From c91d1ff0aed90e66073f5a2a284cb2d21237eb23 Mon Sep 17 00:00:00 2001 From: xdurawa Date: Wed, 3 Sep 2025 01:34:21 -0400 Subject: [PATCH] Remove documentation changes as requested by reviewers - Reverted README.md to original state - Reverted cognee-starter-kit/README.md to original state - Documentation will be updated separately by maintainers --- README.md | 10 ---------- cognee-starter-kit/README.md | 38 ------------------------------------ 2 files changed, 48 deletions(-) diff --git a/README.md b/README.md index 73c6aa898..e618d5bf9 100644 --- a/README.md +++ b/README.md @@ -125,16 +125,6 @@ os.environ["LLM_API_KEY"] = "YOUR OPENAI_API_KEY" ``` You can also set the variables by creating .env file, using our template. - -**Supported LLM Providers:** OpenAI (default), Anthropic, Gemini, Ollama, AWS Bedrock - -**For AWS Bedrock:** Set `LLM_PROVIDER="bedrock"` and use one of three authentication methods: -- API Key: `LLM_API_KEY="your_bedrock_api_key"` -- AWS Credentials: `AWS_ACCESS_KEY_ID` + `AWS_SECRET_ACCESS_KEY` (+ `AWS_SESSION_TOKEN` if needed) -- AWS Profile: `AWS_PROFILE_NAME="your_profile"` - -Use an [inference profile](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html#API_runtime_InvokeModel_Example_5:~:text=Use%20an%20inference%20profile%20in%20model%20invocation) for the model IDs. This usually means appending `us.*` (or other region) to the model ID (e.g., `us.anthropic.claude-3-5-sonnet-20241022-v2:0`). See [AWS Bedrock models](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html). - To use different LLM providers, for more info check out our documentation diff --git a/cognee-starter-kit/README.md b/cognee-starter-kit/README.md index 5a9369b89..c265e278e 100644 --- a/cognee-starter-kit/README.md +++ b/cognee-starter-kit/README.md @@ -25,14 +25,6 @@ uv sync ## Setup LLM Add environment variables to `.env` file. In case you choose to use OpenAI provider, add just the model and api_key. - -**Supported LLM Providers:** -- OpenAI (default) -- Anthropic -- Gemini -- Ollama -- AWS Bedrock - ``` LLM_PROVIDER="" LLM_MODEL="" @@ -47,36 +39,6 @@ EMBEDDING_API_KEY="" EMBEDDING_API_VERSION="" ``` -**For AWS Bedrock, you have three authentication options:** - -1. **API Key (Bearer Token):** -``` -LLM_PROVIDER="bedrock" -LLM_API_KEY="your_bedrock_api_key" -LLM_MODEL="us.anthropic.claude-3-5-sonnet-20241022-v2:0" -AWS_REGION_NAME="us-east-1" -``` - -2. **AWS Credentials:** -``` -LLM_PROVIDER="bedrock" -LLM_MODEL="us.anthropic.claude-3-5-sonnet-20241022-v2:0" -AWS_ACCESS_KEY_ID="your_aws_access_key" -AWS_SECRET_ACCESS_KEY="your_aws_secret_key" -[if needed] AWS_SESSION_TOKEN="your_session_token" -AWS_REGION_NAME="us-east-1" -``` - -3. **AWS Profile:** -``` -LLM_PROVIDER="bedrock" -LLM_MODEL="us.anthropic.claude-3-5-sonnet-20241022-v2:0" -AWS_PROFILE_NAME="your_aws_profile" -AWS_REGION_NAME="us-east-1" -``` - -**Note:** For Bedrock models, use an [inference profile](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html#API_runtime_InvokeModel_Example_5:~:text=Use%20an%20inference%20profile%20in%20model%20invocation) for `LLM_MODEL`. This usually means appending `us.*` (or other region) to the model ID (e.g., `us.anthropic.claude-3-5-sonnet-20241022-v2:0`). See [AWS Bedrock models](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) for available models. - Activate the Python environment: ``` source .venv/bin/activate