LlamaIndex Llms Integration: Litellm
Installation
-
Install the required Python packages:
%pip install llama-index-llms-litellm !pip install llama-index
Usage
Import Required Libraries
import os
from llama_index.llms.litellm import LiteLLM
from llama_index.core.llms import ChatMessage
Set Up Environment Variables
Set your API keys as environment variables:
os.environ["OPENAI_API_KEY"] = "your-api-key"
os.environ["COHERE_API_KEY"] = "your-api-key"
Example: OpenAI Call
To interact with the OpenAI model:
message = ChatMessage(role="user", content="Hey! how's it going?")
llm = LiteLLM("gpt-3.5-turbo")
chat_response = llm.chat([message])
print(chat_response)
Example: Cohere Call
To interact with the Cohere model:
llm = LiteLLM("command-nightly")
chat_response = llm.chat([message])
print(chat_response)
Example: Chat with System Message
To have a chat with a system role:
messages = [
ChatMessage(
role="system", content="You are a pirate with a colorful personality"
),
ChatMessage(role="user", content="Tell me a story"),
]
resp = LiteLLM("gpt-3.5-turbo").chat(messages)
print(resp)
Streaming Responses
To use the streaming feature with stream_complete:
llm = LiteLLM("gpt-3.5-turbo")
resp = llm.stream_complete("Paul Graham is ")
for r in resp:
print(r.delta, end="")
Streaming Chat Example
To stream chat messages:
llm = LiteLLM("gpt-3.5-turbo")
resp = llm.stream_chat(messages)
for r in resp:
print(r.delta, end="")
Asynchronous Example
For asynchronous calls, use:
llm = LiteLLM("gpt-3.5-turbo")
resp = await llm.acomplete("Paul Graham is ")
print(resp)
LLM Implementation example
Metadata
Release files for llama-index-llms-litellm 0.8.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| llama_index_llms_litellm-0.8.0.tar.gz | 10.9 kB | Without provenance | Details for llama_index_llms_litellm-0.8.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| llama_index_llms_litellm-0.8.0-py3-none-any.whl | Python 3 | none | any | Details for llama_index_llms_litellm-0.8.0-py3-none-any.whl |
Total release size: 22.1 kB
Release files / llama_index_llms_litellm-0.8.0.tar.gz
| Download URL | llama_index_llms_litellm-0.8.0.tar.gz |
|---|---|
| Size | 10.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8d1d6ee301e43c5cf00aea43b06b3b4d1509fe63693659175921a9f68b5c74db
|
|
BLAKE2b-256 checksum How to use checksums |
737e5cf3a1865adc58b93323a0dcaac5eea50444723c097ad1d438253b54dc36
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / llama_index_llms_litellm-0.8.0-py3-none-any.whl
| Download URL | llama_index_llms_litellm-0.8.0-py3-none-any.whl |
|---|---|
| Size | 11.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b0087bc5bfe3b99f7b1624c2ce4c4a067ebbe09618a1a3d783e4ef384fd6c233
|
|
BLAKE2b-256 checksum How to use checksums |
0b8a5a08690384e148c5289a22d9a08eb1e2bb5f5b3d00ce5249cdb9b4bbb9a1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.12.7 {"installer":{"name":"uv","version":"0.12.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for llama-index-llms-litellm 0.8.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.