pages/documentation.py

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("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 recursive function that populates a pandas Dataframe as output ")
st.code("""
global_list = []
def recursive_hal_harvest(cursor="*"):
  url = f"https://api.archives-ouvertes.fr/search/UNIV-COTEDAZUR/?q=docType_s:ART&rows=1000&cursorMark={cursor}&fl=uri_s,title_s,subTitle_s,authFullName_s,producedDate_s,domain_t,journalTitle_s,journalPublisher_s,anrProjectCallTitle_s,abstract_s&sort=docid asc"
  print(url)
  response = requests.request("GET", url).text
  data = json.loads(response)
  for doc in data["response"]["docs"]:
    global_list.append(doc)
  if len(data["response"]["docs"]) != 0:
    return recursive_hal_harvest(cursor=data["nextCursorMark"])
  else:
    return global_list
df = pd.DataFrame(recursive_hal_harvest())

""", 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"] = (
    "Title: " + df.title_s + ";Subtitle:" + df.subTitle_s + ";Author:" + df.authFullName_s + ";Date:" + df.producedDate_s + ";Journal Title:" + df.journalTitle_s + ";Publisher:" + df.journalPublisher_s + ";ANR Project:" + df.anrProjectCallTitle_s + "; Abstract: " + df.abstract_s
)

""", language='python')

st.subheader(":blue[OpenAI Embeddings]")

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]
        
# générate embeddings
df["openai_embedding"] = df.combined.apply(lambda x: get_embedding(x, engine=embedding_model) )
df["openai_embedding"] = df.embedding.astype(str).apply(eval).apply(np.array)

""", language='python')

st.subheader(":blue[Huggingface free 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 popular sentence-transformers library applied on free available text embedding models for creating embeddings ")