agentops
0.3.18
Agentops membantu pengembang membangun, mengevaluasi, dan memantau agen AI. Dari prototipe ke produksi.
| Memutar ulang analisis dan debugging | Grafik eksekusi agen langkah demi langkah |
| ? Manajemen Biaya LLM | Pengeluaran Lacak dengan Penyedia Model LLM Foundation |
| ? Benchmarking Agen | Uji agen Anda terhadap 1.000+ eval |
| ? Kepatuhan dan keamanan | Mendeteksi eksploitasi injeksi prompt dan exfiltrasi data umum |
| ? Integrasi kerangka kerja | Integrasi asli dengan Crewai, Autogen, & Langchain |
pip install agentopsInisialisasi klien agenops dan secara otomatis mendapatkan analitik pada semua panggilan LLM Anda.
Dapatkan Kunci API
import agentops
# Beginning of your program (i.e. main.py, __init__.py)
agentops . init ( < INSERT YOUR API KEY HERE > )
...
# End of program
agentops . end_session ( 'Success' ) Semua sesi Anda dapat dilihat di dasbor Agen
Tambahkan pengamatan yang kuat untuk agen, alat, dan fungsi Anda dengan kode sesedikit mungkin: satu baris pada satu waktu.
Lihat dokumentasi kami
# Automatically associate all Events with the agent that originated them
from agentops import track_agent
@ track_agent ( name = 'SomeCustomName' )
class MyAgent :
... # Automatically create ToolEvents for tools that agents will use
from agentops import record_tool
@ record_tool ( 'SampleToolName' )
def sample_tool (...):
... # Automatically create ActionEvents for other functions.
from agentops import record_action
@ agentops . record_action ( 'sample function being record' )
def sample_function (...):
... # Manually record any other Events
from agentops import record , ActionEvent
record ( ActionEvent ( "received_user_input" )) Bangun agen kru dengan kemampuan observasi dengan hanya 2 baris kode. Cukup atur AGENTOPS_API_KEY di lingkungan Anda, dan kru Anda akan mendapatkan pemantauan otomatis di dasbor Agentops.
pip install ' crewai[agentops] ' Dengan hanya dua baris kode, tambahkan pengamatan penuh dan pemantauan ke agen autogen. Tetapkan AGENTOPS_API_KEY di lingkungan Anda dan hubungi agentops.init()
AgenPops bekerja mulus dengan aplikasi yang dibangun menggunakan Langchain. Untuk menggunakan pawang, instal Langchain sebagai ketergantungan opsional:
pip install agentops[langchain]Untuk menggunakan pawang, impor dan setel
import os
from langchain . chat_models import ChatOpenAI
from langchain . agents import initialize_agent , AgentType
from agentops . partners . langchain_callback_handler import LangchainCallbackHandler
AGENTOPS_API_KEY = os . environ [ 'AGENTOPS_API_KEY' ]
handler = LangchainCallbackHandler ( api_key = AGENTOPS_API_KEY , tags = [ 'Langchain Example' ])
llm = ChatOpenAI ( openai_api_key = OPENAI_API_KEY ,
callbacks = [ handler ],
model = 'gpt-3.5-turbo' )
agent = initialize_agent ( tools ,
llm ,
agent = AgentType . CHAT_ZERO_SHOT_REACT_DESCRIPTION ,
verbose = True ,
callbacks = [ handler ], # You must pass in a callback handler to record your agent
handle_parsing_errors = True )Lihatlah buku catatan Langchain untuk detail lebih lanjut termasuk penangan async.
Dukungan kelas satu untuk cohere (> = 5.4.0). Ini adalah integrasi hidup, jika Anda memerlukan fungsi tambahan, silakan pesan kami di Perselisihan!
pip install cohere import cohere
import agentops
# Beginning of program's code (i.e. main.py, __init__.py)
agentops . init ( < INSERT YOUR API KEY HERE > )
co = cohere . Client ()
chat = co . chat (
message = "Is it pronounced ceaux-hear or co-hehray?"
)
print ( chat )
agentops . end_session ( 'Success' ) import cohere
import agentops
# Beginning of program's code (i.e. main.py, __init__.py)
agentops . init ( < INSERT YOUR API KEY HERE > )
co = cohere . Client ()
stream = co . chat_stream (
message = "Write me a haiku about the synergies between Cohere and AgentOps"
)
for event in stream :
if event . event_type == "text-generation" :
print ( event . text , end = '' )
agentops . end_session ( 'Success' )Agen lacak yang dibangun dengan antropik Python SDK (> = 0,32.0).
pip install anthropic import anthropic
import agentops
# Beginning of program's code (i.e. main.py, __init__.py)
agentops . init ( < INSERT YOUR API KEY HERE > )
client = anthropic . Anthropic (
# This is the default and can be omitted
api_key = os . environ . get ( "ANTHROPIC_API_KEY" ),
)
message = client . messages . create (
max_tokens = 1024 ,
messages = [
{
"role" : "user" ,
"content" : "Tell me a cool fact about AgentOps" ,
}
],
model = "claude-3-opus-20240229" ,
)
print ( message . content )
agentops . end_session ( 'Success' )Mengalir
import anthropic
import agentops
# Beginning of program's code (i.e. main.py, __init__.py)
agentops . init ( < INSERT YOUR API KEY HERE > )
client = anthropic . Anthropic (
# This is the default and can be omitted
api_key = os . environ . get ( "ANTHROPIC_API_KEY" ),
)
stream = client . messages . create (
max_tokens = 1024 ,
model = "claude-3-opus-20240229" ,
messages = [
{
"role" : "user" ,
"content" : "Tell me something cool about streaming agents" ,
}
],
stream = True ,
)
response = ""
for event in stream :
if event . type == "content_block_delta" :
response += event . delta . text
elif event . type == "message_stop" :
print ( " n " )
print ( response )
print ( " n " )Async
import asyncio
from anthropic import AsyncAnthropic
client = AsyncAnthropic (
# This is the default and can be omitted
api_key = os . environ . get ( "ANTHROPIC_API_KEY" ),
)
async def main () -> None :
message = await client . messages . create (
max_tokens = 1024 ,
messages = [
{
"role" : "user" ,
"content" : "Tell me something interesting about async agents" ,
}
],
model = "claude-3-opus-20240229" ,
)
print ( message . content )
await main ()Agen lacak yang dibangun dengan antropik Python SDK (> = 0,32.0).
pip install mistralaiSinkronisasi
from mistralai import Mistral
import agentops
# Beginning of program's code (i.e. main.py, __init__.py)
agentops . init ( < INSERT YOUR API KEY HERE > )
client = Mistral (
# This is the default and can be omitted
api_key = os . environ . get ( "MISTRAL_API_KEY" ),
)
message = client . chat . complete (
messages = [
{
"role" : "user" ,
"content" : "Tell me a cool fact about AgentOps" ,
}
],
model = "open-mistral-nemo" ,
)
print ( message . choices [ 0 ]. message . content )
agentops . end_session ( 'Success' )Mengalir
from mistralai import Mistral
import agentops
# Beginning of program's code (i.e. main.py, __init__.py)
agentops . init ( < INSERT YOUR API KEY HERE > )
client = Mistral (
# This is the default and can be omitted
api_key = os . environ . get ( "MISTRAL_API_KEY" ),
)
message = client . chat . stream (
messages = [
{
"role" : "user" ,
"content" : "Tell me something cool about streaming agents" ,
}
],
model = "open-mistral-nemo" ,
)
response = ""
for event in message :
if event . data . choices [ 0 ]. finish_reason == "stop" :
print ( " n " )
print ( response )
print ( " n " )
else :
response += event . text
agentops . end_session ( 'Success' )Async
import asyncio
from mistralai import Mistral
client = Mistral (
# This is the default and can be omitted
api_key = os . environ . get ( "MISTRAL_API_KEY" ),
)
async def main () -> None :
message = await client . chat . complete_async (
messages = [
{
"role" : "user" ,
"content" : "Tell me something interesting about async agents" ,
}
],
model = "open-mistral-nemo" ,
)
print ( message . choices [ 0 ]. message . content )
await main ()Streaming async
import asyncio
from mistralai import Mistral
client = Mistral (
# This is the default and can be omitted
api_key = os . environ . get ( "MISTRAL_API_KEY" ),
)
async def main () -> None :
message = await client . chat . stream_async (
messages = [
{
"role" : "user" ,
"content" : "Tell me something interesting about async streaming agents" ,
}
],
model = "open-mistral-nemo" ,
)
response = ""
async for event in message :
if event . data . choices [ 0 ]. finish_reason == "stop" :
print ( " n " )
print ( response )
print ( " n " )
else :
response += event . text
await main ()AgentOps memberikan dukungan untuk litellm (> = 1.3.1), memungkinkan Anda untuk memanggil 100+ LLM menggunakan format input/output yang sama.
pip install litellm # Do not use LiteLLM like this
# from litellm import completion
# ...
# response = completion(model="claude-3", messages=messages)
# Use LiteLLM like this
import litellm
...
response = litellm . completion ( model = "claude-3" , messages = messages )
# or
response = await litellm . acompletion ( model = "claude-3" , messages = messages )AgenPops bekerja mulus dengan aplikasi yang dibangun menggunakan LlamAinDex, kerangka kerja untuk membangun aplikasi generatif-generatif yang dibeli dengan konteks dengan LLMS.
pip install llama-index-instrumentation-agentopsUntuk menggunakan pawang, impor dan setel
from llama_index . core import set_global_handler
# NOTE: Feel free to set your AgentOps environment variables (e.g., 'AGENTOPS_API_KEY')
# as outlined in the AgentOps documentation, or pass the equivalent keyword arguments
# anticipated by AgentOps' AOClient as **eval_params in set_global_handler.
set_global_handler ( "agentops" )Lihatlah Dokumen Llamaindex untuk lebih jelasnya.
Cobalah!
(segera hadir!)
| Platform | Dasbor | Eval |
|---|---|---|
| ✅ Python SDK | ✅ Metrik multi-sesi dan cross-sesi | ✅ metrik eval khusus |
| ? API Pembangun Evaluasi | ✅ Pelacakan tag acara khusus | Kartu skor agen |
| ✅ JavaScript/TypeScript SDK | ✅ Sesi tayangan ulang | Evaluasi Playground + Papan Tinggi |
| Pengujian kinerja | Lingkungan | Pengujian LLM | PRIBCING DAN EKSEKUSI |
|---|---|---|---|
| ✅ Analisis Latensi Acara | Pengujian Lingkungan Non-Stasioner | Deteksi fungsi non-deterministik llm | ? Loop tak terbatas dan deteksi pemikiran rekursif |
| ✅ Harga Eksekusi Alur Kerja Agen | Lingkungan multi-modal | ? Token Limit Overflow Flags | Deteksi penalaran yang salah |
| ? Validator sukses (eksternal) | Wadah eksekusi | Batas konteks bendera overflow | Validator kode generatif |
| Pengontrol agen/tes keterampilan | ✅ Honeypot dan deteksi injeksi cepat (PromptAmor) | Pelacakan tagihan API | Analisis Breakpoint Kesalahan |
| Pengujian Kendala Konteks Informasi | Penghalang jalan anti-agen (yaitu captchas) | Pemeriksaan Integrasi CI/CD | |
| Pengujian Regresi | Visualisasi kerangka kerja multi-agen |
Tanpa alat yang tepat, agen AI lambat, mahal, dan tidak dapat diandalkan. Misi kami adalah membawa agen Anda dari prototipe ke produksi. Inilah mengapa Agentops menonjol:
Agentops dirancang untuk membuat agen observabilitas, pengujian, dan pemantauan mudah.
Lihatlah pertumbuhan kami di komunitas:
| Gudang | Bintang |
|---|---|
| Geekan / Metagpt | 42787 |
| run-llama / llama_index | 34446 |
| Crewaiinc / Crewai | 18287 |
| Unta-Ai / Camel | 5166 |
| Superagent-Ai / Superagent | 5050 |
| Iyaja / llama-fs | 4713 |
| Berdasarkan Hardware / OMI | 2723 |
| Mervinpraison / praisonai | 2007 |
| Agentops-Ai / Jaiqu | 272 |
| Strnad / Crewai-Studio | 134 |
| ALEJANDRO-AO / EXA-CREWAI | 55 |
| tonykipkemboi / youtube_yapper_trapper | 47 |
| Sethcoast / Cover-Letter-Builder | 27 |
| Bhancockio / chatgpt4o-analisis | 19 |
| Breakstring / Agentic_story_book_workflow | 14 |
| Multi-On / Multion-Python | 13 |
Dihasilkan menggunakan github-dependents-info, oleh nicolas vuillamy
