embedder

rag.py

@@ -21,7 +21,13 @@ from sentence_transformers import SentenceTransformer
 model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2", device="cpu")
 embedder = dspy.Embedder(model.encode)
 """
-embedder = dspy.Embedder('huggingface/BAAI/bge-small-en-v1.5')
+
+import numpy as np
+def my_embedder(texts):
+  return np.random.rand(len(texts), 10)
+
+embedder = dspy.Embedder(my_embedder)
+#embedder = dspy.Embedder('huggingface/BAAI/bge-small-en-v1.5')
 class RecommendProduct(dspy.Signature):
   """
   Recommend RBC financial product based on verbatim

tool.py

@@ -14,7 +14,7 @@ search_client = TavilyClient(api_key=os.environ["T_TOKEN"])
 
 INST="""Recommend banking financial product based on verbatim"""
 def web_search(query: str) -> list[str]:
-    """Run a web search and return the personal banking product from the top 5 search results"""
+    """Run a web search to return the top 3 personal banking product that satisfy the query"""
     response = search_client.search(query)
     return [r["content"] for r in response["results"]]
 
@@ -23,5 +23,5 @@ agent = dspy.ReAct("verbatim -> product", tools=[Tool(web_search)])
 customer="Low APR and great customer service. I would highly recommend if you’re looking for a great credit card company and looking to rebuild your credit. I have had my credit limit increased annually and the annual fee is very low."
 
 def rival_product(customer:str):
-    prediction = agent(verbatim=f"Which banking product best serve this customer needs, pain points: {customer}")
+    prediction = agent(verbatim=f"Which banking product name best serve this customer needs: {customer}")
     return prediction.product