wu-sheng commented on code in PR #13745: URL: https://github.com/apache/skywalking/pull/13745#discussion_r2971470397
########## oap-server/server-starter/src/main/resources/gen-ai-config.yml: ########## @@ -0,0 +1,91 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +# This file configures GenAI provider matching rules and estimated pricing. +# Rules define how to map model names to providers and calculate token costs. + +#Here is a example +#- provider: ollama +# # If a model name starts with these strings, it will be mapped to this provider +# prefix-match: +# - ollama +# models: +# - name: ollama +# # --- PRICING CONFIGURATION --- +# # Costs are defined as the price per 1,000,000 (one million) tokens. +# # The currency depends on your system's default setting (e.g., USD or CNY). +# +# # Estimated cost for every 1,000,000 input (prompt) tokens +# input-cost-per-m: 1 +# +# # Estimated cost for every 1,000,000 output (completion) tokens +# output-cost-per-m: 1 + +providers: + - provider: openai + prefix-match: + - gpt + + - provider: anthropic + prefix-match: + - claude + + - provider: gemini + prefix-match: + - gemini + + - provider: mistral + prefix-match: + - mistral- + + - provider: groq + prefix-match: + - llama-3 + + - provider: deepseek + prefix-match: + - deepseek + + - provider: bytedance + prefix-match: + - doubao + + - provider: zhipu_ai + prefix-match: + - glm + + - provider: alibaba + prefix-match: + - qwen + + - provider: tencent + prefix-match: + - hunyuan + + - provider: moonshot + prefix-match: + - kimi + + - provider: minimax + prefix-match: + - minimax + + - provider: ollama + prefix-match: + - ollama Review Comment: ollama is not a model, right? It is just an app to boot Model runtime. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
