holetron-lab/fleet-memory
1
0
Fork 0
Code Releases Packages Activity Actions

feat: add OpenRouter support for LLM, embeddings, and reranking (#930)

Browse source 
* docs: add best practice for filtering recall by memory shape (#856)

Add guidance on using entity labels with `tag: true` to deterministically
filter recall results when a bank contains different memory shapes
(e.g., concise rules vs. detailed procedures).

* feat: add OpenRouter support for LLM, embeddings, and reranking

OpenRouter is OpenAI-compatible for chat/embeddings and Cohere-compatible
for reranking, so no new provider classes are needed.

- LLM: added as OpenAICompatibleLLM provider (default model: qwen/qwen3.5-9b)
- Embeddings: reuses OpenAIEmbeddings with OpenRouter base URL (default: perplexity/pplx-embed-v1-0.6b)
- Reranker: reuses CohereCrossEncoder with OpenRouter rerank endpoint (default: cohere/rerank-v3.5)
- API key fallback chain: dedicated key → shared OPENROUTER_API_KEY → LLM_API_KEY

* chore: regenerate docs skill references and fix formatting
This commit is contained in:
Nicolò Boschi 2026-04-08 11:24:21 +02:00 committed by GitHub
parent 37348c859e
commit e5944b63e7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 102 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
hindsight-api-slim/hindsight_api/config.py
View file

@ -194,6 +194,13 @@ ENV_RERANKER_COHERE_API_KEY = "HINDSIGHT_API_RERANKER_COHERE_API_KEY"
ENV_RERANKER_COHERE_MODEL = "HINDSIGHT_API_RERANKER_COHERE_MODEL"
ENV_RERANKER_COHERE_BASE_URL = "HINDSIGHT_API_RERANKER_COHERE_BASE_URL"
# OpenRouter configuration (embeddings and reranker)
ENV_OPENROUTER_API_KEY = "HINDSIGHT_API_OPENROUTER_API_KEY"
ENV_EMBEDDINGS_OPENROUTER_API_KEY = "HINDSIGHT_API_EMBEDDINGS_OPENROUTER_API_KEY"
ENV_EMBEDDINGS_OPENROUTER_MODEL = "HINDSIGHT_API_EMBEDDINGS_OPENROUTER_MODEL"
ENV_RERANKER_OPENROUTER_API_KEY = "HINDSIGHT_API_RERANKER_OPENROUTER_API_KEY"
ENV_RERANKER_OPENROUTER_MODEL = "HINDSIGHT_API_RERANKER_OPENROUTER_MODEL"
# Deprecated: Legacy shared Cohere API key (for backward compatibility)
ENV_COHERE_API_KEY = "HINDSIGHT_API_COHERE_API_KEY"
@ -399,6 +406,7 @@ PROVIDER_DEFAULT_MODELS = {
"litellm": "gpt-4o-mini",
"bedrock": "us.amazon.nova-2-lite-v1:0",
"volcano": "doubao-pro-32k",
"openrouter": "qwen/qwen3.5-9b",
}
DEFAULT_LLM_MODEL = "gpt-4o-mini" # Fallback if provider not in table
DEFAULT_LLM_MAX_CONCURRENT = 32
@ -443,6 +451,10 @@ DEFAULT_RERANKER_FLASHRANK_CACHE_DIR = None # Use default cache directory
DEFAULT_EMBEDDINGS_COHERE_MODEL = "embed-english-v3.0"
DEFAULT_RERANKER_COHERE_MODEL = "rerank-english-v3.0"
# OpenRouter defaults
DEFAULT_EMBEDDINGS_OPENROUTER_MODEL = "perplexity/pplx-embed-v1-0.6b"
DEFAULT_RERANKER_OPENROUTER_MODEL = "cohere/rerank-v3.5"
DEFAULT_RERANKER_ZEROENTROPY_MODEL = "zerank-2"
DEFAULT_RERANKER_GOOGLE_MODEL = "semantic-ranker-default-004"
@ -724,6 +736,8 @@ class HindsightConfig:
embeddings_cohere_api_key: str | None
embeddings_cohere_model: str
embeddings_cohere_base_url: str | None
embeddings_openrouter_api_key: str | None
embeddings_openrouter_model: str
embeddings_litellm_api_base: str
embeddings_litellm_api_key: str | None
embeddings_litellm_model: str
@ -756,6 +770,8 @@ class HindsightConfig:
reranker_cohere_api_key: str | None
reranker_cohere_model: str
reranker_cohere_base_url: str | None
reranker_openrouter_api_key: str | None
reranker_openrouter_model: str
reranker_litellm_api_base: str
reranker_litellm_api_key: str | None
reranker_litellm_model: str
@ -1189,6 +1205,11 @@ class HindsightConfig:
embeddings_cohere_api_key=os.getenv(ENV_EMBEDDINGS_COHERE_API_KEY) or os.getenv(ENV_COHERE_API_KEY),
embeddings_cohere_model=os.getenv(ENV_EMBEDDINGS_COHERE_MODEL, DEFAULT_EMBEDDINGS_COHERE_MODEL),
embeddings_cohere_base_url=os.getenv(ENV_EMBEDDINGS_COHERE_BASE_URL) or None,
# OpenRouter embeddings (with fallback to shared OpenRouter key, then LLM key)
embeddings_openrouter_api_key=os.getenv(ENV_EMBEDDINGS_OPENROUTER_API_KEY)
or os.getenv(ENV_OPENROUTER_API_KEY)
or os.getenv(ENV_LLM_API_KEY),
embeddings_openrouter_model=os.getenv(ENV_EMBEDDINGS_OPENROUTER_MODEL, DEFAULT_EMBEDDINGS_OPENROUTER_MODEL),
# LiteLLM embeddings (with backward-compatible fallback to shared config)
embeddings_litellm_api_base=os.getenv(ENV_EMBEDDINGS_LITELLM_API_BASE)
or os.getenv(ENV_LITELLM_API_BASE, DEFAULT_LITELLM_API_BASE),
@ -1253,6 +1274,11 @@ class HindsightConfig:
reranker_cohere_api_key=os.getenv(ENV_RERANKER_COHERE_API_KEY) or os.getenv(ENV_COHERE_API_KEY),
reranker_cohere_model=os.getenv(ENV_RERANKER_COHERE_MODEL, DEFAULT_RERANKER_COHERE_MODEL),
reranker_cohere_base_url=os.getenv(ENV_RERANKER_COHERE_BASE_URL) or None,
# OpenRouter reranker (with fallback to shared OpenRouter key, then LLM key)
reranker_openrouter_api_key=os.getenv(ENV_RERANKER_OPENROUTER_API_KEY)
or os.getenv(ENV_OPENROUTER_API_KEY)
or os.getenv(ENV_LLM_API_KEY),
reranker_openrouter_model=os.getenv(ENV_RERANKER_OPENROUTER_MODEL, DEFAULT_RERANKER_OPENROUTER_MODEL),
# LiteLLM reranker (with backward-compatible fallback to shared config)
reranker_litellm_api_base=os.getenv(ENV_RERANKER_LITELLM_API_BASE)
or os.getenv(ENV_LITELLM_API_BASE, DEFAULT_LITELLM_API_BASE),

12
hindsight-api-slim/hindsight_api/engine/cross_encoder.py
View file

@ -1468,6 +1468,18 @@ def create_cross_encoder_from_env() -> CrossEncoderModel:
model=config.reranker_cohere_model,
base_url=config.reranker_cohere_base_url,
)
elif provider == "openrouter":
api_key = config.reranker_openrouter_api_key
if not api_key:
raise ValueError(
"HINDSIGHT_API_RERANKER_OPENROUTER_API_KEY, HINDSIGHT_API_OPENROUTER_API_KEY, "
f"or HINDSIGHT_API_LLM_API_KEY is required when {ENV_RERANKER_PROVIDER} is 'openrouter'"
)
return CohereCrossEncoder(
api_key=api_key,
model=config.reranker_openrouter_model,
base_url="https://openrouter.ai/api/v1/rerank",
)
elif provider == "flashrank":
model = os.environ.get(ENV_RERANKER_FLASHRANK_MODEL, DEFAULT_RERANKER_FLASHRANK_MODEL)
cache_dir = os.environ.get(ENV_RERANKER_FLASHRANK_CACHE_DIR, DEFAULT_RERANKER_FLASHRANK_CACHE_DIR)

12
hindsight-api-slim/hindsight_api/engine/embeddings.py
View file

@ -1101,6 +1101,18 @@ def create_embeddings_from_env() -> Embeddings:
model = os.environ.get(ENV_EMBEDDINGS_OPENAI_MODEL, DEFAULT_EMBEDDINGS_OPENAI_MODEL)
base_url = os.environ.get(ENV_EMBEDDINGS_OPENAI_BASE_URL) or None
return OpenAIEmbeddings(api_key=api_key, model=model, base_url=base_url)
elif provider == "openrouter":
api_key = config.embeddings_openrouter_api_key
if not api_key:
raise ValueError(
"HINDSIGHT_API_EMBEDDINGS_OPENROUTER_API_KEY, HINDSIGHT_API_OPENROUTER_API_KEY, "
f"or {ENV_LLM_API_KEY} is required when {ENV_EMBEDDINGS_PROVIDER} is 'openrouter'"
)
return OpenAIEmbeddings(
api_key=api_key,
model=config.embeddings_openrouter_model,
base_url="https://openrouter.ai/api/v1",
)
elif provider == "cohere":
api_key = config.embeddings_cohere_api_key
if not api_key:

5
hindsight-api-slim/hindsight_api/engine/llm_wrapper.py
View file

@ -263,7 +263,7 @@ def create_llm_provider(
reasoning_effort=reasoning_effort,
)
elif provider_lower in ("openai", "groq", "ollama", "lmstudio", "minimax", "volcano"):
elif provider_lower in ("openai", "groq", "ollama", "lmstudio", "minimax", "volcano", "openrouter"):
return OpenAICompatibleLLM(
provider=provider,
api_key=api_key,
@ -342,6 +342,7 @@ class LLMProvider:
"litellm",
"bedrock",
"volcano",
"openrouter",
]
if self.provider not in valid_providers:
raise ValueError(f"Invalid LLM provider: {self.provider}. Must be one of: {', '.join(valid_providers)}")
@ -356,6 +357,8 @@ class LLMProvider:
self.base_url = "http://localhost:1234/v1"
elif self.provider == "minimax":
self.base_url = "https://api.minimax.io/v1"
elif self.provider == "openrouter":
self.base_url = "https://openrouter.ai/api/v1"
# Prepare Vertex AI config (if applicable)
vertexai_project_id = None

6
hindsight-api-slim/hindsight_api/engine/providers/openai_compatible_llm.py
View file

@ -100,7 +100,7 @@ class OpenAICompatibleLLM(LLMInterface):
super().__init__(provider, api_key, base_url, model, reasoning_effort, **kwargs)
# Validate provider
valid_providers = ["openai", "groq", "ollama", "lmstudio", "minimax", "volcano"]
valid_providers = ["openai", "groq", "ollama", "lmstudio", "minimax", "volcano", "openrouter"]
if self.provider not in valid_providers:
raise ValueError(f"OpenAICompatibleLLM only supports: {', '.join(valid_providers)}. Got: {self.provider}")
@ -114,13 +114,15 @@ class OpenAICompatibleLLM(LLMInterface):
self.base_url = "http://localhost:1234/v1"
elif self.provider == "minimax":
self.base_url = "https://api.minimax.io/v1"
elif self.provider == "openrouter":
self.base_url = "https://openrouter.ai/api/v1"
# For ollama/lmstudio, use dummy key if not provided
if self.provider in ("ollama", "lmstudio") and not self.api_key:
self.api_key = "local"
# Validate API key for cloud providers
if self.provider in ("openai", "groq", "minimax") and not self.api_key:
if self.provider in ("openai", "groq", "minimax", "openrouter") and not self.api_key:
raise ValueError(f"API key is required for {self.provider}")
# Service tier configuration (from config, not env vars)

25
hindsight-docs/docs/developer/configuration.md
View file

@ -161,7 +161,7 @@ To switch between backends:
| Variable | Description | Default |
|----------|-------------|---------|
| `HINDSIGHT_API_LLM_PROVIDER` | Provider: `openai`, `openai-codex`, `claude-code`, `anthropic`, `gemini`, `groq`, `minimax`, `ollama`, `lmstudio`, `vertexai`, `bedrock`, `litellm`, `volcano`, `none` | `openai` |
| `HINDSIGHT_API_LLM_PROVIDER` | Provider: `openai`, `openai-codex`, `claude-code`, `anthropic`, `gemini`, `groq`, `minimax`, `ollama`, `lmstudio`, `vertexai`, `bedrock`, `litellm`, `volcano`, `openrouter`, `none` | `openai` |
| `HINDSIGHT_API_LLM_API_KEY` | API key for LLM provider | - |
| `HINDSIGHT_API_LLM_MODEL` | Model name | `gpt-5-mini` |
| `HINDSIGHT_API_LLM_BASE_URL` | Custom LLM endpoint | Provider default |
@ -242,6 +242,11 @@ export HINDSIGHT_API_LLM_API_KEY=your-api-key
export HINDSIGHT_API_LLM_BASE_URL=https://ark.cn-beijing.volces.com/api/v3
export HINDSIGHT_API_LLM_MODEL=doubao-pro-32k
# OpenRouter (OpenAI-compatible, access 100+ models)
export HINDSIGHT_API_LLM_PROVIDER=openrouter
export HINDSIGHT_API_LLM_API_KEY=your-openrouter-api-key
export HINDSIGHT_API_LLM_MODEL=qwen/qwen3.5-9b
# AWS Bedrock (native support - no API key needed, uses AWS credentials)
export HINDSIGHT_API_LLM_PROVIDER=bedrock
export HINDSIGHT_API_LLM_MODEL=us.amazon.nova-2-lite-v1:0
@ -352,7 +357,7 @@ export HINDSIGHT_API_RETAIN_LLM_MAX_BACKOFF=120.0 # Cap at 2min instead of 1m
| Variable | Description | Default |
|----------|-------------|---------|
| `HINDSIGHT_API_EMBEDDINGS_PROVIDER` | Provider: `local`, `tei`, `openai`, `cohere`, `google`, `litellm`, or `litellm-sdk` | `local` |
| `HINDSIGHT_API_EMBEDDINGS_PROVIDER` | Provider: `local`, `tei`, `openai`, `openrouter`, `cohere`, `google`, `litellm`, or `litellm-sdk` | `local` |
| `HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL` | Model for local provider | `BAAI/bge-small-en-v1.5` |
| `HINDSIGHT_API_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE` | Allow loading models with custom code (security risk, disabled by default) | `false` |
| `HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU` | Force CPU mode for local embeddings (avoids MPS/XPC issues on macOS) | `false` |
@ -360,6 +365,8 @@ export HINDSIGHT_API_RETAIN_LLM_MAX_BACKOFF=120.0 # Cap at 2min instead of 1m
| `HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY` | OpenAI API key (falls back to `HINDSIGHT_API_LLM_API_KEY`) | - |
| `HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL` | OpenAI embedding model | `text-embedding-3-small` |
| `HINDSIGHT_API_EMBEDDINGS_OPENAI_BASE_URL` | Custom base URL for OpenAI-compatible API (e.g., Azure OpenAI) | - |
| `HINDSIGHT_API_EMBEDDINGS_OPENROUTER_API_KEY` | OpenRouter API key for embeddings (falls back to `HINDSIGHT_API_OPENROUTER_API_KEY`, then `HINDSIGHT_API_LLM_API_KEY`) | - |
| `HINDSIGHT_API_EMBEDDINGS_OPENROUTER_MODEL` | OpenRouter embedding model | `perplexity/pplx-embed-v1-0.6b` |
| `HINDSIGHT_API_EMBEDDINGS_COHERE_API_KEY` | Cohere API key for embeddings | - |
| `HINDSIGHT_API_EMBEDDINGS_COHERE_MODEL` | Cohere embedding model | `embed-english-v3.0` |
| `HINDSIGHT_API_EMBEDDINGS_COHERE_BASE_URL` | Custom base URL for Cohere-compatible API (e.g., Azure-hosted) | - |
@ -403,6 +410,11 @@ export HINDSIGHT_API_EMBEDDINGS_OPENAI_BASE_URL=https://your-resource.openai.azu
export HINDSIGHT_API_EMBEDDINGS_PROVIDER=tei
export HINDSIGHT_API_EMBEDDINGS_TEI_URL=http://localhost:8080
# OpenRouter - access 100+ embedding models
export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openrouter
export HINDSIGHT_API_EMBEDDINGS_OPENROUTER_API_KEY=your-openrouter-api-key # or reuses HINDSIGHT_API_LLM_API_KEY
export HINDSIGHT_API_EMBEDDINGS_OPENROUTER_MODEL=perplexity/pplx-embed-v1-0.6b
# Cohere - cloud-based embeddings
export HINDSIGHT_API_EMBEDDINGS_PROVIDER=cohere
export HINDSIGHT_API_EMBEDDINGS_COHERE_API_KEY=your-api-key
@ -472,7 +484,7 @@ Google's `gemini-embedding-001` produces 3072 dimensions natively but supports c
| Variable | Description | Default |
|----------|-------------|---------|
| `HINDSIGHT_API_RERANKER_PROVIDER` | Provider: `local`, `tei`, `cohere`, `zeroentropy`, `google`, `flashrank`, `litellm`, `litellm-sdk`, `jina-mlx`, or `rrf` | `local` |
| `HINDSIGHT_API_RERANKER_PROVIDER` | Provider: `local`, `tei`, `cohere`, `openrouter`, `zeroentropy`, `google`, `flashrank`, `litellm`, `litellm-sdk`, `jina-mlx`, or `rrf` | `local` |
| `HINDSIGHT_API_RERANKER_LOCAL_MODEL` | Model for local provider | `cross-encoder/ms-marco-MiniLM-L-6-v2` |
| `HINDSIGHT_API_RERANKER_LOCAL_MAX_CONCURRENT` | Max concurrent local reranking (prevents CPU thrashing under load) | `4` |
| `HINDSIGHT_API_RERANKER_LOCAL_TRUST_REMOTE_CODE` | Allow loading models with custom code (security risk, disabled by default) | `false` |
@ -483,6 +495,8 @@ Google's `gemini-embedding-001` produces 3072 dimensions natively but supports c
| `HINDSIGHT_API_RERANKER_TEI_URL` | TEI server URL | - |
| `HINDSIGHT_API_RERANKER_TEI_BATCH_SIZE` | Batch size for TEI reranking | `128` |
| `HINDSIGHT_API_RERANKER_TEI_MAX_CONCURRENT` | Max concurrent TEI reranking requests | `8` |
| `HINDSIGHT_API_RERANKER_OPENROUTER_API_KEY` | OpenRouter API key for reranking (falls back to `HINDSIGHT_API_OPENROUTER_API_KEY`, then `HINDSIGHT_API_LLM_API_KEY`) | - |
| `HINDSIGHT_API_RERANKER_OPENROUTER_MODEL` | OpenRouter rerank model | `cohere/rerank-v3.5` |
| `HINDSIGHT_API_RERANKER_COHERE_API_KEY` | Cohere API key for reranking | - |
| `HINDSIGHT_API_RERANKER_COHERE_MODEL` | Cohere rerank model | `rerank-english-v3.0` |
| `HINDSIGHT_API_RERANKER_COHERE_BASE_URL` | Custom base URL for Cohere-compatible API (e.g., Azure-hosted) | - |
@ -518,6 +532,11 @@ export HINDSIGHT_API_RERANKER_LOCAL_TRUST_REMOTE_CODE=true
export HINDSIGHT_API_RERANKER_PROVIDER=tei
export HINDSIGHT_API_RERANKER_TEI_URL=http://localhost:8081
# OpenRouter - access reranking models via OpenRouter
export HINDSIGHT_API_RERANKER_PROVIDER=openrouter
export HINDSIGHT_API_RERANKER_OPENROUTER_API_KEY=your-openrouter-api-key # or reuses HINDSIGHT_API_LLM_API_KEY
export HINDSIGHT_API_RERANKER_OPENROUTER_MODEL=cohere/rerank-v3.5
# Cohere - cloud-based reranking
export HINDSIGHT_API_RERANKER_PROVIDER=cohere
export HINDSIGHT_API_RERANKER_COHERE_API_KEY=your-api-key

25
skills/hindsight-docs/references/developer/configuration.md
View file

@ -161,7 +161,7 @@ To switch between backends:
| Variable | Description | Default |
|----------|-------------|---------|
| `HINDSIGHT_API_LLM_PROVIDER` | Provider: `openai`, `openai-codex`, `claude-code`, `anthropic`, `gemini`, `groq`, `minimax`, `ollama`, `lmstudio`, `vertexai`, `bedrock`, `litellm`, `volcano`, `none` | `openai` |
| `HINDSIGHT_API_LLM_PROVIDER` | Provider: `openai`, `openai-codex`, `claude-code`, `anthropic`, `gemini`, `groq`, `minimax`, `ollama`, `lmstudio`, `vertexai`, `bedrock`, `litellm`, `volcano`, `openrouter`, `none` | `openai` |
| `HINDSIGHT_API_LLM_API_KEY` | API key for LLM provider | - |
| `HINDSIGHT_API_LLM_MODEL` | Model name | `gpt-5-mini` |
| `HINDSIGHT_API_LLM_BASE_URL` | Custom LLM endpoint | Provider default |
@ -242,6 +242,11 @@ export HINDSIGHT_API_LLM_API_KEY=your-api-key
export HINDSIGHT_API_LLM_BASE_URL=https://ark.cn-beijing.volces.com/api/v3
export HINDSIGHT_API_LLM_MODEL=doubao-pro-32k
# OpenRouter (OpenAI-compatible, access 100+ models)
export HINDSIGHT_API_LLM_PROVIDER=openrouter
export HINDSIGHT_API_LLM_API_KEY=your-openrouter-api-key
export HINDSIGHT_API_LLM_MODEL=qwen/qwen3.5-9b
# AWS Bedrock (native support - no API key needed, uses AWS credentials)
export HINDSIGHT_API_LLM_PROVIDER=bedrock
export HINDSIGHT_API_LLM_MODEL=us.amazon.nova-2-lite-v1:0
@ -352,7 +357,7 @@ export HINDSIGHT_API_RETAIN_LLM_MAX_BACKOFF=120.0 # Cap at 2min instead of 1m
| Variable | Description | Default |
|----------|-------------|---------|
| `HINDSIGHT_API_EMBEDDINGS_PROVIDER` | Provider: `local`, `tei`, `openai`, `cohere`, `google`, `litellm`, or `litellm-sdk` | `local` |
| `HINDSIGHT_API_EMBEDDINGS_PROVIDER` | Provider: `local`, `tei`, `openai`, `openrouter`, `cohere`, `google`, `litellm`, or `litellm-sdk` | `local` |
| `HINDSIGHT_API_EMBEDDINGS_LOCAL_MODEL` | Model for local provider | `BAAI/bge-small-en-v1.5` |
| `HINDSIGHT_API_EMBEDDINGS_LOCAL_TRUST_REMOTE_CODE` | Allow loading models with custom code (security risk, disabled by default) | `false` |
| `HINDSIGHT_API_EMBEDDINGS_LOCAL_FORCE_CPU` | Force CPU mode for local embeddings (avoids MPS/XPC issues on macOS) | `false` |
@ -360,6 +365,8 @@ export HINDSIGHT_API_RETAIN_LLM_MAX_BACKOFF=120.0 # Cap at 2min instead of 1m
| `HINDSIGHT_API_EMBEDDINGS_OPENAI_API_KEY` | OpenAI API key (falls back to `HINDSIGHT_API_LLM_API_KEY`) | - |
| `HINDSIGHT_API_EMBEDDINGS_OPENAI_MODEL` | OpenAI embedding model | `text-embedding-3-small` |
| `HINDSIGHT_API_EMBEDDINGS_OPENAI_BASE_URL` | Custom base URL for OpenAI-compatible API (e.g., Azure OpenAI) | - |
| `HINDSIGHT_API_EMBEDDINGS_OPENROUTER_API_KEY` | OpenRouter API key for embeddings (falls back to `HINDSIGHT_API_OPENROUTER_API_KEY`, then `HINDSIGHT_API_LLM_API_KEY`) | - |
| `HINDSIGHT_API_EMBEDDINGS_OPENROUTER_MODEL` | OpenRouter embedding model | `perplexity/pplx-embed-v1-0.6b` |
| `HINDSIGHT_API_EMBEDDINGS_COHERE_API_KEY` | Cohere API key for embeddings | - |
| `HINDSIGHT_API_EMBEDDINGS_COHERE_MODEL` | Cohere embedding model | `embed-english-v3.0` |
| `HINDSIGHT_API_EMBEDDINGS_COHERE_BASE_URL` | Custom base URL for Cohere-compatible API (e.g., Azure-hosted) | - |
@ -403,6 +410,11 @@ export HINDSIGHT_API_EMBEDDINGS_OPENAI_BASE_URL=https://your-resource.openai.azu
export HINDSIGHT_API_EMBEDDINGS_PROVIDER=tei
export HINDSIGHT_API_EMBEDDINGS_TEI_URL=http://localhost:8080
# OpenRouter - access 100+ embedding models
export HINDSIGHT_API_EMBEDDINGS_PROVIDER=openrouter
export HINDSIGHT_API_EMBEDDINGS_OPENROUTER_API_KEY=your-openrouter-api-key # or reuses HINDSIGHT_API_LLM_API_KEY
export HINDSIGHT_API_EMBEDDINGS_OPENROUTER_MODEL=perplexity/pplx-embed-v1-0.6b
# Cohere - cloud-based embeddings
export HINDSIGHT_API_EMBEDDINGS_PROVIDER=cohere
export HINDSIGHT_API_EMBEDDINGS_COHERE_API_KEY=your-api-key
@ -472,7 +484,7 @@ Google's `gemini-embedding-001` produces 3072 dimensions natively but supports c
| Variable | Description | Default |
|----------|-------------|---------|
| `HINDSIGHT_API_RERANKER_PROVIDER` | Provider: `local`, `tei`, `cohere`, `zeroentropy`, `google`, `flashrank`, `litellm`, `litellm-sdk`, `jina-mlx`, or `rrf` | `local` |
| `HINDSIGHT_API_RERANKER_PROVIDER` | Provider: `local`, `tei`, `cohere`, `openrouter`, `zeroentropy`, `google`, `flashrank`, `litellm`, `litellm-sdk`, `jina-mlx`, or `rrf` | `local` |
| `HINDSIGHT_API_RERANKER_LOCAL_MODEL` | Model for local provider | `cross-encoder/ms-marco-MiniLM-L-6-v2` |
| `HINDSIGHT_API_RERANKER_LOCAL_MAX_CONCURRENT` | Max concurrent local reranking (prevents CPU thrashing under load) | `4` |
| `HINDSIGHT_API_RERANKER_LOCAL_TRUST_REMOTE_CODE` | Allow loading models with custom code (security risk, disabled by default) | `false` |
@ -483,6 +495,8 @@ Google's `gemini-embedding-001` produces 3072 dimensions natively but supports c
| `HINDSIGHT_API_RERANKER_TEI_URL` | TEI server URL | - |
| `HINDSIGHT_API_RERANKER_TEI_BATCH_SIZE` | Batch size for TEI reranking | `128` |
| `HINDSIGHT_API_RERANKER_TEI_MAX_CONCURRENT` | Max concurrent TEI reranking requests | `8` |
| `HINDSIGHT_API_RERANKER_OPENROUTER_API_KEY` | OpenRouter API key for reranking (falls back to `HINDSIGHT_API_OPENROUTER_API_KEY`, then `HINDSIGHT_API_LLM_API_KEY`) | - |
| `HINDSIGHT_API_RERANKER_OPENROUTER_MODEL` | OpenRouter rerank model | `cohere/rerank-v3.5` |
| `HINDSIGHT_API_RERANKER_COHERE_API_KEY` | Cohere API key for reranking | - |
| `HINDSIGHT_API_RERANKER_COHERE_MODEL` | Cohere rerank model | `rerank-english-v3.0` |
| `HINDSIGHT_API_RERANKER_COHERE_BASE_URL` | Custom base URL for Cohere-compatible API (e.g., Azure-hosted) | - |
@ -518,6 +532,11 @@ export HINDSIGHT_API_RERANKER_LOCAL_TRUST_REMOTE_CODE=true
export HINDSIGHT_API_RERANKER_PROVIDER=tei
export HINDSIGHT_API_RERANKER_TEI_URL=http://localhost:8081
# OpenRouter - access reranking models via OpenRouter
export HINDSIGHT_API_RERANKER_PROVIDER=openrouter
export HINDSIGHT_API_RERANKER_OPENROUTER_API_KEY=your-openrouter-api-key # or reuses HINDSIGHT_API_LLM_API_KEY
export HINDSIGHT_API_RERANKER_OPENROUTER_MODEL=cohere/rerank-v3.5
# Cohere - cloud-based reranking
export HINDSIGHT_API_RERANKER_PROVIDER=cohere
export HINDSIGHT_API_RERANKER_COHERE_API_KEY=your-api-key