Merge branch 'main' into sdks
This commit is contained in:
Sebastián Estévez
GitHub
commit
3098533a44
5 changed files with 1422 additions and 1658 deletions
|
|
@ -89,7 +89,7 @@ For example: `What documents are available to you?`
|
|||
|
||||
The agent responds with a summary of OpenRAG's default documents.
|
||||
|
||||
3. To verify the agent's response, click <Icon name="Library" aria-hidden="true"/> **Knowledge** to view the documents stored in the OpenRAG OpenSearch vector database.
|
||||
3. To verify the agent's response, click <Icon name="Library" aria-hidden="true"/> **Knowledge** to view the documents stored in the OpenRAG OpenSearch database.
|
||||
You can click a document to view the chunks of the document as they are stored in the database.
|
||||
|
||||
4. Click **Add Knowledge** to add your own documents to your OpenRAG knowledge base.
|
||||
|
|
@ -106,7 +106,7 @@ You can click a document to view the chunks of the document as they are stored i
|
|||
|
||||
* Click <Icon name="Gear" aria-hidden="true"/> **Function Call: search_documents (tool_call)** to view the log of tool calls made by the agent. This is helpful for troubleshooting because it shows you how the agent used particular tools.
|
||||
|
||||
* Click <Icon name="Library" aria-hidden="true"/> **Knowledge** to confirm that the documents are present in the OpenRAG OpenSearch vector database, and then click each document to see how the document was chunked.
|
||||
* Click <Icon name="Library" aria-hidden="true"/> **Knowledge** to confirm that the documents are present in the OpenRAG OpenSearch database, and then click each document to see how the document was chunked.
|
||||
If a document was chunked improperly, you might need to tweak the ingestion or modify and reupload the document.
|
||||
|
||||
* Click <Icon name="Settings2" aria-hidden="true"/> **Settings** to modify the knowledge ingestion settings.
|
||||
|
|
|
|||
|
|
@ -4,11 +4,11 @@ slug: /
|
|||
hide_table_of_contents: true
|
||||
---
|
||||
|
||||
OpenRAG is an open-source package for building agentic RAG systems that integrates with a wide range of orchestration tools, vector databases, and LLM providers.
|
||||
OpenRAG is an open-source package for building agentic RAG systems that integrates with a wide range of orchestration tools, databases, and LLM providers.
|
||||
|
||||
OpenRAG connects and amplifies three popular, proven open-source projects into one powerful platform:
|
||||
|
||||
* [Langflow](https://docs.langflow.org): Langflow is a versatile tool for building and deploying AI agents and MCP servers. It supports all major LLMs, vector databases, and a growing library of AI tools.
|
||||
* [Langflow](https://docs.langflow.org): Langflow is a versatile tool for building and deploying AI agents and MCP servers. It supports all major LLMs, popular vector databases, and a growing library of AI tools.
|
||||
|
||||
OpenRAG uses several built-in flows, and it provides full access to all Langflow features through the embedded Langflow visual editor.
|
||||
|
||||
|
|
@ -17,7 +17,7 @@ OpenRAG connects and amplifies three popular, proven open-source projects into o
|
|||
* [OpenSearch](https://docs.opensearch.org/latest/): OpenSearch is a community-driven, Apache 2.0-licensed open source search and analytics suite that makes it easy to ingest, search, visualize, and analyze data.
|
||||
It provides powerful hybrid search capabilities with enterprise-grade security and multi-tenancy support.
|
||||
|
||||
OpenRAG uses OpenSearch as the underlying vector database for storing and retrieving your documents and associated vector data (embeddings). You can ingest documents from a variety of sources, including your local filesystem and OAuth authenticated connectors to popular cloud storage services.
|
||||
OpenRAG uses OpenSearch as the underlying database for storing and retrieving your documents and associated vector data (embeddings). You can ingest documents from a variety of sources, including your local filesystem and OAuth authenticated connectors to popular cloud storage services.
|
||||
|
||||
* [Docling](https://docling-project.github.io/docling/): Docling simplifies document processing, supports many file formats and advanced PDF parsing, and provides seamless integrations with the generative AI ecosystem.
|
||||
|
||||
|
|
@ -59,7 +59,7 @@ flowchart TD
|
|||
|
||||
* **OpenRAG backend**: The central orchestration service that coordinates all other components.
|
||||
|
||||
* **Langflow**: This container runs a Langflow instance. It provides the embedded Langflow visual editor for editing and creating flow, and it connects to the **OpenSearch** container for vector storage and retrieval.
|
||||
* **Langflow**: This container runs a Langflow instance. It provides the embedded Langflow visual editor for editing and creating flow, and it connects to the **OpenSearch** container for document storage and retrieval.
|
||||
|
||||
* **Docling Serve**: This is a local document processing service managed by the **OpenRAG backend**.
|
||||
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
|
|||
|
||||
[project]
|
||||
name = "openrag"
|
||||
version = "0.1.53"
|
||||
version = "0.1.54"
|
||||
description = "Add your description here"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.13"
|
||||
|
|
|
|||
|
|
@ -96,7 +96,10 @@ class WelcomeScreen(Screen):
|
|||
try:
|
||||
# Use detected runtime command to check services
|
||||
import subprocess
|
||||
compose_cmd = self.container_manager.runtime_info.compose_command + ["ps", "--format", "json"]
|
||||
compose_cmd = self.container_manager.runtime_info.compose_command + [
|
||||
"-f", str(self.container_manager.compose_file),
|
||||
"ps", "--format", "json"
|
||||
]
|
||||
result = subprocess.run(
|
||||
compose_cmd,
|
||||
capture_output=True,
|
||||
|
|
@ -128,20 +131,38 @@ class WelcomeScreen(Screen):
|
|||
|
||||
# Check if services are running (exclude starting/created states)
|
||||
# State can be lowercase or mixed case, so normalize it
|
||||
running_services = []
|
||||
starting_services = []
|
||||
# Only consider expected services (filter out stale/leftover containers)
|
||||
expected = set(self.container_manager.expected_services)
|
||||
name_map = self.container_manager.container_name_map
|
||||
running_services = set()
|
||||
starting_services = set()
|
||||
for s in services:
|
||||
if not isinstance(s, dict):
|
||||
continue
|
||||
# Get service name - try compose label first (most reliable for Podman)
|
||||
labels = s.get('Labels', {}) or {}
|
||||
service_name = labels.get('com.docker.compose.service', '')
|
||||
if not service_name:
|
||||
# Fall back to container name mapping
|
||||
container_name = s.get('Name') or s.get('Service', '')
|
||||
if not container_name:
|
||||
names = s.get('Names', [])
|
||||
if names and isinstance(names, list):
|
||||
container_name = names[0]
|
||||
# Map container name to service name using container_name_map
|
||||
service_name = name_map.get(container_name, container_name)
|
||||
# Skip if not an expected service
|
||||
if service_name not in expected:
|
||||
continue
|
||||
state = str(s.get('State', '')).lower()
|
||||
if state == 'running':
|
||||
running_services.append(s)
|
||||
running_services.add(service_name)
|
||||
elif 'starting' in state or 'created' in state:
|
||||
starting_services.append(s)
|
||||
|
||||
# Only consider services running if we have running services AND no starting services
|
||||
# This prevents showing the button when containers are still coming up
|
||||
self.services_running = len(running_services) > 0 and len(starting_services) == 0
|
||||
starting_services.add(service_name)
|
||||
|
||||
# Services are running if all expected services are in running state
|
||||
# (i.e., we have all expected services running and none are still starting)
|
||||
self.services_running = len(running_services) == len(expected) and len(starting_services) == 0
|
||||
else:
|
||||
self.services_running = False
|
||||
except Exception:
|
||||
|
|
@ -255,15 +276,15 @@ class WelcomeScreen(Screen):
|
|||
# Check if services are running
|
||||
if self.container_manager.is_available():
|
||||
services = await self.container_manager.get_service_status()
|
||||
expected = set(self.container_manager.expected_services)
|
||||
running_services = [
|
||||
s.name for s in services.values() if s.status == ServiceStatus.RUNNING
|
||||
]
|
||||
starting_services = [
|
||||
s.name for s in services.values() if s.status == ServiceStatus.STARTING
|
||||
]
|
||||
# Only consider services running if we have running services AND no starting services
|
||||
# This prevents showing the button when containers are still coming up
|
||||
self.services_running = len(running_services) > 0 and len(starting_services) == 0
|
||||
# Services are running if all expected services are in running state
|
||||
self.services_running = len(running_services) == len(expected) and len(starting_services) == 0
|
||||
else:
|
||||
self.services_running = False
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue