Skip to content

armgit / dspy

Public Imported from GitHub
0

DSPy: The framework for programming—not prompting—language models

Python

fix(dspy): updating syntax for embeddings method call which will be deprecated

alejandroa048a511f8e9
diff --git a/docs/api/retrieval_model_clients/SnowflakeRM.md b/docs/api/retrieval_model_clients/SnowflakeRM.md
index 7b7a3ee5c..78695dc0c 100644
--- a/docs/api/retrieval_model_clients/SnowflakeRM.md
+++ b/docs/api/retrieval_model_clients/SnowflakeRM.md
@@ -1,5 +1,5 @@
---
-sidebar_position:
+sidebar_position:
---
# retrieve.SnowflakeRM
@@ -20,6 +20,7 @@ SnowflakeRM(
```
**Parameters:**
+
- `snowflake_table_name (str)`: The name of the Snowflake table containing embeddings.
- `snowflake_credentials (dict)`: The connection parameters needed to initialize a Snowflake Snowpark Session.
- `k (int, optional)`: The number of top passages to retrieve. Defaults to 3.
@@ -34,10 +35,12 @@ SnowflakeRM(
Search the Snowflake table for the top `k` passages matching the given query or queries, using embeddings generated via the default `e5-base-v2` model or the specified `embedding_model`.
**Parameters:**
+
- `query_or_queries` (_Union[str, List[str]]_): The query or list of queries to search for.
- `k` (_Optional[int]_, _optional_): The number of results to retrieve. If not specified, defaults to the value set during initialization.
**Returns:**
+
- `dspy.Prediction`: Contains the retrieved passages, each represented as a `dotdict` with schema `[{"id": str, "score": float, "long_text": str, "metadatas": dict }]`
### Quickstart
@@ -53,14 +56,14 @@ from dspy.retrieve.snowflake_rm import SnowflakeRM
import os
connection_parameters = {
-
+
"account": os.getenv('SNOWFLAKE_ACCOUNT'),
"user": os.getenv('SNOWFLAKE_USER'),
"password": os.getenv('SNOWFLAKE_PASSWORD'),
"role": os.getenv('SNOWFLAKE_ROLE'),
"warehouse": os.getenv('SNOWFLAKE_WAREHOUSE'),
"database": os.getenv('SNOWFLAKE_DATABASE'),
- "schema": os.getenv('SNOWFLAKE_SCHEMA')}
+ "schema": os.getenv('SNOWFLAKE_SCHEMA')}
retriever_model = SnowflakeRM(
snowflake_table_name="<YOUR_SNOWFLAKE_TABLE_NAME>",
@@ -74,4 +77,3 @@ results = retriever_model("Explore the meaning of life", k=5)
for result in results:
print("Document:", result.long_text, "\n")
```
-
diff --git a/dspy/retrieve/snowflake_rm.py b/dspy/retrieve/snowflake_rm.py
index 52a73bd6f..ec7dc389a 100644
--- a/dspy/retrieve/snowflake_rm.py
+++ b/dspy/retrieve/snowflake_rm.py
@@ -11,7 +11,7 @@ try:
except ImportError:
raise ImportError(
- "The snowflake-snowpark-python library is required to use SnowflakeRM. Install it with dspy-ai[snowflake]"
+ "The snowflake-snowpark-python library is required to use SnowflakeRM. Install it with dspy-ai[snowflake]",
)
@@ -93,7 +93,7 @@ class SnowflakeRM(dspy.Retrieve):
lit(query_embeddings).cast(VectorType(float, len(query_embeddings))),
).as_("dist"),
)
- .sort("dist",ascending=False)
+ .sort("dist", ascending=False)
.limit(k)
)
@@ -101,15 +101,14 @@ class SnowflakeRM(dspy.Retrieve):
@classmethod
def _init_cortex(cls, credentials: dict) -> None:
-
session = Session.builder.configs(credentials).create()
- session.query_tag = {"origin":"sf_sit", "name":"dspy", "version":{"major":1, "minor":0}}
+ session.query_tag = {"origin": "sf_sit", "name": "dspy", "version": {"major": 1, "minor": 0}}
return session
def _get_embeddings(self, query: str) -> list[float]:
# create embeddings for the query
- embed = snow_fn.builtin("snowflake.cortex.embed_text")
+ embed = snow_fn.builtin("snowflake.cortex.embed_text_768")
cortex_embed_args = embed(snow_fn.lit(self.embeddings_model), snow_fn.lit(query))
return self.client.range(1).withColumn("complete_cal", cortex_embed_args).collect()[0].COMPLETE_CAL