| Name | llama-index-llms-perplexity JSON |
| Version |
0.4.0
JSON |
| download |
| home_page | None |
| Summary | llama-index llms perplexity integration |
| upload_time | 2025-07-30 21:29:25 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | <4.0,>=3.9 |
| license | None |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# LlamaIndex Llms Integration: Perplexity
The Perplexity integration for LlamaIndex allows you to tap into real-time generative search powered by the Perplexity API. This integration supports synchronous and asynchronous chat completions—as well as streaming responses.
## Installation
To install the required packages, run:
```bash
%pip install llama-index-llms-perplexity
!pip install llama-index
```
## Setup
### Import Libraries and Configure API Key
Please refer to the official Perplexity [API documentation](https://docs.perplexity.ai/home) to get started. You can follow the steps outlined [here](https://docs.perplexity.ai/guides/getting-started) to generate your API key.
Import the necessary libraries and set your Perplexity API key:
```python
from llama_index.llms.perplexity import Perplexity
pplx_api_key = "your-perplexity-api-key" # Replace with your actual API key
```
### Initialize the Perplexity LLM
Create an instance of the Perplexity LLM with your API key and desired model settings:
```python
llm = Perplexity(api_key=pplx_api_key, model="sonar-pro", temperature=0.2)
```
## Chat Example
### Sending a Chat Message
You can send a chat message using the `chat` method. Here’s how to do that:
```python
from llama_index.core.llms import ChatMessage
messages_dict = [
{"role": "system", "content": "Be precise and concise."},
{
"role": "user",
"content": "What is the weather like in San Francisco today?",
},
]
messages = [ChatMessage(**msg) for msg in messages_dict]
# Obtain a response from the model
response = llm.chat(messages)
print(response)
```
### Async Chat
For asynchronous conversation processing, use the `achat` method to send messages and await the response:
```python
response = await llm.achat(messages)
print(response)
```
### Stream Chat
For cases where you want to receive a response token by token in real time, use the `stream_chat` method:
```python
resp = llm.stream_chat(messages)
for r in resp:
print(r.delta, end="")
```
### Async Stream Chat
Similarly, for asynchronous streaming, the `astream_chat` method provides a way to process response deltas asynchronously:
```python
resp = await llm.astream_chat(messages)
async for delta in resp:
print(delta.delta, end="")
```
### Tool calling
Perplexity models can easily be wrapped into a llamaindex tool so that it can be called as part of your data processing or conversational workflows. This tool uses real-time generative search powered by Perplexity, and it’s configured with the updated default model ("sonar-pro") and the enable_search_classifier parameter enabled.
Below is an example of how to define and register the tool:
```python
from llama_index.core.tools import FunctionTool
from llama_index.llms.perplexity import Perplexity
from llama_index.core.llms import ChatMessage
def query_perplexity(query: str) -> str:
"""
Queries the Perplexity API via the LlamaIndex integration.
This function instantiates a Perplexity LLM with updated default settings
(using model "sonar-pro" and enabling search classifier so that the API can
intelligently decide if a search is needed), wraps the query into a ChatMessage,
and returns the generated response content.
"""
pplx_api_key = (
"your-perplexity-api-key" # Replace with your actual API key
)
llm = Perplexity(
api_key=pplx_api_key,
model="sonar-pro",
temperature=0.7,
enable_search_classifier=True, # This will determine if the search component is necessary in this particular context
)
messages = [ChatMessage(role="user", content=query)]
response = llm.chat(messages)
return response.message.content
# Create the tool from the query_perplexity function
query_perplexity_tool = FunctionTool.from_defaults(fn=query_perplexity)
```
### LLM Implementation example
https://docs.llamaindex.ai/en/stable/examples/llm/perplexity/
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-llms-perplexity",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": null,
"author_email": "Your Name <you@example.com>",
"download_url": "https://files.pythonhosted.org/packages/9f/9b/da47ff15974f00bbdc3f72957f01daddc0919b0552decfa51c8f4b06e597/llama_index_llms_perplexity-0.4.0.tar.gz",
"platform": null,
"description": "# LlamaIndex Llms Integration: Perplexity\n\nThe Perplexity integration for LlamaIndex allows you to tap into real-time generative search powered by the Perplexity API. This integration supports synchronous and asynchronous chat completions\u2014as well as streaming responses.\n\n## Installation\n\nTo install the required packages, run:\n\n```bash\n%pip install llama-index-llms-perplexity\n!pip install llama-index\n```\n\n## Setup\n\n### Import Libraries and Configure API Key\n\nPlease refer to the official Perplexity [API documentation](https://docs.perplexity.ai/home) to get started. You can follow the steps outlined [here](https://docs.perplexity.ai/guides/getting-started) to generate your API key.\n\nImport the necessary libraries and set your Perplexity API key:\n\n```python\nfrom llama_index.llms.perplexity import Perplexity\n\npplx_api_key = \"your-perplexity-api-key\" # Replace with your actual API key\n```\n\n### Initialize the Perplexity LLM\n\nCreate an instance of the Perplexity LLM with your API key and desired model settings:\n\n```python\nllm = Perplexity(api_key=pplx_api_key, model=\"sonar-pro\", temperature=0.2)\n```\n\n## Chat Example\n\n### Sending a Chat Message\n\nYou can send a chat message using the `chat` method. Here\u2019s how to do that:\n\n```python\nfrom llama_index.core.llms import ChatMessage\n\nmessages_dict = [\n {\"role\": \"system\", \"content\": \"Be precise and concise.\"},\n {\n \"role\": \"user\",\n \"content\": \"What is the weather like in San Francisco today?\",\n },\n]\n\nmessages = [ChatMessage(**msg) for msg in messages_dict]\n\n# Obtain a response from the model\nresponse = llm.chat(messages)\nprint(response)\n```\n\n### Async Chat\n\nFor asynchronous conversation processing, use the `achat` method to send messages and await the response:\n\n```python\nresponse = await llm.achat(messages)\nprint(response)\n```\n\n### Stream Chat\n\nFor cases where you want to receive a response token by token in real time, use the `stream_chat` method:\n\n```python\nresp = llm.stream_chat(messages)\nfor r in resp:\n print(r.delta, end=\"\")\n```\n\n### Async Stream Chat\n\nSimilarly, for asynchronous streaming, the `astream_chat` method provides a way to process response deltas asynchronously:\n\n```python\nresp = await llm.astream_chat(messages)\nasync for delta in resp:\n print(delta.delta, end=\"\")\n```\n\n### Tool calling\n\nPerplexity models can easily be wrapped into a llamaindex tool so that it can be called as part of your data processing or conversational workflows. This tool uses real-time generative search powered by Perplexity, and it\u2019s configured with the updated default model (\"sonar-pro\") and the enable_search_classifier parameter enabled.\n\nBelow is an example of how to define and register the tool:\n\n```python\nfrom llama_index.core.tools import FunctionTool\nfrom llama_index.llms.perplexity import Perplexity\nfrom llama_index.core.llms import ChatMessage\n\n\ndef query_perplexity(query: str) -> str:\n \"\"\"\n Queries the Perplexity API via the LlamaIndex integration.\n\n This function instantiates a Perplexity LLM with updated default settings\n (using model \"sonar-pro\" and enabling search classifier so that the API can\n intelligently decide if a search is needed), wraps the query into a ChatMessage,\n and returns the generated response content.\n \"\"\"\n pplx_api_key = (\n \"your-perplexity-api-key\" # Replace with your actual API key\n )\n\n llm = Perplexity(\n api_key=pplx_api_key,\n model=\"sonar-pro\",\n temperature=0.7,\n enable_search_classifier=True, # This will determine if the search component is necessary in this particular context\n )\n\n messages = [ChatMessage(role=\"user\", content=query)]\n response = llm.chat(messages)\n return response.message.content\n\n\n# Create the tool from the query_perplexity function\nquery_perplexity_tool = FunctionTool.from_defaults(fn=query_perplexity)\n```\n\n### LLM Implementation example\n\nhttps://docs.llamaindex.ai/en/stable/examples/llm/perplexity/\n",
"bugtrack_url": null,
"license": null,
"summary": "llama-index llms perplexity integration",
"version": "0.4.0",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "dc21944b11404dc14382960e42f931bc24020e15a1b90ed1e6097b202d5897fb",
"md5": "cf6fffb18e6c8f900a138e6c0d1d076d",
"sha256": "ea0f5413e19bdcc5eea17e76c044d0e557e8965db6b314259afd6fc9fd55ad46"
},
"downloads": -1,
"filename": "llama_index_llms_perplexity-0.4.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "cf6fffb18e6c8f900a138e6c0d1d076d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 6951,
"upload_time": "2025-07-30T21:29:24",
"upload_time_iso_8601": "2025-07-30T21:29:24.487005Z",
"url": "https://files.pythonhosted.org/packages/dc/21/944b11404dc14382960e42f931bc24020e15a1b90ed1e6097b202d5897fb/llama_index_llms_perplexity-0.4.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "9f9bda47ff15974f00bbdc3f72957f01daddc0919b0552decfa51c8f4b06e597",
"md5": "3417a926c18f7ae171d73e93a48ef5fb",
"sha256": "dc0c8075367eef5a8eba0861582dbc24ca4681c9a5550dfa344022fb1c1c2fb0"
},
"downloads": -1,
"filename": "llama_index_llms_perplexity-0.4.0.tar.gz",
"has_sig": false,
"md5_digest": "3417a926c18f7ae171d73e93a48ef5fb",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 7198,
"upload_time": "2025-07-30T21:29:25",
"upload_time_iso_8601": "2025-07-30T21:29:25.193549Z",
"url": "https://files.pythonhosted.org/packages/9f/9b/da47ff15974f00bbdc3f72957f01daddc0919b0552decfa51c8f4b06e597/llama_index_llms_perplexity-0.4.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-30 21:29:25",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-llms-perplexity"
}
