Merge pull request langchain-ai#6 from haoruiqian/HAI-439

HAI-439 upgrade langchain-community to 0.2.4 to include cost calcuation setting of gpt-4o

.devcontainer/README.md

@@ -10,7 +10,7 @@ You can use the dev container configuration in this folder to build and run the
 You may use the button above, or follow these steps to open this repo in a Codespace:
 1. Click the **Code** drop-down menu at the top of https://github.com/langchain-ai/langchain.
 1. Click on the **Codespaces** tab.
-1. Click **Create codespace on master** .
+1. Click **Create codespace on master**.
 
 For more info, check out the [GitHub documentation](https://docs.github.com/en/free-pro-team@latest/github/developing-online-with-codespaces/creating-a-codespace#creating-a-codespace).
 

.devcontainer/devcontainer.json

@@ -12,7 +12,7 @@
 
 	// The optional 'workspaceFolder' property is the path VS Code should open by default when
 	// connected. This is typically a file mount in .devcontainer/docker-compose.yml
-	"workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
+	"workspaceFolder": "/workspaces/langchain",
 
 	// Prevent the container from shutting down
 	"overrideCommand": true

.devcontainer/docker-compose.yaml

@@ -6,7 +6,7 @@ services:
       context: ..
     volumes:
    # Update this to wherever you want VS Code to mount the folder of your project
-      - ..:/workspaces:cached
+      - ..:/workspaces/langchain:cached
     networks:
       - langchain-network 
   #   environment:

.github/ISSUE_TEMPLATE/documentation.yml

@@ -26,6 +26,13 @@ body:
       [LangChain Github Discussions](https://github.com/langchain-ai/langchain/discussions),
       [LangChain Github Issues](https://github.com/langchain-ai/langchain/issues?q=is%3Aissue),
       [LangChain ChatBot](https://chat.langchain.com/)
+- type: input
+  id: url
+  attributes:
+    label: URL
+    description: URL to documentation
+  validations:
+    required: false
 - type: checkboxes
   id: checks
   attributes:
@@ -48,4 +55,4 @@ body:
     label: "Idea or request for content:"
     description: >
       Please describe as clearly as possible what topics you think are missing
-      from the current documentation.
+      from the current documentation.

.github/PULL_REQUEST_TEMPLATE.md

@@ -26,4 +26,4 @@ Additional guidelines:
 - Changes should be backwards compatible.
 - If you are adding something to community, do not re-import it in langchain.
 
-If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.
+If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, ccurme, vbarda, hwchase17.

.github/actions/people/app/main.py

@@ -537,7 +537,9 @@ def get_top_users(
         "nfcampos",
         "efriis",
         "eyurtsev",
-        "rlancemartin"
+        "rlancemartin",
+        "ccurme",
+        "vbarda",
     }
     hidden_logins = {
         "dev2049",

.github/scripts/check_diff.py

@@ -6,8 +6,8 @@
 LANGCHAIN_DIRS = [
     "libs/core",
     "libs/text-splitters",
-    "libs/community",
     "libs/langchain",
+    "libs/community",
     "libs/experimental",
 ]
 
@@ -19,6 +19,7 @@
         "test": set(),
         "extended-test": set(),
     }
+    docs_edited = False
 
     if len(files) == 300:
         # max diff length is 300 files - there are likely files missing
@@ -47,6 +48,20 @@
                     found = True
                 if found:
                     dirs_to_run["extended-test"].add(dir_)
+        elif file.startswith("libs/standard-tests"):
+            # TODO: update to include all packages that rely on standard-tests (all partner packages)
+            # note: won't run on external repo partners
+            dirs_to_run["lint"].add("libs/standard-tests")
+            dirs_to_run["test"].add("libs/partners/mistralai")
+            dirs_to_run["test"].add("libs/partners/openai")
+            dirs_to_run["test"].add("libs/partners/anthropic")
+            dirs_to_run["test"].add("libs/partners/ai21")
+            dirs_to_run["test"].add("libs/partners/fireworks")
+            dirs_to_run["test"].add("libs/partners/groq")
+
+        elif file.startswith("libs/cli"):
+            # todo: add cli makefile
+            pass
         elif file.startswith("libs/partners"):
             partner_dir = file.split("/")[2]
             if os.path.isdir(f"libs/partners/{partner_dir}") and [
@@ -62,6 +77,8 @@
                 "an update for this new library!"
             )
         elif any(file.startswith(p) for p in ["docs/", "templates/", "cookbook/"]):
+            if file.startswith("docs/"):
+                docs_edited = True
             dirs_to_run["lint"].add(".")
 
     outputs = {
@@ -70,7 +87,8 @@
         ),
         "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
         "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
+        "docs-edited": "true" if docs_edited else "",
     }
     for key, value in outputs.items():
         json_output = json.dumps(value)
-        print(f"{key}={json_output}")  # noqa: T201
+        print(f"{key}={json_output}")

.github/scripts/get_min_versions.py

@@ -4,25 +4,33 @@
 from packaging.version import parse as parse_version
 import re
 
-MIN_VERSION_LIBS = ["langchain-core", "langchain-community", "langchain", "langchain-text-splitters"]
+MIN_VERSION_LIBS = [
+    "langchain-core",
+    "langchain-community",
+    "langchain",
+    "langchain-text-splitters",
+]
 
 
 def get_min_version(version: str) -> str:
+    # base regex for x.x.x with cases for rc/post/etc
+    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
+    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
     # case ^x.x.x
-    _match = re.match(r"^\^(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^\\^({vstring})$", version)
     if _match:
         return _match.group(1)
 
     # case >=x.x.x,<y.y.y
-    _match = re.match(r"^>=(\d+(?:\.\d+){0,2}),<(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
     if _match:
         _min = _match.group(1)
         _max = _match.group(2)
         assert parse_version(_min) < parse_version(_max)
         return _min
 
     # case x.x.x
-    _match = re.match(r"^(\d+(?:\.\d+){0,2})$", version)
+    _match = re.match(f"^({vstring})$", version)
     if _match:
         return _match.group(1)
 
@@ -47,6 +55,9 @@ def get_min_version_from_toml(toml_path: str):
             # Get the version string
             version_string = dependencies[lib]
 
+            if isinstance(version_string, dict):
+                version_string = version_string["version"]
+
             # Use parse_version to get the minimum supported version from version_string
             min_version = get_min_version(version_string)
 
@@ -56,12 +67,13 @@ def get_min_version_from_toml(toml_path: str):
     return min_versions
 
 
-# Get the TOML file path from the command line argument
-toml_file = sys.argv[1]
+if __name__ == "__main__":
+    # Get the TOML file path from the command line argument
+    toml_file = sys.argv[1]
 
-# Call the function to get the minimum versions
-min_versions = get_min_version_from_toml(toml_file)
+    # Call the function to get the minimum versions
+    min_versions = get_min_version_from_toml(toml_file)
 
-print(
-    " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-)  # noqa: T201
+    print(
+        " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
+    )

.github/workflows/.codespell-exclude

@@ -0,0 +1,7 @@
+libs/community/langchain_community/llms/yuan2.py
+"NotIn": "not in",
+- `/checkin`: Check-in
+docs/docs/integrations/providers/trulens.mdx
+self.assertIn(
+from trulens_eval import Tru
+tru = Tru()

.github/workflows/_integration_test.yml

@@ -58,6 +58,7 @@ jobs:
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
           NVIDIA_API_KEY: ${{ secrets.NVIDIA_API_KEY }}
           GOOGLE_SEARCH_API_KEY: ${{ secrets.GOOGLE_SEARCH_API_KEY }}
           GOOGLE_CSE_ID: ${{ secrets.GOOGLE_CSE_ID }}
@@ -75,6 +76,9 @@ jobs:
           ES_API_KEY: ${{ secrets.ES_API_KEY }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # for airbyte
           MONGODB_ATLAS_URI: ${{ secrets.MONGODB_ATLAS_URI }}
+          VOYAGE_API_KEY: ${{ secrets.VOYAGE_API_KEY }}
+          COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
+          UPSTAGE_API_KEY: ${{ secrets.UPSTAGE_API_KEY }}
         run: |
           make integration_tests