Delete pages

pages/documentation.py

@@ -1,107 +0,0 @@
-import streamlit as st
-
-# Set Streamlit page configuration
-st.set_page_config(page_title="Documentation", layout="wide")
-
-# Set up the Streamlit app layout
-st.title("Documentation")
-
-st.header("Dataset creation")
-
-st.subheader(":blue[HAL API harvest]")
-
-st.write("HAL is the french national open archive for scientific publications based on the principles of open access and self-archiving.")
-st.write("All the API documentation is available [here](https://api.archives-ouvertes.fr/docs/search)")
-st.write("All records of article type publications reported in the UNIV-COTEDAZUR collection of HAL are obtained with this looping function that populates a pandas Dataframe as output ")
-st.code("""
-# we retrieve first the total number of records
-url_for_total_count = "https://api.archives-ouvertes.fr/search/UNIV-COTEDAZUR/?q=docType_s:ART&rows=0"
-response = requests.request("GET", url_for_total_count).text
-data = json.loads(response)
-total_count = data["response"]["numFound"]
-
-""", language='python')
-st.code("""
-step = 1000
-df = []
-for i in range(1, int(total_count), int(step)):
-  url = f"https://api.archives-ouvertes.fr/search/UNIV-COTEDAZUR/?q=docType_s:ART&rows={step}&start={i}&wt=csv&fl=uri_s,title_s,subTitle_s,authFullName_s,producedDate_s,domain_t,journalTitle_s,journalPublisher_s,abstract_s"
-  data = pd.read_csv(url, encoding="utf-8")
-  df.append(data)
-df = pd.concat(df)
-# clean up a little bit
-df = df.drop_duplicates(subset=['uri_s'])
-df = df.replace(np.nan, '')
-""", language='python')
-
-st.write("The dataframe's colmumns of metadata are then concatenated into a single combined text in a new column. It is therefore on this new column that the different embeddings models will be applied to encode this combined text and output a single vector embedding.")
-st.code("""
-df = df.astype(str)
-df["combined"] = df.title_s + ". " + df.subTitle_s + ". " +df.abstract_s
-""", language='python')
-
-st.subheader(":blue[Huggingface open models for Embeddings]")
-
-st.write("The open source Huggingface platform hosts a large number of pre-trained models that can then be reused for many tasks (text or image classification, summarization, document QA etc...). We can then use the sentence-transformers library applied on some of these available embedding pre-trained models for creating embeddings.")
-st.write("There is two ways of working with the Huggingface hosted models : by using the [inference API endpoint](https://huggingface.co/inference-api) or by locally importing the model. Here we choose the second way")
-st.write("Two open source transformers-based models have been used to convert the textual metadata into numerical vector representation, which generated two vector embeddings datasets : embeddings_all-MiniLM-L6-v2.pt and embeddings_multi-qa-mpnet-base-dot-v1.pt")
-st.code("""
-import torch
-from sentence_transformers import SentenceTransformer
-        
-embedder = SentenceTransformer('all-MiniLM-L6-v2') # or 'multi-qa-mpnet-base-dot-v1'
-
-corpus_embeddings = embedder.encode(df.combined, convert_to_tensor=True)
-        
-# how to save and reload
-torch.save(corpus_embeddings, f"{LOCAL_PATH}/embeddings_all-MiniLM-L6-v2.pt")
-corpus_embeddings = torch.load(f"{LOCAL_PATH}/embeddings_all-MiniLM-L6-v2.pt")
-
-""", language='python')
-
-st.subheader(":blue[Bonus : OpenAI Embeddings]")
-
-st.write("If you want to do the same with text-embedding-ada-002 (the OpenAI embeddings model)")
-
-st.code("""
-import openai
-import tiktoken
-from openai.embeddings_utils import get_embedding
-        
-openai.api_key = os.getenv("OPENAI_API_KEY")
-
-# embedding model parameters
-embedding_model = "text-embedding-ada-002"
-embedding_encoding = "cl100k_base"  # this the encoding for text-embedding-ada-002
-max_tokens = 8000  # the maximum for text-embedding-ada-002 is 8191
-
-# filtering dataset on text under the max tokens limit      
-encoding = tiktoken.get_encoding(embedding_encoding)
-df["n_tokens"] = df.combined.apply(lambda x: len(encoding.encode(x)))
-df = df[df.n_tokens <= max_tokens]
-        
-# generate embeddings
-def custom_get_embedding(text: str) -> list[float]:
-    return openai.Embedding.create(input=[text], model="text-embedding-ada-002")["data"][0]["embedding"]
-df["openai_embedding"] = df.combined.apply(lambda x: custom_get_embedding(x) )
-
-""", language='python')
-
-st.write("And the Steamlit UI code would be :")
-
-st.code("""
-df["openai_embedding"] = df.openai_embedding.apply(literal_eval).apply(np.array)
-def custom_get_embedding(text: str) -> list[float]:
-    return openai.Embedding.create(input=[text], model="text-embedding-ada-002", openai_api_key=OPENAI_API_KEY)["data"][0]["embedding"]
-def openai_response(query):
-    query_embedding = np.array(custom_get_embedding(
-        query
-    ))
-    df["similarity"] = df.openai_embedding.apply(lambda x: cosine_similarity(x, query_embedding))
-    return df.sort_values("similarity", ascending=False).head(5).to_json(orient="records")
-
-""", language='python')
-
-st.header("Dataset hosting")
-
-st.write("The csv file of the dataset is avalaible in the data folder")