From ecd72d26cfb5b07b3b7dcce5395080460a24b7e0 Mon Sep 17 00:00:00 2001
From: Brad Erickson <195061+13rac1@users.noreply.github.com>
Date: Thu, 22 Feb 2024 08:59:55 -0800
Subject: [PATCH] community: Bugfix - correct Ollama API path to avoid HTTP 307
 (#17895)

Sets the correct /api/generate path, without ending /, to reduce HTTP
requests.

Reference:

https://github.com/ollama/ollama/blob/efe040f8/docs/api.md#generate-request-streaming

Before:

    DEBUG: Starting new HTTP connection (1): localhost:11434
    DEBUG: http://localhost:11434 "POST /api/generate/ HTTP/1.1" 307 0
    DEBUG: http://localhost:11434 "POST /api/generate HTTP/1.1" 200 None

After:

    DEBUG: Starting new HTTP connection (1): localhost:11434
    DEBUG: http://localhost:11434 "POST /api/generate HTTP/1.1" 200 None
---
 libs/community/langchain_community/llms/ollama.py   |  6 +++---
 libs/community/tests/unit_tests/llms/test_ollama.py | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/libs/community/langchain_community/llms/ollama.py b/libs/community/langchain_community/llms/ollama.py
index c6aba99acc..963d28576f 100644
--- a/libs/community/langchain_community/llms/ollama.py
+++ b/libs/community/langchain_community/llms/ollama.py
@@ -65,7 +65,7 @@ class _OllamaCommon(BaseLanguageModel):
     CPU cores your system has (as opposed to the logical number of cores)."""
 
     num_predict: Optional[int] = None
-    """Maximum number of tokens to predict when generating text. 
+    """Maximum number of tokens to predict when generating text.
     (Default: 128, -1 = infinite generation, -2 = fill context)"""
 
     repeat_last_n: Optional[int] = None
@@ -159,7 +159,7 @@ class _OllamaCommon(BaseLanguageModel):
         yield from self._create_stream(
             payload=payload,
             stop=stop,
-            api_url=f"{self.base_url}/api/generate/",
+            api_url=f"{self.base_url}/api/generate",
             **kwargs,
         )
 
@@ -174,7 +174,7 @@ class _OllamaCommon(BaseLanguageModel):
         async for item in self._acreate_stream(
             payload=payload,
             stop=stop,
-            api_url=f"{self.base_url}/api/generate/",
+            api_url=f"{self.base_url}/api/generate",
             **kwargs,
         ):
             yield item
diff --git a/libs/community/tests/unit_tests/llms/test_ollama.py b/libs/community/tests/unit_tests/llms/test_ollama.py
index 6dcb0bd38e..3b1798fd2e 100644
--- a/libs/community/tests/unit_tests/llms/test_ollama.py
+++ b/libs/community/tests/unit_tests/llms/test_ollama.py
@@ -32,7 +32,7 @@ def test_pass_headers_if_provided(monkeypatch: MonkeyPatch) -> None:
     )
 
     def mock_post(url, headers, json, stream, timeout):  # type: ignore[no-untyped-def]
-        assert url == "https://ollama-hostname:8000/api/generate/"
+        assert url == "https://ollama-hostname:8000/api/generate"
         assert headers == {
             "Content-Type": "application/json",
             "Authentication": "Bearer TEST-TOKEN-VALUE",
@@ -53,7 +53,7 @@ def test_handle_if_headers_not_provided(monkeypatch: MonkeyPatch) -> None:
     llm = Ollama(base_url="https://ollama-hostname:8000", model="foo", timeout=300)
 
     def mock_post(url, headers, json, stream, timeout):  # type: ignore[no-untyped-def]
-        assert url == "https://ollama-hostname:8000/api/generate/"
+        assert url == "https://ollama-hostname:8000/api/generate"
         assert headers == {
             "Content-Type": "application/json",
         }
@@ -73,7 +73,7 @@ def test_handle_kwargs_top_level_parameters(monkeypatch: MonkeyPatch) -> None:
     llm = Ollama(base_url="https://ollama-hostname:8000", model="foo", timeout=300)
 
     def mock_post(url, headers, json, stream, timeout):  # type: ignore[no-untyped-def]
-        assert url == "https://ollama-hostname:8000/api/generate/"
+        assert url == "https://ollama-hostname:8000/api/generate"
         assert headers == {
             "Content-Type": "application/json",
         }
@@ -119,7 +119,7 @@ def test_handle_kwargs_with_unknown_param(monkeypatch: MonkeyPatch) -> None:
     llm = Ollama(base_url="https://ollama-hostname:8000", model="foo", timeout=300)
 
     def mock_post(url, headers, json, stream, timeout):  # type: ignore[no-untyped-def]
-        assert url == "https://ollama-hostname:8000/api/generate/"
+        assert url == "https://ollama-hostname:8000/api/generate"
         assert headers == {
             "Content-Type": "application/json",
         }
@@ -166,7 +166,7 @@ def test_handle_kwargs_with_options(monkeypatch: MonkeyPatch) -> None:
     llm = Ollama(base_url="https://ollama-hostname:8000", model="foo", timeout=300)
 
     def mock_post(url, headers, json, stream, timeout):  # type: ignore[no-untyped-def]
-        assert url == "https://ollama-hostname:8000/api/generate/"
+        assert url == "https://ollama-hostname:8000/api/generate"
         assert headers == {
             "Content-Type": "application/json",
         }