PraisonAI 0.0.54__tar.gz → 0.0.55__tar.gz

{praisonai-0.0.54 → praisonai-0.0.55}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PraisonAI
-Version: 0.0.54
+Version: 0.0.55
 Summary: PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration.
 Author: Mervin Praison
 Requires-Python: >=3.10,<3.13
@@ -69,14 +69,38 @@ Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, rep
   </picture>
 </div>
 
-## Google Colab
+## Different User Interfaces:
+
+| Interface | Description | URL |
+|---|---|---|
+| **UI** | Multi Agents such as CrewAI or AutoGen | [https://docs.praison.ai/ui/ui](https://docs.praison.ai/ui/ui) |
+| **Chat** | Chat with 100+ LLMs, single AI Agent | [https://docs.praison.ai/ui/chat](https://docs.praison.ai/ui/chat) |
+| **Code** | Chat with entire Codebase, single AI Agent | [https://docs.praison.ai/ui/code](https://docs.praison.ai/ui/code) |
+
+## Google Colab Multi Agents
 
 |               | Cookbook        | Open in Colab                                                                                                                                                                                                                                  |
 | ------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | Basic         | PraisonAI       | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>       |
 | Include Tools | PraisonAI Tools | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-tools-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a> |
 
-## TL;DR
+## Install
+
+| PraisonAI | PraisonAI Code | PraisonAI Chat |
+| --- | --- | --- |
+| `pip install praisonai` | `pip install "praisonai[code]"` | `pip install "praisonai[chat]"` |
+
+## Key Features
+
+- Automated AI Agents Creation
+- Use CrewAI or AutoGen Framework
+- 100+ LLM Support
+- Chat with ENTIRE Codebase
+- Interactive UIs
+- YAML-based Configuration
+- Custom Tool Integration
+
+## TL;DR Multi Agents
 
 ```bash
 pip install praisonai
@@ -85,14 +109,6 @@ praisonai --init create a movie script about dog in moon
 praisonai
 ```
 
-## Different User Interfaces:
-
-| Interface | Description | URL |
-|---|---|---|
-| **UI** | Multi Agents such as CrewAI or AutoGen | [https://docs.praison.ai/ui/ui](https://docs.praison.ai/ui/ui) |
-| **Chat** | Chat with 100+ LLMs, single AI Agent | [https://docs.praison.ai/ui/chat](https://docs.praison.ai/ui/chat) |
-| **Code** | Chat with entire Codebase, single AI Agent | [https://docs.praison.ai/ui/code](https://docs.praison.ai/ui/code) |
-
 ## Table of Contents
 
 - [Installation](#installation)
@@ -109,7 +125,7 @@ praisonai
 - [Contributing](#contributing)
 - [Star History](#star-history)
 
-## Installation
+## Installation Multi Agents
 
 ```bash
 pip install praisonai
@@ -195,56 +211,17 @@ export OPENAI_API_KEY="Enter your API key"
 praisonai chat
 ```
 
-## Create Custom Tools
-
-- https://docs.praison.ai/tools/custom/
-
-### Step 1: Pre-requisite to Create a Custom Tool
-
-`agents.yaml` file should be present in the current directory.
+## Praison AI Code
 
-If it doesn't exist, create it by running the command `praisonai --init research about the latest AI News and prepare a detailed report`.
-
-### Step 2: to Create a Custom Tool
-
-Create a file called tools.py in the same directory as the agents.yaml file.
-
-```python
-# example tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
+```bash
+pip install "praisonai[code]"
+export OPENAI_API_KEY="Enter your API key"
+praisonai code
 ```
 
-### Step 3: to Create a Custom Tool
-
-Add the tool to the agents.yaml file as show below under the tools section `- InternetSearchTool`.
+## Create Custom Tools
 
-```yaml
-framework: crewai
-topic: research about the latest AI News and prepare a detailed report
-roles:
-  research_analyst:
-    backstory: Experienced in gathering and analyzing data related to AI news trends.
-    goal: Analyze AI News trends
-    role: Research Analyst
-    tasks:
-      gather_data:
-        description:
-          Conduct in-depth research on the latest AI News trends from reputable
-          sources.
-        expected_output: Comprehensive report on current AI News trends.
-    tools:
-      - InternetSearchTool
-```
+- https://docs.praison.ai/tools/custom/
 
 ## Agents Playbook
 

{praisonai-0.0.54 → praisonai-0.0.55}/README.md

@@ -28,14 +28,38 @@ Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, rep
   </picture>
 </div>
 
-## Google Colab
+## Different User Interfaces:
+
+| Interface | Description | URL |
+|---|---|---|
+| **UI** | Multi Agents such as CrewAI or AutoGen | [https://docs.praison.ai/ui/ui](https://docs.praison.ai/ui/ui) |
+| **Chat** | Chat with 100+ LLMs, single AI Agent | [https://docs.praison.ai/ui/chat](https://docs.praison.ai/ui/chat) |
+| **Code** | Chat with entire Codebase, single AI Agent | [https://docs.praison.ai/ui/code](https://docs.praison.ai/ui/code) |
+
+## Google Colab Multi Agents
 
 |               | Cookbook        | Open in Colab                                                                                                                                                                                                                                  |
 | ------------- | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | Basic         | PraisonAI       | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>       |
 | Include Tools | PraisonAI Tools | <a target="_blank" href="https://colab.research.google.com/github/MervinPraison/PraisonAI/blob/main/cookbooks/praisonai-tools-googlecolab.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a> |
 
-## TL;DR
+## Install
+
+| PraisonAI | PraisonAI Code | PraisonAI Chat |
+| --- | --- | --- |
+| `pip install praisonai` | `pip install "praisonai[code]"` | `pip install "praisonai[chat]"` |
+
+## Key Features
+
+- Automated AI Agents Creation
+- Use CrewAI or AutoGen Framework
+- 100+ LLM Support
+- Chat with ENTIRE Codebase
+- Interactive UIs
+- YAML-based Configuration
+- Custom Tool Integration
+
+## TL;DR Multi Agents
 
 ```bash
 pip install praisonai
@@ -44,14 +68,6 @@ praisonai --init create a movie script about dog in moon
 praisonai
 ```
 
-## Different User Interfaces:
-
-| Interface | Description | URL |
-|---|---|---|
-| **UI** | Multi Agents such as CrewAI or AutoGen | [https://docs.praison.ai/ui/ui](https://docs.praison.ai/ui/ui) |
-| **Chat** | Chat with 100+ LLMs, single AI Agent | [https://docs.praison.ai/ui/chat](https://docs.praison.ai/ui/chat) |
-| **Code** | Chat with entire Codebase, single AI Agent | [https://docs.praison.ai/ui/code](https://docs.praison.ai/ui/code) |
-
 ## Table of Contents
 
 - [Installation](#installation)
@@ -68,7 +84,7 @@ praisonai
 - [Contributing](#contributing)
 - [Star History](#star-history)
 
-## Installation
+## Installation Multi Agents
 
 ```bash
 pip install praisonai
@@ -154,56 +170,17 @@ export OPENAI_API_KEY="Enter your API key"
 praisonai chat
 ```
 
-## Create Custom Tools
-
-- https://docs.praison.ai/tools/custom/
-
-### Step 1: Pre-requisite to Create a Custom Tool
-
-`agents.yaml` file should be present in the current directory.
+## Praison AI Code
 
-If it doesn't exist, create it by running the command `praisonai --init research about the latest AI News and prepare a detailed report`.
-
-### Step 2: to Create a Custom Tool
-
-Create a file called tools.py in the same directory as the agents.yaml file.
-
-```python
-# example tools.py
-from duckduckgo_search import DDGS
-from praisonai_tools import BaseTool
-
-class InternetSearchTool(BaseTool):
-    name: str = "InternetSearchTool"
-    description: str = "Search Internet for relevant information based on a query or latest news"
-
-    def _run(self, query: str):
-        ddgs = DDGS()
-        results = ddgs.text(keywords=query, region='wt-wt', safesearch='moderate', max_results=5)
-        return results
+```bash
+pip install "praisonai[code]"
+export OPENAI_API_KEY="Enter your API key"
+praisonai code
 ```
 
-### Step 3: to Create a Custom Tool
-
-Add the tool to the agents.yaml file as show below under the tools section `- InternetSearchTool`.
+## Create Custom Tools
 
-```yaml
-framework: crewai
-topic: research about the latest AI News and prepare a detailed report
-roles:
-  research_analyst:
-    backstory: Experienced in gathering and analyzing data related to AI news trends.
-    goal: Analyze AI News trends
-    role: Research Analyst
-    tasks:
-      gather_data:
-        description:
-          Conduct in-depth research on the latest AI News trends from reputable
-          sources.
-        expected_output: Comprehensive report on current AI News trends.
-    tools:
-      - InternetSearchTool
-```
+- https://docs.praison.ai/tools/custom/
 
 ## Agents Playbook
 

{praisonai-0.0.54 → praisonai-0.0.55}/praisonai/deploy.py

@@ -56,7 +56,7 @@ 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==0.0.54 gunicorn markdown\n")
+            file.write("RUN pip install flask praisonai==0.0.55 gunicorn markdown\n")
             file.write("EXPOSE 8080\n")
             file.write('CMD ["gunicorn", "-b", "0.0.0.0:8080", "api:app"]\n')
             

{praisonai-0.0.54 → praisonai-0.0.55}/praisonai/ui/context.py

@@ -1,6 +1,5 @@
 import os
 import fnmatch
-import re
 import yaml
 from pathlib import Path
 import logging
@@ -34,10 +33,12 @@ class ContextGatherer:
         self.max_file_size = max_file_size
         self.max_tokens = int(os.getenv("PRAISONAI_MAX_TOKENS", max_tokens))
         self.ignore_patterns = self.get_ignore_patterns()
+        self.include_paths = self.get_include_paths()
+        self.included_files = []
 
     def get_ignore_patterns(self):
         """
-        Loads ignore patterns from various sources, prioritizing them in 
+        Loads ignore patterns from various sources, prioritizing them in
         the following order:
             1. .praisonignore
             2. settings.yaml (under code.ignore_files)
@@ -95,6 +96,19 @@ class ContextGatherer:
         logger.debug(f"Final ignore patterns: {modified_ignore_patterns}")
         return modified_ignore_patterns
 
+    def get_include_paths(self):
+        include_paths = []
+
+        # 1. Load from .praisoninclude
+        include_file = os.path.join(self.directory, '.praisoninclude')
+        if os.path.exists(include_file):
+            with open(include_file, 'r') as f:
+                include_paths.extend(
+                    line.strip() for line in f
+                    if line.strip() and not line.startswith('#')
+                )
+        return include_paths
+
     def should_ignore(self, file_path):
         """
         Check if a file or directory should be ignored based on patterns.
@@ -116,31 +130,65 @@ class ContextGatherer:
                any(file_path.endswith(ext) for ext in self.relevant_extensions)
 
     def gather_context(self):
-        """Gather context from relevant files, respecting ignore patterns."""
+        """Gather context from relevant files, respecting ignore patterns and include paths."""
         context = []
         total_files = 0
         processed_files = 0
 
-        for root, dirs, files in os.walk(self.directory):
-            total_files += len(files) 
-            dirs[:] = [d for d in dirs if not self.should_ignore(os.path.join(root, d))]
-            for file in files:
-                file_path = os.path.join(root, file)
-                if not self.should_ignore(file_path) and self.is_relevant_file(file_path):
+        if not self.include_paths:
+            # No include paths specified, process the entire directory
+            for root, dirs, files in os.walk(self.directory):
+                total_files += len(files)
+                dirs[:] = [d for d in dirs if not self.should_ignore(os.path.join(root, d))]
+                for file in files:
+                    file_path = os.path.join(root, file)
+                    if not self.should_ignore(file_path) and self.is_relevant_file(file_path):
+                        try:
+                            with open(file_path, 'r', encoding='utf-8') as f:
+                                content = f.read()
+                                context.append(f"File: {file_path}\n\n{content}\n\n{'='*50}\n")
+                                self.included_files.append(Path(file_path).relative_to(self.directory))
+                        except Exception as e:
+                            logger.error(f"Error reading {file_path}: {e}")
+                    processed_files += 1
+                    print(f"\rProcessed {processed_files}/{total_files} files", end="", flush=True)
+        else:
+            # Process specified include paths
+            for include_path in self.include_paths:
+                full_path = os.path.join(self.directory, include_path)
+                if os.path.isdir(full_path):
+                    for root, dirs, files in os.walk(full_path):
+                        total_files += len(files)
+                        dirs[:] = [d for d in dirs if not self.should_ignore(os.path.join(root, d))]
+                        for file in files:
+                            file_path = os.path.join(root, file)
+                            if not self.should_ignore(file_path) and self.is_relevant_file(file_path):
+                                try:
+                                    with open(file_path, 'r', encoding='utf-8') as f:
+                                        content = f.read()
+                                        context.append(f"File: {file_path}\n\n{content}\n\n{'='*50}\n")
+                                        self.included_files.append(Path(file_path).relative_to(self.directory))
+                                except Exception as e:
+                                    logger.error(f"Error reading {file_path}: {e}")
+                            processed_files += 1
+                            print(f"\rProcessed {processed_files}/{total_files} files", end="", flush=True)
+                elif os.path.isfile(full_path) and self.is_relevant_file(full_path):
                     try:
-                        with open(file_path, 'r', encoding='utf-8') as f:
+                        with open(full_path, 'r', encoding='utf-8') as f:
                             content = f.read()
-                            context.append(f"File: {file_path}\n\n{content}\n\n{'='*50}\n")
+                            context.append(f"File: {full_path}\n\n{content}\n\n{'='*50}\n")
+                            self.included_files.append(Path(full_path).relative_to(self.directory))
                     except Exception as e:
-                        logger.error(f"Error reading {file_path}: {e}")
-                processed_files += 1
-                print(f"\rProcessed {processed_files}/{total_files} files", end="", flush=True)
+                        logger.error(f"Error reading {full_path}: {e}")
+                    processed_files += 1
+                    print(f"\rProcessed {processed_files}/{total_files} files", end="", flush=True)
+
         print()  # New line after progress indicator
         return '\n'.join(context)
 
     def count_tokens(self, text):
         """Count tokens using a simple whitespace-based tokenizer."""
-        return len(text.split()) 
+        return len(text.split())
 
     def truncate_context(self, context):
         """Truncate context to stay within the token limit."""
@@ -165,12 +213,9 @@ class ContextGatherer:
             contents = sorted(path.iterdir())
             pointers = [('└── ' if i == len(contents) - 1 else '├── ') for i in range(len(contents))]
             for pointer, item in zip(pointers, contents):
-                # Use should_ignore for consistency
-                if self.should_ignore(item):
-                    continue
-
                 rel_path = item.relative_to(start_dir)
-                tree.append(f"{prefix}{pointer}{rel_path}")
+                if rel_path in self.included_files:
+                    tree.append(f"{prefix}{pointer}{rel_path}")
 
                 if item.is_dir():
                     add_to_tree(item, prefix + ('    ' if pointer == '└── ' else '│   '))
@@ -193,6 +238,7 @@ class ContextGatherer:
 def main():
     gatherer = ContextGatherer()
     context, token_count, context_tree = gatherer.run()
+    print(context_tree)
     print(f"\nThe context contains approximately {token_count} tokens.")
     print("First 500 characters of context:")
     print(context[:500] + "...")

{praisonai-0.0.54 → praisonai-0.0.55}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "PraisonAI"
-version = "0.0.54"
+version = "0.0.55"
 description = "PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration."
 authors = ["Mervin Praison"]
 license = ""