debug 002
Browse files
backend/chatgpt.py
CHANGED
|
@@ -5,9 +5,11 @@ from backend.populate_vec_db_and_seach import search_book
|
|
| 5 |
|
| 6 |
def generate(user_prompt,book_name):
|
| 7 |
#book_name = "Pride And Prejudice"
|
| 8 |
-
|
|
|
|
|
|
|
| 9 |
# 1. Vector search (returns list of dicts)
|
| 10 |
-
hits = search_book(book_name, user_prompt
|
| 11 |
|
| 12 |
# 2. Prepare a text block summarizing retrieved context
|
| 13 |
context_text = "\n\n".join(
|
|
|
|
| 5 |
|
| 6 |
def generate(user_prompt,book_name):
|
| 7 |
#book_name = "Pride And Prejudice"
|
| 8 |
+
print(f"[DEBUG] In Generate Function with book_name :{book_name!r}")
|
| 9 |
+
print(f"[DEBUG] In Generate Function with user_prompt :{user_prompt!r}")
|
| 10 |
+
|
| 11 |
# 1. Vector search (returns list of dicts)
|
| 12 |
+
hits = search_book(book_name, user_prompt)
|
| 13 |
|
| 14 |
# 2. Prepare a text block summarizing retrieved context
|
| 15 |
context_text = "\n\n".join(
|
backend/populate_vec_db_and_seach.py
CHANGED
|
@@ -148,14 +148,16 @@ def create_populate_collection_if_not_exist(book_name_sup):
|
|
| 148 |
def search_book(
|
| 149 |
bookname: str,
|
| 150 |
query_text: str,
|
| 151 |
-
top_k: int =
|
| 152 |
score_threshold: float | None = None,
|
| 153 |
):
|
| 154 |
|
| 155 |
client = get_client()
|
| 156 |
model = get_model()
|
| 157 |
# 1) Embed the query text
|
|
|
|
| 158 |
query_vector = list(model.embed([query_text]))[0]
|
|
|
|
| 159 |
collection_name = collection_name_for_book(bookname)
|
| 160 |
# 2) Query Qdrant with cosine similarity (collection is configured as COSINE)
|
| 161 |
result = client.query_points(
|
|
@@ -176,6 +178,7 @@ def search_book(
|
|
| 176 |
"text": point.payload["text"]
|
| 177 |
}
|
| 178 |
)
|
|
|
|
| 179 |
return hits
|
| 180 |
|
| 181 |
|
|
|
|
| 148 |
def search_book(
|
| 149 |
bookname: str,
|
| 150 |
query_text: str,
|
| 151 |
+
top_k: int = 10,
|
| 152 |
score_threshold: float | None = None,
|
| 153 |
):
|
| 154 |
|
| 155 |
client = get_client()
|
| 156 |
model = get_model()
|
| 157 |
# 1) Embed the query text
|
| 158 |
+
print("[DEBUG] Calculating Query Vector ........")
|
| 159 |
query_vector = list(model.embed([query_text]))[0]
|
| 160 |
+
print(f"Query Vecot : {query_vector}")
|
| 161 |
collection_name = collection_name_for_book(bookname)
|
| 162 |
# 2) Query Qdrant with cosine similarity (collection is configured as COSINE)
|
| 163 |
result = client.query_points(
|
|
|
|
| 178 |
"text": point.payload["text"]
|
| 179 |
}
|
| 180 |
)
|
| 181 |
+
print(f"We got some paragraphs Hits:{hits[0]}")
|
| 182 |
return hits
|
| 183 |
|
| 184 |
|