MervinPraison/PraisonAI
1
0 Fork 0
mirror of https://github.com/MervinPraison/PraisonAI.git synced 2026-11-07 12:47:55 -10:00
Code Issues Packages Projects Releases 1 Wiki Activity

Release v3.4.0

Browse Source
This commit is contained in:
Mervin Praison committed 2026-01-08 13:29:57 +00:00
1 parent 304952e84d
commit be1e4b3424
72 files changed
+961 -1049
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docker/Dockerfile.chat
+1 -1
View File
@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
# Install Python packages (using latest versions)
RUN pip install --no-cache-dir \
praisonai_tools \
"praisonai>=3.3.1" \
"praisonai>=3.4.0" \
"praisonai[chat]" \
"embedchain[github,youtube]"
docker/Dockerfile.dev
+1 -1
View File
@@ -20,7 +20,7 @@ RUN mkdir -p /root/.praison
# Install Python packages (using latest versions)
RUN pip install --no-cache-dir \
praisonai_tools \
"praisonai>=3.3.1" \
"praisonai>=3.4.0" \
"praisonai[ui]" \
"praisonai[chat]" \
"praisonai[realtime]" \
docker/Dockerfile.ui
+1 -1
View File
@@ -16,7 +16,7 @@ RUN mkdir -p /root/.praison
# Install Python packages (using latest versions)
RUN pip install --no-cache-dir \
praisonai_tools \
"praisonai>=3.3.1" \
"praisonai>=3.4.0" \
"praisonai[ui]" \
"praisonai[crewai]"
docs/profiling-cli.md
-203
View File
@@ -1,203 +0,0 @@
# Profiling CLI
PraisonAI provides unified profiling capabilities for performance analysis and debugging, with **full visibility from ENTER to first response**.
## Quick Start
```bash
# Basic profiling
praisonai "What is 2+2?" --profile
# Deep profiling with call graph, decision trace, and module breakdown
praisonai "What is 2+2?" --profile --profile-deep
# JSON output format
praisonai "What is 2+2?" --profile --profile-format json
```
## Time to First Response (TTFR)
**TTFR** is the key user-perceived latency metric. It measures the time from when you press ENTER until the first visible output appears.
### What contributes to TTFR?
1. **CLI Entry** - Time to reach the CLI entry point
2. **CLI Parse** - Argparse/Typer routing time
3. **Routing** - Command routing to handler
4. **Imports** - Loading required modules
5. **Agent Init** - Initializing the agent
6. **Network Request** - Sending request to LLM API
7. **First Token** - Receiving first token (streaming)
8. **First Output** - Rendering first visible output
### How to reduce TTFR
1. **Warm runs** - Imports are cached after first run
2. **Streaming mode** - See output as tokens arrive
3. **Lighter models** - Faster response times
4. **Local models** - Eliminate network latency
## CLI Flags
| Flag | Description | Default |
|------|-------------|---------|
| `--profile` | Enable profiling with timing breakdown | Disabled |
| `--profile-deep` | Enable deep profiling with call graph (higher overhead) | Disabled |
| `--profile-format` | Output format: `text` or `json` | `text` |
## Profile Command
For more detailed profiling options, use the `profile` subcommand:
```bash
# Profile a query
praisonai profile query "What is 2+2?"
# With deep call tracing
praisonai profile query "Hello" --deep
# Limit functions shown
praisonai profile query "Test" --limit 20
# Save artifacts to directory
praisonai profile query "Test" --save ./profile_results
# JSON output
praisonai profile query "Test" --format json
```
### Profile Query Options
| Option | Description | Default |
|--------|-------------|---------|
| `--model, -m` | Model to use | Default model |
| `--stream/--no-stream` | Use streaming mode | No stream |
| `--deep` | Enable deep call tracing | Disabled |
| `--limit, -n` | Top N functions to show | 30 |
| `--sort, -s` | Sort by: `cumulative` or `tottime` | `cumulative` |
| `--show-callers` | Show caller functions | Disabled |
| `--show-callees` | Show callee functions | Disabled |
| `--save` | Save artifacts to path | None |
| `--format, -f` | Output format: `text` or `json` | `text` |
## Other Profile Commands
```bash
# Profile module import times
praisonai profile imports
# Profile CLI startup time
praisonai profile startup
# Run comprehensive profiling suite
praisonai profile suite
# Create performance snapshots for comparison
praisonai profile snapshot --baseline
praisonai profile snapshot current --compare
# Configure performance optimizations
praisonai profile optimize --show
```
## Output Format
### Text Report
```
======================================================================
PraisonAI Profile Report
======================================================================
Run ID: abc12345
Timestamp: 2024-01-02T12:00:00.000000Z
Method: cli_direct
Version: 3.0.1
## Execution Timeline
---------------------------------------------
Imports : 500.00 ms
Agent Init : 0.50 ms
Execution : 2000.00 ms
───────────────────────────────────────────
⏱ Time to First Response : 2500.50 ms
TOTAL : 2500.50 ms
## Timing Breakdown
----------------------------------------
Imports: 500.00 ms
Agent Init: 0.50 ms
Execution: 2000.00 ms
─────────────────────────────────────
TOTAL: 2500.50 ms
## Decision Trace (deep profile only)
----------------------------------------
Agent Config: default
Model: gpt-4
Streaming: disabled
Profile Layer: 2
## Top Functions by Cumulative Time
----------------------------------------------------------------------
Function Calls Cumul (ms)
----------------------------------------------------------------------
request 1 1800.00
send 1 1750.00
...
```
### JSON Report
```json
{
"schema_version": "1.0",
"run_id": "abc12345",
"timestamp": "2024-01-02T12:00:00.000000Z",
"invocation": {
"method": "cli_direct",
"flags": {"layer": 1, "stream": false, "model": null},
"praisonai_version": "3.0.1",
"python_version": "3.12.0"
},
"timing": {
"total_ms": 2500.5,
"imports_ms": 500.0,
"agent_init_ms": 0.5,
"execution_ms": 2000.0
},
"functions": [...],
"response_preview": "four"
}
```
## Profiling Layers
| Layer | Overhead | Features |
|-------|----------|----------|
| 0 | < 1ms | Wall-clock phases only |
| 1 | ~5% | + cProfile function stats |
| 2 | ~15% | + Call graph (callers/callees) |
- `--profile` uses Layer 1
- `--profile --profile-deep` uses Layer 2
## Performance Tips
1. **Use Layer 0 for production monitoring** - minimal overhead
2. **Use Layer 1 for development profiling** - good balance
3. **Use Layer 2 only for deep debugging** - higher overhead
## Observational Equivalence
The following commands produce equivalent profile reports:
```bash
# CLI direct
praisonai "prompt" --profile
# Profile command
praisonai profile query "prompt"
```
Both use the same unified profiling architecture and produce identical schema output.
docs/profiling-module.md
-257
View File
@@ -1,257 +0,0 @@
# Profiling Module
PraisonAI provides a unified profiling module for programmatic performance analysis.
## Quick Start
```python
from praisonai.cli.execution import (
ExecutionRequest,
Profiler,
ProfilerConfig,
)
# Create execution request
request = ExecutionRequest(prompt="What is 2+2?")
# Configure profiler
config = ProfilerConfig(layer=1)
# Run with profiling
profiler = Profiler(config)
result, report = profiler.profile_sync(request)
# Access results
print(f"Output: {result.output}")
print(f"Total time: {report.timing.total_ms}ms")
```
## ExecutionRequest
Immutable request descriptor for execution.
```python
from praisonai.cli.execution import ExecutionRequest
# Basic request
request = ExecutionRequest(prompt="Hello")
# With model
request = ExecutionRequest(
prompt="Hello",
model="gpt-4",
agent_name="MyAgent",
)
# With streaming
request = ExecutionRequest(
prompt="Hello",
stream=True,
)
```
### Parameters
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `prompt` | str | Required | The prompt to execute |
| `agent_name` | str | "Assistant" | Name of the agent |
| `agent_instructions` | str | None | Custom instructions |
| `model` | str | None | Model to use |
| `stream` | bool | False | Enable streaming |
| `tools` | tuple | () | Tools to provide |
## ProfilerConfig
Configuration for profiling behavior.
```python
from praisonai.cli.execution import ProfilerConfig
# Layer 0: Wall-clock only (< 1ms overhead)
config = ProfilerConfig(layer=0)
# Layer 1: + cProfile stats (~5% overhead)
config = ProfilerConfig(layer=1)
# Layer 2: + Call graph (~15% overhead)
config = ProfilerConfig(
layer=2,
show_callers=True,
show_callees=True,
)
# From CLI flags
config = ProfilerConfig.from_flags(
profile=True,
deep=True,
network=False,
)
```
### Parameters
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `layer` | int | 1 | Profiling layer (0, 1, or 2) |
| `limit` | int | 30 | Max functions to show |
| `sort_by` | str | "cumulative" | Sort by: cumulative, time, calls |
| `show_callers` | bool | False | Show caller functions |
| `show_callees` | bool | False | Show callee functions |
| `track_network` | bool | False | Track network requests |
| `output_format` | str | "text" | Output format: text, json |
| `save_path` | str | None | Path to save artifacts |
## Profiler
The main profiler class that wraps execution.
```python
from praisonai.cli.execution import Profiler, ProfilerConfig, ExecutionRequest
config = ProfilerConfig(layer=1)
profiler = Profiler(config)
request = ExecutionRequest(prompt="Hello")
result, report = profiler.profile_sync(request, invocation_method="api")
```
### Methods
#### `profile_sync(request, invocation_method="profile_command")`
Profile synchronous execution.
**Parameters:**
- `request`: ExecutionRequest - The execution request
- `invocation_method`: str - How this was invoked (for report)
**Returns:** Tuple of (ExecutionResult, ProfileReport)
## ProfileReport
The canonical profile report with timing and statistics.
```python
# Access timing breakdown
print(f"Total: {report.timing.total_ms}ms")
print(f"Imports: {report.timing.imports_ms}ms")
print(f"Agent Init: {report.timing.agent_init_ms}ms")
print(f"Execution: {report.timing.execution_ms}ms")
# Access function stats (layer 1+)
if report.functions:
for func in report.functions[:5]:
print(f"{func.name}: {func.cumulative_time_ms}ms")
# Access call graph (layer 2)
if report.call_graph:
print(f"Edges: {len(report.call_graph.edges)}")
# Export formats
json_str = report.to_json()
text_str = report.to_text()
dict_data = report.to_dict()
```
### Schema Version
The report uses schema version `1.0`. Schema is frozen after release - new fields are always optional with defaults.
### Mandatory Fields
- `schema_version`: str
- `run_id`: str
- `timestamp`: str (ISO 8601)
- `invocation`: InvocationInfo
- `timing`: TimingBreakdown
- `response_preview`: str
### Optional Fields
- `functions`: List[FunctionStat] (layer 1+)
- `call_graph`: CallGraph (layer 2)
- `network`: List[RequestTiming] (if track_network)
## ExecutionResult
Result of execution with output and metadata.
```python
# Access output
print(result.output)
print(result.success)
print(result.run_id)
# Check for errors
if result.error:
print(f"Error: {result.error}")
# Duration
print(f"Duration: {result.duration_ms}ms")
```
## Data Bounds
Profile data is strictly bounded to prevent memory issues:
| Data Type | Maximum |
|-----------|---------|
| Function stats | 1000 |
| Call graph edges | 5000 |
| Network requests | 100 |
## Example: Full Profiling Workflow
```python
from praisonai.cli.execution import (
ExecutionRequest,
Profiler,
ProfilerConfig,
)
# Configure deep profiling
config = ProfilerConfig(
layer=2,
limit=50,
show_callers=True,
show_callees=True,
)
# Create request
request = ExecutionRequest(
prompt="Explain quantum computing in simple terms",
model="gpt-4",
)
# Profile execution
profiler = Profiler(config)
result, report = profiler.profile_sync(request)
# Print text report
print(report.to_text())
# Save JSON report
with open("profile.json", "w") as f:
f.write(report.to_json())
# Analyze timing
print(f"\nTiming Analysis:")
print(f" Import overhead: {report.timing.imports_ms / report.timing.total_ms * 100:.1f}%")
print(f" Execution time: {report.timing.execution_ms / report.timing.total_ms * 100:.1f}%")
# Top 5 hotspots
if report.functions:
print(f"\nTop 5 Hotspots:")
for func in report.functions[:5]:
print(f" {func.name}: {func.cumulative_time_ms:.2f}ms ({func.calls} calls)")
```
## Invariants
The profiling module guarantees:
1. **Output Equivalence**: Profiled execution produces identical output to non-profiled execution
2. **Schema Stability**: Schema version 1.0 is frozen; new fields are always optional
3. **Bounded Data**: All profile data respects maximum bounds
4. **Zero Overhead When Disabled**: No profiling code runs unless explicitly enabled
docs/templates-cli.md
-53
View File
@@ -1,53 +0,0 @@
# Templates CLI
```bash
praisonai templates list
```
```bash
praisonai templates search video
```
```bash
praisonai templates info ai-video-editor
```
```bash
praisonai templates run ai-video-editor --input video.mp4 --output edited.mp4
```
```bash
praisonai templates run ai-video-editor --input video.mp4 --output edited.mp4 --offline
```
```bash
praisonai templates run ai-video-editor --input video.mp4 --output edited.mp4 --strict-tools
```
```bash
praisonai templates run ai-video-editor --input video.mp4 --tools ./my_tools.py
```
```bash
praisonai templates run ai-video-editor --input video.mp4 --tools-dir ./tools
```
```bash
praisonai templates run ai-video-editor --input video.mp4 --tools-source praisonai_tools.video
```
```bash
praisonai templates run ai-video-editor --input video.mp4 --no-template-tools-py
```
```bash
praisonai templates init my-project --template ai-video-editor
```
```bash
praisonai templates cache clear
```
```bash
praisonai templates cache list
```
docs/templates-module.md
-104
View File
@@ -1,104 +0,0 @@
# Templates Module
## Loading Templates
```python
from praisonai.templates.loader import TemplateLoader
loader = TemplateLoader()
# Load from local path
template = loader.load("./my-template")
# Load from URI
template = loader.load("ai-video-editor")
# Load offline
template = loader.load("ai-video-editor", offline=True)
# Check requirements
missing = loader.check_requirements(template)
```
## Template Discovery
```python
from praisonai.templates.discovery import TemplateDiscovery
discovery = TemplateDiscovery(
include_package=True,
include_defaults=True,
)
# Find template
result = discovery.find_template("ai-video-editor")
# List all templates
templates = discovery.list_templates()
```
## Template Config
```python
from praisonai.templates.loader import TemplateConfig
# Access template properties
template.name
template.description
template.version
template.author
template.requires
template.workflow_file
template.agents_file
template.path
```
## Tool Override Integration
```python
from praisonai.templates.tool_override import (
create_tool_registry_with_overrides,
resolve_tools,
)
# Build registry with template sources
tools_sources = template.requires.get("tools_sources", [])
registry = create_tool_registry_with_overrides(
tools_sources=tools_sources,
template_dir=str(template.path),
include_defaults=True,
)
# Resolve tool names
tools = resolve_tools(["shell_tool"], registry=registry)
```
## TEMPLATE.yaml Schema
```yaml
name: my-template
version: "1.0.0"
description: Template description
requires:
tools: [shell_tool]
packages: [praisonai-tools]
env: [OPENAI_API_KEY]
tools_sources:
- praisonai_tools.video
- ./local_tools.py
workflow: workflow.yaml
agents: agents.yaml
config:
input:
type: string
required: true
output:
type: string
defaults:
preset: podcast
```
docs/tools-cli.md
-65
View File
@@ -1,65 +0,0 @@
# Tools CLI
```bash
praisonai tools list
```
```bash
praisonai tools info shell_tool
```
```bash
praisonai tools info internet_search
```
```bash
praisonai tools search "web"
```
```bash
praisonai tools search "file"
```
```bash
praisonai tools doctor
```
```bash
praisonai tools doctor --json
```
```bash
praisonai tools resolve shell_tool
```
```bash
praisonai tools resolve internet_search --template ai-video-editor
```
```bash
praisonai tools resolve my_tool --tools ./my_tools.py
```
```bash
praisonai tools resolve my_tool --tools-dir ./tools
```
```bash
praisonai tools discover
```
```bash
praisonai tools discover --include praisonai_tools.video
```
```bash
praisonai tools discover --entrypoints
```
```bash
praisonai tools show-sources
```
```bash
praisonai tools show-sources --template ai-video-editor
```
docs/tools-module.md
-90
View File
@@ -1,90 +0,0 @@
# Tools Module
## Tool Registry
```python
from praisonai.templates.tool_override import (
create_tool_registry_with_overrides,
resolve_tools,
)
# Create registry with defaults
registry = create_tool_registry_with_overrides(include_defaults=True)
# Create registry with overrides
registry = create_tool_registry_with_overrides(
override_files=["my_tools.py"],
override_dirs=["./tools"],
include_defaults=True,
)
# Create registry with tools_sources
registry = create_tool_registry_with_overrides(
tools_sources=["praisonai_tools.video"],
template_dir="./my-template",
include_defaults=True,
)
# Resolve tool names to callables
tools = resolve_tools(
["shell_tool", "internet_search"],
registry=registry,
)
```
## Tool Override Loader
```python
from praisonai.templates.tool_override import ToolOverrideLoader
loader = ToolOverrideLoader()
# Load from file
tools = loader.load_from_file("my_tools.py")
# Load from directory
tools = loader.load_from_directory("./tools")
# Load from module
tools = loader.load_from_module("praisonai_tools.video")
# Get default tool directories
dirs = loader.get_default_tool_dirs()
```
## Resolution Order
1. CLI `--tools` files (highest priority)
2. CLI `--tools-dir` directories
3. Template `tools_sources` (from TEMPLATE.yaml)
4. Template-local `tools.py`
5. Default dirs (`~/.praison/tools`, `~/.config/praison/tools`)
6. Package discovery (`praisonai_tools`)
7. Built-in tools (lowest priority)
## Creating Custom Tools
```python
from praisonai_tools import tool
@tool
def my_custom_tool(query: str) -> str:
"""My custom tool description.
Args:
query: The search query
"""
return f"Result for: {query}"
```
## Template tools_sources
```yaml
# TEMPLATE.yaml
requires:
tools: [shell_tool]
tools_sources:
- praisonai_tools.video
- ./local_tools.py
- ./tools_dir/
```
examples/agent_centric_api.py
+158
View File
@@ -0,0 +1,158 @@
"""
Agent-Centric API Example
Demonstrates the new consolidated feature parameters for PraisonAI Agents.
These params provide a cleaner, more intuitive API with progressive disclosure.
New Consolidated Params:
- memory: Union[bool, MemoryConfig, MemoryManager] - Memory and session management
- knowledge: Union[bool, List[str], KnowledgeConfig, KnowledgeBase] - RAG and retrieval
- planning: Union[bool, PlanningConfig] - Planning mode
- reflection: Union[bool, ReflectionConfig] - Self-reflection
- guardrails: Union[bool, Callable, GuardrailConfig] - Safety validation
- web: Union[bool, WebConfig] - Web search and fetch
- context: Union[bool, ManagerConfig, ContextManager] - Context management
"""
from praisonaiagents import (
Agent,
# Config classes for progressive disclosure
MemoryConfig,
KnowledgeConfig,
PlanningConfig,
ReflectionConfig,
GuardrailConfig,
WebConfig,
)
def example_simple_enable():
"""Example 1: Simple boolean enable (easiest)"""
print("\n=== Example 1: Simple Boolean Enable ===")
agent = Agent(
instructions="You are a helpful assistant",
memory=True, # Enable memory with defaults
reflection=True, # Enable self-reflection
web=True, # Enable web search + fetch
)
print(f"Agent created with memory={agent._memory_instance is not None}")
print(f" self_reflect={agent.self_reflect}")
print(f" web_search={agent.web_search}")
def example_with_config():
"""Example 2: Using config objects (more control)"""
print("\n=== Example 2: Using Config Objects ===")
agent = Agent(
instructions="You are a research assistant",
memory=MemoryConfig(
backend="file",
user_id="researcher_001",
auto_memory=True,
),
reflection=ReflectionConfig(
min_iterations=1,
max_iterations=5,
llm="gpt-4o-mini",
),
web=WebConfig(
search=True,
fetch=False, # Only search, no full page fetch
max_results=3,
),
)
print(f"Agent created with user_id={agent.user_id}")
print(f" {agent.max_reflect}")
print(f" web_search={agent.web_search}, web_fetch={agent.web_fetch}")
def example_guardrails():
"""Example 3: Guardrails with callable or config"""
print("\n=== Example 3: Guardrails ===")
# Option A: Direct callable
def my_validator(output):
"""Simple validator that checks response length."""
is_valid = len(output.raw) < 1000
return (is_valid, output if is_valid else "Response too long")
agent_a = Agent(
instructions="Be concise",
guardrails=my_validator, # Direct callable
)
print(f"Agent A: guardrail is callable = {callable(agent_a.guardrail)}")
# Option B: Using GuardrailConfig
agent_b = Agent(
instructions="Be helpful and safe",
guardrails=GuardrailConfig(
llm_validator="Ensure the response is helpful, accurate, and safe",
max_retries=3,
),
)
print(f"Agent B: guardrail = {agent_b.guardrail}")
print(f" max_retries = {agent_b.max_guardrail_retries}")
def example_planning():
"""Example 4: Planning mode"""
print("\n=== Example 4: Planning Mode ===")
agent = Agent(
instructions="You are a project planner",
planning=PlanningConfig(
reasoning=True,
read_only=True, # Plan mode - only read operations
),
)
print(f"Agent created with planning={agent.planning}")
print(f" plan_mode={agent.plan_mode}")
print(f" planning_reasoning={agent.planning_reasoning}")
def example_backward_compatible():
"""Example 5: Using new consolidated params"""
print("\n=== Example 5: Consolidated Params ===")
# New consolidated params
agent = Agent(
instructions="Test agent",
reflection=True,
web=WebConfig(search=True, fetch=False),
)
print(f"Consolidated params work: self_reflect={agent.self_reflect}")
print(f" web_search={agent.web_search}, web_fetch={agent.web_fetch}")
def example_real_chat():
"""Example 6: Real chat with new API"""
print("\n=== Example 6: Real Chat ===")
agent = Agent(
instructions="You are a helpful math tutor. Be concise.",
reflection=False,
web=False,
verbose=False,
)
response = agent.start("What is the square root of 144?")
print(f"Response: {response}")
if __name__ == "__main__":
print("=" * 60)
print("PraisonAI Agent-Centric API Examples")
print("=" * 60)
example_simple_enable()
example_with_config()
example_guardrails()
example_planning()
example_backward_compatible()
example_real_chat()
print("\n" + "=" * 60)
print("All examples completed!")
print("=" * 60)
examples/guardrail_example_fixed.py
+4 -4
View File
@@ -67,7 +67,7 @@ agent = Agent(
goal="Summarize web content concisely",
instructions="You are a helpful assistant that summarizes web content",
llm="gemini/gemini-2.5-flash-lite-preview-06-17",
self_reflect=False,
reflection=False,
verbose=True,
tools=[get_url_context] # FIX: tools must be a list, not a single function
)
@@ -77,7 +77,7 @@ task_with_guardrailresult = Task(
name="summarise article with GuardrailResult",
description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary below 500 characters",
agent=agent,
guardrail=validate_length_guardrailresult, # Using GuardrailResult
guardrails=validate_length_guardrailresult, # Using GuardrailResult
expected_output="summary of the article below 500 characters",
max_retries=3 # Will retry up to 3 times if guardrail fails
)
@@ -87,7 +87,7 @@ task_with_tuple = Task(
name="summarise article with tuple",
description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary below 500 characters",
agent=agent,
guardrail=validate_length_tuple, # Using Tuple[bool, Any]
guardrails=validate_length_tuple, # Using Tuple[bool, Any]
expected_output="summary of the article below 500 characters",
max_retries=3
)
@@ -97,7 +97,7 @@ task_with_llm_guardrail = Task(
name="summarise with LLM guardrail",
description="get the context of this url: https://blog.google/technology/ai/dolphingemma/ and produce a summary",
agent=agent,
guardrail="Ensure the summary is professional, factual, and between 100-500 characters",
guardrails="Ensure the summary is professional, factual, and between 100-500 characters",
expected_output="professional summary of the article"
)
examples/python/agents/code-agent.py
+6 -6
View File
@@ -32,9 +32,9 @@ code_writer = Agent(
goal="Write clean, efficient, and well-documented Python code",
backstory="You are a senior Python developer with 10+ years of experience in writing production-quality code.",
instructions="Write Python code that follows PEP 8 standards, includes proper error handling, and has clear documentation.",
self_reflect=True,
min_reflect=2,
max_reflect=5
reflection=True,
)
code_reviewer = Agent(
@@ -108,9 +108,9 @@ general_code_agent = Agent(
4. Refactor code for better performance
5. Add tests and documentation""",
tools=[code_interpreter, analyze_code_complexity],
self_reflect=True,
min_reflect=1,
max_reflect=3
reflection=True,
)
if __name__ == "__main__":
examples/python/agents/image-agent.py
+1 -1
View File
@@ -14,7 +14,7 @@ image_agent = Agent(
backstory="""You are an expert in computer vision and image analysis.
You excel at describing images, detecting objects, and understanding visual content.""",
llm="gpt-5-nano",
self_reflect=False
reflection=False
)
# 1. Task with Image URL
examples/python/agents/image-to-text-agent.py
+1 -1
View File
@@ -14,7 +14,7 @@ image_agent = Agent(
backstory="""You are an expert in computer vision and image analysis.
You excel at describing images, detecting objects, and understanding visual content.""",
llm="gpt-5-nano",
self_reflect=False
reflection=False
)
# 1. Task with Image URL
examples/python/agents/math-agent.py
+9 -9
View File
@@ -65,9 +65,9 @@ calculation_agent = Agent(
backstory="You are an expert mathematician who can handle complex calculations with precision.",
instructions="Perform the requested calculations step by step, showing your work clearly.",
tools=[basic_calculator, solve_quadratic, calculate_statistics],
self_reflect=True,
min_reflect=1,
max_reflect=2
reflection=True,
)
problem_solver_agent = Agent(
@@ -81,9 +81,9 @@ problem_solver_agent = Agent(
3. Determine what needs to be found
4. Show each step of the solution
5. Verify the answer makes sense""",
self_reflect=True,
min_reflect=2,
max_reflect=4
reflection=True,
)
math_tutor_agent = Agent(
@@ -148,9 +148,9 @@ math_assistant = Agent(
Always show your work step by step.""",
tools=[basic_calculator, solve_quadratic, calculate_statistics],
self_reflect=True,
min_reflect=1,
max_reflect=3
reflection=True,
)
if __name__ == "__main__":
examples/python/agents/programming-agent.py
+3 -2
View File
@@ -1,10 +1,11 @@
from praisonaiagents import Agent, Tools
from praisonaiagents import Agent, Tools, ReflectionConfig
from praisonaiagents.tools import execute_code, analyze_code, format_code, lint_code, disassemble_code # Code Tools
from praisonaiagents.tools import execute_command, list_processes, kill_process, get_system_info # Shell Tools
from praisonaiagents.tools import duckduckgo # Web Search Tool
agent = Agent(
instructions="You are a Programming Agent", self_reflect=True, min_reflect=5, max_reflect=10,
instructions="You are a Programming Agent",
reflection=ReflectionConfig(min_iterations=5, max_iterations=10),
tools=[execute_code, analyze_code, format_code, lint_code, disassemble_code, execute_command, list_processes, kill_process, get_system_info, duckduckgo]
)
agent.start(
examples/python/agents/video-agent.py
+1 -1
View File
@@ -8,7 +8,7 @@ video_agent = Agent(
backstory="""You are an expert in computer vision and image analysis.
You excel at describing images, detecting objects, and understanding visual content.""",
llm="gpt-5-nano",
self_reflect=False
reflection=False
)
# Task with Video File
examples/python/agents/wikipedia-agent.py
+3 -3
View File
@@ -4,9 +4,9 @@ from praisonaiagents.tools import wiki_search, wiki_summary, wiki_page, wiki_ran
agent = Agent(
instructions="You are a Wikipedia Agent",
tools=[wiki_search, wiki_summary, wiki_page, wiki_random, wiki_language],
self_reflect=True,
min_reflect=3,
max_reflect=5,
reflection=True,
)
agent.start(
"What is the history of AI?"
examples/python/concepts/chat-with-pdf.py
+3 -3
View File
@@ -27,9 +27,9 @@ pdf_agent = Agent(
instructions="Read the provided PDF document and answer questions about its content. Be specific and cite relevant sections when possible.",
knowledge=["document.pdf"], # Replace with your PDF file path
knowledge_config=config,
self_reflect=True,
min_reflect=1,
max_reflect=3
reflection=True,
)
# Example usage
examples/python/concepts/reasoning-extraction.py
+4 -4
View File
@@ -49,9 +49,9 @@ cot_agent = Agent(
6. Assess your confidence level
Always make your thinking process explicit and transparent.""",
self_reflect=True,
min_reflect=2,
max_reflect=3
reflection=True,
)
# Example 2: Reasoning Extractor Agent
@@ -224,7 +224,7 @@ pattern_reasoning_agent = Agent(
3. Counterfactual: Explore what-if scenarios
4. Systems thinking: Consider interconnections
5. Probabilistic: Assess likelihoods""",
self_reflect=True
reflection=True
)
# Example 8: Interactive Reasoning Extraction
examples/python/concepts/routing-patterns.py
+1 -1
View File
@@ -208,7 +208,7 @@ dynamic_router = Agent(
5. Current system load
Provide clear routing decisions with reasoning.""",
self_reflect=True
reflection=True
)
def dynamic_routing_example():
examples/python/concepts/self-reflection-details.py
+20 -20
View File
@@ -24,9 +24,9 @@ basic_reflection_agent = Agent(
3. Identify areas for improvement
4. Revise and enhance
5. Repeat until satisfied""",
self_reflect=True, # Enable self-reflection
min_reflect=1, # Minimum 1 reflection iteration
max_reflect=3 # Maximum 3 reflection iterations
reflection=True, # Enable self-reflection
# Minimum 1 reflection iteration
# Maximum 3 reflection iterations
)
# Example 2: Advanced Reflection with Different Strategies
@@ -41,9 +41,9 @@ quality_focused_agent = Agent(
- Clarity of presentation
- Logical flow
- Supporting evidence""",
self_reflect=True,
min_reflect=3, # Higher minimum for quality
max_reflect=5 # Allow more iterations
reflection=True,
# Higher minimum for quality
# Allow more iterations
)
efficiency_balanced_agent = Agent(
@@ -52,9 +52,9 @@ efficiency_balanced_agent = Agent(
goal="Achieve good quality with reasonable reflection time",
backstory="You balance quality with efficiency, knowing when good enough is sufficient.",
instructions="Create good content with 1-2 rounds of improvement.",
self_reflect=True,
min_reflect=1,
max_reflect=2 # Limit iterations for efficiency
reflection=True,
# Limit iterations for efficiency
)
# Example 3: No Reflection for Comparison
@@ -64,7 +64,7 @@ no_reflection_agent = Agent(
goal="Provide immediate responses without reflection",
backstory="You provide quick, first-draft responses.",
instructions="Respond immediately with your first thought.",
self_reflect=False # Disable reflection
reflection=False # Disable reflection
)
# Demonstration function to show reflection in action
@@ -113,9 +113,9 @@ def reflection_workflow_example():
role="Initial content creator",
goal="Create first draft with self-improvement",
backstory="You create initial drafts and refine them through reflection.",
self_reflect=True,
min_reflect=2,
max_reflect=3
reflection=True,
)
# Reviewer without reflection (provides feedback)
@@ -124,7 +124,7 @@ def reflection_workflow_example():
role="Content reviewer",
goal="Provide constructive feedback",
backstory="You review content and provide specific improvement suggestions.",
self_reflect=False # No reflection needed for reviewing
reflection=False # No reflection needed for reviewing
)
# Final polisher with reflection
@@ -133,9 +133,9 @@ def reflection_workflow_example():
role="Final content polisher",
goal="Perfect the content based on feedback",
backstory="You take feedback and create the final, polished version.",
self_reflect=True,
min_reflect=1,
max_reflect=2
reflection=True,
)
# Workflow tasks
@@ -202,9 +202,9 @@ custom_reflection_agent = Agent(
backstory="You adapt your reflection process based on content quality.",
instructions="""Create content and reflect on it.
Continue improving until quality standards are met or maximum iterations reached.""",
self_reflect=True,
min_reflect=1,
max_reflect=5
reflection=True,
)
# Example 6: Reflection Impact Analysis
examples/python/concepts/self-reflection-optimization-patterns.py
+4 -4
View File
@@ -17,10 +17,10 @@ reflection_agent = Agent(
goal="Demonstrate self-reflection and iterative improvement patterns",
backstory="Expert researcher with strong self-reflection and continuous improvement capabilities",
tools=[internet_search],
self_reflect=True,
min_reflect=2,
max_reflect=4,
reflect_llm="gpt-5-nano",
reflection=True,
verbose=True
)
examples/python/general/async_example.py
+2 -2
View File
@@ -98,7 +98,7 @@ sync_agent = Agent(
goal="Perform synchronous searches and return structured results",
backstory="Expert in sync operations and data organization",
tools=[sync_search_tool],
self_reflect=False,
reflection=False,
verbose=True,
markdown=True
)
@@ -109,7 +109,7 @@ async_agent = Agent(
goal="Perform asynchronous searches and return structured results",
backstory="Expert in async operations and data organization",
tools=[async_search_tool],
self_reflect=False,
reflection=False,
verbose=True,
markdown=True
)
examples/python/general/async_example_full.py
+2 -2
View File
@@ -53,7 +53,7 @@ async_agent = Agent(
goal="Perform fast parallel searches with structured results",
backstory="Expert in efficient data retrieval and parallel search operations",
tools=[async_search_tool],
self_reflect=False,
reflection=False,
verbose=True,
markdown=True
)
@@ -63,7 +63,7 @@ summary_agent = Agent(
role="Research Synthesizer",
goal="Create concise summaries from multiple search results",
backstory="Expert in analyzing and synthesizing information from multiple sources",
self_reflect=True,
reflection=True,
verbose=True,
markdown=True
)
examples/python/general/async_example_full_multigroups.py
+2 -2
View File
@@ -60,7 +60,7 @@ async_agent = Agent(
goal="Perform fast and efficient asynchronous searches with structured results",
backstory="Expert in parallel search operations and data retrieval",
tools=[async_search_tool],
self_reflect=False,
reflection=False,
verbose=True,
markdown=True
)
@@ -72,7 +72,7 @@ summary_agent = Agent(
backstory="""Expert in analyzing and synthesizing information from multiple sources.
Skilled at identifying patterns, trends, and connections between different topics.
Specializes in creating clear, structured summaries that highlight key insights.""",
self_reflect=True, # Enable self-reflection for better summary quality
reflection=True, # Enable self-reflection for better summary quality
verbose=True,
markdown=True
)
examples/python/general/code_agents_example.py
+2 -2
View File
@@ -25,13 +25,13 @@ code_agent = Agent(
name="code_agent",
llm="gpt-5-nano",
backstory="Expert in writing Python scripts",
self_reflect=False
reflection=False
)
execution_agent = Agent(
name="execution_agent",
llm="gpt-5-nano",
backstory="Expert in executing Python scripts",
self_reflect=False,
reflection=False,
tools=[code_interpreter]
)
examples/python/general/example_callback.py
+3 -3
View File
@@ -129,9 +129,9 @@ def main():
tools=[internet_search_tool],
llm="gpt-5-nano",
markdown=True,
reflect_llm="gpt-5-nano",
min_reflect=2,
max_reflect=4
)
writer = Agent(
examples/python/general/example_custom_tools.py
+1 -1
View File
@@ -112,7 +112,7 @@ data_agent = Agent(
goal="Perform internet searches to collect relevant information.",
backstory="Expert in finding and organizing internet data from multiple sources.",
tools=[internet_search_tool, youtube_search_tool, wikipedia_search_tool],
self_reflect=False
reflection=False
)
# 3. Tasks
examples/python/general/example_sequential.py
+3 -3
View File
@@ -41,9 +41,9 @@ researcher = Agent(
tools=[internet_search_tool],
llm="gpt-5-nano",
markdown=True,
reflect_llm="gpt-5-nano",
min_reflect=2,
max_reflect=4
)
writer = Agent(
name="Writer",
examples/python/general/langchain_example.py
+1 -1
View File
@@ -9,7 +9,7 @@ agent = Agent(
goal="Search for information from multiple sources",
backstory="I am an AI assistant that can search YouTube and Wikipedia.",
tools=[YouTubeSearchTool, WikipediaAPIWrapper],
self_reflect=False
reflection=False
)
# Create tasks to demonstrate both tools
examples/python/general/multimodal.py
+1 -1
View File
@@ -8,7 +8,7 @@ vision_agent = Agent(
backstory="""You are an expert in computer vision and image analysis.
You excel at describing images, detecting objects, and understanding visual content.""",
llm="gpt-5-nano",
self_reflect=False
reflection=False
)
# 1. Task with Image URL
examples/python/general/structured_agents_example.py
+2 -2
View File
@@ -15,7 +15,7 @@ researcher = Agent(
verbose=True,
llm="gpt-5-nano",
tools=[Tools.internet_search],
self_reflect=False
reflection=False
)
# Create an analyst agent
@@ -26,7 +26,7 @@ analyst = Agent(
backstory="Senior data analyst with expertise in pattern recognition",
verbose=True,
llm="gpt-5-nano",
self_reflect=False
reflection=False
)
# Define structured tasks
examples/python/general/structured_response_example.py
+1 -1
View File
@@ -33,7 +33,7 @@ def get_structured_analysis(query: str, verbose: bool = True) -> AnalysisReport:
goal="Analyze topics and provide structured reports",
backstory="Expert at gathering information and providing structured analysis",
verbose=verbose,
self_reflect=True, # Enable self-reflection for better quality
reflection=True, # Enable self-reflection for better quality
markdown=True,
llm="gpt-5-nano"
)
examples/python/general/tools-class.py
+1 -1
View File
@@ -94,7 +94,7 @@ agent = Agent(
goal="Search for information about 'AI Agents Framework'",
backstory="I am an AI assistant that can search GitHub.",
tools=[EXASearchTool],
self_reflect=False
reflection=False
)
# Create tasks to demonstrate both tools
examples/python/general/tools_example.py
+1 -1
View File
@@ -8,7 +8,7 @@ news_agent = Agent(
goal="Collect and analyze news articles from various sources.",
backstory="Expert in news gathering and content analysis.",
tools=[get_article, get_news_sources, get_articles_from_source, get_trending_topics],
self_reflect=False
reflection=False
)
examples/python/general/workflow_example_basic.py
+1 -1
View File
@@ -35,7 +35,7 @@ data_agent = Agent(
goal="Perform internet searches to collect relevant information.",
backstory="Expert in finding and organising internet data.",
tools=[internet_search_tool],
self_reflect=False
reflection=False
)
# 3. Tasks
examples/python/general/workflow_example_detailed.py
+2 -2
View File
@@ -158,7 +158,7 @@ data_agent = Agent(
goal="Collect and validate data about individuals",
backstory="Expert in gathering and validating demographic data",
tools=[random_data_of_individuals],
self_reflect=False
reflection=False
)
process_agent = Agent(
@@ -167,7 +167,7 @@ process_agent = Agent(
goal="Process and categorize individual data",
backstory="Expert in data analysis and categorization",
tools=[process_data_of_individuals],
self_reflect=False
reflection=False
)
# Modify tasks to use Pydantic models
examples/python/guardrails/comprehensive-guardrails-example.py
+5 -5
View File
@@ -125,7 +125,7 @@ email_task = Task(
description="Write a business proposal for a new software project, including contact information",
expected_output="Professional business proposal with contact email addresses",
agent=email_agent,
guardrail=email_format_guardrail,
guardrails=email_format_guardrail,
max_retries=3
)
@@ -135,7 +135,7 @@ content_task = Task(
description="Write an analysis of cloud computing benefits for small businesses",
expected_output="Comprehensive analysis of cloud computing benefits (minimum 50 words)",
agent=content_agent,
guardrail=word_count_guardrail,
guardrails=word_count_guardrail,
max_retries=3
)
@@ -145,7 +145,7 @@ business_task = Task(
description="Provide advice on handling difficult client relationships",
expected_output="Professional advice maintaining appropriate business tone",
agent=business_agent,
guardrail=professional_tone_guardrail,
guardrails=professional_tone_guardrail,
max_retries=3
)
@@ -155,7 +155,7 @@ research_task = Task(
description="Analyze the impact of artificial intelligence on job markets",
expected_output="Research-backed analysis with citations and evidence",
agent=research_agent,
guardrail=factual_accuracy_guardrail,
guardrails=factual_accuracy_guardrail,
max_retries=3
)
@@ -176,7 +176,7 @@ llm_guardrail_task = Task(
agent=llm_guardrail_agent,
# LLM-based guardrail using natural language validation
guardrail="Validate that this marketing content is: 1) Factually accurate with no false claims, 2) Compliant with advertising standards (no misleading statements), 3) Engaging and professional in tone, 4) Includes a clear call-to-action. If any criteria are not met, explain what needs to be improved.",
guardrails="Validate that this marketing content is: 1) Factually accurate with no false claims, 2) Compliant with advertising standards (no misleading statements), 3) Engaging and professional in tone, 4) Includes a clear call-to-action. If any criteria are not met, explain what needs to be improved.",
max_retries=2
)
examples/python/guardrails/production-guardrails-patterns.py
+1 -1
View File
@@ -38,7 +38,7 @@ production_agent = Agent(
goal="Generate safe, compliant content for production use",
backstory="Production-ready agent with built-in safety and compliance checks",
tools=[internet_search],
guardrail=content_guardrail,
guardrails=content_guardrail,
max_retries=3,
verbose=True
)
examples/python/input/advanced_dynamic_input.py
+1 -1
View File
@@ -40,7 +40,7 @@ class DynamicAgentSystem:
goal=f"Conduct {inputs['depth']} research on {inputs['topic']} in {inputs['language']}",
backstory=f"Multilingual expert specializing in {inputs['depth']} analysis",
tools=[duckduckgo],
self_reflect=inputs['depth'] == 'detailed',
reflection=inputs['depth'] == 'detailed',
llm=self.llm_config
)
agents.append(research_agent)
examples/python/input/medium_complexity_input.py
+1 -1
View File
@@ -19,7 +19,7 @@ search_agent = Agent(
goal=f"Find {num_results} relevant results about {topic}",
backstory="Expert in internet research and data collection",
tools=[duckduckgo],
self_reflect=False
reflection=False
)
# Create analysis agent
examples/python/models/googlegemini/any-llm-agents-advanced.py
+1 -3
View File
@@ -34,9 +34,7 @@ agent = Agent(
llm=llm_config, # Pass the detailed configuration
verbose=True, # Enable detailed output
markdown=True, # Format responses in markdown
self_reflect=True, # Enable self-reflection
max_reflect=3, # Maximum reflection iterations
min_reflect=1 # Minimum reflection iterations
reflection=True # Enable self-reflection
)
# Test the agent
examples/python/models/googlegemini/any-llm-agents-async.py
+1 -1
View File
@@ -4,7 +4,7 @@ from praisonaiagents import Agent
agent = Agent(
instructions="You are a helpful assistant",
llm="gemini/gemini-1.5-flash-8b",
self_reflect=True,
reflection=True,
verbose=True
)
examples/python/models/googlegemini/any-llm-agents.py
+1 -1
View File
@@ -3,7 +3,7 @@ from praisonaiagents import Agent
agent = Agent(
instructions="You are a helpful assistant",
llm="gemini/gemini-1.5-flash-8b",
self_reflect=True,
reflection=True,
verbose=True
)
examples/python/scheduled_agents/news_checker_live.py
+1 -1
View File
@@ -87,7 +87,7 @@ def main():
and technology. You provide concise, accurate summaries of important news.""",
tools=[search_tool],
verbose=True,
self_reflect=False # Disable reflection for faster execution
reflection=False # Disable reflection for faster execution
)
# Define the task
examples/python/tasks/advanced-task-management.py
+4 -4
View File
@@ -113,7 +113,7 @@ initial_research = Task(
description="Research the current state of renewable energy adoption in the business sector, including trends, challenges, and opportunities",
expected_output="Comprehensive research report on renewable energy adoption in business",
agent=research_agent,
guardrail=data_quality_validator,
guardrails=data_quality_validator,
max_retries=3
)
@@ -124,7 +124,7 @@ quality_check = Task(
expected_output="Quality assessment report with go/no-go decision for proceeding to analysis",
agent=quality_checker,
context=[initial_research],
guardrail=completeness_validator,
guardrails=completeness_validator,
max_retries=2
)
@@ -153,7 +153,7 @@ additional_research = Task(
agent=research_agent,
context=[initial_research, quality_check],
tools=[duckduckgo],
guardrail=data_quality_validator,
guardrails=data_quality_validator,
max_retries=2
)
@@ -190,7 +190,7 @@ final_report = Task(
expected_output="Executive report with strategic recommendations for renewable energy adoption",
agent=report_writer,
context=[initial_research, quality_check, data_analysis, decision_task],
guardrail=completeness_validator,
guardrails=completeness_validator,
max_retries=2
)
examples/python/tools/cli/app.py
+1 -2
View File
@@ -34,8 +34,7 @@ system_ops_agent = Agent(
backstory="""You are an expert system administrator with deep knowledge of Unix/Linux systems.
You excel at running complex system commands, managing processes, and handling system operations.
You always validate commands before execution and ensure they are safe to run.""",
min_reflect=6,
max_reflect=10,
reflection=True,
tools=[run_terminal_command, save_to_file],
llm="gpt-5-nano"
)
examples/python/tools/e2b/single_agent.py
+1 -2
View File
@@ -53,8 +53,7 @@ web_scraper_agent = Agent(
role="Web Scraper",
goal="Extract URLs from https://news.ycombinator.com/",
backstory="An expert in data extraction from websites, adept at navigating and retrieving detailed information and saving it to a file. and just check if the file is created using run_terminal_command tool",
min_reflect=3,
max_reflect=5,
reflection=True,
tools=[code_interpret, save_to_file, run_terminal_command],
llm="gpt-5-nano"
)
examples/python/usecases/analysis/hackathon-judge-agent.py
+1 -1
View File
@@ -28,7 +28,7 @@ hackathon_judge = Agent(
You excel at evaluating innovation, technical implementation, and presentation quality.
You provide constructive feedback and identify both strengths and areas for improvement.""",
llm="gpt-5-nano", # Using vision-capable model
self_reflect=False,
reflection=False,
knowledge=""
)
examples/python/usecases/analysis/hackathon-judge-streamlit.py
+1 -1
View File
@@ -39,7 +39,7 @@ def get_hackathon_judge():
You excel at evaluating innovation, technical implementation, and presentation quality.
You provide constructive feedback and identify both strengths and areas for improvement.""",
llm="gpt-5-nano", # Using vision-capable model
self_reflect=False,
reflection=False,
knowledge=""
)
scripts/generate_cli_docs.py
-136
View File
@@ -1,136 +0,0 @@
#!/usr/bin/env python3
"""
Auto-generate CLI reference documentation from --help output.
Usage:
python scripts/generate_cli_docs.py > docs/cli/reference.mdx
python scripts/generate_cli_docs.py --output docs/cli/reference.mdx
This script runs `praisonai <cmd> --help` for key commands and generates
deterministic markdown documentation.
"""
import subprocess
import sys
import argparse
from datetime import datetime
from pathlib import Path
# Commands to document
COMMANDS = [
# Top-level
("praisonai", "--help"),
# Knowledge
("praisonai knowledge", "--help"),
("praisonai knowledge index", "--help"),
("praisonai knowledge search", "--help"),
("praisonai knowledge add", "--help"),
("praisonai knowledge list", "--help"),
# RAG
("praisonai rag", "--help"),
("praisonai rag index", "--help"),
("praisonai rag query", "--help"),
("praisonai rag chat", "--help"),
("praisonai rag eval", "--help"),
("praisonai rag serve", "--help"),
# Run
("praisonai run", "--help"),
# Chat
("praisonai chat", "--help"),
]
def run_help(cmd: str, flag: str = "--help") -> str:
"""Run a command with --help and capture output."""
full_cmd = f"{cmd} {flag}"
try:
result = subprocess.run(
full_cmd.split(),
capture_output=True,
text=True,
timeout=30,
)
return result.stdout or result.stderr or "(no output)"
except subprocess.TimeoutExpired:
return "(timeout)"
except FileNotFoundError:
return "(command not found)"
except Exception as e:
return f"(error: {e})"
def generate_markdown() -> str:
"""Generate markdown documentation."""
lines = [
"---",
"title: CLI Reference",
"description: Auto-generated CLI command reference",
"---",
"",
"# PraisonAI CLI Reference",
"",
"This page is auto-generated from `--help` output.",
"",
f"Generated: {datetime.utcnow().strftime('%Y-%m-%d %H:%M:%S')} UTC",
"",
]
for cmd, flag in COMMANDS:
# Section header
cmd_name = cmd.replace("praisonai ", "").replace(" ", "-") or "main"
lines.append(f"## `{cmd}`")
lines.append("")
lines.append("```")
# Get help output
output = run_help(cmd, flag)
lines.append(output.strip())
lines.append("```")
lines.append("")
return "\n".join(lines)
def main():
parser = argparse.ArgumentParser(description="Generate CLI docs from --help")
parser.add_argument(
"--output", "-o",
type=Path,
help="Output file path (default: stdout)",
)
parser.add_argument(
"--check",
action="store_true",
help="Check if output matches existing file (for CI)",
)
args = parser.parse_args()
content = generate_markdown()
if args.check and args.output:
if args.output.exists():
existing = args.output.read_text()
# Compare ignoring timestamp line
existing_lines = [l for l in existing.split("\n") if not l.startswith("Generated:")]
new_lines = [l for l in content.split("\n") if not l.startswith("Generated:")]
if existing_lines != new_lines:
print(f"ERROR: {args.output} is out of date. Run: python scripts/generate_cli_docs.py -o {args.output}", file=sys.stderr)
sys.exit(1)
print(f"OK: {args.output} is up to date")
sys.exit(0)
else:
print(f"ERROR: {args.output} does not exist", file=sys.stderr)
sys.exit(1)
if args.output:
args.output.parent.mkdir(parents=True, exist_ok=True)
args.output.write_text(content)
print(f"Written to {args.output}")
else:
print(content)
if __name__ == "__main__":
main()
src/praisonai-agents/praisonaiagents/__init__.py
+34
View File
@@ -372,6 +372,26 @@ def __getattr__(name):
except ImportError:
return None
# Feature Config classes (agent-centric API)
elif name in ("MemoryConfig", "KnowledgeConfig", "PlanningConfig",
"ReflectionConfig", "GuardrailConfig", "WebConfig",
"MemoryBackend", "ChunkingStrategy", "GuardrailAction",
"WebSearchProvider"):
from .config import feature_configs
result = getattr(feature_configs, name)
_lazy_cache[name] = result
return result
# Context management config (already exists)
elif name == "ManagerConfig":
from .context.manager import ManagerConfig
_lazy_cache[name] = ManagerConfig
return ManagerConfig
elif name == "ContextManager":
from .context.manager import ContextManager
_lazy_cache[name] = ContextManager
return ContextManager
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
@@ -527,4 +547,18 @@ __all__ = [
'RAGConfig',
'RAGResult',
'RAGCitation',
# Feature Configs (agent-centric API)
'MemoryConfig',
'KnowledgeConfig',
'PlanningConfig',
'ReflectionConfig',
'GuardrailConfig',
'WebConfig',
'MemoryBackend',
'ChunkingStrategy',
'GuardrailAction',
'WebSearchProvider',
# Context Management
'ManagerConfig',
'ContextManager',
]
src/praisonai-agents/praisonaiagents/agent/agent.py
+182 -18
View File
@@ -268,35 +268,22 @@ class Agent:
allow_code_execution: Optional[bool] = False,
max_retry_limit: int = 2,
code_execution_mode: Literal["safe", "unsafe"] = "safe",
embedder_config: Optional[Dict[str, Any]] = None,
knowledge: Optional[Union[List[str], Any]] = None,
knowledge: Optional[Union[bool, List[str], Any]] = None,
retrieval_config: Optional[Union[Dict[str, Any], Any]] = None,
knowledge_config: Optional[Dict[str, Any]] = None,
rag_config: Optional[Dict[str, Any]] = None,
embedder_config: Optional[Dict[str, Any]] = None,
user_id: Optional[str] = None,
use_system_prompt: Optional[bool] = True,
markdown: bool = True,
stream: bool = False,
metrics: bool = False,
self_reflect: bool = False,
max_reflect: int = 3,
min_reflect: int = 1,
reflect_llm: Optional[str] = None,
reflect_prompt: Optional[str] = None,
user_id: Optional[str] = None,
reasoning_steps: bool = False,
guardrail: Optional[Union[Callable[['TaskOutput'], Tuple[bool, Any]], str]] = None,
max_guardrail_retries: int = 3,
handoffs: Optional[List[Union['Agent', 'Handoff']]] = None,
base_url: Optional[str] = None,
api_key: Optional[str] = None,
web_search: Optional[Union[bool, Dict[str, Any]]] = None,
web_fetch: Optional[Union[bool, Dict[str, Any]]] = None,
prompt_caching: Optional[bool] = None,
claude_memory: Optional[Union[bool, Any]] = None,
plan_mode: bool = False,
planning: bool = False,
planning_tools: Optional[List[Any]] = None,
planning_reasoning: bool = False,
planning: Optional[Union[bool, Any]] = False,
auto_save: Optional[str] = None,
skills: Optional[List[str]] = None,
skills_dirs: Optional[List[str]] = None,
@@ -313,7 +300,12 @@ class Agent:
output_style: Optional[Any] = None,
thinking_budget: Optional[Any] = None,
# Context management (single param for all context features)
context: Optional[Union[bool, Any]] = False
context: Optional[Union[bool, Any]] = False,
# NEW: Consolidated feature params (agent-centric API)
# These take precedence over individual params when provided
reflection: Optional[Union[bool, Any]] = None, # Union[bool, ReflectionConfig]
guardrails: Optional[Union[bool, Callable, Any]] = None, # Union[bool, Callable, GuardrailConfig]
web: Optional[Union[bool, Any]] = None, # Union[bool, WebConfig]
):
"""Initialize an Agent instance.
@@ -429,6 +421,178 @@ class Agent:
Agent._configure_logging()
Agent._logging_configured = True
# ============================================================
# CONSOLIDATED PARAMS EXTRACTION (agent-centric API)
# New consolidated params take precedence over individual params
# Initialize removed params with defaults before extraction
# ============================================================
# Initialize removed params with defaults (these were removed from signature)
claude_memory = None
self_reflect = False
max_reflect = 3
min_reflect = 1
reflect_llm = None
reflect_prompt = None
guardrail = None
max_guardrail_retries = 3
web_search = None
web_fetch = None
plan_mode = False
planning_tools = None
planning_reasoning = False
# Extract memory settings from consolidated 'memory' param
# memory can be: False, True, MemoryConfig, or MemoryManager instance
_memory_user_id = user_id # Default from param
_memory_session_id = session_id # Default from param
_memory_db = db # Default from param
_memory_auto_memory = auto_memory # Default from param
_memory_claude_memory = claude_memory # Default from param
if memory is not None and memory is not False:
if hasattr(memory, 'user_id') and hasattr(memory, 'backend'):
# It's a MemoryConfig
if memory.user_id:
_memory_user_id = memory.user_id
if memory.session_id:
_memory_session_id = memory.session_id
if memory.db:
_memory_db = memory.db
_memory_auto_memory = memory.auto_memory
_memory_claude_memory = memory.claude_memory
# Convert MemoryConfig to appropriate memory init value
if memory.backend == "file" or (hasattr(memory.backend, 'value') and memory.backend.value == "file"):
memory = True # Use FileMemory
elif memory.config:
memory = memory.config # Use config dict
else:
backend_val = memory.backend.value if hasattr(memory.backend, 'value') else memory.backend
memory = backend_val # Use backend string
# Apply extracted memory values
user_id = _memory_user_id
session_id = _memory_session_id
db = _memory_db
auto_memory = _memory_auto_memory
claude_memory = _memory_claude_memory
# Extract knowledge settings from consolidated 'knowledge' param
# knowledge can be: False, True, List[str], KnowledgeConfig, or KnowledgeBase instance
_knowledge_sources = None
_knowledge_retrieval_config = retrieval_config
_knowledge_embedder_config = embedder_config
if knowledge is not None and knowledge is not False:
if isinstance(knowledge, list):
# It's a list of sources - use directly
_knowledge_sources = knowledge
elif hasattr(knowledge, 'search') and hasattr(knowledge, 'add'):
# It's a Knowledge/KnowledgeBase instance - pass through unchanged
# Don't modify knowledge, let the existing logic handle it
pass
elif hasattr(knowledge, 'sources') and hasattr(knowledge, 'embedder'):
# It's a KnowledgeConfig (has sources list and embedder string)
_knowledge_sources = knowledge.sources
_knowledge_embedder_config = knowledge.embedder_config or embedder_config
# Build retrieval config from KnowledgeConfig
if knowledge.config:
_knowledge_retrieval_config = knowledge.config
else:
_knowledge_retrieval_config = {
'top_k': knowledge.retrieval_k,
'threshold': knowledge.retrieval_threshold,
'rerank': knowledge.rerank,
'rerank_model': knowledge.rerank_model,
}
# Update knowledge to be the sources list for internal processing
knowledge = _knowledge_sources if _knowledge_sources else None
elif knowledge is True:
# Enable knowledge but no sources provided yet
knowledge = None
# Apply extracted knowledge values
retrieval_config = _knowledge_retrieval_config
embedder_config = _knowledge_embedder_config
# Extract planning settings from consolidated 'planning' param
# planning can be: False, True, or PlanningConfig
_planning_enabled = planning
_plan_mode = plan_mode
_planning_tools = planning_tools
_planning_reasoning = planning_reasoning
if planning is not None:
if planning is True:
_planning_enabled = True
elif planning is False:
_planning_enabled = False
elif hasattr(planning, 'reasoning'):
# It's a PlanningConfig
_planning_enabled = True
_planning_tools = planning.tools
_planning_reasoning = planning.reasoning
_plan_mode = planning.read_only
# planning param becomes True for internal use
planning = True
# Apply extracted planning values
plan_mode = _plan_mode
planning_tools = _planning_tools
planning_reasoning = _planning_reasoning
# Extract reflection settings from consolidated 'reflection' param
if reflection is not None:
if reflection is True:
# Enable with defaults
self_reflect = True
elif reflection is False:
self_reflect = False
elif hasattr(reflection, 'min_iterations'):
# It's a ReflectionConfig
self_reflect = True
min_reflect = reflection.min_iterations
max_reflect = reflection.max_iterations
reflect_llm = reflection.llm
reflect_prompt = reflection.prompt
# Extract guardrail settings from consolidated 'guardrails' param
if guardrails is not None:
if guardrails is True:
# Enable with defaults (no-op, user must provide validator)
pass
elif guardrails is False:
guardrail = None
elif callable(guardrails):
# Direct validator function
guardrail = guardrails
elif hasattr(guardrails, 'validator'):
# It's a GuardrailConfig
if guardrails.validator:
guardrail = guardrails.validator
elif guardrails.llm_validator:
guardrail = guardrails.llm_validator
max_guardrail_retries = guardrails.max_retries
# Extract web settings from consolidated 'web' param
if web is not None:
if web is True:
# Enable both search and fetch with defaults
web_search = True
web_fetch = True
elif web is False:
web_search = False
web_fetch = False
elif hasattr(web, 'search'):
# It's a WebConfig
web_search = web.search
web_fetch = web.fetch
# Could also extract search_config, fetch_config if needed
# ============================================================
# END CONSOLIDATED PARAMS EXTRACTION
# ============================================================
# If instructions are provided, use them to set role, goal, and backstory
if instructions:
self.name = name or "Agent"
src/praisonai-agents/praisonaiagents/agents/agents.py
+28 -1
View File
@@ -127,7 +127,34 @@ def process_task_context(context_item, verbose=0, user_id=None):
return str(context_item) # Fallback for unknown types
class PraisonAIAgents:
def __init__(self, agents, tasks=None, verbose=0, completion_checker=None, max_retries=5, process="sequential", manager_llm=None, memory=False, memory_config=None, embedder=None, user_id=None, max_iter=10, stream=True, name: Optional[str] = None, planning: bool = False, planning_llm: Optional[str] = None, auto_approve_plan: bool = False, planning_tools: Optional[List] = None, planning_reasoning: bool = False, on_task_start: Optional[Callable] = None, on_task_complete: Optional[Callable] = None, variables: Optional[Dict[str, Any]] = None, context: Optional[Any] = False):
def __init__(
self,
agents,
tasks=None,
verbose=0,
completion_checker=None,
max_retries=5,
process="sequential",
manager_llm=None,
# Consolidated feature params (agent-centric API)
memory: Optional[Any] = False, # Union[bool, MemoryConfig]
planning: Optional[Any] = False, # Union[bool, PlanningConfig]
context: Optional[Any] = False, # Union[bool, ManagerConfig, ContextManager]
# Legacy params (kept for backward compatibility)
memory_config=None,
embedder=None,
user_id=None,
max_iter=10,
stream=True,
name: Optional[str] = None,
planning_llm: Optional[str] = None,
auto_approve_plan: bool = False,
planning_tools: Optional[List] = None,
planning_reasoning: bool = False,
on_task_start: Optional[Callable] = None,
on_task_complete: Optional[Callable] = None,
variables: Optional[Dict[str, Any]] = None,
):
# Add check at the start if memory is requested
if memory:
try:
src/praisonai-agents/praisonaiagents/config/__init__.py
+43
View File
@@ -0,0 +1,43 @@
"""
Configuration Module for PraisonAI Agents.
Provides feature configuration classes for agent-centric API:
- MemoryConfig: Memory and session management
- KnowledgeConfig: RAG and knowledge retrieval
- PlanningConfig: Planning mode settings
- ReflectionConfig: Self-reflection settings
- GuardrailConfig: Safety and validation
- WebConfig: Web search and fetch
All imports are lazy-loaded for zero performance impact.
"""
__all__ = [
# Enums
"MemoryBackend",
"ChunkingStrategy",
"GuardrailAction",
"WebSearchProvider",
# Config classes
"MemoryConfig",
"KnowledgeConfig",
"PlanningConfig",
"ReflectionConfig",
"GuardrailConfig",
"WebConfig",
# Type aliases
"MemoryParam",
"KnowledgeParam",
"PlanningParam",
"ReflectionParam",
"GuardrailParam",
"WebParam",
]
def __getattr__(name: str):
"""Lazy load config classes."""
if name in __all__:
from . import feature_configs
return getattr(feature_configs, name)
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
src/praisonai-agents/praisonaiagents/config/feature_configs.py
+397
View File
@@ -0,0 +1,397 @@
"""
Feature Configuration Classes for PraisonAI Agents.
Provides dataclasses for consolidated feature configuration:
- MemoryConfig: Memory and session management
- KnowledgeConfig: RAG and knowledge retrieval
- PlanningConfig: Planning mode settings
- ReflectionConfig: Self-reflection settings
- GuardrailConfig: Safety and validation
- WebConfig: Web search and fetch
All configs follow the agent-centric pattern:
- False: Feature disabled (zero overhead)
- True: Feature enabled with safe defaults
- Config: Custom configuration
- Instance: Pre-configured manager/engine
Usage:
from praisonaiagents import Agent, MemoryConfig, KnowledgeConfig
# Simple enable
agent = Agent(instructions="...", memory=True)
# With config
agent = Agent(
instructions="...",
memory=MemoryConfig(backend="redis", user_id="user123"),
knowledge=KnowledgeConfig(sources=["docs/"], rerank=True),
)
"""
from dataclasses import dataclass, field
from typing import Dict, List, Any, Optional, Callable, Tuple, Union
from enum import Enum
class MemoryBackend(str, Enum):
"""Memory storage backends."""
FILE = "file"
SQLITE = "sqlite"
REDIS = "redis"
POSTGRES = "postgres"
MEM0 = "mem0"
MONGODB = "mongodb"
@dataclass
class MemoryConfig:
"""
Configuration for agent memory and session management.
Consolidates: memory, auto_memory, claude_memory, user_id, session_id, db
Usage:
# Simple enable (uses FileMemory)
Agent(memory=True)
# With backend
Agent(memory=MemoryConfig(backend="redis"))
# Full config
Agent(memory=MemoryConfig(
backend="sqlite",
user_id="user123",
session_id="session456",
auto_memory=True,
))
"""
# Backend selection
backend: Union[str, MemoryBackend] = MemoryBackend.FILE
# Session identification
user_id: Optional[str] = None
session_id: Optional[str] = None
# Auto-memory extraction
auto_memory: bool = False
# Claude-specific memory (for Anthropic models)
claude_memory: bool = False
# Database adapter (for advanced use)
db: Optional[Any] = None
# Memory configuration dict (for provider-specific settings)
config: Optional[Dict[str, Any]] = None
def to_dict(self) -> Dict[str, Any]:
"""Convert to dictionary."""
return {
"backend": self.backend.value if isinstance(self.backend, MemoryBackend) else self.backend,
"user_id": self.user_id,
"session_id": self.session_id,
"auto_memory": self.auto_memory,
"claude_memory": self.claude_memory,
"config": self.config,
}
class ChunkingStrategy(str, Enum):
"""Knowledge chunking strategies."""
FIXED = "fixed"
SEMANTIC = "semantic"
SENTENCE = "sentence"
PARAGRAPH = "paragraph"
@dataclass
class KnowledgeConfig:
"""
Configuration for RAG and knowledge retrieval.
Consolidates: knowledge, retrieval_config, knowledge_config, rag_config, embedder_config
Usage:
# Simple enable with sources
Agent(knowledge=["docs/", "data.pdf"])
# With config
Agent(knowledge=KnowledgeConfig(
sources=["docs/"],
embedder="openai",
chunking_strategy="semantic",
retrieval_k=5,
rerank=True,
))
"""
# Knowledge sources (files, directories, URLs)
sources: List[str] = field(default_factory=list)
# Embedder configuration
embedder: str = "openai"
embedder_config: Optional[Dict[str, Any]] = None
# Chunking
chunking_strategy: Union[str, ChunkingStrategy] = ChunkingStrategy.SEMANTIC
chunk_size: int = 1000
chunk_overlap: int = 200
# Retrieval
retrieval_k: int = 5
retrieval_threshold: float = 0.0
# Reranking
rerank: bool = False
rerank_model: Optional[str] = None
# Auto-retrieval (inject context automatically)
auto_retrieve: bool = True
# Full config dict (for advanced use)
config: Optional[Dict[str, Any]] = None
def to_dict(self) -> Dict[str, Any]:
"""Convert to dictionary."""
return {
"sources": self.sources,
"embedder": self.embedder,
"embedder_config": self.embedder_config,
"chunking_strategy": self.chunking_strategy.value if isinstance(self.chunking_strategy, ChunkingStrategy) else self.chunking_strategy,
"chunk_size": self.chunk_size,
"chunk_overlap": self.chunk_overlap,
"retrieval_k": self.retrieval_k,
"retrieval_threshold": self.retrieval_threshold,
"rerank": self.rerank,
"rerank_model": self.rerank_model,
"auto_retrieve": self.auto_retrieve,
"config": self.config,
}
@dataclass
class PlanningConfig:
"""
Configuration for planning mode.
Consolidates: planning, plan_mode, planning_tools, planning_reasoning, planning_llm
Usage:
# Simple enable
Agent(planning=True)
# With config
Agent(planning=PlanningConfig(
llm="gpt-4o",
tools=[search_tool],
reasoning=True,
auto_approve=False,
))
"""
# Planning LLM (if different from main)
llm: Optional[str] = None
# Tools available during planning
tools: Optional[List[Any]] = None
# Enable reasoning during planning
reasoning: bool = False
# Auto-approve plans without user confirmation
auto_approve: bool = False
# Read-only mode (plan_mode) - only read operations allowed
read_only: bool = False
def to_dict(self) -> Dict[str, Any]:
"""Convert to dictionary."""
return {
"llm": self.llm,
"tools": [str(t) for t in (self.tools or [])],
"reasoning": self.reasoning,
"auto_approve": self.auto_approve,
"read_only": self.read_only,
}
@dataclass
class ReflectionConfig:
"""
Configuration for self-reflection.
Consolidates: self_reflect, max_reflect, min_reflect, reflect_llm, reflect_prompt
Usage:
# Simple enable
Agent(reflection=True)
# With config
Agent(reflection=ReflectionConfig(
min_iterations=1,
max_iterations=3,
llm="gpt-4o",
prompt="Evaluate your response for accuracy...",
))
"""
# Iteration limits
min_iterations: int = 1
max_iterations: int = 3
# Reflection LLM (if different from main)
llm: Optional[str] = None
# Custom reflection prompt
prompt: Optional[str] = None
def to_dict(self) -> Dict[str, Any]:
"""Convert to dictionary."""
return {
"min_iterations": self.min_iterations,
"max_iterations": self.max_iterations,
"llm": self.llm,
"prompt": self.prompt,
}
class GuardrailAction(str, Enum):
"""Action to take when guardrail fails."""
RETRY = "retry"
SKIP = "skip"
RAISE = "raise"
@dataclass
class GuardrailConfig:
"""
Configuration for guardrails and safety validation.
Consolidates: guardrail, max_guardrail_retries, policy
Usage:
# With validator function
Agent(guardrails=my_validator_fn)
# With config
Agent(guardrails=GuardrailConfig(
validator=my_validator_fn,
max_retries=3,
on_fail="retry",
))
# With LLM-based validation
Agent(guardrails=GuardrailConfig(
llm_validator="Ensure response is helpful and safe",
max_retries=2,
))
"""
# Validator function: (TaskOutput) -> Tuple[bool, Any]
validator: Optional[Callable[..., Tuple[bool, Any]]] = None
# LLM-based validation prompt
llm_validator: Optional[str] = None
# Retry settings
max_retries: int = 3
on_fail: Union[str, GuardrailAction] = GuardrailAction.RETRY
# Policy engine (for advanced use)
policy: Optional[Any] = None
def to_dict(self) -> Dict[str, Any]:
"""Convert to dictionary."""
return {
"validator": str(self.validator) if self.validator else None,
"llm_validator": self.llm_validator,
"max_retries": self.max_retries,
"on_fail": self.on_fail.value if isinstance(self.on_fail, GuardrailAction) else self.on_fail,
}
class WebSearchProvider(str, Enum):
"""Web search providers."""
DUCKDUCKGO = "duckduckgo"
GOOGLE = "google"
BING = "bing"
TAVILY = "tavily"
SERPER = "serper"
@dataclass
class WebConfig:
"""
Configuration for web search and fetch capabilities.
Consolidates: web_search, web_fetch
Usage:
# Simple enable
Agent(web=True)
# With config
Agent(web=WebConfig(
search=True,
fetch=True,
search_provider="duckduckgo",
max_results=5,
))
"""
# Enable web search
search: bool = True
# Enable web fetch (retrieve full page content)
fetch: bool = True
# Search provider
search_provider: Union[str, WebSearchProvider] = WebSearchProvider.DUCKDUCKGO
# Search settings
max_results: int = 5
# Search config dict (for provider-specific settings)
search_config: Optional[Dict[str, Any]] = None
# Fetch config dict
fetch_config: Optional[Dict[str, Any]] = None
def to_dict(self) -> Dict[str, Any]:
"""Convert to dictionary."""
return {
"search": self.search,
"fetch": self.fetch,
"search_provider": self.search_provider.value if isinstance(self.search_provider, WebSearchProvider) else self.search_provider,
"max_results": self.max_results,
"search_config": self.search_config,
"fetch_config": self.fetch_config,
}
# Type aliases for Union types used in Agent.__init__
MemoryParam = Union[bool, MemoryConfig, Any] # Any = MemoryManager instance
KnowledgeParam = Union[bool, List[str], KnowledgeConfig, Any] # Any = KnowledgeBase instance
PlanningParam = Union[bool, PlanningConfig]
ReflectionParam = Union[bool, ReflectionConfig]
GuardrailParam = Union[bool, Callable[..., Tuple[bool, Any]], GuardrailConfig, Any] # Any = GuardrailEngine
WebParam = Union[bool, WebConfig]
__all__ = [
# Enums
"MemoryBackend",
"ChunkingStrategy",
"GuardrailAction",
"WebSearchProvider",
# Config classes
"MemoryConfig",
"KnowledgeConfig",
"PlanningConfig",
"ReflectionConfig",
"GuardrailConfig",
"WebConfig",
# Type aliases
"MemoryParam",
"KnowledgeParam",
"PlanningParam",
"ReflectionParam",
"GuardrailParam",
"WebParam",
]
src/praisonai-agents/pyproject.toml
+1 -1
View File
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
[project]
name = "praisonaiagents"
version = "0.8.1"
version = "0.9.0"
description = "Praison AI agents for completing complex tasks with Self Reflection Agents"
readme = "README.md"
requires-python = ">=3.10"
src/praisonai-agents/uv.lock
Generated
+1 -1
View File
@@ -2422,7 +2422,7 @@ wheels = [
[[package]]
name = "praisonaiagents"
version = "0.8.1"
version = "0.9.0"
source = { editable = "." }
dependencies = [
{ name = "aiohttp" },
src/praisonai/praisonai.rb
+2 -2
View File
@@ -3,8 +3,8 @@ class Praisonai < Formula
desc "AI tools for various AI applications"
homepage "https://github.com/MervinPraison/PraisonAI"
url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.3.1.tar.gz"
sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.3.1.tar.gz | shasum -a 256`.split.first
url "https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.4.0.tar.gz"
sha256 `curl -sL https://github.com/MervinPraison/PraisonAI/archive/refs/tags/v3.4.0.tar.gz | shasum -a 256`.split.first
license "MIT"
depends_on "[email protected]"
src/praisonai/praisonai/deploy.py
+1 -1
View File
@@ -57,7 +57,7 @@ class CloudDeployer:
file.write("FROM python:3.11-slim\n")
file.write("WORKDIR /app\n")
file.write("COPY . .\n")
file.write("RUN pip install flask praisonai==3.3.1 gunicorn markdown\n")
file.write("RUN pip install flask praisonai==3.4.0 gunicorn markdown\n")
file.write("EXPOSE 8080\n")
file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
src/praisonai/praisonai/version.py
+1 -1
View File
@@ -1 +1 @@
__version__ = "3.3.1"
__version__ = "3.4.0"
src/praisonai/pyproject.toml
+1 -1
View File
@@ -12,7 +12,7 @@ dependencies = [
"rich>=13.7",
"markdown>=3.5",
"pyparsing>=3.0.0",
"praisonaiagents>=0.8.1",
"praisonaiagents>=0.9.0",
"python-dotenv>=0.19.0",
"instructor>=1.3.3",
"PyYAML>=6.0",
tests/unit/cli/queue/__init__.py → src/praisonai/tests/unit/cli/queue/__init__.py
View File
File renamed without changes.
tests/unit/cli/queue/test_models.py → src/praisonai/tests/unit/cli/queue/test_models.py
View File
File renamed without changes.
tests/unit/cli/queue/test_persistence.py → src/praisonai/tests/unit/cli/queue/test_persistence.py
View File
File renamed without changes.
tests/unit/cli/queue/test_scheduler.py → src/praisonai/tests/unit/cli/queue/test_scheduler.py
View File
File renamed without changes.
tests/unit/cli/tui/__init__.py → src/praisonai/tests/unit/cli/tui/__init__.py
View File
File renamed without changes.
tests/unit/cli/tui/test_events.py → src/praisonai/tests/unit/cli/tui/test_events.py
View File
File renamed without changes.
tests/unit/cli/tui/test_mock_provider.py → src/praisonai/tests/unit/cli/tui/test_mock_provider.py
View File
File renamed without changes.
tests/unit/cli/tui/test_orchestrator.py → src/praisonai/tests/unit/cli/tui/test_orchestrator.py
View File
File renamed without changes.
src/praisonai/uv.lock
Generated
+4 -4
View File
@@ -4276,7 +4276,7 @@ requires-dist = [
{ name = "praisonai-tools", marker = "extra == 'autogen'", specifier = ">=0.1.0" },
{ name = "praisonai-tools", marker = "extra == 'autogen-v4'", specifier = ">=0.1.0" },
{ name = "praisonai-tools", marker = "extra == 'crewai'", specifier = ">=0.1.0" },
{ name = "praisonaiagents", specifier = ">=0.8.1" },
{ name = "praisonaiagents", specifier = ">=0.9.0" },
{ name = "pyautogen", marker = "extra == 'autogen'", specifier = "==0.2.29" },
{ name = "pydantic", marker = "extra == 'chat'", specifier = "<=2.10.1" },
{ name = "pydantic", marker = "extra == 'code'", specifier = "<=2.10.1" },
@@ -4324,7 +4324,7 @@ wheels = [
[[package]]
name = "praisonaiagents"
version = "0.8.1"
version = "0.9.0"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "aiohttp" },
@@ -4333,9 +4333,9 @@ dependencies = [
{ name = "pydantic" },
{ name = "rich" },
]
sdist = { url = "https://files.pythonhosted.org/packages/d1/a1/3577e22f24fd64c870d1b5e0cb56f7addd88c45d0c2fbb649a63cbf509d5/praisonaiagents-0.8.1.tar.gz", hash = "sha256:f17f6e8bdecdebb7c0c234ebc7103070c4546b31d41e878572208c75e6ef19ef", size = 897661, upload-time = "2026-01-08T12:24:08.607Z" }
sdist = { url = "https://files.pythonhosted.org/packages/f5/a8/c2e09f15cc54dec0afe91c69ad75fc8a1634de9ae2701d08c1e7cd64a4b5/praisonaiagents-0.9.0.tar.gz", hash = "sha256:a1f1e38676f723e7fbc1d8fa9314e63d1884fb8a069fbafa5ea028ec4fb9bf66", size = 902419, upload-time = "2026-01-08T13:23:10.826Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/71/01/d0afaf98e78da1d1293f6f1a53e6b2f7b14c8ba1908b70eed16e5b138427/praisonaiagents-0.8.1-py3-none-any.whl", hash = "sha256:b898f8f1f38ae8d010dfba69f443f146faa2d685c997aa5a4992e786dc115654", size = 866252, upload-time = "2026-01-08T12:24:05.975Z" },
{ url = "https://files.pythonhosted.org/packages/3f/da/341d32c829f9928ad858ffaf736e10a84ca3710fe3811e714a0d2cd576a2/praisonaiagents-0.9.0-py3-none-any.whl", hash = "sha256:1de58782b547ef5f2ec9df1ab3a41a9fb7b990fd3b0769eea5a47d9544ecf7f8", size = 871844, upload-time = "2026-01-08T13:23:08.584Z" },
]
[[package]]