test chromadb

.gitignore

@@ -0,0 +1 @@
+.DS_Store

app.py

@@ -1,31 +1,31 @@
-import streamlit as st
-from PIL import Image
-import easyocr
-import numpy as np
-import cv2
+# import streamlit as st
+# from PIL import Image
+# import easyocr
+# import numpy as np
+# import cv2
 
-reader = easyocr.Reader(['en'])
+# reader = easyocr.Reader(['en'])
 
-uploaded_file = st.file_uploader("Please upload your image file", type=["jpg", "jpeg", "png"])
+# uploaded_file = st.file_uploader("Please upload your image file", type=["jpg", "jpeg", "png"])
 
-if uploaded_file is not None:
-    image = Image.open(uploaded_file)
+# if uploaded_file is not None:
+#     image = Image.open(uploaded_file)
 
-    st.image(image, caption="Uploaded Image", use_column_width=True)
+#     st.image(image, caption="Uploaded Image", use_column_width=True)
 
-    image_np = np.array(image)
-    image_np = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
-    with st.spinner("Performing OCR..."):
-        result = reader.readtext(image_np)
+#     image_np = np.array(image)
+#     image_np = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
+#     with st.spinner("Performing OCR..."):
+#         result = reader.readtext(image_np)
 
-    if result:
-        st.subheader("OCR Results:")
-        extracted_text = "\n".join([text[1] for text in result])
-        st.text_area("Extracted Text", extracted_text, height=200)
-    else:
-        st.warning("No text found in the image.")
-else:
-    st.info("Please upload an image file")
+#     if result:
+#         st.subheader("OCR Results:")
+#         extracted_text = "\n".join([text[1] for text in result])
+#         st.text_area("Extracted Text", extracted_text, height=200)
+#     else:
+#         st.warning("No text found in the image.")
+# else:
+#     st.info("Please upload an image file")
 
 
 # import streamlit as st
@@ -37,3 +37,27 @@ else:
 # if text:
 #     out = pipe(text)
 #     st.json(out)
+
+import streamlit as st
+from langchain_community.vectorstores import Chroma
+from langchain_huggingface import HuggingFaceEmbeddings
+
+CHROMA_GOOD_PATH = "chroma_good"
+CHROMA_BAD_PATH = "chroma_bad"
+
+text = st.text_area("enter some text")
+embedding_function = HuggingFaceEmbeddings()
+db_good = Chroma(persist_directory=CHROMA_GOOD_PATH, embedding_function=embedding_function)
+db_bad = Chroma(persist_directory=CHROMA_BAD_PATH, embedding_function=embedding_function)
+
+if text:
+    results_good = db_good.similarity_search_with_relevance_scores(text, k=3)
+    if len(results_good) == 0 or results_good[0][1] < 0.7:
+        print(f"Unable to find matching results_good.")
+        return
+    st.json(results_good)
+    results_bad = db_bad.similarity_search_with_relevance_scores(text, k=3)
+    if len(results_bad) == 0 or results_bad[0][1] < 0.7:
+        print(f"Unable to find matching results_bad.")
+        return
+    st.json(results_bad)

requirements.txt

@@ -2,11 +2,11 @@ streamlit
 chromadb
 easyocr
 langchain
-langchain-community
-langchain-openai
+langchain-huggingface
 numpy
 opencv-python-headless
 openai
 Pillow
+sentence-transformers
 transformers
-torch
+torch