Spaces:
Sleeping
Sleeping
Commit
·
1b14b9b
1
Parent(s):
400f53b
Adding chat response
Browse files
app.py
CHANGED
@@ -25,17 +25,18 @@ prompt = PromptTemplate(template = prompt_template, input_variables = ["context"
|
|
25 |
|
26 |
chain = prompt | gemini
|
27 |
|
28 |
-
|
|
|
|
|
29 |
raw_documents = []
|
30 |
for path in pdf_path:
|
31 |
raw_documents.extend(PyPDFLoader(path).load())
|
|
|
32 |
text_splitter = CharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
|
33 |
documents = text_splitter.split_documents(raw_documents)
|
34 |
|
35 |
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
|
36 |
|
37 |
-
index_name = "langchain-test-index"
|
38 |
-
|
39 |
index = pc.Index(host="https://langchain-test-index-la2n80y.svc.aped-4627-b74a.pinecone.io")
|
40 |
|
41 |
if index.list():
|
@@ -55,6 +56,26 @@ description = "A simple Gradio interface to query PDFs and compare vector databa
|
|
55 |
examples = [[["data/amazon-10-k-2024.pdf"], 1000, 100],
|
56 |
[["data/goog-10-k-2023.pdf"], 1000, 100]]
|
57 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
|
59 |
gr.Markdown(f"# {title}\n{description}")
|
60 |
with gr.Row():
|
@@ -68,7 +89,22 @@ with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
|
|
68 |
with gr.Column():
|
69 |
message = gr.Textbox(label="Status", type="text")
|
70 |
|
71 |
-
submit_btn.click(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
72 |
|
73 |
examples_obj = gr.Examples(examples=examples, inputs=[pdf, chunk_size, chunk_overlap])
|
74 |
|
|
|
25 |
|
26 |
chain = prompt | gemini
|
27 |
|
28 |
+
index_name = "langchain-test-index"
|
29 |
+
|
30 |
+
def store_embeddings(pdf_path, chunk_size, chunk_overlap):
|
31 |
raw_documents = []
|
32 |
for path in pdf_path:
|
33 |
raw_documents.extend(PyPDFLoader(path).load())
|
34 |
+
|
35 |
text_splitter = CharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
|
36 |
documents = text_splitter.split_documents(raw_documents)
|
37 |
|
38 |
pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])
|
39 |
|
|
|
|
|
40 |
index = pc.Index(host="https://langchain-test-index-la2n80y.svc.aped-4627-b74a.pinecone.io")
|
41 |
|
42 |
if index.list():
|
|
|
56 |
examples = [[["data/amazon-10-k-2024.pdf"], 1000, 100],
|
57 |
[["data/goog-10-k-2023.pdf"], 1000, 100]]
|
58 |
|
59 |
+
def inference(query):
|
60 |
+
chroma_db = Chroma(persist_directory="./chroma_db", embedding_function=embeddings)
|
61 |
+
chroma_docs = chroma_db.similarity_search(query)
|
62 |
+
chroma_answer = chain.invoke({"context":chroma_docs, "question": query}, return_only_outputs=True)
|
63 |
+
|
64 |
+
faiss_db = FAISS.load_local("./faiss_db", embeddings, allow_dangerous_deserialization=True)
|
65 |
+
faiss_docs = faiss_db.similarity_search(query)
|
66 |
+
faiss_answer = chain.invoke({"context":faiss_docs, "question": query}, return_only_outputs=True)
|
67 |
+
|
68 |
+
lance_db = LanceDB(embedding=embeddings, uri="./lance_db")
|
69 |
+
lance_docs = lance_db.similarity_search(query)
|
70 |
+
lance_answer = chain.invoke({"context":lance_docs, "question": query}, return_only_outputs=True)
|
71 |
+
|
72 |
+
pinecone_db = PineconeVectorStore(index="langchain-test-index", embedding=embeddings)
|
73 |
+
pinecone_docs = pinecone_db.similarity_search(query)
|
74 |
+
pinecoce_answer = chain.invoke({"context":pinecone_docs, "question": query}, return_only_outputs=True)
|
75 |
+
|
76 |
+
return chroma_answer, faiss_answer, lance_answer, pinecoce_answer
|
77 |
+
|
78 |
+
|
79 |
with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
|
80 |
gr.Markdown(f"# {title}\n{description}")
|
81 |
with gr.Row():
|
|
|
89 |
with gr.Column():
|
90 |
message = gr.Textbox(label="Status", type="text")
|
91 |
|
92 |
+
submit_btn.click(store_embeddings, inputs=[pdf, chunk_size, chunk_overlap], outputs=message)
|
93 |
+
|
94 |
+
with gr.Row():
|
95 |
+
with gr.Column():
|
96 |
+
text = gr.Textbox(label="Question", type="text")
|
97 |
+
with gr.Row():
|
98 |
+
chat_clear_btn = gr.ClearButton(components=[text])
|
99 |
+
chat_submit_btn = gr.Button("Submit", variant='primary')
|
100 |
+
with gr.Column():
|
101 |
+
chroma_out = gr.Textbox(label="ChromaDB Response", type="text")
|
102 |
+
faiss_out = gr.Textbox(label="FaissDB Response", type="text")
|
103 |
+
lance_out = gr.Textbox(label="LanceDB Response", type="text")
|
104 |
+
pinecone_out = gr.Textbox(label="PineconeDB Response", type="text")
|
105 |
+
|
106 |
+
chat_submit_btn.click(inference, inputs=[text], outputs=[chroma_out, faiss_out, lance_out,
|
107 |
+
pinecone_out])
|
108 |
|
109 |
examples_obj = gr.Examples(examples=examples, inputs=[pdf, chunk_size, chunk_overlap])
|
110 |
|