apunkt/MetaGPT
1
0
Fork 0
mirror of https://github.com/FoundationAgents/MetaGPT.git synced 2026-06-20 15:38:09 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge pull request #1172 from seehi/feat-rag-embedding

Browse source 
Make RAG embedding configurable and add gpt-4-turbo in token_counter.
This commit is contained in:
Alexander Wu 2024-04-10 15:59:31 +08:00 • committed by GitHub
commit 63ca5452bc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 268 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

10
config/config2.example.yaml
View file

@ -13,6 +13,16 @@ llm:
# - gpt-4 8k: "gpt-4"
# See for more: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/
# RAG Embedding.
# For backward compatibility, if the embedding is not set and the llm's api_type is either openai or azure, the llm's config will be used.
embedding:
api_type: "" # openai / azure / gemini / ollama etc. Check EmbeddingType for more options.
base_url: ""
api_key: ""
model: ""
api_version: ""
embed_batch_size: 100
repair_llm_output: true # when the output is not a valid json, try to repair it
proxy: "YOUR_PROXY" # for tools like requests, playwright, selenium, etc.