From ebe0618dee4be7a3dc386f7cff4ff0ac221b8877 Mon Sep 17 00:00:00 2001 From: Sergey Kozyrenko Date: Sat, 20 Jun 2026 07:30:06 +0700 Subject: [PATCH] docs: add Atlas Cloud as a custom OpenAI-compatible provider (refs #332) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reworks PR #332 to follow the repo's provider-doc convention instead of its README-marketing form: - add examples/configs/atlas.provider.yml, modeled on the existing aggregator example configs (deepinfra/openrouter/novita) - list Atlas Cloud in the README aggregators line - LLM_SERVER_PROVIDER left EMPTY for direct access — it is a LiteLLM model-name prefix, and #332 incorrectly recommended `openai`, which would break /models discovery for Atlas's vendor-prefixed model ids Dropped from #332 (not matching any existing aggregator's docs): vendor logo/banner, UTM-tracked links, and the static 59-model table. Co-Authored-By: Claude Opus 4.8 --- README.md | 6 +- examples/configs/atlas.provider.yml | 119 ++++++++++++++++++++++++++++ 2 files changed, 122 insertions(+), 3 deletions(-) create mode 100644 examples/configs/atlas.provider.yml diff --git a/README.md b/README.md index 06d1f4f0..fbf70109 100644 --- a/README.md +++ b/README.md @@ -72,7 +72,7 @@ You can watch the video **PentAGI overview**: - Persistent Storage. All commands and outputs are stored in PostgreSQL with [pgvector](https://hub.docker.com/r/vxcontrol/pgvector) extension. - Scalable Architecture. Microservices-based design supporting horizontal scaling. - Self-Hosted Solution. Complete control over your deployment and data. -- Flexible Authentication. Support for 10+ LLM providers ([OpenAI](https://platform.openai.com/), [Anthropic](https://www.anthropic.com/), [Google AI/Gemini](https://ai.google.dev/), [AWS Bedrock](https://aws.amazon.com/bedrock/), [Ollama](https://ollama.com/), [DeepSeek](https://www.deepseek.com/en/), [GLM](https://z.ai/), [Kimi](https://platform.moonshot.ai/), [Qwen](https://www.alibabacloud.com/en/), Custom) plus aggregators ([OpenRouter](https://openrouter.ai/), [DeepInfra](https://deepinfra.com/)). For production local deployments, see our [vLLM + Qwen3.5-27B-FP8 guide](examples/guides/vllm-qwen35-27b-fp8.md). +- Flexible Authentication. Support for 10+ LLM providers ([OpenAI](https://platform.openai.com/), [Anthropic](https://www.anthropic.com/), [Google AI/Gemini](https://ai.google.dev/), [AWS Bedrock](https://aws.amazon.com/bedrock/), [Ollama](https://ollama.com/), [DeepSeek](https://www.deepseek.com/en/), [GLM](https://z.ai/), [Kimi](https://platform.moonshot.ai/), [Qwen](https://www.alibabacloud.com/en/), Custom) plus aggregators ([OpenRouter](https://openrouter.ai/), [DeepInfra](https://deepinfra.com/), [Atlas Cloud](https://www.atlascloud.ai/)). For production local deployments, see our [vLLM + Qwen3.5-27B-FP8 guide](examples/guides/vllm-qwen35-27b-fp8.md). - API Token Authentication. Secure Bearer token system for programmatic access to REST and GraphQL APIs. - Quick Deployment. Easy setup through [Docker Compose](https://docs.docker.com/compose/) with comprehensive environment configuration. @@ -3000,10 +3000,10 @@ docker exec -it pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/ollam To use these configurations, your `.env` file only needs to contain: ``` -LLM_SERVER_URL=https://openrouter.ai/api/v1 # or https://api.deepinfra.com/v1/openai or https://api.openai.com/v1 or https://api.novita.ai/openai +LLM_SERVER_URL=https://openrouter.ai/api/v1 # or https://api.deepinfra.com/v1/openai or https://api.openai.com/v1 or https://api.novita.ai/openai or https://api.atlascloud.ai/v1 LLM_SERVER_KEY=your_api_key LLM_SERVER_MODEL= # Leave empty, as models are specified in the config -LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml # or deepinfra.provider.ymll or custom-openai.provider.yml or novita.provider.yml +LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml # or deepinfra.provider.yml or custom-openai.provider.yml or novita.provider.yml or atlas.provider.yml LLM_SERVER_PROVIDER= # Provider name for LiteLLM proxy (e.g., openrouter, deepseek, moonshot, novita) LLM_SERVER_LEGACY_REASONING=false # Controls reasoning format, for OpenAI must be true (default: false) LLM_SERVER_PRESERVE_REASONING=false # Preserve reasoning content in multi-turn conversations (required by Moonshot, default: false) diff --git a/examples/configs/atlas.provider.yml b/examples/configs/atlas.provider.yml new file mode 100644 index 00000000..eca5e52e --- /dev/null +++ b/examples/configs/atlas.provider.yml @@ -0,0 +1,119 @@ +simple: + model: "Qwen/Qwen3-Next-80B-A3B-Instruct" + temperature: 0.7 + top_p: 0.95 + n: 1 + max_tokens: 4000 + price: + input: 0.14 + output: 1.4 + +simple_json: + model: "Qwen/Qwen3-Next-80B-A3B-Instruct" + temperature: 0.7 + top_p: 1.0 + n: 1 + max_tokens: 4000 + json: true + price: + input: 0.14 + output: 1.4 + +primary_agent: + model: "moonshotai/kimi-k2.6" + temperature: 1.0 + n: 1 + max_tokens: 6000 + price: + input: 0.4 + output: 2.0 + +assistant: + model: "moonshotai/kimi-k2.6" + temperature: 1.0 + n: 1 + max_tokens: 8000 + price: + input: 0.4 + output: 2.0 + +generator: + model: "deepseek-ai/deepseek-v4-pro" + temperature: 1.0 + n: 1 + max_tokens: 8000 + price: + input: 1.0 + output: 3.0 + +refiner: + model: "deepseek-ai/deepseek-r1-0528" + temperature: 1.0 + n: 1 + max_tokens: 8000 + price: + input: 1.0 + output: 3.0 + +adviser: + model: "deepseek-ai/deepseek-v4-pro" + temperature: 1.0 + n: 1 + max_tokens: 4000 + price: + input: 1.0 + output: 3.0 + +reflector: + model: "Qwen/Qwen3-Next-80B-A3B-Instruct" + temperature: 1.0 + n: 1 + max_tokens: 4000 + price: + input: 0.14 + output: 1.4 + +searcher: + model: "qwen/qwen3-32b" + temperature: 1.0 + n: 1 + max_tokens: 4000 + price: + input: 0.1 + output: 0.3 + +enricher: + model: "qwen/qwen3-32b" + temperature: 1.0 + n: 1 + max_tokens: 6000 + price: + input: 0.1 + output: 0.3 + +coder: + model: "anthropic/claude-sonnet-4.6" + temperature: 1.0 + n: 1 + max_tokens: 8000 + price: + input: 3.3 + output: 16.5 + +installer: + model: "google/gemini-3.5-flash" + temperature: 1.0 + n: 1 + max_tokens: 6000 + price: + input: 0.3 + output: 2.5 + +pentester: + model: "moonshotai/kimi-k2.6" + temperature: 1.0 + n: 1 + max_tokens: 6000 + price: + input: 0.4 + output: 2.0