Skip to content

Commit

Permalink
Switched to Milvus
Browse files Browse the repository at this point in the history
  • Loading branch information
shivankacker committed Jul 3, 2024
1 parent c29dae8 commit dc0d1e2
Show file tree
Hide file tree
Showing 23 changed files with 1,196 additions and 858 deletions.
1 change: 1 addition & 0 deletions .envs/.local/.django
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ IPYTHONDIR=/app/.ipython
# Redis
# ------------------------------------------------------------------------------
REDIS_URL=redis://redis:6379/0
DATABASE_URL=postgres://debug:debug@postgres:5432/ayushma

# Celery
# ------------------------------------------------------------------------------
Expand Down
5 changes: 4 additions & 1 deletion Makefile
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,10 @@ logs:
docker compose -f $(docker_config_file) logs

makemigrations: up
docker exec django bash -c "python manage.py makemigrations"
docker compose -f $(docker_config_file) exec django bash -c "python manage.py makemigrations"

migrate: up
docker compose -f $(docker_config_file) exec django bash -c "python manage.py migrate"

checkmigration:
docker compose -f $(docker_config_file) exec django bash -c "python manage.py makemigrations --check --dry-run"
Expand Down
3 changes: 2 additions & 1 deletion Pipfile
Original file line number Diff line number Diff line change
Expand Up @@ -24,7 +24,7 @@ drf-nested-routers = "==0.93.4"
drf-spectacular = "==0.27.0"
requests = "==2.31.0"
openai = "==1.2.4"
pinecone-client = "==2.2.4"
pinecone-client = "==4.1.1"
pypdf2 = "==3.0.1"
tiktoken = "==0.5.2"
langchain = "==0.0.352"
Expand All @@ -41,6 +41,7 @@ nltk = "==3.8.1"
gunicorn = "==21.2.0"
psycopg = {extras = ["c"], version = "==3.1.17"}
sentry-sdk = "==1.30.0"
pymilvus = "*"

[dev-packages]
ipdb = "==0.13.13"
Expand Down
1,425 changes: 780 additions & 645 deletions Pipfile.lock

Large diffs are not rendered by default.

4 changes: 0 additions & 4 deletions Procfile

This file was deleted.

56 changes: 27 additions & 29 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,50 +1,48 @@
# Ayushma AI

This is a Django Project.
This is a Django Project

## Requirements

- Python 3.8
- Postgres 15
- OpenAI Account with a valid API Key
- Pinecone Account with a valid API Key
- Docker

## Optional Requirements

- Docker
- AWS SES Accout
- AWS S3 Account
- Google Cloud account with access to speech to text API

## Installation
## Running the Project

create a virtual environment and install the requirements
> We strongly recommend using Docker to run the project. Manual methods are not supported at the moment.
```bash
pip3 install --user virtualenv
virtualenv .venv
source .venv/bin/activate
pip3 install -r requirements/local.txt
make up
```

## Env Variables

You can add these at the end of your `activate` file in `[virtualenvfolder] -> bin` like `export [env] = [value]`

| Variable | Description
| --- | ---
| AI_NAME | Name of the AI (default: Ayushma)
| OPENAI_API_KEY | OpenAI API Key
| PINECONE_API_KEY | Pinecone API Key
| PINECONE_ENVIRONMENT | Pinecone Environment
| PINECONE_INDEX | Pinecone Index
| CURRENT_DOMAIN | Current Domain where the frontend is hosted. ex. `https://ayushma.ohc.network`
| EMAIL_HOST | SES Email Host (Optional)
| EMAIL_USER | SES Email User (Optional)
| EMAIL_PASSWORD | SES Email Password (Optional)
| GOOGLE_APPLICATION_CREDENTIALS | Google Cloud Credentials (Optional). These should be in a file named `gc_credential.json` in the root of the project
| S3_SECRET_KEY | AWS S3 Secret Key (Optional)
| S3_KEY_ID | AWS S3 Key ID (Optional)
| S3_BUCKET_NAME | AWS S3 Bucket Name (Optional)
| S3_REGION | AWS S3 Region (Optional)
| GOOGLE_RECAPTCHA_SECRET_KEY | Google Recaptcha Secret Key (Optional)
Add these environment variables to your `.env` file.

| Variable | Description |
| ------------------------------ | -------------------------------------------------------------------------------------------------------------------- |
| AI_NAME | Name of the AI (default: Ayushma) |
| OPENAI_API_KEY | OpenAI API Key |
| PINECONE_API_KEY | Pinecone API Key |
| PINECONE_INDEX | Pinecone Index |
| CURRENT_DOMAIN | Current Domain where the frontend is hosted. ex. `https://ayushma.ohc.network` |
| EMAIL_HOST | SES Email Host (Optional) |
| EMAIL_USER | SES Email User (Optional) |
| EMAIL_PASSWORD | SES Email Password (Optional) |
| GOOGLE_APPLICATION_CREDENTIALS | Google Cloud Credentials (Optional). These should be in a file named `gc_credential.json` in the root of the project |
| S3_SECRET_KEY | AWS S3 Secret Key (Optional) |
| S3_KEY_ID | AWS S3 Key ID (Optional) |
| S3_BUCKET_NAME | AWS S3 Bucket Name (Optional) |
| S3_REGION | AWS S3 Region (Optional) |
| GOOGLE_RECAPTCHA_SECRET_KEY | Google Recaptcha Secret Key (Optional) |

## Google Cloud

To use Google Cloud Speech to Text API, you need to enable the API and create a service account. Download the credentials and save them in a file named `gc_credential.json` in the root of the project.
Empty file removed ayushma/management/__init__.py
Empty file.
83 changes: 0 additions & 83 deletions ayushma/management/commands/upsert.py

This file was deleted.

46 changes: 46 additions & 0 deletions ayushma/migrations/0053_alter_chat_model_alter_project_model.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
# Generated by Django 4.2.6 on 2024-07-02 16:07

from django.db import migrations, models


class Migration(migrations.Migration):

dependencies = [
("ayushma", "0052_document_failed"),
]

operations = [
migrations.AlterField(
model_name="chat",
name="model",
field=models.IntegerField(
blank=True,
choices=[
(1, "Gpt 3 5"),
(2, "Gpt 3 5 16K"),
(3, "Gpt 4"),
(4, "Gpt 4 32K"),
(5, "Gpt 4 Visual"),
(6, "Gpt 4 Turbo"),
(7, "Gpt 4 Omni"),
],
null=True,
),
),
migrations.AlterField(
model_name="project",
name="model",
field=models.IntegerField(
choices=[
(1, "Gpt 3 5"),
(2, "Gpt 3 5 16K"),
(3, "Gpt 4"),
(4, "Gpt 4 32K"),
(5, "Gpt 4 Visual"),
(6, "Gpt 4 Turbo"),
(7, "Gpt 4 Omni"),
],
default=1,
),
),
]
1 change: 1 addition & 0 deletions ayushma/models/enums.py
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,7 @@ class ModelType(IntegerChoices):
GPT_4_32K = 4
GPT_4_VISUAL = 5
GPT_4_TURBO = 6
GPT_4_OMNI = 7


class StatusChoices(IntegerChoices):
Expand Down
5 changes: 4 additions & 1 deletion ayushma/utils/langchain.py
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,8 @@

import openai
from django.conf import settings
from langchain import LLMChain, PromptTemplate
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
from langchain.callbacks.manager import AsyncCallbackManager
from langchain.chat_models import ChatOpenAI
from langchain.llms import AzureOpenAI
Expand Down Expand Up @@ -38,6 +39,8 @@ def get_model_name(model_type: ModelType):
return "gpt-4-vision-preview"
elif model_type == ModelType.GPT_4_TURBO:
return "gpt-4-1106-preview"
elif model_type == ModelType.GPT_4_OMNI:
return "gpt-4o"
else:
if settings.OPENAI_API_TYPE == "azure":
return settings.AZURE_CHAT_MODEL
Expand Down
61 changes: 14 additions & 47 deletions ayushma/utils/openaiapi.py
Original file line number Diff line number Diff line change
Expand Up @@ -10,14 +10,14 @@
from django.conf import settings
from langchain.schema import AIMessage, HumanMessage
from openai import OpenAI
from pinecone import QueryResponse

from ayushma.models import ChatMessage
from ayushma.models.chat import Chat
from ayushma.models.document import Document
from ayushma.models.enums import ChatMessageType, ModelType
from ayushma.utils.langchain import LangChainHelper
from ayushma.utils.language_helpers import text_to_speech, translate_text
from ayushma.utils.vectordb import VectorDB
from core.settings.base import AI_NAME


Expand Down Expand Up @@ -67,39 +67,6 @@ def get_embedding(
return [record.embedding for record in res.data]


def get_sanitized_reference(pinecone_references: List[QueryResponse]) -> str:
"""
Extracts the text from the Pinecone QueryResponse object and sanitizes it.
Args:
pinecone_reference (List[QueryResponse]): The similar documents retrieved from
the Pinecone index.
Returns:
A string containing the document id and text from the Pinecone QueryResponse object.
Example usage:
>>> get_sanitized_reference([QueryResponse(...), QueryResponse(...)])
"{'28': 'Hello how are you, I am fine, thank you.', '21': 'How was your day?, Mine was good.'}"
"""
sanitized_reference = {}

for reference in pinecone_references:
for match in reference.matches:
try:
document_id = str(match.metadata["document"])
text = str(match.metadata["text"]).replace("\n", " ") + ","
if document_id in sanitized_reference:
sanitized_reference[document_id] += text
else:
sanitized_reference[document_id] = text
except Exception as e:
print(f"Error extracting reference: {e}")
pass

return json.dumps(sanitized_reference)


def num_tokens_from_string(string: str, encoding_name: str) -> int:
"""Returns the number of tokens in a text string."""
encoding = tiktoken.get_encoding(encoding_name)
Expand Down Expand Up @@ -155,18 +122,18 @@ def get_reference(text, openai_key, namespace, top_k):
raise Exception(
"[Reference] Error generating embeddings for split text"
)
# find similar embeddings from pinecone index for each embedding
pinecone_references: List[QueryResponse] = []

for embedding in embeddings:
similar: QueryResponse = settings.PINECONE_INDEX_INSTANCE.query(
vector=embedding,
top_k=int(top_k),
namespace=namespace,
include_metadata=True,
)
pinecone_references.append(similar)
return get_sanitized_reference(pinecone_references=pinecone_references)
# find similar embeddings from vector index for each embedding

flat_embeddings = [item for sublist in embeddings for item in sublist]
vdb = VectorDB()
similar = vdb.search(
embeddings=flat_embeddings,
partition_name=namespace,
limit=int(top_k),
)

print("References fetched")
return vdb.sanitize(similar)


def add_reference_documents(chat_message):
Expand Down Expand Up @@ -299,7 +266,7 @@ def converse(
reference = get_reference(
english_text,
openai_key,
str(chat.project.external_id),
str(chat.project.external_id).replace("-", "_"),
match_number,
)
except Exception as e:
Expand Down
Loading

0 comments on commit dc0d1e2

Please sign in to comment.