> ## Documentation Index
> Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Archived Changelog
> Archive of previous TrueFoundry platform changelog entries with release notes and upgrade instructions.
## Improvement: Add ownership to Virtual Account
You can now add owner to each virutal account using team. All the members of the team would be able to access activities including model/mcp server metrics and traces of that virtual account.
{" "}
### More Updates
* Added support for Anthropic messages endpoint with cost tracing, logging and others. [Read more](https://docs.truefoundry.com/docs/ai-gateway/messages-overview)
* Enhanced experience for using Claude Code via gateway. [Read more](https://docs.truefoundry.com/docs/ai-gateway/claude-code#claude-code)
* Added support for Video MIME type in AWS Bedrock models.
### Release instructions
* Update `truefoundry` helm chart version to `0.98.3`.
**Bug fixes and improvements (No major changes)**
### More Updates
* Added support for cost tracking in OCR models like Mistral AI, Document AI, etc in both Azure and Mistral providers.
* Added support for `task_type` in Google embeddings. ([https://docs.cloud.google.com/vertex-ai/generative-ai/docs/embeddings/task-types](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/embeddings/task-types))
### Release instructions
* Update `truefoundry` helm chart version to `0.97.1`.
## New: Export Gateway request traces to your OTEL Platform
You can now export the Gateway request traces to your own OTEL Platform. [Read more](https://docs.truefoundry.com/docs/ai-gateway/export-opentelemetry-data)
{" "}
### More Updates
* Added support for Cloudera Model provider. [Read more](https://docs.truefoundry.com/docs/ai-gateway/cloudera#cloudera)
* Added support for manual regeneration of Virual Account token.
### Release instructions
* Update `truefoundry` helm chart version to `0.96.4`.
**Bug fixes and improvements (No major changes)**
### Release instructions
* Update `truefoundry` helm chart version to `0.95.2`.
## New: Virtual MCP servers
Combine multiple MCP servers with specific tools to create Virtual MCP servers. [Read more](https://docs.truefoundry.com/docs/ai-gateway/virtual-mcp-server#virtual-mcp-server)
{" "}
### More Updates
* Added support for Snowflake Cortex model provider.
* **Changed** In MCP Server integration, transport has been added as a required field. Please update all your MCP Server integrations.
### Release instructions
* Update `truefoundry` helm chart version to `0.94.5`.
## New: Token lifecycle in Virtual Account
We have added multiple new lifecycle features in virtual account including auto-rotation, notification, token syncing to secret store, etc. [Read more](https://docs.truefoundry.com/docs/platform/virtual-account-management#virtual-account-lifecycle)
{" "}
### More updates
* Added support for Hashicorp secret manager.
* Authorize MCP Servers using Virtual Account.
* Added support for privilege escalation with tenant admin permissions to Virtual Account.
### Release instructions
* Update `truefoundry` helm chart version to `0.93.1`.
**Bug fixes and improvements (No major changes)**
### Release instructions
* Update `truefoundry` helm chart version to `0.92.2`.
## New: Added tracing for OpenAI `response` APIs
{" "}
### More Updates
* Added `reasoning` content to request logs.
* Fix tool call issue in Strands Agent SDK (tool content array is now supported)
* Support Vertex AI in Gemini CLI proxy. [Read more](https://docs.truefoundry.com/docs/ai-gateway/gemini-cli#gemini-cli)
* Added Support for `service_tier` priority in `responses` API. [Read more](https://platform.openai.com/docs/api-reference/responses/create#responses-create-service_tier)
* Introduced `not in` and `starts with` filter operator in AI Gateway monitoring.
### Release instructions
* Update `truefoundry` helm chart version to `0.91.2`.
## New: Added new integrations with Cerebra, Pangea, Patronus
* Add support for Cerebra model provider. [Read more](https://docs.truefoundry.com/docs/ai-gateway/cerebras)
* Add support for Pangea and Patronus Guardrails. [Read more](https://docs.truefoundry.com/docs/ai-gateway/crowdstrike) (Pangea is now part of CrowdStrike.)
{" "}
### More Updates
* **Deprecating**: In self-hosted model spec, vLLM, TGI, TEI, Infinity, SGLang, or any other OpenAI compatible model servers should use `OpenAI-Compatible` as we will be deprecating them soon.
* Allowed model servers in self-hosted models going forward would be `OpenAI-Compatible`, `Cohere-Rerank-V2`, and `Nemo-retriever`.
### Release instructions
* Update `truefoundry` helm chart version to `0.90.1`.
## New: MCP server UI revamp
You can see tools and try tools from UI itself.
{" "}
### More Updates
1. Added support for batches API in groq
2. New: Guardrail Metrics
3. Guardrail Updates: Default behaviour changed to not block the request on Guardrail rules violation.
4. Added support for cerebras as a model provider
5. Added support for per metadata key based Rate Limit / Budget Limit
6. Added support for image APIs from Bedrock
7. Automated User management and RBAC using SSO. [Read more](https://docs.truefoundry.com/docs/sso#automated-user-management-and-rbac)
### Release instructions
* Update `truefoundry` helm chart version to `0.89.6`.
## New: MCP server metrics
Track all your MCP server metrics across different MCP servers and their tools.
{" "}
### Release instructions
* Update `truefoundry` helm chart version to `0.88.2`.
### Updates
* Added support for OpenAI oss models with VertexAI integration.
* Added support for audio models with OpenAI/Azure-OpenAI integrations.
* Added support for image variations API with OpenAI integration.
### Release instructions
* Update `truefoundry` helm chart version to `0.87.3`.
## New AI Gateway request log view backed by blob storage.
Traces complete ChatCompletion or AgentCompletion request and backed by blob storage to store the data.
{" "}
### More Updates
* Improved reliability of data caching layer in AI Gateway.
* Dynamic code snippet generation - can change `stream`, `prompt`, `inputs`, etc. using AI Playground and get the complete code snippet auto-gererated for same.
### Release instructions
* Update `truefoundry` helm chart version to `0.86.0`.
* Deprecated: `tfy-clickhouse` has been deprecated and will be removed from the stack.
```yaml lines theme={"dark"}
tfy-clickhouse:
enabled: false
```
## Server-side Prompt rendering in AI Gateway Requests
* You can directly pass prompt id/prompt fqn to your request to let the prompt render on server-side.
* No code required to fetch or render the prompt before hand.
{" "}
### More updates
* Added support for AWS Sagemaker models in AI Gateway. [Read more](https://docs.truefoundry.com/docs/ai-gateway/aws-sagemaker)
* Improved error message for Guardrail response.
* Added support for custom CA certs for self-hosted models integration.
### Release instructions
* Update `truefoundry` helm chart version to `0.85.2`.
## `uv` and `poetry` support in `PythonBuild`
Services, Async Services and Jobs now can be built using `uv` and `poetry` using `pyproject.toml` and lock files.
{" "}
### Release instructions
* Update `truefoundry` helm chart version to `0.84.8`.
* Deprecated: `global.existingImagePullSecretName` is deprecated. Please add `global.imagePullSecrets` section for passing image pull secret:
```yaml lines theme={"dark"}
global:
imagePullSecrets:
- name: truefoundry-image-pull-secret
```
## Add support for deleting users from System.
In order to delete decommisioned users, we now support delete user option.
{" "}
### More Updates
* Added Guardrail integration with Fiddler.
### Breaking Changes
#### AI Gateway: OpenAI Base URL Handling
**Current Behavior**: If a base URL is provided without /v1 at the end, the gateway automatically appends /v1.
**Change**: AI Gateway will no longer automatically append /v1 to base URLs.
**Required Action**: Update your custom OpenAI base URLs to explicitly include the API version path (e.g., [https://your-custom-endpoint/v1](https://your-custom-endpoint/v1)).
#### AI Gateway: Google Vertex AI Project ID Source
**Current Behavior**: Project ID is read from the service account JSON if provided, with fallback to the project ID specified in the form field.
**Change**: Project ID will be taken directly from the form field input, ignoring any project ID in the service account JSON.
**Required Action**: Verify that the correct project ID is entered in the project ID form field, especially if you previously relied on the project ID from the service account JSON.
### Release instructions
* Update `truefoundry` helm chart version to `0.82.2`.
## Interactive UI to set AI Gateway configs like rate limit, routing config, budget config
{" "}
### More updates
* Added Guardrail integration with Palo Alto Prisma AIRS. [Read more](https://docs.truefoundry.com/docs/ai-gateway/palo-alto-airs)
* Priority-Based Routing introduced as a new type of load balancing.
* **Deprecating**: Fallback Configuration has been deprecated.
* Retry Support added to load balancing configuration, allowing configurable retries on failures.
### Release instructions
* Update `truefoundry` helm chart version to `0.80.6`.
## New: Add managers to teams
You can now add managers to teams who can add and remove members from the team without tenant admin permissions.
{" "}
### More updates
* Added support for OpenRouter models. [Read more](https://docs.truefoundry.com/docs/ai-gateway/openrouter)
### Release instructions
* Update `truefoundry` helm chart version to `0.79.7`.
**Bug fixes and improvements (No major changes)**
### Release instructions
* Update `truefoundry` helm chart version to `0.78.0`.
**Bug fixes and improvements (No major changes)**
### Release instructions
* Update `truefoundry` helm chart version to `0.77.1`.
**Bug fixes and improvements (No major changes)**
### Release instructions
* Update `truefoundry` helm chart version to `0.76.1`.
## Improvements on Model deployment
* Upgraded vLLM version to 0.10.0.
* Added startup probe for model loading to reduce liveness probe failure.
* Added support for text2text generation models.
* Added support for mxfp4 models (gpt-oss).
### More updates
* AI Gateway Requests and Metrics tab moved under Monitor sidebar.
* Use tfy-secrets to deploy K8s secrets in your cluster for Helm charts. [Read more](https://docs.truefoundry.com/docs/deploy-helm-charts#using-secrets-in-helm-deployments)
* TrueFoundry SDK documentation available [here](https://docs.truefoundry.com/docs/truefoundry_sdk)
### Release instructions
* Update `truefoundry` helm chart version to `0.75.4`.
## New: Security settings - enhanced control over personal access tokens
You can now configure maximum possible expiration time of personal access tokens and limit maximum number of personal access tokens per user across the organization.
{" "}
-
Revamped personal access token page with new UI and better navigation.
* Admins can revoke all PATs for a user at once in case of any security concern.
### Release instructions
* Update `truefoundry` helm chart version to `0.74.2`.
* ServiceAccount Unification: We would be using single default serviceaccount `truefoundry` for all microservices. Add any existing labels or annotations to [`global.serviceAccount`](https://github.com/truefoundry/infra-charts/blob/main/charts/truefoundry/values.yaml#L67)
## Improved: New navigation sidebar
We have revamped the navigation sidebar to make it more intuitive and easier to use.
{" "}
### More updates
* Improved UX for code snippet generation in AI Gateway.
### Release instructions
* Update `truefoundry` helm chart version to `0.73.1`.
## New: AI Gateway playground chat history
You can now see the chat history in the AI Gateway playground. This will help you to easily see the chat history and continue the conversation.
{" "}
### More updates
* We have added support for Enkrypt AI in Guardrails.
{" "}
### Release instructions
* Update `truefoundry` helm chart version to `0.72.4`.
## Improvement: Copy code snippet for AI Gateway with pre-filled token.
You can now copy the code snippet for AI Gateway with pre-filled token. This will help you to easily copy and run the code snippet without having to manually fill the token.
{" "}
### Release instructions
* Update `truefoundry` helm chart version to `0.71.4`.
* Global [`global.config.storageConfiguration`](https://github.com/truefoundry/infra-charts/blob/main/charts/truefoundry/values.yaml#L79) for all applications used to define blob storage configured for control plane.
## New: Easily configure different settings for your organization
{" "}
- Configure
SSO for authentication. We support SAML and OIDC with multiple providers like
Google, Okta, Azure AD, etc. [Read more](https://docs.truefoundry.com/docs/sso)
* Configure different settings for AI features like common tools, troubleshoot,
etc.
### More updates
* Enhanced logs browsing experience in monitoring tab. Smooth scrolling and better navigation to Nearby logs.
## New: Integrate and Use Guardrails in AI Gateway
You can now integrate and use Guardrails in AI Gateway. Use bedrock and openai moderation as direct integrations. For custom guardrails, you can use custom guardrails integrations. [Read more](https://docs.truefoundry.com/docs/ai-gateway/guardrails-overview)
{" "}
* Integrate and manage RBAC for Guardrails at the guardrail group level.
* Configure and enforce input and output guardrails per model, user, or team. - Combine multiple guardrail types (Bedrock, OpenAI Moderation, Custom) for flexible protection.
* View and audit guardrail enforcement in the AI Gateway Playground. - Easily extend with custom guardrails.
### More updates
* New: Add cluster level alerts
### New: Logs Volume
You can now see logs volume in the logs tab. This helps you to understand frequency of logs and ease zooming into specific time range.
### More updates
* AI Gateway: Added support for Rerank models in AWS Bedrock.
* Autopilot: We can now detect issues in k8s Node and automatically fix them either by restarting the node or by draining the node.
### Improvements and Bug fixes
* Support for Troubleshoot in Services/Models. It is a tool that helps you to troubleshoot your services by providing you with a list of possible issues and solutions after analyzing the logs and metrics.
* Enabled free tools like `Web Search`, `Code Execution`, `Sequential Thinking` in AI Gateway Playground
### Improvements and Bug fixes
* Support for Databricks embeddings models
* Support OAuth authentication for Databricks model provider
### Improvements and Bug fixes
* Support `global` region in Google Vertex
* Support integration with Claude code
### New: Integrate and use MCP servers in AI Gateway
You can now integrate and use MCP servers in AI Gateway. Connect to hosted MCP servers or deploy your own MCP servers in the platform. [Read more](https://docs.truefoundry.com/docs/ai-gateway/mcp-overview)
{" "}
* Integrate and manage RBAC for MCP servers at organization level.
* You can now select specific tools from different MCP server in AI Gateway Playground.
* Deploy your own MCP servers with your own custom tools.
* Easily integrate with MCP servers in your applications with example code snippets.
**Bug fixes and improvements (No major changes)**
### Support for Budget Limits in AI Gateway
You can now set a budget limit in your AI Gateway. It sets budgets to a specificed cost per day/month for requests. This will help you to control the cost of your GenAI applications. [Read more](https://docs.truefoundry.com/docs/ai-gateway/budgetlimiting)
{" "}
### More updates
* New: added support for PagerDuty integration as Notification channel. [Read more](https://docs.truefoundry.com/docs/pagerduty-integration)
* New: added support to see diff in manifest with live manifest while applying using GitOps. [Read more](https://docs.truefoundry.com/docs/using-tfy-apply#what-is-show-diff%3F)
### Enhanced views and filters in AI Gateway Metrics
You can now group metrics with View By option to `Model`, `User`, `Team` or any custom `metadata` field.
{" "}
### More updates
* New: added support for Google ADK code snippet in AI Gateway Playground.
* Support for JWT auth for non-exposed services as well
* You can now deploy workloads in nodepools with additional taints - our system will automatically identify the required tolerations and add them to the workload. This will unblock custom use cases where you wish to deploy a workload on a specific os like Windows, etc.
### Revamp AI Gateway Models access & management
{" "}
- You can
now add and manage models in AI Gateway > Models tab" " - Older models present
in Integration will also continue to work, but will be migrated to a new tab. -
You can now select the following permissions for users at the Provider Account
level: - Manage Models - permission to add or edit models in the account - Use
Models - permission to use the models in the account - In integrations like
OpenAI, AWS Bedrock, Vertex, Azure OpenAI, etc, you need only to configure the
API Key at the account level, while for Azure Foundry, you can still configure
the auth and endpoint per model within the same account - In Virtual Account,
you can now give a complete provider account as well as individual models
access.
### More updates
* New: Cost for AI gateway models: We automatically populate publicly available cost for most of the models while keeping it flexible for you to add your custom value.
* New: You can now switch between Assistant and User role while adding a message in AI Gateway Playground. This will help you experiment and save useful prompts.
* New: We have introduced Alerts tab for all applications to allow you set alerts and notification channel for your application. You can choose our recommended alert rules or create your own custom alert rule using prometheus query. We have support for Slack and Email as notification channels and PagerDuty is coming soon. [Read more](https://docs.truefoundry.com/docs/setup-alerts)
### Revamp sidebar
Revamped navigation sidebar with replacement of few tabs. ML Repo is now referred as Repository, Cluster and Integrations are part of Platform along with Git, Policy & Environment, while Virtual account, Users, Teams, & PAT are part of Access along with Audit logs.
{" "}
### More updates
* Improvements: Faster the image pull time for model server images by parallelizing the pull.
* Improvements: Maintain idempotency on redeployments - when deploying a paused service, it will not resume the service.
* Deprecating: We are deprecating `trigger_on_deploy` from Job manifest and will be removed in the future releases. To continue triggering job while deploying, you can pass `--trigger-on-deploy` flag in the `tfy deploy` command.
* Insights & Recommendations: Storage cost saving with volume recommendation for Notebooks/SSH servers.
### Enhanced Experience: Better UX for model selection and navigation in AI Gateway.
Enhanced UX for model selection and navigation in AI Gateway. You can now list all the models available in the organization and manage them from a single place.
{" "}
### More updates
* New: Support for multimodal inputs added in AI Gateway. You can now upload images and videos to the AI Gateway and use them in your prompts. [Read more](https://docs.truefoundry.com/docs/ai-gateway/chat-completions-multimodal#working-with-multi-modal)
* Bug fixes & Improvements: Fixes in error handling for chat requests and return user-friendly error messages.
### New Feature: Ease out process to setup standard policies using pre-defined templates
We've introduced pre-defined templates for standard policies. This makes it easier to setup policies for common use cases. [Read more](https://docs.truefoundry.com/docs/applying-custom-policies#creating-a-policy)
{" "}
### More updates
* New: Access AI Gateway using Langchain class. Syntax available in code snippet.
### New Feature: Support for Nvidia NIM LLM models and Nemo retriever
We've introduced support for deployment of Nvidia NIM LLM models and Nemo retriever.
{" "}
### More updates
* New: Access AI Gateway using Langchain class. Syntax available in code snippet.
### New Feature: Latency Based Routing in AI Gateway
We've introduced a new feature in the AI Gateway that allows you to route requests based on latency. This is a great way to ensure that your requests are routed to the fastest model available, which can help improve the performance of your applications.
{" "}
### More updates
* New: Added support for Workflows and added username and previous manifest in the policy context. [Read more](https://docs.truefoundry.com/docs/applying-custom-policies#enhancing-policies-with-more-context)
* New: Export LLM Playground metrics to CSV. You can now export your LLM Playground metrics as a handy CSV file. It's perfect for bringing into your favorite analytics tools and diving deeper into your data.
* Deprecating: Changed in Kustomize patch in deployment spec. [Read more](https://docs.truefoundry.com/docs/kustomize)
### New Deployment Deletion Status
We've introduced a new status indicator to show when a deployment is in the process of being deleted. Once the deletion is complete, you'll receive a notification confirming its success. If the deletion fails, the status will update to deletion\_failed, along with a message explaining the reason for the failure.
{" "}
### More updates
* Support for non-OpenAI models from Azure on per API basis.
* Removing mandate to pass a "valid" model name is request. You can now do full header based routing. \[ just need to comply with openai standards]
* Support for Responses API \[Beta]. You can now use codium in your terminal via TrueFoundry LLM Gateway
### Gateway Metrics Just Got a Big Upgrade! ๐
We've given Gateway metrics a full makeover โ and it's better than ever! In addition to the metrics you already know and love, you can now explore brand new insights like Request Latency, Requests per Second (RPS), Time to First Token, and Inter-Token Latency. More visibility = more power!
{" "}
But wait, there's more! You now have dedicated views for User Activity and Model
Usage, making it super easy to track input/output tokens, total requests, and total
cost per user and model.
{" "}
And yes โ we've got your config metrics covered too! TrueFoundry Gateway continues
to support settings like rate limits, fallbacks, and load balancing. Now, you can
actually see which configs were applied to requests over time, complete with clear
visuals and data.
In short: more clarity, better control, and a smoother experience! ๐
### Finetuning Just Got Smarter โ Say Hello to Dora!
We're excited to share that finetuning now supports Dora by default! Dora is a big step up from LoRA โ offering improved performance that gets you much closer to full finetuning, without the extra complexity.
It's faster, smarter, and more efficient โ what's not to love?
๐ Learn more about Dora and how to get started [here](https://developer.nvidia.com/blog/introducing-dora-a-high-performing-alternative-to-lora-for-fine-tuning/).
{" "}
### LLM Deployment Just Got a Boost with TRT-LLM + NVIDIA Triton!
Great news โ you can now deploy LLM models using the TRT-LLM backend with the NVIDIA Triton Inference Server!
We've got you covered with prebuilt engines for Llama models, so you can get started right away. Have another model in mind? No problem โ you can also request custom engines for any model of your choice!
Faster inference, smoother deployment โ let's go! ๐ฅ
{" "}
### Improved Retry Information in Workflows
We've given the info panel a fresh new lookโfor both map and non-map tasks! Now, whenever a task gets retried, you can simply expand the row to dive into all the details. See the retry history, track the duration(for non-map tasks), and easily visualize logs, events, and metrics for each retry attempt.
It's all right there, just a click awayโcleaner, clearer, and way more insightful!
### Auto-pilot insights on cost savings and reliability fixes
Exciting update! ๐ We've added two new metrics to help you easily spot the amazing impact of autopilot! Head over to the audit logs page, switch to the autopilot filter, and you'll be able to see the total cost saved and the number of reliability issues fixed by autopilot in your chosen time range. How cool is that?
Want to enable autopilot too? It's super simple! Just go to your cluster details view to enable autopilot for all deployments within the cluster, or visit the specific deployment page to turn it on for individual deployments. Enjoy the benefits! ๐๐
And here's a fun tidbitโon our internal dev setup, autopilot saved us an amazing \$2590 and fixed 470 reliability issues!
{" "}
### Other Features, Fixes & Improvements:
* Search functionality added to all integration select dropdowns
* Moved readme tab to the beginning for SSH server details page for improved discoverability
* Minor Bug fixes and UI/UX improvements
### Setup Custom OAuth for Service Deployment
Great news! ๐ TrueFoundry now makes it super easy to integrate custom JWT authentication, giving you the ability to set up JWT-based authentication using JWKS. Once you've added your custom integration, you'll be able to use it right in your deployment settings for endpoint login and authentication. Plus, it supports a variety of providers like Google, Okta, AzureAD, Cognito, and many more โ including TrueFoundry! ๐
{" "}
### Filter deployments by Auto-pilot Recommendations
This was a highly requested functionality. Now you will be able to filter all deployments based on if they have any recommendations by auto-pilot.
{" "}
### Support for fractional GPU in On-Prem clusters
This for our enterprise clients. If you setup on-prem clusters then now you can enjoy the benefits of fractional GPUs!
{" "}
### Other Features, Fixes & Improvements:
* Added new menu items to simplify creation and updation of model versions
* Minor Bug fixes and UI/UX improvements
### Audit Logs
As an admin, you can now monitor all user and virtual account activity across the platform. You'll be able to view the specific actions performed, such as "Create Deployment" or "Start Notebook," along with detailed metadata, including the associated resource and the user who triggered each action.
{" "}
### Other Features, Fixes & Improvements:
* Workflow node enhancement for map nodes โ You can now view the status of underlying map tasks directly within the map node, without needing to open the detailed view.
* On LLM Gateway v0.27.0, the rate limit config now supports virtualaccount instead of serviceaccount under subjects. To reduce the risk during the upgrade:
* Before upgrade, We can add new subects with virtualaccountwhere ever serivceaccount.
* Complete the upgrade
* After the upgrade, remove sericeaccount subjects.
* Minor Bug fixes and UI/UX improvements
### Automated Upgrades for Infrastructure Add-ons.
Staying up to date just got a whole lot easier. We're rolling out automated upgrades for infrastructure add-on components like tfy-agent, argo, istio etc, ensuring your stack is always running the latest compatible versions โwithout the manual hassle. Whenever a new stable release drops, we'll handle the upgrade seamlessly, so you can focus on shipping instead of maintaining.
Of course, we're not just throwing updates over the fence. Our system checks for compatibility before rolling anything out, minimising disruptions and keeping things smooth. You get the latest features and security patches without lifting a finger. Set it, forget it, and let your infra take care of itself.
To enable this for your cluster simply visit the cluster drawer and enable "Auto-pilot" for add-ons.
{" "}
### Other Features, Fixes & Improvements:
* Enhancements to autopilot: Added recommendations for CPU throttling, capacity type selection based on environment, and a volume size fix for Prometheus/Loki.
* LLM Gateway: Introduced support for real-time models.
* Minor Bug fixes and UI/UX improvements
### New Features & Improvements:
* Added functionality to edit configuration of workflows from UI
* Support for reranker models in playground
* Pagination support in teams
* Added version field in manifest for artifact
### Bug fixes:
* Minor Bug fixes and UI/UX improvements