diff --git a/docs/extras/integrations/text_embedding/aleph_alpha.ipynb b/docs/extras/integrations/text_embedding/aleph_alpha.ipynb index f813329bfc..05fcebeaec 100644 --- a/docs/extras/integrations/text_embedding/aleph_alpha.ipynb +++ b/docs/extras/integrations/text_embedding/aleph_alpha.ipynb @@ -20,7 +20,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 1, "id": "8a920a89", "metadata": {}, "outputs": [], @@ -30,7 +30,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 2, "id": "f2d04da3", "metadata": {}, "outputs": [], @@ -41,17 +41,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "e6ecde96", "metadata": {}, "outputs": [], "source": [ - "embeddings = AlephAlphaAsymmetricSemanticEmbedding()" + "embeddings = AlephAlphaAsymmetricSemanticEmbedding(normalize=True, compress_to_size=128)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "90e68411", "metadata": {}, "outputs": [], @@ -61,7 +61,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "55903233", "metadata": {}, "outputs": [], @@ -79,7 +79,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "eabb763a", "metadata": {}, "outputs": [], @@ -89,7 +89,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 7, "id": "0ad799f7", "metadata": {}, "outputs": [], @@ -99,17 +99,17 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "af86dc10", "metadata": {}, "outputs": [], "source": [ - "embeddings = AlephAlphaSymmetricSemanticEmbedding()" + "embeddings = AlephAlphaSymmetricSemanticEmbedding(normalize=True, compress_to_size=128)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "id": "d292536f", "metadata": {}, "outputs": [], @@ -119,7 +119,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "id": "c704a7cf", "metadata": {}, "outputs": [], @@ -130,7 +130,7 @@ { "cell_type": "code", "execution_count": null, - "id": "33492471", + "id": "5d999f8f", "metadata": {}, "outputs": [], "source": [] @@ -152,7 +152,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.1" + "version": "3.9.13" }, "vscode": { "interpreter": { diff --git a/libs/langchain/langchain/embeddings/aleph_alpha.py b/libs/langchain/langchain/embeddings/aleph_alpha.py index f53d509a9c..1f5c4b8b19 100644 --- a/libs/langchain/langchain/embeddings/aleph_alpha.py +++ b/libs/langchain/langchain/embeddings/aleph_alpha.py @@ -16,10 +16,11 @@ class AlephAlphaAsymmetricSemanticEmbedding(BaseModel, Embeddings): Example: .. code-block:: python - from aleph_alpha import AlephAlphaAsymmetricSemanticEmbedding - embeddings = AlephAlphaSymmetricSemanticEmbedding() + embeddings = AlephAlphaAsymmetricSemanticEmbedding( + normalize=True, compress_to_size=128 + ) document = "This is a content of the document" query = "What is the content of the document?" @@ -30,24 +31,55 @@ class AlephAlphaAsymmetricSemanticEmbedding(BaseModel, Embeddings): """ client: Any #: :meta private: - """Aleph Alpha client.""" - model: Optional[str] = "luminous-base" + + # Embedding params + model: str = "luminous-base" """Model name to use.""" - hosting: Optional[str] = "https://api.aleph-alpha.com" - """Optional parameter that specifies which datacenters may process the request.""" - normalize: Optional[bool] = True - """Should returned embeddings be normalized""" - compress_to_size: Optional[int] = 128 + compress_to_size: Optional[int] = None """Should the returned embeddings come back as an original 5120-dim vector, or should it be compressed to 128-dim.""" + normalize: Optional[bool] = None + """Should returned embeddings be normalized""" contextual_control_threshold: Optional[int] = None """Attention control parameters only apply to those tokens that have explicitly been set in the request.""" - control_log_additive: Optional[bool] = True + control_log_additive: bool = True """Apply controls on prompt items by adding the log(control_factor) to attention scores.""" + + # Client params aleph_alpha_api_key: Optional[str] = None """API key for Aleph Alpha API.""" + host: str = "https://api.aleph-alpha.com" + """The hostname of the API host. + The default one is "https://api.aleph-alpha.com")""" + hosting: Optional[str] = None + """Determines in which datacenters the request may be processed. + You can either set the parameter to "aleph-alpha" or omit it (defaulting to None). + Not setting this value, or setting it to None, gives us maximal flexibility + in processing your request in our + own datacenters and on servers hosted with other providers. + Choose this option for maximal availability. + Setting it to "aleph-alpha" allows us to only process the request + in our own datacenters. + Choose this option for maximal data privacy.""" + request_timeout_seconds: int = 305 + """Client timeout that will be set for HTTP requests in the + `requests` library's API calls. + Server will close all requests after 300 seconds with an internal server error.""" + total_retries: int = 8 + """The number of retries made in case requests fail with certain retryable + status codes. If the last + retry fails a corresponding exception is raised. Note, that between retries + an exponential backoff + is applied, starting with 0.5 s after the first retry and doubling for each + retry made. So with the + default setting of 8 retries a total wait time of 63.5 s is added between + the retries.""" + nice: bool = False + """Setting this to True, will signal to the API that you intend to be + nice to other users + by de-prioritizing your request below concurrent ones.""" @root_validator() def validate_environment(cls, values: Dict) -> Dict: @@ -57,12 +89,21 @@ class AlephAlphaAsymmetricSemanticEmbedding(BaseModel, Embeddings): ) try: from aleph_alpha_client import Client + + values["client"] = Client( + token=aleph_alpha_api_key, + host=values["host"], + hosting=values["hosting"], + request_timeout_seconds=values["request_timeout_seconds"], + total_retries=values["total_retries"], + nice=values["nice"], + ) except ImportError: raise ValueError( "Could not import aleph_alpha_client python package. " "Please install it with `pip install aleph_alpha_client`." ) - values["client"] = Client(token=aleph_alpha_api_key) + return values def embed_documents(self, texts: List[str]) -> List[List[float]]: @@ -152,7 +193,9 @@ class AlephAlphaSymmetricSemanticEmbedding(AlephAlphaAsymmetricSemanticEmbedding from aleph_alpha import AlephAlphaSymmetricSemanticEmbedding - embeddings = AlephAlphaAsymmetricSemanticEmbedding() + embeddings = AlephAlphaAsymmetricSemanticEmbedding( + normalize=True, compress_to_size=128 + ) text = "This is a test text" doc_result = embeddings.embed_documents([text]) diff --git a/libs/langchain/langchain/llms/aleph_alpha.py b/libs/langchain/langchain/llms/aleph_alpha.py index cd4aec1682..1df17c3a87 100644 --- a/libs/langchain/langchain/llms/aleph_alpha.py +++ b/libs/langchain/langchain/llms/aleph_alpha.py @@ -125,12 +125,43 @@ class AlephAlpha(LLM): raw_completion: bool = False """Force the raw completion of the model to be returned.""" - aleph_alpha_api_key: Optional[str] = None - """API key for Aleph Alpha API.""" - stop_sequences: Optional[List[str]] = None """Stop sequences to use.""" + # Client params + aleph_alpha_api_key: Optional[str] = None + """API key for Aleph Alpha API.""" + host: str = "https://api.aleph-alpha.com" + """The hostname of the API host. + The default one is "https://api.aleph-alpha.com")""" + hosting: Optional[str] = None + """Determines in which datacenters the request may be processed. + You can either set the parameter to "aleph-alpha" or omit it (defaulting to None). + Not setting this value, or setting it to None, gives us maximal + flexibility in processing your request in our + own datacenters and on servers hosted with other providers. + Choose this option for maximal availability. + Setting it to "aleph-alpha" allows us to only process the + request in our own datacenters. + Choose this option for maximal data privacy.""" + request_timeout_seconds: int = 305 + """Client timeout that will be set for HTTP requests in the + `requests` library's API calls. + Server will close all requests after 300 seconds with an internal server error.""" + total_retries: int = 8 + """The number of retries made in case requests fail with certain retryable + status codes. If the last + retry fails a corresponding exception is raised. Note, that between retries + an exponential backoff + is applied, starting with 0.5 s after the first retry and doubling for + each retry made. So with the + default setting of 8 retries a total wait time of 63.5 s is added + between the retries.""" + nice: bool = False + """Setting this to True, will signal to the API that you intend to be + nice to other users + by de-prioritizing your request below concurrent ones.""" + class Config: """Configuration for this pydantic object.""" @@ -143,9 +174,16 @@ class AlephAlpha(LLM): values, "aleph_alpha_api_key", "ALEPH_ALPHA_API_KEY" ) try: - import aleph_alpha_client + from aleph_alpha_client import Client - values["client"] = aleph_alpha_client.Client(token=aleph_alpha_api_key) + values["client"] = Client( + token=aleph_alpha_api_key, + host=values["host"], + hosting=values["hosting"], + request_timeout_seconds=values["request_timeout_seconds"], + total_retries=values["total_retries"], + nice=values["nice"], + ) except ImportError: raise ImportError( "Could not import aleph_alpha_client python package. " @@ -241,3 +279,9 @@ class AlephAlpha(LLM): if stop is not None or self.stop_sequences is not None: text = enforce_stop_tokens(text, params["stop_sequences"]) return text + + +if __name__ == "__main__": + aa = AlephAlpha() + + print(aa("How are you?"))