Victor2323 commited on
Commit
7e0035d
1 Parent(s): 6c49815

Upload 9 files

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ chroma/chroma.sqlite3 filter=lfs diff=lfs merge=lfs -text
Dockerfile ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ FROM python:3.12.4
2
+
3
+ RUN useradd -m -u 1000 user
4
+ USER user
5
+ ENV PATH="/home/user/.local/bin:$PATH"
6
+
7
+ WORKDIR /app
8
+
9
+ COPY --chown=user ./requirements.txt requirements.txt
10
+ RUN pip install --no-cache-dir --upgrade -r requirements.txt
11
+
12
+ COPY --chown=user . /app
13
+ CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
app.py ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ from fastapi import FastAPI, HTTPException
3
+ from pydantic import BaseModel
4
+ from typing import List
5
+ from langchain_community.vectorstores import Chroma
6
+ from langchain.prompts import ChatPromptTemplate
7
+ from get_embedding_function import get_embedding_function
8
+ from langchain_groq import ChatGroq
9
+
10
+ app = FastAPI()
11
+
12
+ # Configurar variáveis de ambiente
13
+ os.environ["OPENAI_API_BASE"] = 'https://api.groq.com/openai/v1'
14
+ os.environ["OPENAI_MODEL_NAME"] = 'llama3-8b-8192'
15
+ os.environ["GROQ_API_KEY"] = os.getenv("GROQ_API_KEY")
16
+
17
+ CHROMA_PATH = "chroma"
18
+
19
+ PROMPT_TEMPLATE = """
20
+ You are 'Vasu', an experienced professor with extensive knowledge in Cryptocurrency, Artificial Intelligence, and related projects.
21
+ Provide relevant 'Links' "http://", but include links only when they are particularly useful for understanding the response.
22
+ Answer the question based solely on the following context: {context}
23
+
24
+ Based on the above context, answer the question: {question}.
25
+ """
26
+
27
+ class QueryRequest(BaseModel):
28
+ query: str
29
+
30
+ class QueryResponse(BaseModel):
31
+ response: str
32
+ sources: List[str]
33
+
34
+ def query_rag(query_text: str):
35
+ # Configurar o modelo Groq
36
+ chat_groq = ChatGroq(temperature=0, model_name="llama3-8b-8192")
37
+
38
+ # Preparar o DB
39
+ embedding_function = get_embedding_function()
40
+ db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
41
+
42
+ # Buscar no DB
43
+ results = db.similarity_search_with_score(query_text, k=10)
44
+
45
+ context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
46
+ prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
47
+ prompt = prompt_template.format(context=context_text, question=query_text)
48
+
49
+ # Obter a resposta usando Groq
50
+ response_text = chat_groq.invoke(prompt).content
51
+
52
+ sources = [doc.metadata.get("id", None) for doc, _score in results]
53
+ return response_text, sources
54
+
55
+ @app.post("/query", response_model=QueryResponse)
56
+ async def query_api(request: QueryRequest):
57
+ try:
58
+ response_text, sources = query_rag(request.query)
59
+ return QueryResponse(response=response_text, sources=sources)
60
+ except Exception as e:
61
+ raise HTTPException(status_code=500, detail=str(e))
chroma/45ca7996-a391-40cb-a525-0676e4c9d12b/data_level0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95042e844cfb77b20e578cf65635282a99d7c4dd20e589ac062f38bc389f8e58
3
+ size 4236000
chroma/45ca7996-a391-40cb-a525-0676e4c9d12b/header.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc596bc1909f7cc610d5839236c90513b4fbad06776c253fa1b21bfd712e940
3
+ size 100
chroma/45ca7996-a391-40cb-a525-0676e4c9d12b/length.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc19b1997119425765295aeab72d76faa6927d4f83985d328c26f20468d6cc76
3
+ size 4000
chroma/45ca7996-a391-40cb-a525-0676e4c9d12b/link_lists.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855
3
+ size 0
chroma/chroma.sqlite3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62e5a3345fbe263e9af31b3a3e57215dffa1475129a9762da20c7a9f85bfe155
3
+ size 10698752
get_embedding_function.py ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ from langchain_community.embeddings.ollama import OllamaEmbeddings
2
+
3
+ def get_embedding_function():
4
+ embeddings = OllamaEmbeddings(model="mxbai-embed-large",
5
+ show_progress=True)
6
+ return embeddings
requirements.txt ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ fastapi
2
+ uvicorn[standard]
3
+ langchain_community
4
+ langchain
5
+ chainlit
6
+ python-dotenv