gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

chat service stops working

Browse source
This commit is contained in:
April M 2025-12-22 13:07:43 -08:00
parent adcd0a9e52
commit 7417e30004
4 changed files with 33 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
docs/docs/_partial-prereq-no-script.mdx
View file

@ -4,6 +4,7 @@
The OpenRAG team recommends, at minimum, 8 GB of RAM for container VMs.
However, if you plan to upload large files regularly, more RAM is recommended.
For more information, see [Troubleshoot OpenRAG](/support/troubleshoot).
* Install [`podman-compose`](https://docs.podman.io/en/latest/markdown/podman-compose.1.html) or [Docker Compose](https://docs.docker.com/compose/install/).
To use Docker Compose with Podman, you must alias Docker Compose commands to Podman commands.

10
docs/docs/core-components/chat.mdx
View file

@ -99,4 +99,12 @@ To simplify this integration, you can get pre-configured code snippets directly
The following example demonstrates how to generate and use code snippets for the **OpenRAG OpenSearch Agent** flow:
<PartialIntegrateChat />
<PartialIntegrateChat />
## Troubleshoot chat {#troubleshoot-chat}
The following issues can occur when using the OpenRAG **Chat** feature:
* Documents seem to be missing or interpreted incorrectly: See [Troubleshoot ingestion](/ingestion#troubleshoot-ingestion).
* Service is suddenly unavailable when it was working previously: If there is no other obvious cause, such as the service or container VM being stopped or disconnected, there might be a problem with the flow configuration. Use the [**Restore flow** option](/agents#revert-a-built-in-flow-to-its-original-configuration) to revert the **OpenRAG OpenSearch Agent** flow to its original configuration.
If you made customizations to the flow, make sure to [export your flow](https://docs.langflow.org/concepts-flows-import) before restoring the flow.

2
docs/docs/core-components/ingestion.mdx
View file

@ -248,6 +248,8 @@ If an ingestion task fails, do the following:
* Make sure your Podman/Docker VM has sufficient memory for the ingestion tasks.
The minimum recommendation is 8 GB of RAM.
If you regularly upload large files, more RAM is recommended.
For more information, see [Memory issue with Podman on macOS](/support/troubleshoot#memory-issue-with-podman-on-macos) and [Container out of memory errors](/support/troubleshoot#container-out-of-memory-errors).
* If OCR ingestion fails due to OCR missing, see [OCR ingestion fails (easyocr not installed)](/support/troubleshoot#ocr-ingestion-fails-easyocr-not-installed).
### Problems when referencing documents in chat

30
docs/docs/support/troubleshoot.mdx
View file

@ -7,13 +7,17 @@ import PartialOllamaModels from '@site/docs/_partial-ollama-models.mdx';
This page provides troubleshooting advice for issues you might encounter when using OpenRAG or contributing to OpenRAG.
## OpenSearch fails to start
## Installation and start up issues
The following issues relate to OpenRAG installation and start up.
### OpenSearch fails to start
Check that the value of the `OPENSEARCH_PASSWORD` [environment variable](/reference/configuration) meets the [OpenSearch password complexity requirements](https://docs.opensearch.org/latest/security/configuration/demo-configuration/#setting-up-a-custom-admin-password).
If you need to change the password, you must [reset the OpenRAG services](/manage-services).
## OpenRAG fails to start from the TUI with operation not supported
### OpenRAG fails to start from the TUI with operation not supported
This error occurs when starting OpenRAG with the TUI in [WSL (Windows Subsystem for Linux)](https://learn.microsoft.com/en-us/windows/wsl/install).
@ -21,7 +25,7 @@ The error occurs because OpenRAG is running within a WSL environment, so `webbro
To access the OpenRAG application, open a web browser and enter `http://localhost:3000` in the address bar.
## OpenRAG installation fails with unable to get local issuer certificate
### OpenRAG installation fails with unable to get local issuer certificate
If you are installing OpenRAG on macOS, and the installation fails with `unable to get local issuer certificate`, run the following command, and then retry the installation:
@ -36,14 +40,18 @@ Replace `VERSION` with your installed Python version, such as `3.13`.
Verify that the value of the `LANGFLOW_SUPERUSER` environment variable is correct.
For more information about this variable and how this variable controls Langflow access, see [Langflow settings](/reference/configuration#langflow-settings).
## Container out of memory errors
## Container out of memory errors {#container-out-of-memory-errors}
Increase Docker memory allocation or use the CPU-only deployment (base `docker-compose.yml` without GPU override) to reduce memory usage.
Increase your container VM's allocated memory, or use a CPU-only deployment to reduce memory usage.
## Memory issue with Podman on macOS
For TUI-managed deployments, you can enable **CPU mode** on the TUI's **Status** page.
For self-managed deployments, CPU-only deployments use the `docker-compose.yml` file that doesn't have GPU overrides.
## Memory issue with Podman on macOS {#memory-issue-with-podman-on-macos}
If you're using Podman on macOS, you might need to increase VM memory on your Podman machine.
This example increases the machine size to 8 GB of RAM, which should be sufficient to run OpenRAG.
This example increases the machine size to 8 GB of RAM, which is the minimum recommended RAM for OpenRAG:
```bash
podman machine stop
@ -63,7 +71,7 @@ With the default [environment variable](/reference/configuration) values, OpenRA
* 8000: Docling API
* 9200: OpenSearch service
## OCR ingestion fails (easyocr not installed)
## OCR ingestion fails (easyocr not installed) {#ocr-ingestion-fails-easyocr-not-installed}
Docling ingestion can fail with an OCR-related error that mentions `easyocr` is missing.
This is likely due to a stale `uv` cache when you [install OpenRAG with `uvx`](/install-uvx).
@ -143,4 +151,8 @@ See [Troubleshoot ingestion](/ingestion#troubleshoot-ingestion).
## Ollama model issues
<PartialOllamaModels />
<PartialOllamaModels />
## Chat issues
See [Troubleshoot chat](/core-components/chat#troubleshoot-chat).