From 5eae392dbd4fc789829ac2f47a24614dbc5db5e9 Mon Sep 17 00:00:00 2001 From: sigoden Date: Wed, 1 May 2024 06:01:10 +0800 Subject: refactore: add models for openai-compatible platforms (#471) --- config.example.yaml | 57 ++++++++++++++++------------------------------------- 1 file changed, 17 insertions(+), 40 deletions(-) (limited to 'config.example.yaml') diff --git a/config.example.yaml b/config.example.yaml index 47f644a..ea9e2fa 100644 --- a/config.example.yaml +++ b/config.example.yaml @@ -70,6 +70,7 @@ clients: # See https://docs.mistral.ai/ - type: openai-compatible name: mistral + api_base: https://api.mistral.ai/v1 api_key: xxx # ENV: {client}_API_KEY # See https://docs.cohere.com/docs/the-cohere-platform @@ -77,11 +78,15 @@ clients: api_key: xxx # ENV: {client}_API_KEY # See https://docs.perplexity.ai/docs/getting-started - - type: perplexity + - type: openai-compatible + name: perplexity + api_base: https://api.perplexity.ai api_key: pplx-xxx # ENV: {client}_API_KEY # See https://console.groq.com/docs/quickstart - - type: groq + - type: openai-compatible + name: groq + api_base: https://api.groq.com/openai/v1 api_key: gsk_xxx # ENV: {client}_API_KEY # See https://github.com/jmorganca/ollama @@ -137,71 +142,43 @@ clients: api_key: sk-xxx # ENV: {client}_API_KEY # See https://platform.moonshot.cn/docs/intro - - type: moonshot + - type: openai-compatible + name: moonshot + api_base: https://api.moonshot.cn/v1 api_key: sk-xxx # ENV: {client}_API_KEY # See https://docs.endpoints.anyscale.com/ - type: openai-compatible name: anyscale + api_base: https://api.endpoints.anyscale.com/v1 api_key: xxx # ENV: {client}_API_KEY - models: - # https://docs.endpoints.anyscale.com/text-generation/query-a-model#select-a-model - - name: meta-llama/Meta-Llama-3-70B-Instruct - max_input_tokens: 8192 - input_price: 1 - output_price: 1 # See https://deepinfra.com/docs - type: openai-compatible name: deepinfra + api_base: https://api.deepinfra.com/v1/openai api_key: xxx # ENV: {client}_API_KEY - models: - # https://deepinfra.com/models - - name: meta-llama/Meta-Llama-3-70B-Instruct - max_input_tokens: 8192 - input_price: 0.59 - output_price: 0.79 # See https://readme.fireworks.ai/docs/quickstart - type: openai-compatible name: fireworks + api_base: https://api.fireworks.ai/inference/v1 api_key: xxx # ENV: {client}_API_KEY - models: - # https://fireworks.ai/models - - name: accounts/fireworks/models/llama-v3-70b-instruct - max_input_tokens: 8192 - input_price: 0.9 - output_price: 0.9 # See https://openrouter.ai/docs#quick-start - type: openai-compatible name: openrouter + api_base: https://openrouter.ai/api/v1 api_key: xxx # ENV: {client}_API_KEY - models: - # https://openrouter.ai/docs#models - - name: meta-llama/llama-3-70b-instruct - max_input_tokens: 8192 - input_price: 0.81 - output_price: 0.81 # See https://octo.ai/docs/getting-started/quickstart - type: openai-compatible name: octoai + api_base: https://text.octoai.run/v1 api_key: xxx # ENV: {client}_API_KEY - models: - # https://octo.ai/docs/getting-started/inference-models - - name: meta-llama-3-70b-instruct - max_input_tokens: 8192 - input_price: 0.86 - output_price: 0.86 # See https://docs.together.ai/docs/quickstart - type: openai-compatible name: together - api_key: xxx # ENV: {client}_API_KEY - models: - # https://docs.together.ai/docs/inference-models - - name: meta-llama/Llama-3-70b-chat-hf - max_input_tokens: 8192 - input_price: 0.9 - output_price: 0.9 \ No newline at end of file + api_base: https://api.together.xyz/v1 + api_key: xxx # ENV: {client}_API_KEY \ No newline at end of file -- cgit v1.2.3