scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 89
litellm/docs/my-website/docs
History
Exact
Ishaan Jaff bfceb7fc3f
feat(perplexity): add embedding support for pplx-embed-v1 models (#22610) 
* feat: add Perplexity embedding support (pplx-embed-v1)

Add support for Perplexity AI's embedding models via the LLM HTTP handler:

Models:
- pplx-embed-v1-0.6b (1024 dims, 32K context, $0.004/1M tokens)
- pplx-embed-v1-4b (2560 dims, 32K context, $0.03/1M tokens)

Implementation:
- PerplexityEmbeddingConfig in litellm/llms/perplexity/embedding/
- Registered in ProviderConfigManager, __init__.py lazy imports, main.py dispatch
- Model pricing added to model_prices_and_context_window.json
- Supports dimensions and encoding_format parameters
- Uses base_llm_http_handler.embedding() pattern

Tests:
- 19 unit tests covering transformation, params, URLs, provider config, model info

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>

* docs: add Perplexity AI embeddings documentation

- Create providers/perplexity_embedding.md with SDK and proxy usage examples
- Convert Perplexity from flat doc to category in sidebars.js
- Category includes existing chat/responses doc + new embeddings doc
- Covers pplx-embed-v1-0.6b and pplx-embed-v1-4b models
- Documents supported parameters (dimensions, encoding_format)
- Includes proxy config and curl examples

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>

* fix: decode Perplexity base64_int8 embeddings to OpenAI-format float arrays

Perplexity returns embeddings as base64-encoded signed int8 values by default,
not float arrays like OpenAI. This commit adds decoding in
transform_embedding_response so the proxy returns standard OpenAI-compatible
float arrays (normalized to [-1, 1]).

- Added _decode_base64_embedding() static method
- Handles both base64 strings (decoded) and float lists (passthrough)
- Added 3 new tests for base64 decoding + passthrough

Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Ishaan Jaff <ishaan-jaff@users.noreply.github.com>
2026-03-02 17:37:50 -08:00
..
adding_provider Merge pull request #21326 from BerriAI/litellm_oss_staging_02_16_2026 2026-02-18 17:47:57 +05:30
anthropic_unified fix: prompt registry 2026-02-18 00:34:54 +05:30
caching fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
completion fix: add prompt_cache_key and prompt_cache_retention support for OpenAI 2026-02-24 16:42:54 -08:00
contribute_integration docs(community.md): add new integration partner doc 2025-12-09 18:17:14 -08:00
contributing [Feat] Allow adding OpenAI compatible chat providers using .json + add public ai provider (#17448) 2025-12-04 17:59:25 -08:00
debugging Update local_debugging.md (#8308) 2025-02-06 16:19:32 -08:00
embedding docs: improve Getting Started page and SDK documentation structure (#17614) 2025-12-08 13:05:50 -08:00
extras fix: prompt registry 2026-02-18 00:34:54 +05:30
guides fix: prompt registry 2026-02-18 00:34:54 +05:30
integrations fix: prompt registry 2026-02-18 00:34:54 +05:30
langchain added tags to langchain 2025-09-10 00:32:26 -04:00
observability fix: req changes 2026-02-25 22:27:51 +05:30
pass_through Development environment setup (#22432) 2026-02-28 14:50:06 -08:00
projects fix: prompt registry 2026-02-18 00:34:54 +05:30
provider_registration docs openai 2025-12-04 18:32:23 -08:00
providers feat(perplexity): add embedding support for pplx-embed-v1 models (#22610) 2026-03-02 17:37:50 -08:00
proxy Add CrowdStrike AIDR guardrail hook (#17876) 2026-03-02 17:26:54 -08:00
search Add duckcukgo in docs 2026-02-18 16:17:39 +05:30
secret_managers fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
troubleshoot feat: add in_flight_requests metric to /health/backlog + prometheus (#22319) 2026-02-27 18:00:50 -08:00
tutorials Update docs/my-website/docs/tutorials/fallbacks.md 2026-03-02 16:03:55 -05:00
vector_stores Add vector store support for ragflow 2025-12-03 15:29:47 +05:30
a2a.md fix: prompt registry 2026-02-18 00:34:54 +05:30
a2a_agent_permissions.md [Docs] A2a - Permission management (#17515) 2025-12-04 17:29:47 -08:00
a2a_cost_tracking.md fix: prompt registry 2026-02-18 00:34:54 +05:30
a2a_invoking_agents.md fix: prompt registry 2026-02-18 00:34:54 +05:30
aiohttp_benchmarks.md docs benchmarks 2025-05-24 17:43:38 -07:00
anthropic_count_tokens.md fix: prompt registry 2026-02-18 00:34:54 +05:30
apply_guardrail.md Implement Bedrock Guardrail apply_guardrail endpoint support (#15892) 2025-10-24 10:24:03 -07:00
assistants.md docs: improve Getting Started page and SDK documentation structure (#17614) 2025-12-08 13:05:50 -08:00
audio_transcription.md Add support of audio transcription for OVHcloud (#17305) 2025-12-01 18:26:39 -08:00
batches.md fix: prompt registry 2026-02-18 00:34:54 +05:30
bedrock_converse.md docs boto3 instructions 2025-10-16 16:34:56 -07:00
bedrock_invoke.md docs boto3 instructions 2025-10-16 16:34:56 -07:00
benchmarks.md fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
budget_manager.md
contact.md docs: update broken Slack invite links to support page (#16546) 2025-11-12 12:41:55 -08:00
container_files.md fix: prompt registry 2026-02-18 00:34:54 +05:30
containers.md [docs] add docs for containers files api + code interpreter on LiteLLM (#17749) 2025-12-09 18:11:28 -08:00
contributing.md fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
data_retention.md fix: prompt registry 2026-02-18 00:34:54 +05:30
data_security.md docs(data_security.md): data_security.md 2025-06-09 17:53:11 -07:00
default_code_snippet.md
enterprise.md fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
evals_api.md fix: prompt registry 2026-02-18 00:34:54 +05:30
exception_mapping.md Adds support for returning Azure Content Policy error information when exceptions from Azure OpenAI occur (#16231) 2025-11-08 16:04:36 -08:00
files_endpoints.md Add support for file content download for bedrock batches 2025-12-04 13:27:53 +05:30
fine_tuning.md fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
generateContent.md fix: Metadata / Trace ID Missing in S3 Streaming Callbacks 2026-02-25 14:16:42 +05:30
image_edits.md fix: prompt registry 2026-02-18 00:34:54 +05:30
image_generation.md fix: prompt registry 2026-02-18 00:34:54 +05:30
image_variations.md New stable release - release notes (#8148) 2025-01-31 10:02:59 -08:00
index.md fix: prompt registry 2026-02-18 00:34:54 +05:30
interactions.md fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
load_test.md fix: prompt registry 2026-02-18 00:34:54 +05:30
load_test_advanced.md fix: prompt registry 2026-02-18 00:34:54 +05:30
load_test_rpm.md docs: usaged-based routing perf warnings (#14080) 2025-08-29 17:31:12 -07:00
load_test_sdk.md
mcp.md Merge pull request #20509 from ryan-crabbe/docs/mcp-trailing-slash 2026-02-24 16:38:29 -08:00
mcp_control.md fix: prompt registry 2026-02-18 00:34:54 +05:30
mcp_cost.md [MCP Gateway] QA/Fixes - Ensure Team/Key level enforcement works for MCPs (#15305) 2025-10-07 17:34:48 -07:00
mcp_guardrail.md fix: prompt registry 2026-02-18 00:34:54 +05:30
mcp_oauth.md fix: prompt registry 2026-02-18 00:34:54 +05:30
mcp_public_internet.md fix: prompt registry 2026-02-18 00:34:54 +05:30
mcp_semantic_filter.md fix: prompt registry 2026-02-18 00:34:54 +05:30
mcp_troubleshoot.md fix: prompt registry 2026-02-18 00:34:54 +05:30
mcp_usage.md [MCP Gateway] QA/Fixes - Ensure Team/Key level enforcement works for MCPs (#15305) 2025-10-07 17:34:48 -07:00
migration.md
migration_policy.md
moderation.md docs(moderation.md): fix moderation quick start docs 2025-11-07 16:25:08 -08:00
ocr.md Enable local file support for OCR (#22133) 2026-02-27 10:50:02 -08:00
oidc.md fix: prompt registry 2026-02-18 00:34:54 +05:30
old_guardrails.md Use the -d flag in docs instead of -D (#12179) 2025-06-30 15:25:42 -07:00
projects.md
proxy_api.md Corrected docs updates sept 2025 (#14916) 2025-09-25 15:49:19 -07:00
proxy_auth.md fix: prompt registry 2026-02-18 00:34:54 +05:30
proxy_server.md Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE (#9995) (#10423) 2025-04-29 21:27:37 -07:00
rag_ingest.md fix: prompt registry 2026-02-18 00:34:54 +05:30
rag_query.md fix: prompt registry 2026-02-18 00:34:54 +05:30
realtime.md feat(realtime): guardrails support for /v1/realtime WebSocket endpoint (#22152) 2026-02-25 21:34:22 -08:00
reasoning_content.md Add support for reasoning and tools viaconfig 2026-02-20 16:22:19 +05:30
rerank.md feat: Add IBM watsonx.ai rerank support (#21303) 2026-02-16 20:12:16 -08:00
response_api.md feat: add session_id to have better routing 2026-02-21 18:45:50 +05:30
response_api_compact.md fix: prompt registry 2026-02-18 00:34:54 +05:30
router_architecture.md docs(router_architecture.md): add router architecture docs 2024-11-26 12:54:38 +05:30
routing.md fix: prompt registry 2026-02-18 00:34:54 +05:30
rules.md
scheduler.md docs: usaged-based routing perf warnings (#14080) 2025-08-29 17:31:12 -07:00
sdk_custom_pricing.md
secret.md fix(ollama): thread api_base to get_model_info + graceful fallback (#21970) 2026-02-23 21:00:37 -08:00
set_keys.md Contributor PR - Support OPENAI_BASE_URL in addition to OPENAI_API_BASE (#9995) (#10423) 2025-04-29 21:27:37 -07:00
skills.md [Docs] Claude Skills API (#17052) 2025-11-24 15:32:03 -08:00
text_completion.md Guardrails - Responses API, Image Gen, Text completions, Audio transcriptions, Audio Speech, Rerank, Anthropic Messages API support via the unified apply_guardrails function (#15706) 2025-10-25 13:38:57 -07:00
text_to_speech.md fix: prompt registry 2026-02-18 00:34:54 +05:30
traffic_mirroring.md fix: prompt registry 2026-02-18 00:34:54 +05:30
troubleshoot.md fix: prompt registry 2026-02-18 00:34:54 +05:30
vector_store_files.md fix docs 2025-11-15 16:58:47 -08:00
vertex_batch_passthrough.md Litellm sameer oct staging (#15806) 2025-10-24 12:17:22 -07:00
videos.md [Feat] New Provider - Add RunwayML Provider for video generations (#16505) 2025-11-11 18:48:23 -08:00
wildcard_routing.md Litellm dev 12 28 2024 p2 (#7458) 2024-12-28 19:38:06 -08:00