This page is machine-translated from French. Read the French original.
Frequently asked questions
Confidentiality
Is my data leaving my infrastructure?
In a fully local configuration, no: documents, indexes, conversations, and templates remain on your system. Each output results from an explicit choice—external template provider, hosted vector database, web search engine. The screen Réglages → Confidentialité gives the actual state.
Does WivenLLM work without an internet connection? Yes, in a fully local configuration. A connection is only required to download a model for the first time, import a remote source, or use an external service.
Is the data used to train a model? Not on the WivenLLM side: nothing is sent anywhere by default. If you connect an external provider, then... his conditions that apply — to be verified, professional offers often differ from consumer offers.
Do my colleagues see my conversations? No. An administrator, however, can view the instance's history — this is necessary for operation, and Users must be informed of this..
Where is the data physically stored? The instance is installed where it is located: your workstation, your server, or the datacenter of the hosted instance. There is no central storage.
Costs
How much does it cost to use? In a fully local setup, there are no usage fees: the cost is that of the hardware and its operation. With an external provider, billing is proportional to the volume exchanged.
What causes the bill to increase with an external supplier? The pinned documents (injected with each message), a long history, a large number of recovered fragments, and above all the agents — each step is an additional call.
How to reduce costs without compromising quality? A router models : a default economic model, a powerful model for complex cases. Also reduce the history and only pin what is strictly necessary.
Quality of responses
The assistant is making up answers. What to do? Three actions, in this order: pass the space into Query mode ; lower the temperature ; specify in the prompt system that any information missing from the documents must be indicated as such.
He cannot find information that is nevertheless present. Check that the document is added to the space and not just imported. Then lower the similarity threshold and increase the number of fragments. Finally, check that the text has been extracted correctly — a scanned PDF may be unreadable.
He quotes unrelated passages. The similarity threshold is too low, or you are requesting too many fragments.
The responses deteriorated suddenly. A change in model, embedding engine, or search parameters. A change in the embedding engine without reindexing degrades search performance without displaying an error message.
He's responding in the wrong language. Add the instruction to the system prompt in the space: "Always answer in French." The interface language does not determine the language of the answers.
Models
Which model should I choose? Consult the hardware diagnostics It indicates for each model in the catalog whether it is suitable for your machine. If in doubt, start small and work your way up. → Choosing your models
Can I change the model later? Yes, without consequence: the documents remain indexed and the conversations readable. However, Changing the embeddings engine requires reindexing..
Local responses are slow. Normal without a graphics card. Get a smaller model, or switch that space to an external provider.
Can I mix local and cloud storage? Yes. The model is chosen per workspace, and a router can arbitrate message by message.
Documents
How many documents can I index? The integrated local database easily handles corpora of tens of thousands of fragments. Beyond that, an enterprise database is justified.
Can a document be used in multiple spaces? Yes: it is extracted once and indexed in each space where you add it.
What happens to a deleted document? When removed from a space, it loses its vectors in that space but remains in the library. When deleted from the library, it disappears from all spaces and its extracted text is erased.
My scanned PDFs are not being read properly. Character recognition depends on scan quality. A tilted or low-resolution scan will produce incorrect text. Rescanning correctly, or using a dedicated recognition tool beforehand, is the only real solution.
Agents Verification Status
Can an agent send an email on their own? Messaging skills are designed for prepare rather than dispatching, so that a valid human can handle it. And an unactivated skill does not exist for the agent.
Can an agent modify my files? Only if the corresponding skill is enabled, and in the authorized directory. Each elementary operation can be disabled separately.
My agent isn't using the right tools. The pattern is almost always the same: operating tools is more demanding than conversing. Assign the agent the most capable model you have available. Then verify that the required skill is indeed activated in that role.
Why is an agent so slow? It makes several calls to the model, one per step. A ten-step task takes about ten times longer than a simple question.
Exploitation
What needs to be saved? The storage directory and the configuration file. Nothing else — the application will reinstall. Try a restore.
How do I update? Save your data, restore the new version, and restart while preserving your storage space. Any necessary migrations will be applied at startup.
How many simultaneous users? It depends on the model and the hardware, not the application. A local model processes requests one after another; an external provider absorbs competition much more easily.
Can I migrate from a workstation to a server? Yes. The content fits in the storage directory; moving it moves the instance.
A user cannot see a workspace. He is not a member. Add him from the space settings, under the Members tab.
One more question?
- The screen Help The application links to this documentation.
- The support address set by your administrator can be found in the application footer.