init devika repo

docs/Installation/ollama.md

@@ -0,0 +1,20 @@
+# Ollama Installation Guide
+
+This guide will help you set up Ollama for Devika. Ollama is a tool that allows you to run open-source large language models (LLMs) locally on your machine. It supports varity of models like Llama-2, mistral, code-llama and many more.
+
+## Installation
+
+1. go to the [Ollama](https://ollama.com) website.
+2. Download the latest version of the Ollama.
+3. After installing the Ollama, you have to download the model you want to use. [Models](https://ollama.com/library)
+4. select the model you want to download and copy the command. for example, `ollama run llama2`.it will download the model and start the server. 
+5. `ollama list` will show the list of models you have downloaded.
+6. if the server isn't running then you can manually start by `ollama serve`. default address for the server is `http://localhost:11434`
+7. for changing port and other configurations, follow the FAQ [here](https://github.com/ollama/ollama/blob/main/docs/faq.md)
+8. for more information, `ollama [command] --help` will show the help menu. for example, `ollama run --help` will show the help menu for the run command.
+
+
+## Devika Configuration
+
+- if you serve the Ollama on a different address, you can change the port in the `config.toml` file or you can change it via UI.
+- if you are using the default address, devika will automatically detect the server and and fetch the models list.

docs/Installation/search_engine.md

@@ -0,0 +1,33 @@
+# search Engine setup
+
+To use the search engine capabilities of Devika, you need to set up the search engine API keys. Currently, Devika supports Bing, Google and DuckDuckGo search engines. If you want to use duckduckgo, you don't need to set up any API keys.
+
+For Bing and Google search engines, you need to set up the API keys. Here's how you can do it:
+
+## Bing Search API
+- Create Azure account. You can create a free account [here](https://azure.microsoft.com/en-us/free/). 
+- Go to the [Bing Search API](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api) website.
+- click on the `Try now` button.
+- Sign in/sign up with your Azure account.
+- Create a new resource group (if you don't have any).
+![alt text](images/bing.png)
+- click on the `Review and create` button.
+- if everything is fine, click on the `Create` button.
+- Once the resource is created, go to the `Keys and Endpoint` tab.
+![alt text](images/bing-1.png)
+- Copy either `Key1` or `Key2` and paste it into the `API_KEYS` field with the name `BING` in the `config.toml` file located in the root directory of Devika, or you can set it via the UI.
+- Copy the `Endpoint` and paste it into the `API_Endpoints` field with the name `BING` in the `config.toml` file located in the root directory of Devika, or you can set it via the UI.
+
+
+## Google Search API
+- if don't have then create GCP account [Google Cloud Console](https://console.cloud.google.com/).
+- visit [Here](https://developers.google.com/custom-search/v1/overview) is the official documentation.
+- click on `Get a Key`.
+- select the project you have or create a new project. click on next.
+![alt text](images/google.png)
+- it enable the Custom Search API for the project and create the API key.
+- Copy the API key and paste it in the API_KEYS field with the name `GOOGLE_SEARCH` in the `config.toml` file in the root directory of Devika or you can set it via UI.
+- for the search engine id, go to the [Google Custom Search Engine](https://programmablesearchengine.google.com/controlpanel/all) website.
+- click on the `Add` button.
+![alt text](images/google-2.png)
+- After creating the engine. Copy the `Search Engine ID` and paste it in the API_Endpoints field with the name `GOOGLE_SEARCH_ENGINE_ID` in the `config.toml` file in the root directory of Devika or you can set it via UI.