> ## Documentation Index > Fetch the complete documentation index at: https://docs.withwhile.com/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > Install with `uv add whileai`; import as `import whileai as wai`. > Run the offline path first (`simulator=False`, `wai.seeded_agent`, a callable judge); no key is needed for it. > Report every pass rate with its interval and n, as `scored.pass_at` prints it. # Integrations > Every model API, trainer, GPU provider, data source and judge the SDK talks to, with the one line that connects each and the page that shows it running.
OpenAI OpenAI Anthropic Anthropic Fireworks Fireworks Amazon Bedrock Amazon Bedrock vLLM vLLM Ollama Ollama Hugging Face and TRL Hugging Face and TRL Prime Intellect and verifiers Prime Intellect and verifiers Modal Modal OpenTelemetry OpenTelemetry
The SDK sits between your agent and your trainer. Everything below is a string or one call; keys stay in your environment and never reach While. ## Models the agent runs on The agent, the situation writer and the simulated person take the same spec or backend object. [Connect your agent](/get-started/connect-your-agent) shows each one in a run. | Provider | How | Key | | ---------------------------------------------------------- | ------------------------------------------------------------------------------- | ----------------------------------------------------------- | | OpenAI | `wai.OpenAI("gpt-4.1-mini")` or `"openai:"` | `OPENAI_API_KEY`; `OPENAI_BASE_URL` for a compatible server | | Anthropic | `wai.Anthropic("claude-haiku-4-5")` or `"anthropic:"` | `ANTHROPIC_API_KEY` | | Fireworks | `wai.Fireworks("accounts/fireworks/models/qwen3-4b")` or `"fireworks:"` | `FIREWORKS_API_KEY` | | Amazon Bedrock | `wai.models.Bedrock(model_id, region=)` or `"bedrock:[@]"` | `AWS_BEARER_TOKEN_BEDROCK`, else AWS credentials | | vLLM, SGLang, TGI, LM Studio, any OpenAI-compatible server | `wai.Endpoint(model, url="http://localhost:8000/v1")` or `"vllm:@"` | `VLLM_API_KEY` when the server wants one | | Ollama | `wai.Ollama("llama3")` or `"ollama:"` | none | | The model While hosts | `wai.Hosted()`, the default when nothing is configured | `whileai login` | | Your own code | `my_agent(message) -> {"steps": [...], "final_text": "..."}` | yours | ## Judges | Judge | How | Page | | --------------- | ---------------------------------------------------------------------------- | ------------------------------------------- | | Any model above | `wai.Judge(rubric=..., model=wai.OpenAI("gpt-4.1"))` | [Evals](/evals) | | TypeSafe Jev | `"typesafe:"` as the judge spec: one probability per verdict | [Overview](/reference/overview) | | A verifier | `wai.verify.MathEqual()`, `wai.verify.CodeExec(tests=...)`, or your function | [Verifiers](/recipes/01-simulate/verifiers) | ## Training Rows leave the SDK in the shape each trainer reads, with the tool-call round trip checked for that shape. | Trainer | How | Page | | ----------------------------------------------- | ------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------- | | TRL (`SFTTrainer`, `DPOTrainer`, `GRPOTrainer`) | `select(mode="sft").export("train.jsonl", format="trl")`; `wai.HackMonitor` inside the loop | [SFT](/recipes/04-train/sft), [DPO](/recipes/04-train/dpo), [GRPO](/recipes/04-train/grpo) | | Fireworks managed training and serving | `export(..., format="fireworks")`, then `firectl sftj create` and a deployment | [Train on Fireworks](/recipes/04-train/fireworks) | | prime-rl and verifiers on Prime Intellect | `wai.prime_rl_config(...)` writes the run; `export_environment` writes the environment | [prime-rl](/recipes/04-train/prime-rl), [Prime Intellect RL](/recipes/03-select/prime-intellect-rl) | | Modal | the training recipes run there on your account, one A10G | [SFT](/recipes/04-train/sft), [Text-to-SQL](/recipes/04-train/text-to-sql) | | While hosted GPUs | `wai.train(...)`, then `wai.serve(...)` gives back an OpenAI-compatible endpoint | [Hosted loop](/recipes/04-train/hosted-loop) | ## Data in and out | Source or destination | How | Page | | ------------------------ | --------------------------------------------------------------------------------------------------------- | ----------------------------------------------------- | | OpenTelemetry traces | `wai.simulations.rows_from_otel(batch)`, then `simulate(..., traces=rows)` | [Connect your agent](/get-started/connect-your-agent) | | Your own traces as JSONL | `simulate(..., traces="traces.jsonl")` | [Connect your agent](/get-started/connect-your-agent) | | Hugging Face Hub | `export(..., push_to="me/my-set")` for datasets, `wai.hub.push("out/adapter", "me/my-lora")` for adapters | [Hugging Face](/recipes/05-export/hugging-face) | | The While platform | `push`, `train`, `serve`, and the experiments page that tracks every run | [Platform](/platform) | Something you use is not here? [Open an issue](https://github.com/whilehq/whileai-sdk/issues/new) with the provider and the call you expected.