github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3492] Add enhancement to allow RAG functionnality #2150

New Issue
Open
opened 2026-04-12 12:22:49 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 12:22:49 -05:00
Owner
Copy Link

Originally created by @g02200jeff on GitHub (Apr 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3492

What are you trying to do?

I want use a custom script on ollama server (windows) to execute Retrieval Augmented Generation (RAG) process. How can I do ?
(I have an example which is working with a python script, langchain and ollama but I can't do it behing the ollama server using api restful).

How should we solve this?

Allow Retrieval Augmented Generation (RAG) or add an example

What is the impact of not solving this?

No response

Anything else?

No response

Originally created by @g02200jeff on GitHub (Apr 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3492 ### What are you trying to do? I want use a custom script on ollama server (windows) to execute Retrieval Augmented Generation (RAG) process. How can I do ? (I have an example which is working with a python script, langchain and ollama but I can't do it behing the ollama server using api restful). ### How should we solve this? Allow Retrieval Augmented Generation (RAG) or add an example ### What is the impact of not solving this? _No response_ ### Anything else? _No response_
GiteaMirror added the feature request label 2026-04-12 12:22:49 -05:00
GiteaMirror commented 2026-04-12 12:22:50 -05:00
Author
Owner
Copy Link

@ThisModernDay commented on GitHub (Apr 4, 2024):

@g02200jeff When I need to do RAG using ollama I have always used a vector database and an embedding model (EX: nomic-embed-text:latest) on the embeddings endpoint to generate my embeddings and then search for the closest matching embedding.

<!-- gh-comment-id:2037605997 --> @ThisModernDay commented on GitHub (Apr 4, 2024): @g02200jeff When I need to do RAG using ollama I have always used a vector database and an embedding model (EX: nomic-embed-text:latest) on the embeddings endpoint to generate my embeddings and then search for the closest matching embedding.
GiteaMirror commented 2026-04-12 12:22:50 -05:00
Author
Owner
Copy Link

@eusebiu commented on GitHub (Apr 6, 2024):

Check out this: https://python.langchain.com/docs/integrations/llms/ollama/
https://python.langchain.com/docs/use_cases/question_answering/quickstart/

<!-- gh-comment-id:2041045445 --> @eusebiu commented on GitHub (Apr 6, 2024): Check out this: https://python.langchain.com/docs/integrations/llms/ollama/ https://python.langchain.com/docs/use_cases/question_answering/quickstart/
GiteaMirror commented 2026-04-12 12:22:50 -05:00
Author
Owner
Copy Link

@aosan commented on GitHub (Apr 6, 2024):

@g02200jeff have a look at my little project, it is a RAG with ollama back-end: https://github.com/aosan/VaultChat

<!-- gh-comment-id:2041069646 --> @aosan commented on GitHub (Apr 6, 2024): @g02200jeff have a look at my little project, it is a RAG with ollama back-end: https://github.com/aosan/VaultChat
GiteaMirror commented 2026-04-12 12:22:51 -05:00
Author
Owner
Copy Link

@mr-pepe69 commented on GitHub (Apr 25, 2024):

i am intrested too, without a way of scoring the output query against the input prompt it is really hard to determinate if the answer is any good, i would love to see ollama get more stuff like that.

<!-- gh-comment-id:2076938042 --> @mr-pepe69 commented on GitHub (Apr 25, 2024): i am intrested too, without a way of scoring the output query against the input prompt it is really hard to determinate if the answer is any good, i would love to see ollama get more stuff like that.
GiteaMirror commented 2026-04-12 12:22:51 -05:00
Author
Owner
Copy Link

@RobbyCBennett commented on GitHub (May 28, 2024):

I love the reliability and speed of Ollama. It would be great to add RAG support because it essentially creates an infinite context window size. This has limitations of speed and accuracy, but it's a great solution for the context window problem.

<!-- gh-comment-id:2135798128 --> @RobbyCBennett commented on GitHub (May 28, 2024): I love the reliability and speed of Ollama. It would be great to add RAG support because it essentially creates an infinite context window size. This has limitations of speed and accuracy, but it's a great solution for the context window problem.
GiteaMirror commented 2026-04-12 12:22:51 -05:00
Author
Owner
Copy Link

@ralyodio commented on GitHub (Jul 31, 2024):

once i query the vector db for related embeddings, how do I call ollama api to use them in a query?

<!-- gh-comment-id:2260114199 --> @ralyodio commented on GitHub (Jul 31, 2024): once i query the vector db for related embeddings, how do I call ollama api to use them in a query?
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2150
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?