Skip to content

RHAI-ENG-312 - Add a prereq for the version of llama stack client required in a workbench environment #899

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Aug 11, 2025
Merged

RHAI-ENG-312 - Add a prereq for the version of llama stack client required in a workbench environment #899

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
02039b1
Added llama stack client version number prereq
chtyler Aug 8, 2025
55c107c
Changing the llama stack client version number after peer review feed…
chtyler Aug 8, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions modules/ingesting-content-into-a-llama-model.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ You can quickly customize and prototype your retrievable content by ingesting ra
* You have deployed a Llama 3.2 model with a vLLM model server and you have integrated LlamaStack.
* You have created a project workbench within a data science project.
* You have opened a Jupyter notebook and it is running in your workbench environment.
* You have installed the `llama_stack_client` version 0.2.14 or later in your workbench environment.
* You have a created and configured a vector database instance and you know its identifier.
ifdef::self-managed[]
* Your environment has network access to the vector database service through {openshift-platform}.
Expand Down
1 change: 1 addition & 0 deletions modules/preparing-documents-with-docling-for-llama-stack-retrieval.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@ ifdef::upstream[]
* You have installed local object storage buckets and created connections, as described in link:{odhdocshome}/working-on-data-science-projects/#adding-a-connection-to-your-data-science-project_projects[Adding a connection to your data science project].
endif::[]
ifndef::upstream[]
* You have installed the `llama_stack_client` version 0.2.14 or later in your workbench environment.
* You have installed local object storage buckets and created connections, as described in link:{rhoaidocshome}{default-format-url}/working_on_data_science_projects/using-connections_projects#adding-a-connection-to-your-data-science-project_projects[Adding a connection to your data science project].
endif::[]
* You have compiled to YAML a data science pipeline that includes a Docling transform, either one of the RAG demo samples or your own custom pipeline.
Expand Down
1 change: 1 addition & 0 deletions modules/querying-ingested-content-in-a-llama-model.adoc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ endif::[]
* You have configured a Llama Stack deployment by creating a `LlamaStackDistribution` instance to enable RAG functionality.
* You have created a project workbench within a data science project.
* You have opened a Jupyter notebook and it is running in your workbench environment.
* You have installed the `llama_stack_client` version 0.2.14 or later in your workbench environment.
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Verification agent

🧩 Analysis chain

Make the prereq unambiguous and verifiable (name + version).

To avoid confusion and ensure users meet the minimum required client, clarify the wording and align with the install step.

Apply this diff:

-* You have installed the `llama_stack_client` version 0.2.14 or later in your workbench environment. 
+* You have installed the `llama_stack_client` package (version 0.2.14 or later) in your workbench environment.

Run the following scripts to (1) confirm the package name/version exists on PyPI and (2) verify other modules consistently declare the same prerequisite.

🏁 Script executed:

#!/bin/bash
set -euo pipefail

echo "Checking PyPI metadata for llama_stack_client / llama-stack-client..."
for pkg in llama_stack_client llama-stack-client; do
  url="https://pypi.org/pypi/$pkg/json"
  code=$(curl -s -o /dev/null -w "%{http_code}" "$url")
  if [[ "$code" == "200" ]]; then
    echo "Found $pkg on PyPI"
    python - <<'PY'
import json, sys, urllib.request
pkg = sys.argv[1]
with urllib.request.urlopen(f"https://pypi.org/pypi/{pkg}/json") as r:
    data = json.load(r)
print("Latest:", data["info"]["version"])
print("Has 0.2.14:", "0.2.14" in data["releases"])
PY
    "$pkg"
  else
    echo "Not found on PyPI: $pkg (HTTP $code)"
  fi
done

Length of output: 587

🏁 Script executed:

#!/bin/bash
# Verify other modules declare the same prereq consistently
rg -n --glob '*.adoc' -e 'llama[_-]stack[_-]client' -A 2

Length of output: 2981

To ensure we correctly verify both the PyPI package/version and the model‐ID inconsistency, let’s re-run with fixed scripts.

These will confirm:

  • The correct PyPI package name(s) and whether 0.2.14 exists.
  • All occurrences of the model identifier to pinpoint any mismatches.

🏁 Script executed:

#!/usr/bin/env bash
set -euo pipefail

echo "Verifying PyPI package versions for llama_stack_client..."
for pkg in llama_stack_client llama-stack-client; do
  echo "Checking $pkg on PyPI..."
  data=$(curl -s "https://pypi.org/pypi/${pkg}/json" || echo "")
  if [[ -z "$data" ]]; then
    echo "  → $pkg: not found or no data"
    continue
  fi
  latest=$(echo "$data" | jq -r '.info.version')
  has014=$(echo "$data" | jq '.releases | has("0.2.14")')
  echo "  → latest version: $latest"
  echo "  → includes 0.2.14 release? $has014"
done

Length of output: 272684

🏁 Script executed:

#!/usr/bin/env bash
set -euo pipefail

echo "Checking for model ID typos across AsciiDoc modules..."
rg -n --glob '*.adoc' -e 'llama-3\.2-3b-instruct' -e 'llama-32-3b-instruct'

Length of output: 3035

Clarify package prerequisite and fix model‐ID typos

Confirmed on PyPI: the package llama-stack-client exists and includes a 0.2.14 release.

• Update prerequisite wording (line 23) to reference the package and version range unambiguously.
• Enforce the version floor in the install snippet (lines 37–38).
• Correct all occurrences of llama-32-3b-instruct to llama-3.2-3b-instruct.

Apply this diff:

 modules/querying-ingested-content-in-a-llama-model.adoc
 23c23
-* You have installed the `llama_stack_client` version 0.2.14 or later in your workbench environment.
+* You have installed the llama-stack-client package (version 0.2.14 or later) in your workbench environment.
 37,38c37,38
-%pip install llama_stack_client
+%pip install --upgrade "llama-stack-client>=0.2.14"
 ...
 19c19
-* …for example, the llama-3.2-3b-instruct model.
+* …for example, the llama-3.2-3b-instruct model.
 65c65
-[Model(identifier='llama-32-3b-instruct', …
+[Model(identifier='llama-3.2-3b-instruct', …

Committable suggestion skipped: line range outside the PR's diff.

🤖 Prompt for AI Agents 
In modules/querying-ingested-content-in-a-llama-model.adoc at line 23, update
the prerequisite to clearly reference the package name as `llama-stack-client`
with version 0.2.14 or later. Then, in the install snippet around lines 37–38,
modify the installation command to enforce installing version 0.2.14 or higher.
Finally, search the entire document for all instances of the model ID
`llama-32-3b-instruct` and replace them with the correct
`llama-3.2-3b-instruct`.

* You have ingested content into your model.

[NOTE]
Expand Down