fix: support other regions for aws s3 storage (#11340)

44faac91 · Vitali Avagyan · GitHub · ebf757b7 · 44faac91 · 44faac91
Unverified Commit 44faac91 authored 1 year ago by Vitali Avagyan Committed by GitHub 1 year ago
--- a/docs/examples/llm/mymagic.ipynb
+++ b/docs/examples/llm/mymagic.ipynb
@@ -66,6 +66,7 @@
    "    session=\"your-session-name\",  # files should be located in this folder on which batch inference will be run\n",
    "    role_arn=\"your-role-arn\",\n",
    "    system_prompt=\"your-system-prompt\",\n",
+    "    region=\"your-bucket-region\",\n",
    ")"
   ]
  },
@@ -123,6 +124,7 @@
    "        session=\"your-session-name\",  # files should be located in this folder on which batch inference will be run\n",
    "        role_arn=\"your-role-arn\",\n",
    "        system_prompt=\"your-system-prompt\",\n",
+    "        region=\"your-bucket-region\",\n",
    "    )\n",
    "    response = await allm.acomplete(\n",
    "        question=\"your-question\",\n",

 %% Cell type:markdown id: tags:
 # MyMagic AI LLM
 %% Cell type:markdown id: tags:
 ## Introduction
 This notebook demonstrates how to use MyMagicAI for batch inference on massive data stored in cloud buckets. The only enpoints implemented are `complete` and `acomplete` which can work on many use cases including Completion, Summariation and Extraction.
 To use this notebook, you need an API key (Personal Access Token) from MyMagicAI and data stored in cloud buckets.
 Sign up by clicking Get Started at [MyMagicAI's website](https://mymagic.ai/) to get your API key.
 %% Cell type:markdown id: tags:
 ## Setup
 To set up your bucket and grant MyMagic API a secure access to your cloud storage, please visit [MyMagic docs](https://docs.mymagic.ai/) for reference.
 If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙.
 %% Cell type:code id: tags:
 ``` python
 %pip install llama-index-llms-mymagic
 ```
 %% Cell type:code id: tags:
 ``` python
 !pip install llama-index
 ```
 %% Cell type:code id: tags:
 ``` python
 from llama_index.llms.mymagic import MyMagicAI
 ```
 %% Cell type:code id: tags:
 ``` python
 llm = MyMagicAI(
    api_key="your-api-key",
    storage_provider="s3",  # s3, gcs
    bucket_name="your-bucket-name",
    session="your-session-name",  # files should be located in this folder on which batch inference will be run
    role_arn="your-role-arn",
    system_prompt="your-system-prompt",
+    region="your-bucket-region",
 )
 ```
 %% Cell type:code id: tags:
 ``` python
 resp = llm.complete(
    question="your-question",
    model="chhoose-model",  # currently we support mistral7b, llama7b, mixtral8x7b,codellama70b, llama70b, more to come...
    max_tokens=5,  # number of tokens to generate, default is 10
 )
 ```
 %% Cell type:code id: tags:
 ``` python
 # The response indicated that the final output is stored in your bucket or raises an exception if the job failed
 print(resp)
 ```
 %% Cell type:markdown id: tags:
 ## Asynchronous Requests by using `acomplete` endpoint
 For asynchronous operations, use the following approach.
 %% Cell type:code id: tags:
 ``` python
 import asyncio
 ```
 %% Cell type:code id: tags:
 ``` python
 async def main():
    allm = MyMagicAI(
        api_key="your-api-key",
        storage_provider="s3",  # s3, gcs
        bucket_name="your-bucket-name",
        session="your-session-name",  # files should be located in this folder on which batch inference will be run
        role_arn="your-role-arn",
        system_prompt="your-system-prompt",
+        region="your-bucket-region",
    )
    response = await allm.acomplete(
        question="your-question",
        model="chhoose-model",  # currently we support mistral7b, llama7b, mixtral8x7b,codellama70b, llama70b, more to come...
        max_tokens=5,  # number of tokens to generate, default is 10
    )
    print("Async completion response:", response)
 ```
 %% Cell type:code id: tags:
 ``` python
 await main()
 ```

--- a/llama-index-integrations/llms/llama-index-llms-mymagic/llama_index/llms/mymagic/base.py
+++ b/llama-index-integrations/llms/llama-index-llms-mymagic/llama_index/llms/mymagic/base.py
@@ -36,7 +36,7 @@ class MyMagicAI(LLM):
        description="The session to use. This is a subfolder in the bucket where your data is located.",
    )
    role_arn: Optional[str] = Field(
-        None, description="ARN for role assumption in AWS S3"
+        None, description="ARN for role assumption in AWS S3."
    )
    system_prompt: str = Field(
        default="Answer the question based only on the given content. Do not give explanations or examples. Do not continue generating more text after the answer.",
@@ -45,6 +45,9 @@ class MyMagicAI(LLM):
    question_data: Dict[str, Any] = Field(
        default_factory=dict, description="The data to send to the MyMagicAI API."
    )
+    region: Optional[str] = Field(
+        "eu-west-2", description="The region the bucket is in. Only used for AWS S3."
+    )
    def __init__(
        self,
@@ -54,6 +57,7 @@ class MyMagicAI(LLM):
        session: str,
        system_prompt: Optional[str],
        role_arn: Optional[str] = None,
+        region: Optional[str] = None,
        **kwargs: Any,
    ) -> None:
        super().__init__(**kwargs)
@@ -66,6 +70,7 @@ class MyMagicAI(LLM):
            "max_tokens": self.max_tokens,
            "role_arn": role_arn,
            "system_prompt": system_prompt,
+            "region": region,
        }
    @classmethod