Update langchain library versions and imports in the sample apps (#398)

* Update langchain library versions in the sample apps * Update langchain version * Update imports * Fix lint errors * Fix key name in auth context
daxa-ai · Jun 13, 2024 · b0ca38b · b0ca38b
1 parent 5f6c842
commit b0ca38b
Show file tree

Hide file tree

Showing 15 changed files with 36 additions and 36 deletions.
diff --git a/README.md b/README.md
@@ -84,7 +84,7 @@ Add `PebbloSafeLoader` wrapper to the existing Langchain document loader(s) used
 Here is the snippet of Lanchain RAG application using `CSVLoader` before enabling `PebbloSafeLoader`.
 
 ```python
-    from langchain.document_loaders.csv_loader import CSVLoader
+    from langchain_community.document_loaders import CSVLoader
 
     loader = CSVLoader(file_path)
     documents = loader.load()
@@ -94,7 +94,7 @@ Here is the snippet of Lanchain RAG application using `CSVLoader` before enablin
 The Pebblo SafeLoader can be enabled with few lines of code change to the above snippet.
 
 ```python
-    from langchain.document_loaders.csv_loader import CSVLoader
+    from langchain_community.document_loaders import CSVLoader
     from langchain_community.document_loaders.pebblo import PebbloSafeLoader
 
     loader = PebbloSafeLoader(

diff --git a/docs/gh_pages/docs/rag.md b/docs/gh_pages/docs/rag.md
@@ -11,7 +11,7 @@ Assume a Langchain RAG application snippet using `CSVLoader` to read a CSV docum
 Here is the snippet of Lanchain RAG application using `CSVLoader`.
 
 ```python
-    from langchain.document_loaders.csv_loader import CSVLoader
+    from langchain_community.document_loaders import CSVLoader
 
     loader = CSVLoader(file_path)
     documents = loader.load()
@@ -21,7 +21,7 @@ Here is the snippet of Lanchain RAG application using `CSVLoader`.
 The Pebblo SafeLoader can be enabled with few lines of code change to the above snippet.
 
 ```python
-    from langchain.document_loaders.csv_loader import CSVLoader
+    from langchain_community.document_loaders import CSVLoader
     from langchain_community.document_loaders.pebblo import PebbloSafeLoader
 
     loader = PebbloSafeLoader(

diff --git a/pebblo_cloud/langchain/README.md b/pebblo_cloud/langchain/README.md
@@ -5,7 +5,7 @@
 Pebblo Cloud can be enabled by adding API key in the Pebblo SafeLoader and Pebblo SafeRetriever initializations. 
 
 ```python
-    from langchain.document_loaders.csv_loader import CSVLoader
+    from langchain_community.document_loaders import CSVLoader
     from langchain_community.document_loaders.pebblo import PebbloSafeLoader
 
     loader = PebbloSafeLoader(

diff --git a/pebblo_cloud/langchain/rag-sample/requirements.txt b/pebblo_cloud/langchain/rag-sample/requirements.txt
@@ -1,11 +1,11 @@
-langchain>=0.1.7
-langchain-community
-langchain-openai
+langchain==0.2.3
+langchain-community==0.2.4 # For PebbloSafeLoader, PebbloRetrievalQA, VectorStore
+langchain-google-community>=1.0.4 # For GoogleDriveLoader
+langchain-openai>=0.1.7 # For OpenAI LLM and OpenAIEmbeddings
 python-dotenv==1.0.0
 requests==2.31.0
 google-api-python-client
 google-auth-httplib2
 google-auth-oauthlib
 unstructured[all-docs]
-qdrant-client
-langchain_google_community # For GoogleDriveLoader
+qdrant-client
diff --git a/pebblo_safeloader/README.md b/pebblo_safeloader/README.md
@@ -7,7 +7,7 @@ Pebblo Safeloader enables safe data ingestion for Langchain document loader. Thi
 The Pebblo SafeLoader can be enabled with few lines of code change to the above snippet.
 
 ```python
-    from langchain.document_loaders.csv_loader import CSVLoader
+    from langchain_community.document_loaders import CSVLoader
     from langchain_community.document_loaders.pebblo import PebbloSafeLoader
 
     loader = PebbloSafeLoader(

diff --git a/pebblo_safeloader/langchain/acme-corp-rag/acme_corp_rag.py b/pebblo_safeloader/langchain/acme-corp-rag/acme_corp_rag.py
@@ -4,8 +4,8 @@
 # in this directory before proceeding
 from dotenv import load_dotenv
 from langchain.chains import RetrievalQA
-from langchain.document_loaders.csv_loader import CSVLoader
 from langchain.schema import Document
+from langchain_community.document_loaders import CSVLoader
 from langchain_community.vectorstores import Chroma
 from langchain_community.vectorstores.utils import filter_complex_metadata
 from langchain_openai.embeddings import OpenAIEmbeddings

diff --git a/pebblo_safeloader/langchain/acme-corp-rag/acme_corp_rag_pebblo.py b/pebblo_safeloader/langchain/acme-corp-rag/acme_corp_rag_pebblo.py
@@ -4,8 +4,8 @@
 # in this directory before proceeding
 from dotenv import load_dotenv
 from langchain.chains import RetrievalQA
-from langchain.document_loaders.csv_loader import CSVLoader
 from langchain.schema import Document
+from langchain_community.document_loaders.csv_loader import CSVLoader
 from langchain_community.document_loaders.pebblo import PebbloSafeLoader
 from langchain_community.vectorstores import Chroma
 from langchain_community.vectorstores.utils import filter_complex_metadata

diff --git a/pebblo_safeloader/langchain/acme-corp-rag/requirements.txt b/pebblo_safeloader/langchain/acme-corp-rag/requirements.txt
@@ -1,6 +1,6 @@
-langchain>=0.1.7
-langchain-community
-langchain-openai
+langchain==0.2.3
+langchain-community==0.2.4 # For PebbloSafeLoader, VectorStore
+langchain-openai>=0.1.7 # For OpenAI LLM and OpenAIEmbeddings
 chromadb==0.4.7
 python-dotenv==1.0.0
 tiktoken

diff --git a/pebblo_saferetriever/README.md b/pebblo_saferetriever/README.md
@@ -34,7 +34,7 @@ Here is the sample code for `GoogleDriveLoader` with `load_auth` parameter set t
 Here is the sample code for `Pebblo SafeRetriever` with `authorized_groups` from the user accessing RAG application passed in `auth_context`
 
 ```python
-        from langchain.chains.pebblo_retrieval.models import AuthContext, ChainInput
+        from langchain_community.chains.pebblo_retrieval.models import AuthContext, ChainInput
 
         retrieval_chain = PebbloRetrievalQA.from_chain_type(
             llm=self.llm,

diff --git a/pebblo_saferetriever/langchain/identity-n-semantic-rag/requirements.txt b/pebblo_saferetriever/langchain/identity-n-semantic-rag/requirements.txt
@@ -1,6 +1,7 @@
-langchain>=0.1.7
-langchain-community
-langchain-openai
+langchain==0.2.3
+langchain-community==0.2.4 # For PebbloSafeLoader, PebbloRetrievalQA, VectorStore
+langchain-google-community>=1.0.4 # For GoogleDriveLoader
+langchain-openai>=0.1.7 # For OpenAI LLM and OpenAIEmbeddings
 python-dotenv==1.0.0
 requests==2.31.0
 Markdown==3.5
@@ -9,5 +10,4 @@ google-api-python-client
 google-auth-httplib2
 google-auth-oauthlib
 qdrant-client==1.8.0 # for Qdrant VectorStore
-PyPDF2
-langchain_google_community # For GoogleDriveLoader
+PyPDF2
diff --git a/pebblo_saferetriever/langchain/identity-n-semantic-rag/semantic_rag.py b/pebblo_saferetriever/langchain/identity-n-semantic-rag/semantic_rag.py
@@ -112,7 +112,7 @@ def ask(
     ):
         auth_context = {
             "user_id": user_email,
-            "authorized_identities": auth_identifiers,
+            "user_auth": auth_identifiers,
         }
         auth_context = AuthContext(**auth_context)
         semantic_context = dict()

diff --git a/pebblo_saferetriever/langchain/identity-rag/pebblo_identity_rag.py b/pebblo_saferetriever/langchain/identity-rag/pebblo_identity_rag.py
@@ -79,7 +79,7 @@ def embeddings(self):
     def ask(self, question: str, user_email: str, auth_identifiers: list):
         auth_context = {
             "user_id": user_email,
-            "authorized_identities": auth_identifiers,
+            "user_auth": auth_identifiers,
         }
         auth_context = AuthContext(**auth_context)
         chain_input = ChainInput(query=question, auth_context=auth_context)

diff --git a/pebblo_saferetriever/langchain/identity-rag/requirements.txt b/pebblo_saferetriever/langchain/identity-rag/requirements.txt
@@ -1,6 +1,7 @@
-langchain>=0.1.7
-langchain-community
-langchain-openai
+langchain==0.2.3
+langchain-community==0.2.4 # For PebbloSafeLoader, PebbloRetrievalQA, VectorStore
+langchain-google-community>=1.0.4 # For GoogleDriveLoader
+langchain-openai>=0.1.7 # For OpenAI LLM and OpenAIEmbeddings
 python-dotenv==1.0.0
 tiktoken
 requests==2.31.0
@@ -10,5 +11,4 @@ google-api-python-client
 google-auth-httplib2
 google-auth-oauthlib
 qdrant-client==1.8.0 # for Qdrant VectorStore
-PyPDF2
-langchain_google_community # For GoogleDriveLoader
+PyPDF2
diff --git a/pebblo_saferetriever/langchain/semantic-rag/requirements.txt b/pebblo_saferetriever/langchain/semantic-rag/requirements.txt
@@ -1,6 +1,7 @@
-langchain>=0.1.7
-langchain-community
-langchain-openai
+langchain==0.2.3
+langchain-community==0.2.4 # For PebbloSafeLoader, PebbloRetrievalQA, VectorStore
+langchain-google-community>=1.0.4 # For GoogleDriveLoader
+langchain-openai>=0.1.7 # For OpenAI LLM and OpenAIEmbeddings
 python-dotenv==1.0.0
 requests==2.31.0
 Markdown==3.5
@@ -9,5 +10,4 @@ google-api-python-client
 google-auth-httplib2
 google-auth-oauthlib
 qdrant-client==1.8.0 # for Qdrant VectorStore
-PyPDF2
-langchain_google_community # For GoogleDriveLoader
+PyPDF2
diff --git a/tests/integration/samples/pebblo_csv_loader/pebblo_csvloader.py b/tests/integration/samples/pebblo_csv_loader/pebblo_csvloader.py
@@ -3,11 +3,11 @@
 
 from dotenv import load_dotenv
 from langchain.chains import RetrievalQA
-from langchain.document_loaders.csv_loader import CSVLoader
 from langchain.schema import Document
-from langchain.vectorstores.utils import filter_complex_metadata
+from langchain_community.document_loaders import CSVLoader
 from langchain_community.document_loaders.pebblo import PebbloSafeLoader
 from langchain_community.vectorstores import Chroma
+from langchain_community.vectorstores.utils import filter_complex_metadata
 from langchain_openai.embeddings import OpenAIEmbeddings
 from langchain_openai.llms import OpenAI