> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# August 2024

> New Releases, Enhancements, + Changes

## What's New

August 23, 2024

#### Create Spaces Programmatically

Users can now create spaces programmatically with graphQL. [Learn more →](/docs/ax/graphql-reference/apis/admin-api)

#### Online Evals Update

We've added support for [three new LLM integrations for Online Tasks](/docs/ax/evaluate/run-evals-on-traces): Azure OpenAI, Bedrock, and Vertex / Gemini.

#### Event Based Snowflake Jobs

Users can now trigger Snowflake queries using graphQL. [Learn more →](/docs/ax/graphql-reference/apis/table-importer-api#event-based-table-import-jobs)

#### Auto Instrumentation

August 8, 2024

Automatically collect traces from an expanded set of frameworks and libraries.

* [Haystack](/docs/ax/integrations/python-agent-frameworks/haystack/haystack-tracing)

* [LiteLLM](/docs/ax/integrations/llm-providers/litellm/litellm-tracing)

* [CrewAI](/docs/ax/integrations/python-agent-frameworks/crewai/crewai-tracing)

* [Prompt Flow](/docs/ax/integrations/platforms/prompt-flow/prompt-flow-tracing)

* [Groq](/docs/ax/integrations/llm-providers/groq/groq-tracing)

Arize natively supports collecting traces generated via OpenInference automatic instrumentation. View all the supported instrumentations [here](/docs/ax/integrations).

## Enhancements

August 23, 2024

#### Python SDK v7.20.1

* Enable delayed tags for stream logging

* Experiment eval metadata

* Ingest data to Arize using `space_id`

Learn about Python SDK fixes and improvements [here](https://pypi.org/project/arize/).

#### Python SDK v7.19.0

August 8, 2024

* Perform CRUD operations on datasets

* Create experiments on said datasets

Learn about Python SDK fixes and improvements [here](https://pypi.org/project/arize/).

### 📚 New Content

🪡 [How To Trace Your Haystack LLM App](https://arize.com/blog/trace-your-haystack-application-with-phoenix/)

🦙 [LlamaIndex Workflows](https://arize.com/blog/llamaindex-workflows-a-new-way-to-build-cyclical-agents/): Navigating a New Way To Build Cyclical agents

🚧 [Types of LLM Guardrails](https://arize.com/blog-course/llm-guardrails-types-of-guards/)

✋ How To Use [Annotations for Human Feedback](https://arize.com/blog/how-to-use-annotations-to-collect-human-feedback-on-your-llm-application/)

🧑‍⚖️ [Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges](https://arize.com/blog/judging-the-judges-llm-as-a-judge/)

🦙 Breaking Down [Llama 3](https://arize.com/blog/breaking-down-meta-llama-3/)

✨ [How Flipkart Leverages Generative AI for 600 Million Users](https://arize.com/blog/how-flipkart-leverages-generative-ai-for-600-million-users/)

🏥 [Atropos Health](https://arize.com/blog/how-atropos-health-accelerates-research-with-llm-observability/): Leveraging LLM Observability

▶️ [Prompt Playground](https://arize.com/resource/prompt-playground/)

▶️ [Online LLM Evaluations](https://arize.com/resource/online-llm-evaluations/)

▶️ [LLM Token Counter](https://arize.com/resource/llm-token-counting/)

🎛️ [LLM Instrumentation](https://arize.com/blog/different-ways-to-instrument-your-llm-application/): How To

🚧 [LLM Guardrails](https://arize.com/blog-course/llm-guardrails-protecting-your-ai-application/): How To Protect Your LLM Application, Including from Itself

✨ [Text To SQL: Evaluating SQL Gen with LLM as a Judge](https://arize.com/blog/text-to-sql-evaluating-sql-generation-with-llm-as-a-judge/)

🤖 [How To Build an Agent](https://arize.com/blog/developing-copilot-what-ai-engineers-can-learn-from-our-experience-building-an-ai-assistant/): Lessons Learned with Arize Copilot