+export const ollamaChatModel = 'mistral';
+```
+
+You can see the complete list of available models at https://ollama.ai/models.
+
+After changing the models, you also need to fetch the new models by running the command:
+
+```bash
+ollama pull <model-name>
+```
 
 </details>
 

docs/quickstart.md

@@ -16,7 +16,7 @@ description: Create your own serverless ChatGPT with Retrieval-Augmented-Generat
 ---
 
 <!-- Learn samples onboarding: https://review.learn.microsoft.com/en-us/help/contribute/samples/process/onboarding?branch=main -->
-
+<!-- prettier-ignore -->
 This sample shows how to build a serverless ChatGPT-like experience with Retrieval-Augmented Generation using [LangChain.js](https://js.langchain.com/) and Azure. The application is hosted on [Azure Static Web Apps](https://learn.microsoft.com/azure/static-web-apps/overview) and [Azure Functions](https://learn.microsoft.com/azure/azure-functions/functions-overview?pivots=programming-language-javascript), with [Azure Cosmos DB for MongoDB vCore](https://learn.microsoft.com/azure/cosmos-db/mongodb/vcore/) as the vector database. You can use it as a starting point for building more complex AI applications.
 
 <!-- TODO: gif -->
@@ -53,12 +53,11 @@ This application is made from multiple components:
 
 You can run this project directly in your browser by using GitHub Codespaces, which will open a web-based VS Code.
 
-1. [**Fork**](https://github.com/Azure-Samples/langchainjs-quickstart-demo/fork) the project to create your own copy of this repository.
+1. [**Fork**](https://github.com/Azure-Samples/serverless-ai-langchainjs/fork) the project to create your own copy of this repository.
 2. On your forked repository, select the **Code** button, then the **Codespaces** tab, and clink on the button **Create codespace on main**.
 <div align="center">
   <img src="./images/codespaces.png" alt="Screenshot showing how to create a new codespace" width="400px" />
 </div>
-
 3. Wait for the Codespace to be created, it should take a few minutes.
 
 ## Deploy on Azure