Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #1299] how to update knowledge files and ollama model #819

New Issue
Closed
opened 2026-02-22 18:21:34 -05:00 by yindo · 3 comments
yindo commented 2026-02-22 18:21:34 -05:00
Owner
Copy Link
Copy Source

Originally created by @ddimit2020 on GitHub (May 7, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1299

Gretting~
i use the docker-compose up to bulid anything llm,also use the local ollama llm bound on anything
but when i update the knowledge and ollama model,actually i can't find the newer knowledge and ollama models
### 1.knowledge e.g.
image
i already upload the 5 files,but when i ask anying and get the answer just the 2 files
image

### 2.ollama model e.g.

the local ollama model include the 6 models
image
but the anything webui can't find the all models
image
if i want choose the llama3, can't choose this model on anything

anything command i shoud command update or any tips?
tks

Originally created by @ddimit2020 on GitHub (May 7, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/1299 Gretting~ i use the docker-compose up to bulid anything llm,also use the local ollama llm bound on anything but when i update the knowledge and ollama model,actually i can't find the newer knowledge and ollama models **### 1.knowledge e.g.** ![image](https://github.com/Mintplex-Labs/anything-llm/assets/164116068/683ed822-7248-40d0-8377-17d61ce8f50b) i already upload the 5 files,but when i ask anying and get the answer just the 2 files ![image](https://github.com/Mintplex-Labs/anything-llm/assets/164116068/74e33dca-4ed9-4985-9c88-7bea953fd7c0) ### ### 2.ollama model e.g. the local ollama model include the 6 models ![image](https://github.com/Mintplex-Labs/anything-llm/assets/164116068/51d95f9e-edc9-4a5e-bc3d-5f3458c2f71a) but the anything webui can't find the all models ![image](https://github.com/Mintplex-Labs/anything-llm/assets/164116068/f44eda78-4f1d-426c-b9de-f4344a1504f6) if i want choose the llama3, can't choose this model on anything anything command i shoud command update or any tips? tks
yindo added the needs info / can't replicate label 2026-02-22 18:21:34 -05:00
yindo closed this issue 2026-02-22 18:21:34 -05:00
yindo commented 2026-02-22 18:21:34 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 7, 2024):

I see you have all your documents pinned, you cannot pin 10K of context into an 8K context window, so in this case, i am pretty sure that is what is preventing the rest of the files from showing during retrieval. Unless all of those file together result in < 8K context that is what is going on there.

As for the second item, did you scroll the input - it may be below phi? I am assuming you did, in which case you are able to see llama3 in the main LLM preference but not in workspace? Correct?

@timothycarambat commented on GitHub (May 7, 2024): I see you have all your documents pinned, you cannot pin 10K of context into an 8K context window, so in this case, i am pretty sure that is what is preventing the rest of the files from showing during retrieval. Unless all of those file together result in < 8K context that is what is going on there. As for the second item, did you scroll the input - it may be below `phi`? I am assuming you did, in which case you are able to see `llama3` in the main LLM preference but **not** in workspace? Correct?
yindo commented 2026-02-22 18:21:34 -05:00
Author
Owner
Copy Link
Copy Source

@ddimit2020 commented on GitHub (May 7, 2024):

@timothycarambat
Gretting~
1.so the major reason it's over 8k, later will not pinned after try it.
2.yes,i pretty sure scroll the input ,can't find match all Model on workspace,also finally checklist again
local ollama list model---->Model have 6
image
but the workspace---->Model have 6
image
but something different,
may i know the workspace the config choose the Ollama should be concurrent match the true all-config,
but actually not really,and i'm make sure when i install the anything llm from docker install,
after something modify the local ollama models del or add,
so after result the Model can't really match ,but i don't have idea how to update the anytingllm to match local Model

@ddimit2020 commented on GitHub (May 7, 2024): @timothycarambat Gretting~ 1.so the major reason it's over 8k, later will not pinned after try it. 2.yes,i pretty sure scroll the input ,can't find match all Model on workspace,also finally checklist again local ollama list model---->Model have 6 ![image](https://github.com/Mintplex-Labs/anything-llm/assets/164116068/cb33fe0e-2962-4a58-9011-3ce3ed51ce37) but the workspace---->Model have 6 ![image](https://github.com/Mintplex-Labs/anything-llm/assets/164116068/61b0c9d2-e457-4e80-822f-d40683d6795d) but something different, may i know the workspace the config choose the Ollama should be concurrent match the true all-config, but actually not really,and i'm make sure when i install the anything llm from docker install, after something modify the local ollama models del or add, so after result the Model can't really match ,but i don't have idea how to update the anytingllm to match local Model
yindo commented 2026-02-22 18:21:34 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 20, 2024):

Is it possible you have two ollama instances running? One on the host and one in docker? Im going to close & mark this as unable to replicate as nobody else has reported this issue so I'm unsure how you can get two different model responses from the same ollama instance since we ping the provider URL directly. The fact we get responses at all means that the AnythingLLM side of things is working, but there is something going on with your setup/configuration as it is clearly pulling some other set of models?

@timothycarambat commented on GitHub (May 20, 2024): Is it possible you have two ollama instances running? One on the host and one in docker? Im going to close & mark this as unable to replicate as nobody else has reported this issue so I'm unsure how you can get two different model responses from the same ollama instance since we ping the provider URL directly. The fact we get responses at all means that the AnythingLLM side of things is working, but there is something going on with your setup/configuration as it is clearly pulling some other set of models?
yindo changed title from how to update knowledge files and ollama model to [GH-ISSUE #1299] how to update knowledge files and ollama model 2026-06-05 14:37:22 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label needs info / can't replicate
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#819
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?