Skip to main content

llama-index llms dashscope integration

Project description

LlamaIndex Llms Integration: Dashscope

Installation

  1. Install the required Python package:

    pip install llama-index-llms-dashscope
    
  2. Set the DashScope API key as an environment variable:

    export DASHSCOPE_API_KEY=YOUR_DASHSCOPE_API_KEY
    

    Alternatively, you can set it in your Python script:

    import os
    
    os.environ["DASHSCOPE_API_KEY"] = "YOUR_DASHSCOPE_API_KEY"
    

Usage

Basic Recipe Generation

To generate a basic vanilla cake recipe:

from llama_index.llms.dashscope import DashScope, DashScopeGenerationModels

# Initialize DashScope object
dashscope_llm = DashScope(model_name=DashScopeGenerationModels.QWEN_MAX)

# Generate a vanilla cake recipe
resp = dashscope_llm.complete("How to make cake?")
print(resp)

Streaming Recipe Responses

For real-time streamed responses:

responses = dashscope_llm.stream_complete("How to make cake?")
for response in responses:
    print(response.delta, end="")

Multi-Round Conversation

To have a conversation with the assistant and ask for a sugar-free cake recipe:

from llama_index.core.base.llms.types import MessageRole, ChatMessage

messages = [
    ChatMessage(
        role=MessageRole.SYSTEM, content="You are a helpful assistant."
    ),
    ChatMessage(role=MessageRole.USER, content="How to make cake?"),
]

# Get first round response
resp = dashscope_llm.chat(messages)
print(resp)

# Continue conversation
messages.append(
    ChatMessage(role=MessageRole.ASSISTANT, content=resp.message.content)
)
messages.append(
    ChatMessage(role=MessageRole.USER, content="How to make it without sugar?")
)

# Get second round response
resp = dashscope_llm.chat(messages)
print(resp)

Handling Sugar-Free Recipes

For sugar-free cake recipes using honey as a sweetener:

resp = dashscope_llm.complete("How to make cake without sugar?")
print(resp)

LLM Implementation example

https://docs.llamaindex.ai/en/stable/examples/llm/dashscope/

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llama_index_llms_dashscope-0.2.5.tar.gz (5.0 kB view details)

Uploaded Source

Built Distribution

File details

Details for the file llama_index_llms_dashscope-0.2.5.tar.gz.

File metadata

  • Download URL: llama_index_llms_dashscope-0.2.5.tar.gz
  • Upload date:
  • Size: 5.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.12 Linux/6.5.0-1025-azure

File hashes

Hashes for llama_index_llms_dashscope-0.2.5.tar.gz
Algorithm Hash digest
SHA256 5e5f11691eb550239a425898428e9291a9201dce5829298ce372a869f5ff134f
MD5 e083b565b9e9cc449b96152a2f2f64d0
BLAKE2b-256 514df6bea7fb986c9bc10e93b35d9c2a6e1b531aeaeb7cdc5aadf0886dce3eda

See more details on using hashes here.

File details

Details for the file llama_index_llms_dashscope-0.2.5-py3-none-any.whl.

File metadata

File hashes

Hashes for llama_index_llms_dashscope-0.2.5-py3-none-any.whl
Algorithm Hash digest
SHA256 7f14c393e8ddcf248605d0a4ce517211181e9f4a743553b039d2460282fe6016
MD5 fe54e1bc774c27cf9fa51a5db4f519dc
BLAKE2b-256 64f665b9bda69ec3dd609cc0b9090ab8984d6343de833c9cbd3a947d0873ccab

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page