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. 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. 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/). * 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. 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: 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. * Make sure your Podman/Docker VM has sufficient memory for the ingestion tasks.
The minimum recommendation is 8 GB of RAM. The minimum recommendation is 8 GB of RAM.
If you regularly upload large files, more RAM is recommended. 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 ### 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. 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). 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). 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). 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. 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: 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. 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). 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. 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 ```bash
podman machine stop podman machine stop
@ -63,7 +71,7 @@ With the default [environment variable](/reference/configuration) values, OpenRA
* 8000: Docling API * 8000: Docling API
* 9200: OpenSearch service * 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. 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). 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 ## Ollama model issues
<PartialOllamaModels /> <PartialOllamaModels />
## Chat issues
See [Troubleshoot chat](/core-components/chat#troubleshoot-chat).