Add models and naming convention to API docs and project description

[barun-saha]

Closes #158.

Summary by CodeRabbit

• Documentation
  • Added comprehensive Models documentation page describing supported LLM providers and their characteristics.
  • Clarified model naming conventions with format examples for easy reference.
  • Included detailed table of supported models with provider codes, API requirements, and content generation capabilities.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

Walkthrough

Adds comprehensive documentation for SlideDeck AI's model naming convention and supported LLMs. Updates include a detailed models.md guide, a provider-code reference table, and integration into the documentation structure via index.rst.

Changes

Cohort / File(s)	Summary
Documentation Structure docs/index.rst	Added models.md to documentation toctree to include model naming and provider reference in visible sections.
Model Documentation README.md, docs/models.md	Introduced comprehensive model naming documentation explaining the [code]model-name format with two-character provider codes (e.g., [oa], [gg]). Created new models.md file and updated README with supported LLMs table, including provider codes, API-key requirements, content-generation characteristics, and usage examples.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

• Straightforward documentation additions with no code logic changes
• Verify accuracy of model names, provider codes, and table formatting
• Confirm consistency between README.md and docs/models.md content

Possibly related PRs

• Add new models and providers (OpenAI, SambaNova) #174: Introduces provider identifiers and model entries that this PR documents in the naming convention and supported models table.
• Update contributions #148: Modifies LLM documentation and README content, addressing related model information updates.
• Add Colab quickstart link and update project description #181: Updates LLM/provider documentation and supported-LLM table wording with overlapping documentation scope.

Poem

🐰 A model naming guide, clear and bright,
With provider codes written just right!
Tables of LLMs, all in a row,
The format [code]model now aglow! ✨
Documentation hops forward with pride,
Making model selection a joyful ride!

Pre-merge checks and finishing touches

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately describes the main changes: adding documentation about models and the naming convention to both API docs and README.
Linked Issues check	✅ Passed	The PR successfully addresses issue #158 by documenting the [code]model-name naming convention in README.md and providing comprehensive model documentation.
Out of Scope Changes check	✅ Passed	All changes are in-scope: README.md documents the naming convention, docs/models.md provides detailed model information, and docs/index.rst integrates the new documentation.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✨ Finishing touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch visual

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

README.md (1)

96-114: Replace generic "GPT" with a specific Azure OpenAI model identifier in both README.md and docs/models.md.

The table entry at line 106 (README.md) and line 30 (docs/models.md) lists "GPT" for Azure OpenAI, which is inconsistent with the naming convention documented in the codebase and too generic compared to other entries like "GPT-4.1-mini" or "GPT-3.5 Turbo". The code configuration in global_config.py shows the pattern as [az]azure/open-ai, and the naming convention requires [code]model-name format. Update this entry to a specific model identifier such as [az]gpt-4o to match the pattern used throughout the table and provide a concrete example for users.

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 128d056 and 4053c80.

⛔ Files ignored due to path filters (2)

• docs/generated/slidedeckai.cli.rst is excluded by !**/generated/**
• docs/generated/slidedeckai.core.SlideDeckAI.rst is excluded by !**/generated/**

📒 Files selected for processing (3)

• README.md (1 hunks)
• docs/index.rst (1 hunks)
• docs/models.md (1 hunks)

🧰 Additional context used

🧠 Learnings (1)

📚 Learning: 2025-09-23T04:32:09.863Z

Learnt from: barun-saha
Repo: barun-saha/slide-deck-ai PR: 139
File: helpers/llm_helper.py:70-84
Timestamp: 2025-09-23T04:32:09.863Z
Learning: Hugging Face model support has been discontinued in the slide-deck-ai project, so PROVIDER_HUGGING_FACE should remain commented out in GlobalConfig.VALID_PROVIDERS and validation should continue rejecting 'hf' providers.

Applied to files:

• docs/models.md
• README.md

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)

• GitHub Check: test (3.11)
• GitHub Check: test (3.12)
• GitHub Check: test (3.10)

🔇 Additional comments (3)

docs/models.md (1)

1-13: Clear naming convention explanation that directly addresses PR objective.

The explanation of the [code]model-name format with two-character provider prefixes effectively communicates the naming convention. This directly fulfills issue #158's request to highlight the model naming format in documentation.

docs/index.rst (1)

13-15: Proper documentation structure integration.

Adding models.md to the "Getting Started" toctree section is appropriate and aligns well with the existing documentation structure alongside installation and usage guides.

README.md (1)

90-90: Naming convention explanation clearly addresses issue #158.

The addition of detailed explanation about the [code]model-name format with concrete examples ([oa] for OpenAI, [gg] for Google Gemini) directly fulfills the requirement to "highlight model naming format in README."

[coderabbitai]

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🏁 Script executed:

# Search for Azure OpenAI related configurations and model references
rg -i "azure|openai|gpt" docs/models.md -A 2 -B 2

Repository: barun-saha/slide-deck-ai

Length of output: 3076

---

🏁 Script executed:

# Search for any model configuration or mapping in the codebase
fd -type f -name "*.md" -o -name "*.json" -o -name "*.py" -o -name "*.js" -o -name "*.ts" | head -20

Repository: barun-saha/slide-deck-ai

Length of output: 238

---

🏁 Script executed:

# Look for Azure-specific configuration or constants
rg -i "azure.*openai|gpt.*azure" --type-add 'config:*.{json,yaml,yml,toml}' -t config -t py -t js -t ts

Repository: barun-saha/slide-deck-ai

Length of output: 3402

---

🏁 Script executed:

# Search the entire docs directory for Azure-related recommendations
rg -i "azure|deployment" docs/ -B 2 -A 2

Repository: barun-saha/slide-deck-ai

Length of output: 1227

---

🏁 Script executed:

# Check the README or setup documentation for Azure model guidance
fd -type f -name "*.md" | xargs grep -l -i "azure" | head -5

Repository: barun-saha/slide-deck-ai

Length of output: 238

---

🏁 Script executed:

# Look for any Azure deployment examples or configurations
rg "deployment" --type md

Repository: barun-saha/slide-deck-ai

Length of output: 156

---

🏁 Script executed:

# Check if there's any example or reference to specific Azure deployment names
rg "gpt-4|gpt-35|gpt-4o" . --type md --type py --type json

Repository: barun-saha/slide-deck-ai

Length of output: 1253

---

🏁 Script executed:

# Search for any Azure configuration examples in main app or docs
fd "*.md" | xargs grep -i "deployment" 2>/dev/null

Repository: barun-saha/slide-deck-ai

Length of output: 353

---

🏁 Script executed:

# Check the full context of Azure OpenAI configuration in global_config.py
grep -A 5 -B 5 "PROVIDER_AZURE_OPENAI" src/slidedeckai/global_config.py | head -30

Repository: barun-saha/slide-deck-ai

Length of output: 896

---

Clarify the Azure OpenAI model identifier to follow the documented format.

The table lists "GPT" as the model name for Azure OpenAI, which is too generic and inconsistent with the documented [code]model-name format used elsewhere (e.g., [oa]gpt-4.1-mini, [gg]gemini-2.0-flash). For Azure OpenAI, specify an actual deployment name or model identifier like [az]gpt-4o, [az]gpt-4-turbo, or [az]gpt-35-turbo to provide users with clear, actionable guidance.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!