Über LiteLLM
Rufen Sie alle LLM APIs im OpenAI-Format auf [Bedrock, Huggingface, VertexAI, TogetherAI, Azure, OpenAI, Groq etc.]
Funktionen
- Übersetzt Eingaben in die
completion
,embedding
undimage_generation
Endpunkte des Anbieters - Konsistente Ausgabe, Textantworten sind immer unter
['choices'][0]['message']['content']
verfügbar - Wiederholungs-/Fallback-Logik über mehrere Deployments (z.B. Azure/OpenAI) - Router
- Festlegen von Budgets & Ratelimits pro Projekt, API-Schlüssel, Modell LiteLLM Proxy Server (LLM Gateway)
Umgebungsvariablen
Umgebungsvariablen anzeigen
- PROJECT
- litellm
- DOMAIN
- stack.localhost
- LITELLM_MASTER_KEY
- "sk-1234" # Your master key for the proxy server. Can use this to send /chat/completion requests etc
- LITELLM_SALT_KEY
- "sk-XXXXXXXX" # Can NOT CHANGE THIS ONCE SET - It is used to encrypt/decrypt credentials stored in DB. If value of 'LITELLM_SALT_KEY' changes your models cannot be retrieved from DB
- OPENAI_API_KEY
- ""
- OPENAI_API_BASE
- ""
- COHERE_API_KEY
- ""
- OR_SITE_URL
- ""
- OR_APP_NAME
- "LiteLLM Example app"
- OR_API_KEY
- ""
- AZURE_API_BASE
- ""
- AZURE_API_VERSION
- ""
- AZURE_API_KEY
- ""
- REPLICATE_API_KEY
- ""
- REPLICATE_API_TOKEN
- ""
- ANTHROPIC_API_KEY
- ""
- INFISICAL_TOKEN
- ""