upgrade to v0.3.0 (#320)

* upgrade to v0.3.0

* feat: add support for ollama fast model

* upgrade to v0.3.0

* feat: add support for ollama fast model

* styles: update the thinking color and change the heading font sizes

* feat(docs): Added changes in documents WRT latest code

---------

Co-authored-by: oindrilabanerjee <banerjee.oindrila.ob@gmail.com>

Author: zereraz

docs/apikeys/apikeys.mdx

@@ -6,7 +6,7 @@ icon: 'key'
 
 This guide providers more details about creating and setting AI api keys in your .env file for using Xyne's chat feature.
 
-To use **AI chat**, you need to configure access credentials. You can use one of the following providers: ***AWS, OpenAI, or Ollama***.
+To use **AI chat**, you need to configure access credentials. You can use one of the following providers: ***AWS, OpenAI, Ollama, Together AI or Fireworks AI***.
 
 ### AWS (Amazon Bedrock) 
 
@@ -15,6 +15,8 @@ To use **AI chat**, you need to configure access credentials. You can use one of
 - Add them as environment variables in your ```.env.default``` file:
     ```javascript   .env.default
     AWS_ACCESS_KEY=<YOUR_AWS_ACCESS_KEY> 
+    AWS_SECRET_KEY=<YOUR_AWS_SECRET_KEY>  
+    AWS_REGION=<YOUR_AWS_REGION>     
     ```
     <Note> The ```AWS_REGION``` key is optional in the ```.env.default``` file; if not provided, it defaults to ```us-west-2``` </Note>
 
@@ -25,15 +27,73 @@ To use **AI chat**, you need to configure access credentials. You can use one of
     OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> 
     ```
 ### Ollama (Local LLM)
-- Install Ollama and the desired model from ollama.com.
+- Install Ollama and the desired model from [Ollama](https://ollama.com/).
 - Add the model name in your .env.default file:
     ```javascript .env.default
     OLLAMA_MODEL=<YOUR_OLLAMA_MODEL_NAME> 
     ```
-<Tip> If you're using Ollama, ensure the specified model is downloaded locally. </Tip>    
+<Tip> If you're using Ollama, ensure the specified model is downloaded locally. </Tip> 
+
+### Together AI
+- Create your API key in [Together AI](https://www.together.ai/)
+- Select the model from your choice.
+- Add the following to your .env.default file:
+    ```javascript .env.default
+    TOGETHER_API_KEY=<YOUR_TOGETHER_API_KEY>
+    TOGETHER_MODEL=<YOUR_TOGETHER_MODEL>
+    TOGETHER_FAST_MODEL=<YOUR_TOGETHER_FAST_MODEL>
+    ```
+
+### Fireworks AI
+- Create your API key in [Fireworks AI](https://fireworks.ai/)
+- Select the model from your choice.
+- Add the following to your .env.default file:
+    ```javascript .env.default
+    FIREWORKS_API_KEY=<YOUR_FIREWORKS_API_KEY>
+    FIREWORKS_MODEL=<YOUR_FIREWORKS_MODEL>
+    FIREWORKS_FAST_MODEL=<YOUR_FIREWORKS_FAST_MODEL>
+    ```
+
+## Setting up for Reasoning [Together | Fireworks | Ollama] : 
+
+For addition of only reasoning in your model, you need to add REASONING in your .env.default file:
+```javascript .env.default
+REASONING=true
+```
+
+### For example : 
+
+#### Reasoning with Together AI : 
+
+```javascript .env.default
+TOGETHER_API_KEY=<YOUR_TOGETHER_API_KEY>
+TOGETHER_MODEL=deepseek-ai/DeepSeek-R1
+TOGETHER_FAST_MODEL=deepseek-ai/DeepSeek-V3
+REASONING=true
+FAST_MODEL_REASONING=false
+```
+#### Reasoning with Fireworks AI : 
+
+```javascript .env.default
+FIREWORKS_API_KEY=<YOUR_FIREWORKS_API_KEY>
+FIREWORKS_MODEL=accounts/fireworks/models/deepseek-r1
+FIREWORKS_FAST_MODEL=accounts/fireworks/models/deepseek-v3
+REASONING=true
+FAST_MODEL_REASONING=false
+```
+
+#### Reasoning with Ollama : 
+
+```javascript .env.default
+OLLAMA_MODEL=<REASONING_MODEL>
+OLLAMA_FAST_MODEL=non reasoning model
+REASONING=true
+FAST_MODEL_REASONING=false
+```
+
 ### Key Selection Order : 
 If multiple keys are set in the environment variable, our system follows this precedence:
 ```javascript 
-AWS → OpenAI → Ollama
+AWS → OpenAI → Ollama → Together AI → Fireworks AI
 ```
-<Tip>Only anyone provider is required to get started. This means either AWS or OpenAI or Ollama can be used, all of them aren't required.</Tip>
+<Tip>Only anyone provider is required to get started. This means either AWS or OpenAI, Ollama, Together AI or Fireworks AI can be used, all of them aren't required.</Tip>

docs/authentication/service-accounts.mdx

@@ -45,7 +45,7 @@ Once you've filled out the details, click on `CREATE AND CONTINUE`
 - Choose the ```json``` option for downloading the key file, and click on ```Create```.
 <img height="200" src="../images/serv-acc5.png" />
 - Remember the ```Client id``` associated with this json file.
-- Once the key file has been created, choose a reliable location for downloading the key file, this will be used for putting it in the [```.env``` of the application](https://docs.xynehq.com/deployment/cloud/aws/aws-deployment-with-docker#setting-the-environment-variables)
+- Once the key file has been created, choose a reliable location for downloading the key file, this will be used for putting it in the [```.env``` of the application](https://docs.xynehq.com/quickstart#setting-the-environment-variables)
 
 
 ## Enabling APIs

docs/contribution/devmode.mdx

@@ -40,21 +40,40 @@ In the ```.env.development``` file, you can paste the following :
 ENCRYPTION_KEY=<YOUR_ENCRYPTION_KEY>
 # If you wish to execute authorization using Service Account then use :
  SERVICE_ACCOUNT_ENCRYPTION_KEY=<YOUR_SERVICE_ACCOUNT_ENCRYPTION_KEY> 
-# If you wish to execute authorization using Oauth then use :   
+
+
 GOOGLE_CLIENT_ID=<YOUR_GOOGLE_CLIENT_ID>
 GOOGLE_CLIENT_SECRET=<YOUR_GOOGLE_CLIENT_SECRET>
 GOOGLE_REDIRECT_URI=http://localhost:3000/v1/auth/callback
+
 HOST=http://localhost:3000
+
 JWT_SECRET=<YOUR_JWT_SECRET>
+
 DATABASE_HOST=xyne-db
 VESPA_HOST=vespa
+
+
+## If using AWS Bedrock
 AWS_ACCESS_KEY=<YOUR_AWS_ACCESS_KEY>
 AWS_SECRET_KEY=<YOUR_AWS_ACCESS_SECRET>
-## OR
+AWS_REGION=<YOUR_AWS_REGION>
+  
+## OR [ If using Open AI ]
 OPENAI_API_KEY=<YOUR_OPEN_API_KEY>
-## OR
+
+## OR [ If using Ollama ] 
 OLLAMA_MODEL=<YOUR_OLLAMA_MODEL_NAME> 
-AWS_REGION=<YOUR_AWS_REGION>
+
+## OR  [ If using Together AI ] 
+TOGETHER_API_KEY=<YOUR_TOGETHER_API_KEY>
+TOGETHER_MODEL=<YOUR_TOGETHER_MODEL>
+TOGETHER_FAST_MODEL=<YOUR_TOGETHER_FAST_MODEL>
+
+## OR  [ If using Fireworks AI ] 
+FIREWORKS_API_KEY=<YOUR_FIREWORKS_API_KEY>
+FIREWORKS_MODEL=<YOUR_FIREWORKS_MODEL>
+FIREWORKS_FAST_MODEL=<YOUR_FIREWORKS_FAST_MODEL>
 ```
 
 ### Set up Docker

docs/deployment/cloud/aws/aws-deployment-with-docker.mdx

@@ -54,33 +54,73 @@ Setup your Google Credentials for the application.
 Inside the ```server``` folder of the ```xyne``` folder, you will find a ```.env.default``` file, this is the .env file that our docker uses.
 For the moment you will find some default generated environment variables that we've set up for the app to work.
 
-<Warning> We strictly recommend generating your own ENCRYPTION_KEY, SERVICE_ACCOUNT_ENCRYPTION_KEY and JWT_SECRET values for security.</Warning>
+<Warning> We strictly recommend generating your own ***ENCRYPTION_KEY, SERVICE_ACCOUNT_ENCRYPTION_KEY and JWT_SECRET*** values for security.</Warning>
+
+
+<Tip>Due to our agentic RAG implementation, the maximum TPM limit exceeds for Open AI's gpt4o model. 
+ For the ***best experience***, we recommend using ***AWS Bedrock or Claude***, as it enhances performance and accuracy. </Tip>
 
 In the ```.env.default``` file, you can modify the following and replace the missing values with your own :
 
 ```javascript .env.default file
 ENCRYPTION_KEY=<YOUR_ENCRYPTION_KEY>
 SERVICE_ACCOUNT_ENCRYPTION_KEY=<YOUR_SERVICE_ACCOUNT_ENCRYPTION_KEY> 
-# If you wish to execute authorization using Oauth then use :   
+
+  
 GOOGLE_CLIENT_ID=<YOUR_GOOGLE_CLIENT_ID>
 GOOGLE_CLIENT_SECRET=<YOUR_GOOGLE_CLIENT_SECRET>
 GOOGLE_REDIRECT_URI=http://localhost:3001/v1/auth/callback
 GOOGLE_PROD_REDIRECT_URI=<YOUR_Public_IPv4_DNS_ADDRESS>/v1/auth/callback
+
 JWT_SECRET=<YOUR_JWT_SECRET>
+
+
 DATABASE_HOST=xyne-db
 VESPA_HOST=vespa
+
+
+## If using AWS Bedrock
 AWS_ACCESS_KEY=<YOUR_AWS_ACCESS_KEY>
 AWS_SECRET_KEY=<YOUR_AWS_ACCESS_SECRET>
-## OR
+AWS_REGION=<YOUR_AWS_REGION>
+  
+## OR [ If using Open AI ]
 OPENAI_API_KEY=<YOUR_OPEN_API_KEY>
-## OR
+
+## OR [ If using Ollama ] 
 OLLAMA_MODEL=<YOUR_OLLAMA_MODEL_NAME> 
+
+## OR  [ If using Together AI ] 
+TOGETHER_API_KEY=<YOUR_TOGETHER_API_KEY>
+TOGETHER_MODEL=<YOUR_TOGETHER_MODEL>
+TOGETHER_FAST_MODEL=<YOUR_TOGETHER_FAST_MODEL>
+
+## OR  [ If using Fireworks AI ] 
+FIREWORKS_API_KEY=<YOUR_FIREWORKS_API_KEY>
+FIREWORKS_MODEL=<YOUR_FIREWORKS_MODEL>
+FIREWORKS_FAST_MODEL=<YOUR_FIREWORKS_FAST_MODEL>
+
+
 HOST=<YOUR_Public_IPv4_DNS_ADDRESS>
-AWS_REGION=<YOUR_AWS_REGION>
 ```
 
 <Warning> Ensure that these IPv4 address is the same as the one you've added in your Google Cloud Project</Warning>
 
+
+<Tip>To use the chat feature of Xyne, you need any one AI provider (AWS, Ollama, OpenAI Together AI or Fireworks AI). Missing keys will disable chat functionality.</Tip>
+
+You can checkout the AI Providers section for better clarity : 
+
+<Card
+  title="Setup AI Providers for Xyne"
+  icon="key"
+  href="/apikeys/apikeys"
+>
+Setup your AI Provider.
+</Card>
+
+<Warning> Chat will be unavailable without a Service Account or OAuth Account connection. </Warning>
+
 ## Deploy Xyne with Docker  :
 
 Run the following command to run the application :

docs/images/slashd.png

@@ -49,45 +49,45 @@
       "group": "Get Started",
       "pages": ["introduction", "quickstart"]
     },
-    {
-      "group": "AI Providers",
-      "pages": ["apikeys/apikeys"]      
- },
-    {
-      "group": "Deployment",
-      "pages": [
-        {
-          "group": "Cloud Deployment",
-          "icon": "cloud",
-          "pages": [
-            {
-              "group": "AWS",
-              "icon": "aws",
-              "pages": ["deployment/cloud/aws/aws-deployment-with-docker"]
-            }
-          ]
-        }
-      ]
-    },
     {
       "group": "Authentication",
       "pages": ["authentication/get-credentials", "authentication/oauth", "authentication/service-accounts"]
     },
-    {
-      "group": "For Developers",
-      "pages": ["contribution/contribute", "contribution/devmode"]
-    },
     {
       "group": "Ingesting Data",
       "pages": ["ingestion/ingestion","ingestion/oauth-ingest", "ingestion/service-ingest"]      
       },
+      {
+        "group": "AI Providers",
+        "pages": ["apikeys/apikeys"]      
+   },
+   {
+    "group": "Deployment",
+    "pages": [
+      {
+        "group": "Cloud Deployment",
+        "icon": "cloud",
+        "pages": [
+          {
+            "group": "AWS",
+            "icon": "aws",
+            "pages": ["deployment/cloud/aws/aws-deployment-with-docker"]
+          }
+        ]
+      }
+    ]
+  },
       {
         "group": "Re-Ingesting Data",
         "pages": ["re-ingest/reingest"]      
         },
     {
       "group": "Changelog",
       "pages": ["changelog/overview"]
+    },
+    {
+      "group": "For Developers",
+      "pages": ["contribution/contribute", "contribution/devmode"]
     }
   ],
   "redirects": [

docs/mint.json

@@ -76,26 +76,46 @@ In the ```.env.default``` file, you can modify the following and replace the mis
 ```javascript .env.default file
 ENCRYPTION_KEY=<YOUR_ENCRYPTION_KEY>
 SERVICE_ACCOUNT_ENCRYPTION_KEY=<YOUR_SERVICE_ACCOUNT_ENCRYPTION_KEY> 
-# If you wish to execute authorization using Oauth then use :   
+  
+
 GOOGLE_CLIENT_ID=<YOUR_GOOGLE_CLIENT_ID>
 GOOGLE_CLIENT_SECRET=<YOUR_GOOGLE_CLIENT_SECRET>
 GOOGLE_REDIRECT_URI=http://localhost:3000/v1/auth/callback
 GOOGLE_PROD_REDIRECT_URI=http://localhost:3001/v1/auth/callback
+
+
 JWT_SECRET=<YOUR_JWT_SECRET>
+
+
 DATABASE_HOST=xyne-db
 VESPA_HOST=vespa
+
+## If using AWS Bedrock
 AWS_ACCESS_KEY=<YOUR_AWS_ACCESS_KEY>
 AWS_SECRET_KEY=<YOUR_AWS_ACCESS_SECRET>
-## OR
+AWS_REGION=<YOUR_AWS_REGION>
+  
+## OR [ If using Open AI ]
 OPENAI_API_KEY=<YOUR_OPEN_API_KEY>
-## OR
+
+## OR [ If using Ollama ] 
 OLLAMA_MODEL=<YOUR_OLLAMA_MODEL_NAME> 
+
+## OR  [ If using Together AI ] 
+TOGETHER_API_KEY=<YOUR_TOGETHER_API_KEY>
+TOGETHER_MODEL=<YOUR_TOGETHER_MODEL>
+TOGETHER_FAST_MODEL=<YOUR_TOGETHER_FAST_MODEL>
+
+## OR  [ If using Fireworks AI ] 
+FIREWORKS_API_KEY=<YOUR_FIREWORKS_API_KEY>
+FIREWORKS_MODEL=<YOUR_FIREWORKS_MODEL>
+FIREWORKS_FAST_MODEL=<YOUR_FIREWORKS_FAST_MODEL>
+
+
 HOST=http://localhost:3001
-## Set your desired AI provider 
-AWS_REGION=<YOUR_AWS_REGION>
 ```
 
-<Tip>To use the chat feature of Xyne, you need any one AI provider (AWS, Ollama, or OpenAI). Missing keys will disable chat functionality.</Tip>
+<Tip>To use the chat feature of Xyne, you need any one AI provider (AWS, Ollama, OpenAI Together AI or Fireworks AI). Missing keys will disable chat functionality.</Tip>
 
 You can checkout the AI Providers section for better clarity :